Energies 15 01602

Download as pdf or txt
Download as pdf or txt
You are on page 1of 17

energies

Article
Predicting Gasoline Vehicle Fuel Consumption in Energy and
Environmental Impact Based on Machine Learning and
Multidimensional Big Data
Yushan Yang 1 , Nuoya Gong 2 , Keying Xie 3,4 and Qingfei Liu 5, *

1 School of Economics and Management, Beijing University of Posts and Telecommunications,


Beijing 100876, China; yangyushan@bupt.edu.cn
2 College of Japanese, Beijing International Studies University, Beijing 100024, China;
2020220207@stu.bisu.edu.cn
3 School of Economics, Beijing Wuzi University, Beijing 101149, China; 2019103026@bwu.edu.cn
4 School of Fashion Communication, Beijing Institute of Fashion Technology, Beijing 100029, China
5 Undergraduate School, National University of Defense Technology, Changsha 410073, China
* Correspondence: shenliulei12@nudt.edu.cn

Abstract: The underestimation of fuel consumption impacts various aspects. In the vehicle market,
manufacturers often advertise fuel economy for marketing. In fact, the fuel consumption reference
value provided by the manufacturer is quite different from the real-world fuel consumption of the
vehicles. The divergence between reference fuel consumption and real-world fuel consumption
also has negative effect on the aspects of policy and environment. In order to effectively promote
the sustainable development of transport, it is urged to recognize the real-world fuel consumption
 of vehicles. The gaps in previous studies includes small sample size, single data dimension, and
 lack of feature weight evaluation. To fill the research gap, in this study, we conduct a comparative
Citation: Yang, Y.; Gong, N.; Xie, K.; analysis through building five regression models to forecast the real-world fuel consumption rate
Liu, Q. Predicting Gasoline Vehicle of light-duty gasoline vehicles in China based on big data from the perspectives of vehicle factors,
Fuel Consumption in Energy and
environment factors, and driving behavior factors. Results show that the random forest regression
Environmental Impact Based on
model performs best among the five candidate models, with a mean absolute error of 0.630 L/100 km,
Machine Learning and
a mean absolute percentage error of 7.5%, a mean squared error of 0.805, an R squared of 0.776, and
Multidimensional Big Data. Energies
a 10-fold cross-validation score of 0.791. Further, we capture the most important features affecting
2022, 15, 1602. https://doi.org/
10.3390/en15051602
fuel consumption among the 25 factors from the above three perspectives. According to the relative
weight of each factor in the most optimal model, the three most important factors are brake and
Academic Editor: Victor Manuel
accelerator habits, engine power, and the fuel economy consciousness of vehicle owners in sequence.
Ferreira Moutinho

Received: 31 December 2021 Keywords: fuel consumption; energy and environmental; machine learning
Accepted: 11 February 2022
Published: 22 February 2022

Publisher’s Note: MDPI stays neutral


1. Introduction
with regard to jurisdictional claims in
published maps and institutional affil- Real-world fuel consumption has been underestimated [1] and the underestimation
iations. has severe impact on various aspects. In terms of the environment, transportation is one of
the industries most responsible for decreasing fossil fuel consumption and environmental
pollution. According to the new round of investigation into fine particle sources in Beijing,
mobile sources, especially vehicles, have replaced coal combustion to become the primary
Copyright: © 2022 by the authors. source of PM 2.5 [2]. Furthermore, it becomes hard to assess current and plan future policy
Licensee MDPI, Basel, Switzerland. to fulfill the promise of carbon peak and carbon neutrality [3]. In terms of industry, goals set
This article is an open access article to be achieved through the introduction of new technologies such as lightweight materials
distributed under the terms and
now seem to achievable solely through traditional methods, thus adversely affecting
conditions of the Creative Commons
innovation. In addition, manufacturers often advertise fuel economy for marketing in the
Attribution (CC BY) license (https://
vehicle market, while the fuel consumption reference value provided by the manufacturer
creativecommons.org/licenses/by/
is quite different from the real-world vehicles fuel consumption. Therefore, to effectively
4.0/).

Energies 2022, 15, 1602. https://doi.org/10.3390/en15051602 https://www.mdpi.com/journal/energies


Energies 2022, 15, 1602 2 of 17

promote the sustainable development of transport, it is urged to recognize the real-world


fuel consumption of vehicles [1].
At present, the main reference fuel consumption of vehicles is provided by the Ministry
of Industry and Information Technology (MIIT) of China, which is measured by indirect
measurement method as follows. For light vehicles (maximum total quality is not more
than 3.5 tons of vehicles), the vehicle is in the experimental stage, the actual driving
speed is simulated and loaded on the road, and the carbon dioxide, carbon monoxide and
hydrocarbon emissions are measured according to New European Driving Cycle (NEDC)
working conditions. Then, the fuel consumption is derived from the measurement based
on carbon mass balance in the exhaust gas [4].
On 20 February 2021, The State Administration for Market Regulation and the Stan-
dardization Administration approved and released the mandatory national standard of
Fuel Consumption Limits for Passenger Vehicles (GB 19578-2021) organized by the MIIT,
which was formally implemented on July 1. It is proposed that before 2025, the test condi-
tions of traditional energy passenger vehicles and plug-in hybrid passenger vehicles will be
switched from NEDC to WLTC (Worldwide Harmonized Light Vehicles Test Cycle) [5]. The
change of operating conditions will affect the comprehensive fuel consumption of vehicles,
which means that the NEDC standard will fully withdraw from MIIT. Compared with the
NEDC working condition in the 1970s, the WLTC test condition officially completed in 2015
was more stringent [4]. The maximum speed, average speed, maximum acceleration and
deceleration, acceleration and deceleration range, and test time are significantly improved;
as a result, it could better reflect the actual driving situation.
However, a series of studies have identified that the reference fuel consumption is
widely different from the real-world fuel consumption. Liu et al. (2018) found a gap
between the test results under the NEDC working conditions and the real-world driving
situation in China in terms of fuel consumption is approximately 30% [6]. Duarte et al.‘s
study (2016) presents that fuel consumption is 23.9 ± 16.8% higher than certification values
in average [7]. Even in the WLTC operating environment, there are a number of studies
that reveal a wide discrepancy between the reference consumption information and the
actual case [8–10].
Studies have identified the factors that cause the widespread divergence between the
reference fuel consumption rate and the actual fuel consumption rate [11]. The main cause
is the operation under off-cycle conditions. Since the operating conditions, the driving
behavior of vehicle owner, and other external factors are various in the real life, no matter
how accurately the test protocol is designed, it is scarcely possible to precisely predict the
real-world fuel consumption.
Machine learning is popular in solving the prediction problems of complex systems
such as fuel consumption prediction. By making the model learn the training set, it is
possible for the model to show a better prediction effect on the test set [12]. There have been
a large number of studies on fuel consumption prediction with machine learning models,
which tend to focus on a single aspect of factors that affect fuel consumption prediction,
involving vehicle factors [13], driving behavior factors [14], road conditions factors [15],
weather factors [16], and so on. However, fuel consumption is affected by many factors,
and it can hardly make accurate prediction only by focusing on a single dimension. In this
case, due to the limitation of data acquisition, there is a lack of fuel consumption prediction
research based on multi-dimensional factor data.
In addition, a model was considered good as long as it could predict correctly in the
past, and there was not much focus on which variables led to the higher accuracy of the
final results. Therefore, it seems that machine learning models are black-boxes that make
precise predictions while not being able to understand the logic behind those predictions.
Fuel consumption forecasting, in this case, becomes a complicated black-box problem as a
result of the asymmetric information. There is a need of attempt to unlock the black box and
help to understand the models better, including revealing the most important feature in the
model and how much influence each feature has on the results of the model’s prediction.
Energies 2022, 15, 1602 3 of 17

In this paper, we extract data from the BearOil app, which is a well-known vehicle
owner service app, with 7 million installed users, over 1.2 million monthly active owners,
and more than 30 billion kilometers of mass test total mileage. At the same time, we take
vehicle factors such as vehicle brand, engine power, and engine displacement; driving
behavior factors such as usual driving speed, driving skills, brake and accelerator habits,
fuel economy awareness, and car use frequency; and environmental factors such as tem-
perature, wind speed, and precipitation into consideration. Above all, we aim to predict
the real-world fuel consumption in sustainable transport based on multidimensional data
and obtain more accurate predicted fuel consumption value through a machine learning
method. Moreover, we focus on identifying the most important factors that affect the
real-world consumption rate.
The rest of the paper is organized as follows. In Section 2, we review the related
literature. In Section 3, we discuss the data source, the extraction factors in the aspect of
real-world fuel consumption rate, the driving behavior, and the environment. Section 4
describes the criteria of model selection and the architecture of models. Then, we present
the results which include the prediction results and the optimal model, as well as evaluating
the most important factors. In Section 5, we analyze the most important features and in
Section 6, we present the conclusions.

