0% found this document useful (0 votes)
19 views24 pages

基于机器学习的数据处理

Uploaded by

julius.yzhu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
19 views24 pages

基于机器学习的数据处理

Uploaded by

julius.yzhu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 24

Applying Machine Learning for

Oil & Gas Production Data Analytics

Yi Zhu, Computer Science

Graduation Defense

May 1st, 2018


1/31/20 10:41:34 AM 0
Outlines
• Introduction
• Solutions
• Implementation
• Results
• Discussion

1/31/20 10:41:40 AM 1
Introduction

• Project overview
- Big data from oil/gas production
- Missing values and errors to fix
- Data prediction after fixing

1/31/20 10:41:40 AM 2
Introduction
• Background
- In whole life-span of oil/gas
production, data from the surface
and underground is created, stored.
- Huge datasets should be
processed, analyzed to make the
right decisions for any enterprise

1/31/20 10:41:41 AM 3
Introduction
• Big data
- Huge datasets are created every day:
e.g.: in production data, a record with 20 attributes created every 3
minutes (175,200 records/year) for a single producing well
- Main attributes in data: fluid rates, pressure & temperature in downhole
and surface, and other parameters, like controlling device size, status, etc.
TIME OIL_PRODUCTION
>7000 MPFM_STATUS
GAS_PRODUCTION
WATER_PRODUCTION
MPFM_PRESSURE
MPFM_TEMPTHP THT
7/8/11 0:00 0 0 3 0 0 4258.31257 74.0502012 4263.49939 51.030014
7/8/11 0:03 0 0 3 0 0 4258.49291 73.9946195 4263.67881 50.9100151
7/8/11 0:06 0 0 3 0 0 4258.69183 73.9390926 4263.87671 50.7900124
7/8/11 0:09 0 0 3 0 0 4258.85497 73.8835649 4264.03901 50.6700134
7/8/11 0:12 0 0 3 0 0 4259.05251 73.8279839 4264.23555 50.5500107
7/8/11 0:15 0 0 3 0 0 4259.68645 73.7724563 4264.86625 50.4300118

1/31/20 10:41:41 AM 4
Introduction
• Big data
- All kinds of big data,
such as seismic, geology,
well-logging, drilling…
- Devices from recording
data can be damaged or
failed due to the harsh
environments List of attributes:
['OIL_PRODUCTION','MPFM_STATUS', 'GAS_PRODUCTION',
'WATER_PRODUCTION', 'MPFM_PRESSURE', 'MPFM_TEMP', 'THP', 'THT',
'FLP’, 'FLT', 'CHP', 'CHOKE_SIZE', 'CHT', 'DHPT1', 'DHTT1', 'DHPT2', 'DHTT2']

1/31/20 10:41:41 AM 5
Introduction
• Goals

Oil Rate (ton/d)


