ARTIFICIAL INTELLIGENCE

IN CIVIL ENGINEERING
PRESENTED BY
1
ASEENA.L
ROLL NO:20
S7 CE

MCET
2 CONTENTS
1. Introduction

2. Development of AI

3. Intelligent optimization methods in civil engineering

4. Application of AI in civil engineering

5. Future trends

6. Advantages

7. Disadvantages

8. Conclusion

9. Reference
 INTRODUCTION
3
• Branch of computer science, involves- research, design and application of computer
science- developed in 1956

• Goal- how to imitate and execute some of the intelligent functions of human brain

• Interaction of several kinds of disciplines such as

 Computer science

 Cybernetics

 Information theory

 Psychology

 Neurophysiology
4
• Main theories and methods -

 Symbolism

 Behaviourism

 Connectionism approach
5
DEVELOPMENT OF AI

• Developed by John McCarthy

• Describes the process of human thinking as a mechanical manipulation of symbols

• Main constituents of soft computing -

 Neural networks

 Evolutionary algorithms

 Probability reasoning

 Fuzzy-logic
6
• Application of AI in civil engineering include the use of ANN in

 Designing

 Planning

 Construction and management of infrastructures

• Helps to predict tender bids, construction cost and construction budget

performance
 INTELLIGENT OPTIMIZATION METHODS
7 IN CIVIL ENGINEERING

• Applied in

 Expert system

 Knowledge base system

 Intelligent database system

 Intelligent robot system

• Expert system- “the knowledge management and decision-making technology of the

21st century”
 APPLICATION OF AI IN CIVIL
8
ENGINEERING

• Used in construction management, building materials, hydraulic optimization,

geotechnical and transportation engineering

• Construction planners generate and evaluate optimal/near-optimal construction

scheduling plans

• The smart system refers to a device which can sense changes in its environment

• Development of robots and automated system

9
1. Structural health monitoring

• Embedding sensors- monitor stress and damage can reduce maintenance cost and
increase lifespan

• Used in over 40 bridges worldwide

2. Self repair materials

• Embedding thin tubes containing uncured resin

• Due to damage these tubes break, exposing the resin which fills any damage and
sets

• It is important in inaccessible environments such as underwater or in space

10 3. Structural engineering

• Used to evaluate durability

• Smart materials or structures are restricted to sensing

• They adapt to their surrounding environment

• Monitor the integrity of bridges, dams, offshore oil drilling towers etc.

4. Waste management

• Challenging, expensive and time consuming task

• Smart material helps to automate the process

• Even it shows a role in food waste management

 5. Concrete mix design
11
• Difficult and sensitive

• Based on the principle of workability of concrete, desired strength and durability of

concrete which in turn is governed by water cement ratio law

• Strength of concrete determined by the characteristics of mortar and coarse aggregate

6. Estimation

• Suited for developing decision aids with analogy based problem solving capabilities

7. Analogy based solution to mark-up estimation problem

• A methodology is presented and used to develop a practical model

• The model design, training, and testing are described along with the generalization
improvements
 8. Neuromodex- Neural network system for modular construction decision making

12
• Decision is based on several decision
attributes

 Plant location

 Labour related

 Plant characteristics

 Project risks

Fig 1: Neural network system

 9. Neuroform- Neural network system for vertical formwork selection
13

• A computer system- provides the

selection of vertical formwork
system for a building site

• A statistical hypothesis test

demonstrates the system’s fault-
tolerant and generalization
properties

Fig 2: Neuroform
 10. Belief networks for construction performance diagnostics
14
• Form of artificial intelligence that incorporates
uncertainty through probability theory and
conditional dependence

• Variables - conditional dependence

relationships

• First defining the variables in the domain and

the relationships between those variables

• Computer simulation - used to model the

construction operations
Fig 3: Belief network
 11. Building KBES for diagnosing PC pile with ANN
15
• Diagnosis of damage of prestressed concrete piles during driving - important
problem in foundation engineering

• ANN can work sufficiently as a knowledge acquisition tool for the diagnosis
problem

• Reasoning strategy that hybridizes forward-and backward-reasoning schemes is

proposed
 12.Construction robot fleet management system
16

Fig 6: Construction robot fleet management

 13. Modelling initial design process using ANN

17

• Initial design process - extremely

difficult to computerize

• Development of a network for the

initial design of reinforced-concrete
rectangular single-span beams has
been reported