2. Literature Review
2.1. Fuel Consumption Forecasting Models
The fuel consumption prediction model can be divided into white-box model and
black-box model. White-box model mainly refers to the mathematical or physical frame-
work to predict fuel consumption which requires scholars to have a comprehensive and
through understanding of the model and related knowledge. In contrast, the black-box
model only uses input-output data and lacks physics in the model structure [17].
A typical white-box model in this field includes a mean value phenomenological
model constructed by Heywood (2018) based on knowledge on internal combustion engine
which consists of an intake system, a delivery system, a torque production system, and an
exhaust system [18]. In general, the prediction of fuel consumption using the white-box
model poses a high requirement on the understanding of the entire engine system. In
addition, there are a large number of parameters involved, even some of the parameters
are unavailable. Therefore, white-box is not practical for forecasting fuel consumption
although it is transparent.
A class of outstanding black-box models are predictive models based on machine
learning methods. They are completely data-driven and have no requirement on physical
explanation. All coefficients are determined based on big data using multiple regression
methods. The accuracy of the black-box model is always satisfied. However, the coefficients
lack interpretability. Additionally, collecting such large amounts of data for the black-box
model requires huge labor and time.

2.2. Machine Learning-Based Fuel Consumption Prediction


In the research on fuel consumption prediction, the use of a machine learning model is
the main trend worthy of attention in recent years. Parlak et al. (2006) [19] adopt a back prop-
agation learning algorithm to predict specific fuel consumption and exhaust temperature
of a diesel engine for various injection timings. The comparison between the model results
and the experimental results showed a high consistence. Togun and Baysec (2010) [20]
present a genetic programming (GP)-based model to predict the torque and brake spe-
cific fuel consumption of a gasoline engine according to spark advance, throttle position,
and engine speed, and find that the proposed GP models show satisfactory accuracy.
Silva et al. (2006) [21] selected EcoGest, CMEM, and ADVISOR to simulate a sample of
14 urban trips for two 1999 Ford Taurus vehicles, which achieved a relatively high confi-
dence to predict the fuel consumption. Based on 1750 records, Ziolkowski et al. (2021) [22]
selected the Multi-Layer Perceptron 22-10-3 network to predict the fuel consumption and
Energies 2022, 15, 1602 4 of 17

reached satisfactory MAPE for 6–10%. Similar studies used artificial neural network (ANN)
model conducted by Togun and Baysec (2010) [23] in 81 data sets, Jahirul et al. (2009) [24]
and Hjellvik and Maria (2019) [25] also suggest that ANN is very efficient for predicting fuel
consumption. Syahputra (2016) [26] presented the application of neuro-fuzzy method for
prediction of fuel consumption which shows a training RMSE of 2.767. Yao et al. (2020) [27]
used back propagation neural network, support vector regression, and random forests
to predict vehicle fuel consumption based on the mobile phone terminals and on-board
diagnostic system installed in taxis riving behavior data. Results show that all three models
are accurate with an absolute relative error less than 10%. Also focusing on driver-related
factors, Ping et al. [28] developed a deep learning-based model as a predictor of the fuel con-
sumption associated with driving behavior under the dynamic driving conditions. In terms
of data, increasing big data-driven studies which focus on the topic of fuel consumption
rate prediction extract data from the BearOil app [2,29–32].

2.3. Factors Related to Fuel Consumption Prediction


Studies have identified a series of important factors that affect vehicle fuel consumption.
Zhou et al. (2016) [17] summarizes that the main factors affecting fuel consumption are
travel-related, weather-related, vehicle-related, roadway-related, and driver-related factors.
In terms of travel-related factors, Ahn and Rakha (2008) [33] demonstrate that utilizing
a slower arterial route could save energy but incur additional travel time. Greenwood et al.’s
study (2007) [34] recommend that it is important to include information on the level of
congestion in the driving patterns to get more accurate emission predictions.
In the aspect of weather, studies show that fuel consumption is higher at −30 ◦ C
than at 20 ◦ C [35] and rises with the thermal load. He et al. (2016) [36] prove that the
best strategy to reach fuel economy is to limit the acceleration if the combined effect of
the road grade, rolling resistance, and wind is small. Test results also show that the fuel
consumption is related to the inlet humidity [37].
According to Sriwilai et al. (2016) [38], engine size and type are related to energy
consumption in Thailand. A similar conclusion based on an analytical approach was drawn
by Ben et al. (2013) [39]. In addition, vehicle speed and acceleration are widely regarded as
intuitive variables that have a significant effect on fuel consumption [40–42].
A number of scholars suggest the effect of road grade on fuel consumption by com-
paring flat routes and hilly routes [43–45]. Specifically, Renouf (1979) [46] addresses that
increased energy requirements can be up to 9% due to a low-radius curve.
Driver-related factors refer to driver behavior and aggressiveness [17]. Sanchez et al.
(2006) [47] identified that aggressive driving consumes more fuel than calm driving. More-
over, a study conducted by Mierlo et al. (2004) [14] based on on-road test demonstrated
that fuel consumption could be reduced by up to 25% if drivers changed the driving style
according to instruction.
Above all, the prediction formula based on physics often differs greatly from the
actual case of fuel consumption. Meanwhile, existing studies which build machine learning
models lack large-scale data; a small dataset means that there is no guarantee that the
prediction model can be widely applied to a large number of car models under different
conditions. Moreover, existing studies tend to focus on a single dimension, that is, choosing
only the vehicle-related factors, the environment-related factors, or the driving behavior-
related factors to predict the fuel consumption. However, fuel consumption prediction is
complex work with a number of unknown features; there is a lack of related research that
combines multi-dimensional information.
In addition, even though there are studies with various indicators, the weights are not
assessed, which is still asymmetric in information, and thus is weakly interpretable. To
open the black box, obtain accurate predictions, and expand the applicability of predictions,
it is necessary to comprehensively assess the impact of factors and try to capture the most
important features to provide meaningful recommendations for vehicle owners, industries,
and government.
Energies 2022, 15, 1602 5 of 17

To fill the above research gap, we construct machine learning models based on big
data in the aspects of the car models, the environment conditions, and driving behavior
information to describe the driving reality as much as possible to predict the fuel consump-
tion. Then, we comprehensively assess the impact of factors to open the so-called black
box and try to capture the features that influence the fuel consumption in the sustainable
transport. In this paper, we propose five models including linear regression, naïve Bayes
regression, neural network regression, random forest regression, and LightGBM models.
Each of them is helpful to improve the accuracy of the prediction after training on big data.
The prediction results are compared to identify the optimal model. To clarify the scope of
the study, our study focuses on gasoline vehicles as they are the most common road traffic
vehicles in real life.

3. Materials and Methods


3.1. Data
We obtained data from three resources: the real-world fuel consumption rate recorded
by vehicle owners in the BearOil app, results of a questionnaire survey on driving behavior of
vehicle owners, and the monthly information of the climate and road grade in cities of China.
To generate the real-world fuel consumption rate, firstly, each time the vehicle owners
refuel, they record the time, the mileage, the liters of fuel, and the payment via the BearOil
app. They then mark whether the oil tank is full or not and update the record. The liters of
oil added between two adjacent records marked as filled is the fuel consumption during the
trip. We get the average fuel consumption rate by weighted averaging the fuel consumption
of all trips of the vehicle owner with the mileage as the weight. Next, according to the
average fuel consumption of different owners of the same car model, the samples with
obvious errors are eliminated and the remaining samples are taken as valid samples.
The driving behavior questionnaire contains 20 questions from seven dimensions:
gender, age, driving speed, driving skills, driving habits, fuel economy awareness, and
car use frequency. We assign values to each option and calculate the score of each vehicle
owner in each dimension. After processing the driving behavior questionnaire data, we
matched driving behavior with the corresponding fuel consumption data on user ID and
the external environmental data, including temperature, win speed, pressure, humidity,
precipitation, sunshine, road grade, etc., based on the city and date information of the
vehicle owners. Finally, we take the mean of the average fuel consumption of those with the
same driving behavior, driving the same car model, and in the same external environment.

3.1.1. Fuel Consumption Data and Vehicle Factors


About 1.7 million records reported by gasoline vehicle owners in 315 cities of China
during 2013 and 2017 were extracted from the BearOil app in this study. Examples of the
records are shown in Table 1. Only the last eight digits of the user number (User ID) are
displayed for privacy reasons.
The User ID is the unique ID of a user in the BearOil app and each User ID corre-
sponds to multiple samples. Multiple records of one user are the user’s fuel consumption
information at different dates and in different cities.
Vehicle information is also given in the records which includes the vehicle brand,
series, version, engine, and gearbox. The engine parameters consist of displacement engine
power and the number of cylinders. The gearbox parameters show the type of transmission.
MT is short for manual transmission, AT is short for automatic transmission, AMT is short
for automated manual transmission, CVT is short for continuously variable transmission,
DSG is short for direct shift gearbox, and so on.
Energies 2022, 15, 1602 6 of 17

Table 1. Example of row records from BearOil app.

Feature Record 0 Record 1 Record 2 Record 3


User ID 02194194 70192504 40468960 74150957
City Dali Yangshan Tianjin Wuhan
Time March 2013 March 2014 March 2015 March 2016
Brand Name FORTHING BYD TOYOTA HAVAL
Series Name JOYEAR BYD G6 E’Z HAVAL H2
Version Year 2010 2012 2014 2016
Engine 1.5 L/120 ps/L4 2.0 L/140 ps/L4 1.8 L/140 ps/L4 1.5 T/150 ps/L4
Gearbox MT-5 MT-5 E-CVT AMT-6
refConsumption
7.2 8.3 7.4 9
(L/100 km)
realConsumption
6.4 9.1 8.9 8.2
(L/100 km)

The reference fuel consumption rate (Ref Consumption) of each car model is pro-
vided by the MIIT of China under the second stage of the NEDC working condition. The
distribution of actual and reference fuel consumption is displayed in Table 2 according
to displacement. It shows that most of the samples are with displacement coverages of
0.8–2.5 L. The reference fuel consumption rate of vehicles with displacement coverages
of 0.8–1.6 L is 6.459 while the corresponding real-world consumption rate is 7.888. In
addition, the reference fuel consumption rate of vehicles with displacement coverages of
1.6–2.5 L is 7.794 while the corresponding real-world consumption rate is 9.598. In a sum,
the discrepancy between reference value and the real value suggests that the reference fuel
consumption rate is often a poor estimation.

Table 2. Distribution of fuel consumption rates.

Engine Displacement (ED)


ED ≤ 0.8 L 0.8 L < ED ≤ 1.6 L 1.6 L < ED ≤ 2.5 L 2.5 L < ED ≤ 4.0 L ED > 4.0 L

Standard Ref Consumption (L/100 km) 0.486 0.778 1.211 1.270 0.582
deviation Real Consumption (L/100 km) 1.021 1.512 2.115 2.306 2.245
Ref Consumption (L/100 km) 5.700 1.600 2.000 7.600 11.100
Min
Real Consumption (L/100 km) 4.429 0.829 1.350 6.278 12.352
Ref Consumption (L/100 km) 6.700 9.800 12.300 15.700 13.200
Max
Real Consumption (L/100 km) 10.815 16.915 20.379 20.675 20.214
Ref Consumption (L/100 km) 5.700 5.900 7.100 9.900 13.200
P25
Real Consumption (L/100 km) 5.082 6.846 8.207 11.029 14.119
Ref Consumption (L/100 km) 6.700 6.400 7.800 10.400 13.200
Median
Real Consumption (L/100 km) 5.454 7.738 9.501 12.657 15.655
Ref Consumption (L/100 km) 6.301 6.459 7.794 10.608 13.038
Mean
Real Consumption (L/100 km) 5.728 7.888 9.598 12.701 15.773
Ref Consumption (L/100 km) 6.700 6.900 8.600 11.000 13.200
P75
Real Consumption (L/100 km) 5.974 8.774 10.889 14.178 17.059
Observation 113 116,302 53,788 866 13

To clarify our research objectives again, our objective is to predict the average real-
world fuel consumption rate of a given gasoline vehicle model under certain climate
conditions and certain driving behaviors of the vehicle owner. Therefore, the real-world
fuel consumption rate of users in the same city, the same month, and with the same driving
behavior is averaged.
Gasoline vehicles with different brands, engine, and transmission are significantly
different in fuel consumption rate. The above parameters are related to the vehicle series
information. However, too many dimensions will be generated in the one-hot coding
Energies 2022, 15, 1602 7 of 17

stage if the vehicle series is encoded as the input. As a result, we chose engine power,
displacement, the number of cylinders, and gearbox type as the model input. Moreover,
although the reference value provided by MIIT cannot be used as a direct estimate of the
actual fuel consumption rate, we can still use the reference value to reduce the error caused
by the abnormal real fuel consumption rate. Therefore, we incorporate the reference fuel
consumption rate in our models.

3.1.2. Driving Behavior Factors


Driving behavior data were collected from questionnaires. We asked nearly 25,000 users
in BearOil app to fill out the questionnaires about their driving behavior. Our questionnaire
contains 20 questions from seven dimensions: gender, age, driving speed, driving skills,
driving habits, fuel economy awareness, and car use frequency. The scoring for each
dimension is shown below.
In the gender dimension, options are 0 for males and 1 for females; in the age dimen-
sion, integers 1 to 4 are assigned to four different age groups, with older people scoring
higher. The questions of the remaining five dimensions are shown in Table 3.

Table 3. Questions of the driving behavior questionnaire.

Dimensions Questions
Car use Q1. Do you drive when the trip is less than 5 km?
frequency Q2. Do you always consider alternatives such as buses, subways, or bicycles instead of driving by yourself?
Q1. Do you avoid using equipment that increases fuel consumption such as air conditioners and high-power
car appliances as much as possible?
Q2. Are you used to leaving anything such as sneakers, ball bags, and spare barbecue oil in the trunk?
Fuel
Q3. What is your attitude towards the maintenance, tire pressure, and car deposition condition of your car?
economy
Q4. Will you turn off the engine if the expected idle time is more than 3 min?
consciousness
Q5. Would you consider finding out the reason and adjusting your driving habits if you knew you were
getting more gas mileage than your friends?
Q6. Will you pay attention to the traffic situation to avoid possible traffic jams in advance?
Q1. What do you think of your parking skills?
Driving skill
Q2. What do you think of your driving skills?
Q1. Do you overspeed a lot on the highway?
Driving speed
Q2. What is your general approach in the traffic?Q3. What is the average speed of your driving?
Q1. What is your general strategy for intersection with red traffic light?
Q2. What kind of road conditions have you been driving with in the past year?
Q3. Do you tend to pedal to the ground when starting or accelerating?
Driving habit
Q4. How do you drive when you find that you have to slow down in the 100 m ahead on the road?
Q5. Imagine that you are driving, the green light is on, and the road ahead is empty, while one kilometer
away is the destination where you have to pull over; how do you drive?