• The network predicts a good initial

design for a given set of input
parameters
Fig 4: Initial design process
 14. Intelligent planning of construction project
18

• Represent knowledge about how to generate plans

• Researchers Kartam and Levitt, have chosen the system for

interactive planning and execution (SIPE)
19

Fig 5: Intelligent planning

20 15. Bridge planning using GIS and Expert system approach

• GIS and expert systems -

two methodologies in
comparing candidate site
and candidate type
• Computation power and
quantitative comparison
can be done faster

Fig 7: Bridge planning using GIS and expert system

approach
21
16. ANN approach for pavement maintenance

• Selecting an appropriate maintenance and repair action for a defected pavement

• Done by collecting condition data, analysing and selecting appropriate

maintenance and repair actions

17. ANN for EHS

• Robot carrying out tasks in construction

• Accidents would potentially be zero because of the lack of human errors

 18. Tidal forecasting
22
• Important factor in determining constructions or activity in maritime areas

• Kalman(1960) proposed the Kalman filtering method - calculate the harmonic

parameters

19. Earthquake induced liquefaction

• Damage of civil structures occur in two modes

 Structural failure

 Foundation failure

• Estimation of the earthquake induced liquefaction potential - essential for civil

engineers in the design procedure

• Helps in the design of structures to safeguard against earthquakes

 FUTURE TRENDS
23
1. Fuzzy processing, integrated intelligent technology and intelligent emotion
technology in civil engineering

2. Hybrid intelligence system and a large civil expert system approach

3. Used in many areas of civil engineering

 ADVANTAGES
24

1. Reduce the risk of accidents in the workplace

2. Not affected by hostile environments

3. Can replace tiresome tasks

4. Don’t need break at work time

 DISADVANTAGES
25

1. Can be very expensive

2. Not able to work outside of what they are programmed to do

3. Unemployment may rise

4. Robots do not get better with experience…yet

 CONCLUSION
26

• Applied to many civil engineering areas

• Plays a major role in constructing and maintaining different aspects of civil

engineering problems

• Perform better than the conventional methods

• Help inexperienced users solve engineering problems and experienced users to

improve the work efficiency

• Powerful and practical tool for solving many problems in civil engineering field

• Instruments based on the algorithms and database to reduce the efforts and cost
of construction and management
 REFERENCE
27
1. Akshata Patil, Lata Patted, Mahesh Tenagi, Vaishnavi Jahagirdar, Madhuri Patil and Rahul
Gautam(2017), “Artificial Intelligence as a Tool in Civil Engineering- A Review”, IOSR Journal of
Computer Engineering

2. Artificial intelligence, 2012, http://en.wikipedia.org/wiki/Artificial_intelligence

3. Pengzhen Lu, Shengyong Chen and Yujun Zheng (2012), “Artificial intelligence in Civil engineering,
Mathematical Problems in Engineering”, Volume 2012, Article ID 145974, 22 pages
http://dx.doi.org/10.1155/2012/145974

4. P. Krcaronemen and Z. Kouba, “Ontology-driven information system design,” IEEE Transactions on

Systems, Man and Cybernetics C, vol. 42, no. 3, 2012

5. R. Bendaña, A. Del Caño, and M. P. De La Cruz, “Contractor selection: Fuzzy-control

approach,” Canadian Journal of Civil Engineering, vol. 35, no. 5, pp. 473–486, 2008

6. http://ai.business/2016/11/23/10-use-cases-of-ai-in-the-field-of-construction
 7. Jeng, D. S.; Cha, D. H.; Blumenstein, M. “Application of Neural Networks in Civil Engineering
28
Problems.” // Proceedings of the International Conference on Advances in the Internet, Processing,
Systems and Interdisciplinary Research, 2003

8. A. Khalafallah and M. Abdel-Raheem, “Electimize: new evolutionary algorithm for optimization with
application in construction engineering,” Journal of Computing in Civil Engineering, vol. 25, no. 3, pp.
192–201, 2011

9. M. Rezania, A. A. Javadi, and O. Giustolisi, “An evolutionary-based data mining technique for assessment
of civil engineering systems,” Engineering Computations (Swansea, Wales), vol. 25, no. 6, pp. 500–517,
2008

10. S. Sharma and A. Das, “Backcalculation of pavement layer moduli from falling weight deflectometer data
using an artificial neural network,” Canadian Journal of Civil Engineering, vol. 35, no. 1, pp. 57–66, 2008
29

THANK YOU