The total score of the two questions in the dimension of car use frequency ranges from
2 to 8. When the vehicle owner chose the option representing the lower frequency in Q1,
and the option representing the higher frequency in Q2, the score would be higher. That is,
the higher the score is, the lower the car use frequency is. The fuel economy consciousness
dimension includes six questions, with a total score ranges from 6 to 28. When the vehicle
owner has a greater willingness to avoid using fuel consumption equipment in Q1, has
fewer behaviors in reality as shown in Q2, pays more attention to the situation mentioned
in Q3, Q5, Q6, and has a greater likelihood to turn off the engine in the given situation
in Q4, the score would be higher. That is, a higher score indicates stronger fuel economy
consciousness. The driving skills dimension includes two questions on a scale of 2 to 8 and
higher score indicates better driving skills (Q2) and parking skills (Q1) the user thinks he
or she is. There are 3 questions in the driving speed dimension, scoring between 3 to 13.
Vehicle owners score higher when they are more likely to speed on the highway (Q1), more
likely to race ahead of other cars in traffic (Q2), and drive at a higher average speed (Q3).
Energies 2022, 15, 1602 8 of 17

The driving habits dimension consists of 5 questions, with a total score of 5 to 19. When the
vehicle owner is more likely to avoid pedaling down or slamming on the brakes in the case
of Q1, Q3, Q4, and Q5, and chose less stop-go, more unblocked road in the past year, the
vehicle owner is seen as having better driving habits, as a result, the score is higher.
Table 4 shows the age and gender distribution of the users who filled in the question-
naire and descriptive statistics of scores in the other dimensions are shown in Table 5.

Table 4. Age and gender distribution.

Age
Gender 18–25 26–35 36–45 45+ Total
Male 3035 14,360 4910 1270 23,575
Female 85 361 104 24 574
Total 3120 14,721 5014 1294 24,149

Table 5. Descriptive statistics of scores.

Dimensions Min Max P50 Mean


Car frequency 2.0 8.0 5.0 4.7
Fuel economy consciousness 6.0 28.0 20.0 19.6
Driving skill 2.0 8.0 6.0 5.7
Driving speed 3.0 13.0 9.0 9.3
Driving habit 6.0 19.0 16.0 15.9

3.1.3. Environment Factors


Environment factors include climate factors and road grade. Information on climate
factors was extracted from the meteorological departments of the provincial regions in
China. We extracted data on temperature, wind speed, air pressure, precipitation, sunlight,
and so on during the period from 2013 to 2017. Road grade data were sourced from the
research carried out by Gao et al. (2020) [48], specifically, splicing the Map of China based
on Shuttle Radar Topography Mission (SRTM) Global Digital Elevation Model, and then
connected with the administrative boundary data of China at the county level. Next, the
administrative boundary of the county was cut out, and the road grade of each grid in the
region was calculated. Finally, the average value, minimum value, maximum value, and
standard difference of road grade in each region are obtained. We selected the average road
grade of each county in this study.
Each piece of climate data consists of a regional station number and monthly weather
information. Climate information varies greatly in regions during the observation period
so that it should not be ignored when predicting the real-world fuel consumption rate
of vehicles. Since the climate of a certain city during a certain month is almost in a fixed
pattern, we averaged each climate factor in each month of different cities. Specifically,
number 1 was assigned to north wind and the number increased by 1 for every 22.5 degrees
clockwise for the wind direction factor. Additionally, if the wind speed does not reach
0.2 m/s, it is considered calm and the number 17 is assigned. In total, wind direction
categories consist of numbers successively from 1 to 17.
It is worth noting that strong correlation between climate features often leads to
multicollinearity, so we conducted a correlation coefficient test on the input climate features.
For the feature pairs with correlation coefficient above 0.8, we eliminated one of them.
Finally, the environment factors selected in this study are shown in Table 6.
Energies 2022, 15, 1602 9 of 17

Table 6. Selected environment factors.

Environment Factors Unit


Average pressure 0.1 hPa
Average temperature 0.1 ◦ C
Average temperature anomaly 0.1 ◦ C
Mean relative humidity 1%
Average wind speed 0.1 m/s
Maximum wind direction azimuth
Extreme maximum wind direction azimuth
Average precipitation 0.1 mm
Daily precipitation ≥ 0.1 mm days 1 day
Sunshine time 0.1 h
Road grade ◦

We matched the real-world fuel consumption rate with the corresponding driving
behavior information and climate information by User ID, city, and date, and combined
them to be used as input variables in our models.

3.2. Model Selection and Criteria


The selection of the input factors is described in the above section and in this section,
we introduce the model selection procedure.
Firstly, fuel consumption forecast is a continuous variable forecast, where regression
models should be applied. In addition to the pursuit of accuracy of fuel consumption
prediction, our research also aims to identify the most important factors affecting fuel
consumption to strengthen the interpretability of each model. In this case, linear regression,
also as the fastest and the most typical regression prediction algorithm, is suitable. However,
maximum likelihood estimation of linear regression only considers the maximization of
likelihood function. From the perspective of Bayes’ theorem, maximum posterior estimation
treats parameter values as random variables, therefore, Naïve Bayes regression was selected.
Moreover, linear regression cannot capture a nonlinear relationship. As a result, we
selected neural network regression and decision tree regression, which are widely used in
nonlinear relationship prediction. It should be noted that decision tree regression is often
not accurate since it is prone to over-fitting. Low bias and high variance often occur in a
tree with deep depth and there are two ways commonly used to improve decision tree
regression, namely bagging and boosting.
Random forest regression averages multiple decision trees based on bagging algorithm
and can significantly reduce variance to improve overfitting. A typical example of an
improved decision tree regression based on boosting is the GBDT model. Compared with
the traditional GBDT model, XGBoost model adds regular terms in the cost function to
control the complexity of the model, and it allows column sampling to prevent overfitting.
LightGBM, as an improvement of XGBoost model, which takes up less memory and reduces
complexity of data segmentation, has shown high prediction speed in many studies.
Above all, we selected linear regression, naïve Bayes regression, neural network
regression, random forest regression, and LightGBM in this paper.
The architecture of the models are as follows. There are 64 neurons in the input layer of
the neural network model. The activation function is set as max(0,x) to follow the common
practice [49]. While the number of neurons is 64 according to the geometric pyramid
rule proposed by Masters in the hidden layer [50], and the activation function is set as
max(0,x). To reduce overfitting [51], the input matrix is processed with L2 regularization
and the output matrix is processed with L1 regularization while the value of lambda is
set as 0.05. There is one neuron in the third layer. At the same time, we selected RMSprop as
the optimizer [52], MSE as the loss function, and MAE as the metric function [53,54]. For the
random forest regression, the number of estimators is set as 20 which is the setting that achieves
Energies 2022, 15, 1602 10 of 17

best performance through multiple tests. For better accuracy [55], we set 25 leaf nodes in the
LightGBM model with the learning rate of 0.01 and the number of iterations of 5000.
The rules for model comparison include the mean absolute error (MAE), mean absolute
percentage error (MAPE), mean squared error (MSE), R squared (R2 ), cross-validation scores
and the calculation formula of MAE, MAPE, MSE, and R2 are shown below.

1 n
n i∑
MAE = yi − yi0 (1)
=1

1 n yi − yi0
n i∑
MAPE = (2)
=1
yi

1 n

2
MSE = yi − yi0 (3)
n i =1
2
2 ∑in=1 yi − yi0
R = 1− 2
(4)
∑in=1 (yi − yi )
where yi refers to the true value, yi0 refers to the predicted value, and yi refers to the mean
actual value. The smaller the value of MAE, MAPE, and MSE, the larger the value of R2
and cross-validation score, the smaller the error between the predicted and the actual value,
which also indicates the better performance.

4. Results
4.1. Training and Test Results
Row data include 1,335,232 records from 24,149 gasoline vehicle owners during the
period from 2004 to 2019. In the process of data preprocessing, 10,708 records with miss-
ing values and 355,185 records outside the observation period were removed, leaving
969,339 records. Next, we excluded detected fuel consumption outliers and 773,469 data
records remained in this stage. Finally, we averaged the fuel consumption of vehicle own-
ers with the same vehicle model and with same driving behaviors. The ultimate dataset
contains 171,089 pieces of data.
After merging the environment factors, we divided the dataset into training sets and
test sets in a ratio of 7 to 3, which is a common practice for predicting the performance
of vehicle engines with machine learning models. In Table 7, refConsumption refers to
the reference fuel consumption value provided by MIIT. It can be seen that there is a large
gap between the reference fuel consumption rate value and the actual case. Table 7 also
presents errors of the training and testing process of each proposed model.

Table 7. Result of each regression model.

Training Data Testing Data


Model
MAE MAPE MSE R2 MAE MAPE MSE R2
RefConsumption 1.650 24.2% 4.276 −2.234 1.654 24.2% 4.322 −2.288
Linear regression 0.959 11.7% 1.550 0.558 0.965 11.7% 1.585 0.559
Naïve Bayes 0.959 11.7% 1.550 0.558 0.965 11.7% 1.585 0.559
Neural network 0.800 9.6% 1.146 0.674 0.827 9.9% 1.225 0.659
Random forest 0.245 2.9% 0.127 0.964 0.630 7.5% 0.805 0.776
LightGBM 0.701 8.5% 1.876 0.750 0.747 9.0% 1.011 0.718

In Table 8, we present average prediction results of 10 runs of 5 proposed model by dis-


placement distribution, referring to the practice by Liu et al. (2018) [6] and Zeng et al. (2021) [32].
The displacement range is divided according to Chinese national standard GB3730.1-88.
Clearly, random forest regression show the best prediction validation in vehicles in all
engine displacement ranges.
Energies 2022, 15, 1602 11 of 17

Table 8. Average predicted results.

Engine Displacement (ED)


Model
ED ≤ 0.8 L 0.8 L < ED ≤ 1.6 L 1.6 L < ED ≤ 2.5 L 2.5 L < ED ≤ 4.0 L ED > 4.0 L

Linear regression Predicted value 7.258 7.813 8.868 10.187 14.853


Deviation 1 26.413% 0.225% 0.164% 3.396% 4.566%
Energies 2022, 15, x FOR PEER REVIEW 12 of 18
Naïve Bayes Predicted value 7.257 7.813 8.868 10.188 14.854
Deviation 26.401% 0.225% 0.164% 3.401% 4.561%
Predicted value 6.019 7.969 9.015 9.900 14.822
Neural network Deviation 2.726% 1.485% 1.596% 1.730% 8.557%
Predicted value which is5.851
more accurate with 7.851 8.872
a MAPE of 7.5%. Results show that our9.874 15.690
proposed regression
Random forest Deviation 0.138% 0.025% 0.014% 0.222% 1.979%
Predicted value model could
5.743 be applied into practice
7.842 for prediction
8.872 and revision. 12.491 15.721
LightGBM
Deviation In 1.975%
addition, in order 0.140%
to avoid the impact0.137% 0.345%
of sample size on the 3.013%
model performance,
1 we selected
Deviation the mean
= | Predicted square
value− Real value| errors (MSE) as comparison criteria as well. According to
× 100.
Real value
Figure 1, results reveal that MSE of the random forest regression is the smallest. Again,
thisModels
4.2. provesComparison
that random forest is the best model among all the candidate models.
R2, on the other hand, can measure the extent to which independent variables explain
Figure 1 shows the mean absolute error (MAE) between the model prediction values
dependent variables. Moreover, unlike the comparison criteria above, R 2 has clear upper
and the
and loweractual values.
limits. MAE in
As shown from the 1,
Figure reference consumption
the reference rate provided
fuel consumption rate is by
notthe MIIT is
explan-
1.654 L/100 km, while MAE from our models including vehicle factors and environment
atory to the actual case, while random forest regression reaches the largest R2 value. It
factors is all
indicates thatbelow 1 L/100 km.
the independent Among
variables therandom
in the five models, MAE of the
forest regression random
explain 77.6%forest
of
regression model
the variation (0.630
in the L/100 km)
dependent is the lowest.
variable.

1.800
1.585 1.585
1.600

1.400
1.225
1.200
0.965 0.965 1.011
1.000
0.827 0.805
0.747 0.776
0.800 0.718
0.630 0.659
0.559 0.559
0.600

0.400

0.200 11.7%11.7% 9.9% 7.5% 9.0%

0.000
MAE(L/100km) MAPE(%) MSE(L/100km)² R²
Linear regression Naïve Bayes Neural network Random Forest LightGBM

Figure 1. Evaluation indicators of the five models.


Figure 1. Evaluation indicators of the five models.
Since MAE
While the training dataset and
is the absolute test
value ofdataset are selected
the prediction error,randomly,
it may notregression results
sufficiently capture
may have random fluctuations, we then applied the 10-fold cross-validation to assess the
how much the deviation is relative to the actual value. For this reason, we also calculated the
performance of five regression models. The scoring function of 10-fold cross-validation is
mean absolute percentage error (MAPE). The reference fuel consumption rate is deviated
R2. The scores of the models each time are shown in Figure 2 and the average scores of the
greatly from the actual case since the MAPE between them is approximately 24.2%. Under
10-fold cross-validation are shown in Table 9. Figure 2 indicates that linear regression and
this standard, the best prediction model is still random forest regression, which is more
naïve Bayes regression show similar accuracy since the corresponding two lines are over-
accurate with a MAPE of 7.5%. Results show that our proposed regression model could be
lapping. Clearly, random forest regression performs the best with the highest line in Fig-
applied into practice for prediction and revision.
ure 2 and the largest value in Table 9.
In addition, in order to avoid the impact of sample size on the model performance,
we selected the mean square errors (MSE) as comparison criteria as well. According to
Figure 1, results reveal that MSE of the random forest regression is the smallest. Again, this
proves that random forest is the best model among all the candidate models.
R2 , on the other hand, can measure the extent to which independent variables ex-
plain dependent variables. Moreover, unlike the comparison criteria above, R2 has clear
upper and lower limits. As shown in Figure 1, the reference fuel consumption rate is not
explanatory to the actual case, while random forest regression reaches the largest R2 value.
Energies 2022, 15, 1602 12 of 17

It indicates that the independent variables in the random forest regression explain 77.6% of
the variation in the dependent variable.
Since the training dataset and test dataset are selected randomly, regression results
may have random fluctuations, we then applied the 10-fold cross-validation to assess the
performance of five regression models. The scoring function of 10-fold cross-validation is
R2 . The scores of the models each time are shown in Figure 2 and the average scores of
the 10-fold cross-validation are shown in Table 9. Figure 2 indicates that linear regression
and naïve Bayes regression show similar accuracy since the corresponding two lines are
overlapping. Clearly, random forest regression performs the best with the highest
Energies 2022, 15, x FOR PEER REVIEW line
13 of 18 in
Figure 2 and the largest value in Table 9.

0.850
0.800
0.750
0.700
0.650
0.600
0.550
0.500
0.450
0.400
1 2 3 4 5 6 7 8 9 10
Number of times of cross-validation
Linear regression Naïve Bayes Neural network Random Forest LightGBM

Figure 2. Scores of the models each time.


Figure 2. Scores of the models each time.
Table 9. Average scores of the 10-fold cross-validation.
Table 9. Average scores of the 10-fold cross-validation.
Model Average Cross Validation Score
Model Average Cross Validation Score
Linear regression 0.5583183
Linear
Naï regression
ve Bayes 0.5583183
0.5583183
Naïve
Neural Bayes
network 0.5583183
0.5952532
Neural network 0.5952532
Random forest 0.7913839
Random forest 0.7913839
LightGBM
LightGBM 0.7221006
0.7221006

The above results indicate that the prediction errors of the actual fuel consumption
rateThe above
based results
on the data indicate
of vehiclethat the prediction
factors, errors ofand
driving behaviors, theenvironment
actual fuel consumption
factors are
rate based on the data of vehicle factors, driving behaviors, and
far lower than that of the reference fuel consumption rate. Specifically, environment
the MAPEfactors
value isare
far lower than
decreased that ofbythe
by 16.7% reference
random forest fuel consumption
regression, which rate.
is theSpecifically,
optimal model the with
MAPE thevalue
best is
decreased by 16.7%
performance. by show
Results random thatforest regression,
the proposed which ismodel
prediction the optimal
can bemodel with
put into the best
practice
performance.
for providingResults show that
more precise the proposed
estimates prediction
of the fuel model
consumption ratecan be put
in the into practice
real-world appli-for
providing
cations. more precise estimates of the fuel consumption rate in the real-world applications.

5.5.Discussion
Discussion
Comparison
Comparisonanalysis
analysis indicates that the
indicates that therandom
randomforest
forestregression
regression achieved
achieved thethe best
best
performance.
performance.Therefore,
Therefore, we estimated theweight
estimated the weightofofinput
inputparameters
parameters inin random
random forest
forest
regression,
regression,and
andthe
theresult
resultisisshown
shown in Figure 3.
Figure 3.
According to Figure 3, reference fuel consumption rate is the parameter with the
highest weight, which indicates that it could be a basis for the fuel consumption predic-
tion.
Energies 2022,15,
Energies2022, 15,1602
x FOR PEER REVIEW 13 of 17
14 18

0.479
0.5

0.4

0.3
Weight

0.2

0.1 0.061 0.057


0.035 0.031 0.03 0.028 0.027 0.024 0.022 0.02 0.019 0.018 0.017 0.017 0.016 0.016 0.015 0.015 0.012 0.01 0.01 0.006 0.001 0.001
0

Feature

Figure3.
Figure 3. Weights
Weightsof
of25
25factors
factorsin
inthe
therandom
randomforest
forestmodel.
model.

Among all to
According theFigure
factors,3, the drivingfuel
reference behavior-related
consumption rate factors weigh
is the the heaviest
parameter with and
the
have the
highest greatest
weight, influence
which on fuel
indicates that consumption. Specifically,
it could be a basis for the fuel driving habit dimension
consumption prediction. in
Among
this study all theon
focuses factors, the driving
two aspects, that is,behavior-related
whether there are factors weigh stop-and-go
frequently the heaviestdriv- and
have
ing andthe whether
greatest influence
the vehicle onowners
fuel consumption. Specifically,
often brake sharply or pressdriving
the habit dimension
accelerator hard.
in this study
Previous focuses
studies haveon two aspects,
revealed that is, whether
that stop-and-go driving there
and are slam frequently
on the brake stop-and-go
behavior
driving and whether
are wasteful for fuel the[56].vehicle
Evansowners oftenrecommended
(1978) also brake sharply that or press the anticipate
drivers acceleratorcondi-
hard.
Previous
tions ahead studies have revealed
to minimize braking thatsince
stop-and-go
previousdriving
extracted andenergy
slam on the brake
would behavior
be unproduc-
are wasteful
tively for fuel
dissipated [56].there
when Evansis(1978) also recommended
a braking [57]. The second thatmost drivers anticipate
important conditions
factor in this
ahead to minimize braking since previous extracted energy
regard is fuel economy consciousness. In this study, six questions were set to score the would be unproductively
dissipated
fuel economy when there is a braking
consciousness [57]. The
of gasoline second
vehicle mostThe
owners. important
result isfactor
in lineinwith
this regard
common is
fuel economy consciousness. In this study, six questions were
sense, that is, the more fuel economy consciousness vehicle owners have, the more they set to score the fuel economy
consciousness
avoid excess power of gasoline vehicle during
consumption owners.driving
The result
and theis inmoreline with common
they care aboutsense, that
the condi-
is, theofmore
tion fuelthe
the car, economy consciousness
less gasoline vehicleThis
they consume. owners have, thebymore
is followed car usetheyfrequency
avoid excessand
power consumption during driving and the more they care about
driving skills, which indicates that the frequency of vehicle use, the driving and parking the condition of the car,
the less gasoline they consume. This is followed by car use frequency
skills of car owners in daily life are also closely related to car fuel consumption. In addi- and driving skills, which
indicates that the
tion, driving frequency
speed of vehicleasuse,
is recognized the driving
having effectsandonparking skills of car owners
fuel consumption. Haworth in daily
and
life are also closely related to car fuel consumption. In addition, driving
Symmons (2001) also suggest that driving speed is positively related to fuel consumption speed is recognized as
having effects on fuel consumption. Haworth and Symmons
[58] and research highlights that the optimum fuel economy cruising speeds range be- (2001) also suggest that driving
speed
tweenis40positively
and 50 km/hrelated to fuel consumption [58] and research highlights that the optimum
[59].
fuel economy cruising speeds
Engine power is the second rangeimportant
between 40factor
and 50among
km/h all [59].the related factors with a
Engine power is the second important factor among all the related factors with a
weight of more than 0.05. It has been widely acknowledged that more horsepower implies
weight of more than 0.05. It has been widely acknowledged that more horsepower implies
more fuel consumption [60]. The following is brand name with a weight of 0.028. In the
more fuel consumption [60]. The following is brand name with a weight of 0.028. In the
reality, some manufacturers carry out brand marketing with the slogan of fuel saving. For
reality, some manufacturers carry out brand marketing with the slogan of fuel saving. For
example, Japanese cars have always been known for fuel economy, and Honda and
example, Japanese cars have always been known for fuel economy, and Honda and Toyota
Toyota are the typical brands of fuel economy [61]. Gearbox type is also seen as an im-
are the typical brands of fuel economy [61]. Gearbox type is also seen as an important
portant vehicle-related factor when predicting the fuel consumption with a weight of
vehicle-related factor when predicting the fuel consumption with a weight of 0.022.
0.022.
Moreover, in the aspect of environmental factors, air pressure was identified as the
Moreover, in the aspect of environmental factors, air pressure was identified as the
most important environmental factor in this study, with a weight of 0.027. Air pressure
most important environmental factor in this study, with a weight of 0.027. Air pressure
affects fuel consumption by directly affecting tire pressure. When tire pressure is relatively
affects fuel consumption by directly affecting tire pressure. When tire pressure is rela-
large, fuel consumption is considered to be lower [62]. Air temperature also affects fuel
tively large, fuel
consumption consumption
through is considered
tire pressure [63], andtoitsbeweight
lower [62].in thisAirstudy
temperature
is 0.018.also affects
Average
fuel consumption through tire pressure [63], and its weight in
wind speed and road grade are the second and third most important environmental factors, this study is 0.018. Average
wind speed and
respectively. road grade
The higher are the wind
the average second and is,
speed third
the most
greater important environmental
the air resistance is, and fac-
the
tors, respectively. The higher the average wind
greater the road grade is, the more gasoline the car consumes [64]. speed is, the greater the air resistance is,
and the greater the road grade is, the more gasoline the car consumes [64].
Energies 2022, 15, 1602 14 of 17

Above all, in this section we conducted a comparative analysis of the factors from
aspects of vehicle attribution, driving behavior, and environment to capture the factors that
influence the fuel consumption value and found that, among all the factors, the driving
behavior factors that have the greatest impact on the real-world fuel consumption rate
are engine power and brand name. The driving behavior factors that have the greatest
impact are driving habit, fuel economy consciousness, car use frequency, and driving skills.
The environment factors that have the greatest impact are average pressure, average wind
speed, road grade, and average temperature.

6. Conclusions
The prediction of fuel consumption is a black-box problem with asymmetric informa-
tion. In China, the fuel consumption information mainly comes from the reference values
provide by Ministry of Industry and Information Technology of the People’s Republic of
China. However, the real-world fuel consumption is greater than the reference value in
most situations. The underestimation of fuel consumption brings negative effect in multiple
aspects of policy, industry, and market.
Since machine learning models have been widely applied to prediction problems
in the field of engine performance, we utilized five regression models, namely, linear
regression, naïve Bayes regression, neural network regression, random forest regression,
and LightGBM models, to forecast the real-world fuel consumption rate of light-duty
vehicles, and capture the important features that influence fuel consumption, based on big
data from the aspects of vehicle factors, environment factors, and driving behavior factors
in this paper.
After training and testing, results show that the mean absolute error, mean absolute
percentage error, mean squared error, R squared, and 10-fold cross-validation values
between the prediction values and the actual fuel consumption rate are far better than the
reference value. The comparison analysis of the different models suggest that the random
forest regression model performs best among the 5 proposed models under all the criteria
with a mean absolute error of 0.630 L/100 km, a mean absolute percentage error of 7.5%, a
mean squared error of 0.805, an R squared of 0.776, and a 10-fold cross-validation score of
0.791, respectively.
Finally, we assess the weight of 25 different factors and capture the priority order
of each factor. Clearly, the three most important factors affecting fuel consumption are
brake and accelerator habits, engine power, and the fuel economy consciousness of vehicle
owners in sequence, according to the relative weight of each factor in the random forest
model. For a vehicle owner who is not a BearOil app user, the real fuel consumption of
the vehicle can be predicted according to reference fuel consumption and related feature
information based on our model. Research results provide a meaningful reference for
consumers, manufacturers, and related government departments.

Author Contributions: Conceptualization, Y.Y. and Q.L.; methodology, Y.Y., N.G., and K.X.; formal
analysis, Y.Y.; resources, Y.Y. and Q.L.; data curation, Y.Y.; writing—original draft preparation, Y.Y.;
writing—review and editing, K.X. and N.G.; funding acquisition, Q.L. All authors have read and
agreed to the published version of the manuscript.
Funding: The project was sponsored by the National Natural Science Foundation of China (11902350).
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Acknowledgments: For helpful comments and discussions, we thank Liulei Shen.
Conflicts of Interest: The authors declare no conflict of interest.
Energies 2022, 15, 1602 15 of 17

References
1. Tietge, U.; Mock, P.; Franco, V.; Zacharof, N. From laboratory to road: Modeling the divergence between official and real-world
fuel consumption and CO2 emission values in the German passenger car market for the years 2001–2014. Energy Policy 2017, 103,
212–222. [CrossRef]
2. Zeng, I.Y.; Tan, S.; Xiong, J.; Ding, X.; Li, Y.; Wu, T. Estimation of real-world fuel consumption rate of light-duty vehicles based on
the records reported by vehicle owners. Energies 2021, 14, 7915. [CrossRef]
3. Zhao, X.; Ma, X.; Chen, B.; Shang, Y.; Song, M. Challenges toward carbon neutrality in China: Strategies and countermeasures.
Resour. Conserv. Recycl. 2022, 176, 105959. [CrossRef]
4. Pavlovic, J.; Marotta, A.; Ciuffo, B. CO2 emissions and energy demands of vehicles tested under the NEDC and the new WLTP
type approval test procedures. Appl. Energy 2016, 177, 661–670. [CrossRef]
5. Chen, K.; Zhao, F.; Liu, X.; Hao, H.; Liu, Z. Impacts of the new worldwide light-duty test procedure on technology effectiveness
and china’s passenger vehicle fuel consumption regulations. Int. J. Environ. Res. Public Health 2021, 18, 3199. [CrossRef]
6. Liu, Y.; Xu, Y.; Li, M.; Qin, K.; Yu, H.; Zhou, H. Feasibility study of using WLTC for fuel consumption certification of Chinese
light-duty vehicles. In Proceedings of the SAE International WCX World Congress Experience 2018, Detroit, MI, USA, 10–12
April 2018; pp. 1–8.
7. Duarte, G.; Gonçalves, G.; Farias, T. Analysis of fuel consumption and pollutant emissions of regulated and alternative driving
cycles based on real-world measurements. Transp. Res. Part D Transp. Environ. 2016, 44, 43–54. [CrossRef]
8. Luján, J.M.; Garcia, A.; Monsalve-Serrano, J.; Martínez-Boggio, S. Effectiveness of hybrid powertrains to reduce the fuel
consumption and NOx emissions of a Euro 6d-temp diesel engine under real-life driving conditions. Energy Convers. Manag.
2019, 199, 111987. [CrossRef]
9. Wang, Y.; Hao, C.; Ge, Y.; Hao, L.; Tan, J.; Wang, X.; Zhang, P.; Wang, Y.; Tian, W.; Lin, Z. Fuel consumption and emission performance
from light-duty conventional/hybrid-electric vehicles over different cycles and real driving tests. Fuel 2020, 278, 118340. [CrossRef]
10. Karagöz, Y. Analysis of the impact of gasoline, biogas and biogas+ hydrogen fuels on emissions and vehicle performance in the
WLTC and NEDC. Int. J. Hydrog. Energy 2019, 44, 31621–31632. [CrossRef]
11. Redsell, M.; Lucas, G.; Ashford, N. Factors affecting car fuel consumption. Proc. Inst. Mech. Eng. Part D J. Automob. Eng. 1993, 207, 1–22.
[CrossRef]
12. Kashinath, K.; Mustafa, M.; Albert, A.; Wu, J.; Jiang, C.; Esmaeilzadeh, S.; Azizzadenesheli, K.; Wang, R.; Chattopadhyay, A.; Singh, A.
Physics-informed machine learning: Case studies for weather and climate modelling. Philos. Trans. R. Soc. A 2021, 379, 20200093.
[CrossRef] [PubMed]
13. Wickramanayake, S.; Bandara, H.D. Fuel consumption prediction of fleet vehicles using machine learning: A comparative
study. In Proceedings of the 2016 Moratuwa Engineering Research Conference (MERCon), Moratuwa, Sri Lanka, 5–6 April 2016;
pp. 90–95.
14. Van Mierlo, J.; Maggetto, G.; Van de Burgwal, E.; Gense, R. Driving style and traffic measures-influence on vehicle emissions and
fuel consumption. Proc. Inst. Mech. Eng. Part D J. Automob. Eng. 2004, 218, 43–50. [CrossRef]
15. Perrotta, F.; Parry, T.; Neves, L.C. Application of machine learning for fuel consumption modelling of trucks. In Proceedings of
the 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, USA, 11–14 December 2017; pp. 3810–3815.
16. Rahman, A.; Smith, A.D. Predicting fuel consumption for commercial buildings with machine learning algorithms. Energy Build.
2017, 152, 341–358. [CrossRef]
17. Zhou, M.; Jin, H.; Wang, W. A review of vehicle fuel consumption models to evaluate eco-driving and eco-routing. Transp. Res.
Part D Transp. Environ. 2016, 49, 203–218. [CrossRef]
18. Heywood, J.B. Internal Combustion Engine Fundamentals. McGraw-Hill Education: New York, NY, USA, 2018.
19. Parlak, A.; Islamoglu, Y.; Yasar, H.; Egrisogut, A. Application of artificial neural network to predict specific fuel consumption and
exhaust temperature for a diesel engine. Appl. Therm. Eng. 2006, 26, 824–828. [CrossRef]
20. Togun, N.; Baysec, S. Genetic programming approach to predict torque and brake specific fuel consumption of a gasoline engine.
Appl. Energy 2010, 87, 3401–3408. [CrossRef]
21. Silva, C.; Farias, T.; Frey, H.C.; Rouphail, N.M. Evaluation of numerical models for simulation of real-world hot-stabilized fuel
consumption and emissions of gasoline light-duty vehicles. Transp. Res. Part D Transp. Environ. 2006, 11, 377–385. [CrossRef]
22. Ziółkowski, J.; Oszczypała, M.; Małachowski, J.; Szkutnik-Rogoż, J. Use of Artificial Neural Networks to Predict Fuel Consumption
on the Basis of Technical Parameters of Vehicles. Energies 2021, 14, 2639. [CrossRef]
23. Togun, N.K.; Baysec, S. Prediction of torque and specific fuel consumption of a gasoline engine by using artificial neural networks.
Appl. Energy 2010, 87, 349–355. [CrossRef]
24. Jahirul, M.; Saidur, R.; Masjuki, H.H. Application of artificial neural network to predict brake specific fuel consumption of
retrofitted cng engine. Int. J. Mech. Mater. Eng. 2009, 4, 249–255.
25. Hjellvik, M.A.; Ratnayake, R.C. Machine learning based approach to predict short-term fuel consumption on mobile offshore
drilling units. In Proceedings of the 2019 IEEE International Conference on Industrial Engineering and Engineering Management
(IEEM), Macao, China, 15–18 December 2019; pp. 1067–1073.
26. Syahputra, R. Application of neuro-fuzzy method for prediction of vehicle fuel consumption. J. Theor. Appl. Inf. Technol. 2016, 86,
138–150.
Energies 2022, 15, 1602 16 of 17

27. Yao, Y.; Zhao, X.; Liu, C.; Rong, J.; Zhang, Y.; Dong, Z.; Su, Y. Vehicle fuel consumption prediction method based on driving
behavior data collected from smartphones. J. Adv. Transp. 2020, 2020. [CrossRef]
28. Ping, P.; Qin, W.; Xu, Y.; Miyajima, C.; Takeda, K. Impact of driver behavior on fuel consumption: Classification, evaluation and
prediction using machine learning. IEEE Access 2019, 7, 78515–78532. [CrossRef]
29. Li, Y.; Tang, G.; Du, J.; Zhou, N.; Zhao, Y.; Wu, T. Multilayer perceptron method to estimate real-world fuel consumption rate of
light duty vehicles. IEEE Access 2019, 7, 63395–63402. [CrossRef]
30. Dror, M.B.; Qin, L.; An, F. The gap between certified and real-world passenger vehicle fuel consumption in China measured using
a mobile phone application data. Energy Policy 2019, 128, 8–16. [CrossRef]
31. Wu, T.; Han, X.; Zheng, M.M.; Ou, X.; Sun, H.; Zhang, X. Impact factors of the real-world fuel consumption rate of light duty
vehicles in China. Energy 2020, 190, 116388. [CrossRef]
32. Zhou, B.; Zhang, S.; Wu, Y.; Ke, W.; He, X.; Hao, J. Energy-saving benefits from plug-in hybrid electric vehicles: Perspectives
based on real-world measurements. Mitig. Adapt. Strateg. Glob. Change 2018, 23, 735–756. [CrossRef]
33. Ahn, K.; Rakha, H. The effects of route choice decisions on vehicle energy consumption and emissions. Transp. Res. Part D Transp.
Environ. 2008, 13, 151–167. [CrossRef]
34. Greenwood, I.; Dunn, R.; Raine, R. Estimating the effects of traffic congestion on fuel consumption and vehicle emissions based
on acceleration noise. J. Transp. Eng. 2007, 133, 96–104. [CrossRef]
35. Ostrouchov, N. Effect of cold weather on motor vehicle emissions and fuel economy. In Proceedings of the SAE International 1978
Automotive Engineering Congress and Exposition, Detroit, MI, USA, 27 February–3 March 1978; pp. 1–16.
36. He, C.R.; Maurer, H.; Orosz, G. Fuel consumption optimization of heavy-duty vehicles with grade, wind, and traffic information.
J. Comput. Nonlinear Dyn. 2016, 11. [CrossRef]
37. Pekula, N.; Kuritz, B.; Hearne, J.; Marchese, A.; Hesketh, R. The effect of ambient temperature, humidity, and engine speed on
idling emissions from heavy-duty diesel trucks. SAE Transac. 2003, 112, 148–158.
38. Sriwilai, A.; Pattaraprakorn, W.; Chutiprapat, V.; Sansilah, C.; Bhasaputra, P. The study on the effect of electric car to energy
consumption in Thailand. In Proceedings of the 2016 13th International Conference on Electrical Engineering/Electronics,
Computer, Telecommunications and Information Technology (ECTI-CON), Chiang Mai, Thailand, 28 June–1 July 2016; pp. 1–5.
39. Ben-Chaim, M.; Shmerling, E.; Kuperman, A. Analytic modeling of vehicle fuel consumption. Energies 2013, 6, 117–127. [CrossRef]
40. Joumard, R.; Jost, P.; Hickman, J. Influence of instantaneous speed and acceleration on hot passenger car emissions and fuel
consumption. SAE Tech. Paper 1995, 950928. [CrossRef]
41. Ericsson, E. Independent driving pattern factors and their influence on fuel-use and exhaust emission factors. Transp. Res. Part D
Transp. Environ. 2001, 6, 325–345. [CrossRef]
42. El-Shawarby, I.; Ahn, K.; Rakha, H. Comparative field evaluation of vehicle cruise speed and acceleration level impacts on hot
stabilized emissions. Transp. Res. Part D Transp. Environ. 2005, 10, 13–30. [CrossRef]
43. Kamal, M.A.S.; Mukai, M.; Murata, J.; Kawabe, T. Ecological vehicle control on roads with up-down slopes. IEEE Trans. Intell.
Transp. Syst. 2011, 12, 783–794. [CrossRef]
44. Barth, M.; Boriboonsomsin, K.; Vu, A. Environmentally-friendly navigation. In Proceedings of the 2007 IEEE Intelligent
Transportation Systems Conference, Bellevue, WA, USA, 30 September–3 October 2007; pp. 684–689.
45. Biggs, D. ARFCOM: Models for Estimating Light to Heavy Vehicle Fuel Consumption; ARRB Transport Research Ltd.: Vermont, SA,
Australia, 1988.
46. Renouf, M. Prediction of the Fuel Consumption of Heavy Goods Vehicles by Computer Simulation; Transport and Road Research Lab.:
Crowthorne, UK, 1979.
47. Sanchez, M.; Cano, J.-C.; Kim, D. Predicting traffic lights to improve urban traffic fuel consumption. In Proceedings of the 2006
6th International Conference on ITS Telecommunications, Chengdu, China, 21–23 June 2006; pp. 331–336.
48. Gao, Y.; Liu, Z.; Li, R.; Shi, Z. Long-term impact of China’s returning farmland to forest program on rural economic development.
Sustainability 2020, 12, 1492. [CrossRef]
49. Agarap, A.F. Deep Learning Using Rectified Linear Units (RELU). arXiv 2018, arXiv:1803.08375.
50. Masters, T. Practical Neural Network Recipes in C++; Morgan Kaufmann: Burlington, MA, USA, 1993.
51. Ying, X. An overview of overfitting and its solutions. J. Phys. Conf. Ser. 2019, 1168, 022022. [CrossRef]
52. Zou, F.; Shen, L.; Jie, Z.; Zhang, W.; Liu, W. A sufficient condition for convergences of adam and rmsprop. In Proceedings of the
IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 16–17 June 2019; pp. 11127–11135.
53. Christoffersen, P.; Jacobs, K. The importance of the loss function in option valuation. J. Financ. Econ. 2004, 72, 291–318. [CrossRef]
54. Chai, T.; Draxler, R.R. Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the
literature. Geosci. Model Dev. 2014, 7, 1247–1250. [CrossRef]
55. Ke, G.; Meng, Q.; Finley, T.; Wang, T.; Chen, W.; Ma, W.; Ye, Q.; Liu, T.-Y. Lightgbm: A highly efficient gradient boosting decision
tree. Adv. Neural Inf. Processing Syst. 2017, 30, 3146–3154.
56. Hooker, J.N. Optimal driving for single-vehicle fuel economy. Transp. Res. Part A Gen. 1988, 22, 183–201. [CrossRef]
57. Evans, L. Driver behavior effects on fuel consumption in urban driving. In Proceedings of the Human Factors Society Annual
Meeting, Los Angeles, CA, USA, 1 October 1978; pp. 437–442.
58. Haworth, N.; Symmons, M. Driving to reduce fuel consumption and improve road safety. In Proceedings of the Australasian
Road Safety Research, Policing and Education Conference, Melbourn, VIC, Australia, 18–20 November 2001.
Energies 2022, 15, 1602 17 of 17

59. Wang, J.; Rakha, H.A. Fuel consumption model for conventional diesel buses. Appl. Energy 2016, 170, 394–402. [CrossRef]
60. Walnum, H.J.; Simonsen, M. Does driving behavior matter? An analysis of fuel consumption data from heavy-duty trucks. Transp.
Res. Part D Transp. Environ. 2015, 36, 107–120. [CrossRef]
61. Plotkin, S.E. European and Japanese fuel economy initiatives: What they are, their prospects for success, their usefulness as a
guide for US action. Energy Policy 2001, 29, 1073–1084. [CrossRef]
62. Rahimi-Gorji, M.; Ghajar, M.; Kakaee, A.-H.; Ganji, D.D. Modeling of the air conditions effects on the power and fuel consumption
of the SI engine using neural networks and regression. J. Braz. Soc. Mech. Sci. Eng. 2017, 39, 375–384. [CrossRef]
63. Ehsani, M.; Ahmadi, A.; Fadai, D. Modeling of vehicle fuel consumption and carbon dioxide emission in road transport. Renew.
Sustain. Energy Rev. 2016, 53, 1638–1648. [CrossRef]
64. Fontaras, G.; Zacharof, N.-G.; Ciuffo, B. Fuel consumption and CO2 emissions from passenger cars in Europe–Laboratory versus
real-world emissions. Prog. Energy Combust. Sci. 2017, 60, 97–131. [CrossRef]

You might also like