- To fill missing values
- To correct errors
- To predict future
TIME OIL_PRODUCTION
MPFM_STATUS
GAS_PRODUCTION
WATER_PRODUCTION
MPFM_PRESSURE
MPFM_TEMPTHP THT FLP FLT CHP CHOKE_SIZE
CHT DHPT1 DHTT1 DHPT2 DHTT2 PMV PWV
2011-07-10 05:39:00 9495.9248 3 4536.686035 0 3676.8076 96.9805527 3686 107.1 1751.5 111.86 4666 3 49.891 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 05:42:00 9681.14258 3 4301.38623 0 3676.2578 96.9859695 3686 107.1 1751 111.86 4666 3 49.893 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 05:45:00 9619.49902 3 4361.977539 0 3676.4556 96.9913864 3685 107.1 1751 111.86 4666 3 49.894 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 05:48:00 9550.86133 3 4485.098633 0 3676.5051 96.9968033 3685 107.1 1753 111.86 4667 3 49.895 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 05:51:00 9589.40332 3 4408.477539 0 3676.3938 97.0022202 3685 107.1 1752 111.87 4667 3 49.896 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 05:54:00 9608.23047 3 4317.250488 0 3676.2375 97.007637 3685 107.1 1750.8 111.87 4667 3 49.898 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 05:57:00 9575.52832 3 4296.837402 0 3676.2825 97.0130539 3685 107.1 1752 111.87 4667 3 49.899 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 06:00:00 9719.98438 3 4168.305176 0 3676.2959 97.0184784 3685 107.1 1753 111.87 4667 3 49.9 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 06:03:00 9655.06738 3 4376.468262 0 3676.3904 97.0238953 3685 107.1 1754 111.88 4668 3 49.901 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 06:06:00 9578.36133 3 4327.151367 0 3675.9705 97.0293121 3685 107.1 1753 111.88 4668 3 49.903 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 06:09:00 9588.01172 3 4502.195801 0 3675.7161 97.034729 3685 107.1 1753.8 111.88 4668 3 49.904 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 06:12:00 9705.90625 3 4373.979492 0 3675.9441 97.0401459 3685 107.1 1751.5 111.88 4668 3 49.905 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 06:15:00 9537.95801 3 4294.16748 0 3675.6318 97.0455627 3685 107.1 1751.5 111.89 4669 3 49.906 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 06:18:00 9614.85449 3 4080.184814 0 3675.2998 97.0509796 3685 107.1 1749 111.89 4669 3 49.908 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 06:21:00 9504.20313 3 4417.126465 0 3674.968 97.0563965 3685 107.1 1749.8 111.89 4669 3 49.909 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 06:24:00 9687.53223 3 4259.660645 0 3674.7427 97.061821 3685 107.1 1747.7 111.89 4669 3 49.91 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 06:27:00 9565.47559 3 4346.114746 0 3675.2307 97.0672379 3684 107.1 1749.3 111.9 4669.5 3 49.911 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
1/31/20
2011-07-10 10:41:41
06:30:00 AM
9552.11621 3 4653.112793 0 3675.103 97.0726547 3684 107.1 1749.2 111.9 4670 3 49.913 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN 6
OPEN
2011-07-10 06:33:00 9577.39941 3 4207.010742 0 3674.7095 97.0780716 3684 107.1 1749 111.9 4670 3 49.914 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
2011-07-10 06:36:00 9689.75879 3 3982.271973 0 3674.6611 97.0834885 3684 107.1 1748 111.9 4670 3 49.915 I/O Timeout
I/O Timeout
I/O Timeout I/O Timeout OPEN OPEN
Solution
• No existing solutions for this specific problems and goals
• Machine learning is the main methods in the whole process
- Data selection for model building
- Data correction and filling with models
- Machine learning for prediction Fluid
Prediction

Predict Pressure
Prediction

Temp
Prediction
1/31/20 10:41:41 AM 7
Solution
r u le s
a l
p hysic
s s in g r s by PE
p r o ce a re e rr o
AN
Da ta h va l u e s
to b e N
e s
• i z e w h i c
d e rr o rs
b le va l u
og n s a n so n a
- rec a l u e r r e a
i s s ing v r re c to
- put
m
w i th co
l l N AN
a
- fi l l g
d i c tin e di c t
a p re ata y ’ to p r
D at f i xe d d
‘h istor
ative
• th
d
e
on the
tc h te r n
a s al
e a ion
- bas l s tom ol u t
e m ode e n c e’ s
- us a ta s ci
e k a ‘d
- se
1/31/20 10:41:43 AM 8
Implementation

Data selecting-> Model building-> Model saving->Data processing->Data predicting


1/31/20 10:41:43 AM 9
Implementation
• data selection
Ø Physical rules of petroleum engineering adopted
Obey oil producing equation, that is production is control by pressure difference
between reservoir and downhole
Oil rate and downhole pressure can not climb simultaneously
When the well is shut down, the downhole pressure should be growing to
maximum
When production increases, the downhole pressure is supposed to be dropping
Downhole pressure should be higher than wellhead values and can never be
zero
And so on…

1/31/20 10:41:43 AM 10
Implementation
• Modelling
Ø Linear regression is used

1/31/20 10:41:43 AM 11
Implementation
• Predicting
Ø A forecast module Prophet from Python Library, which is for time series data
prediction, is use.

The applications of this forecasting


module
1/31/20 10:41:43 AM 12
Results
• Data Processing
Ø Production correction and filling

o Cleaning all the errors


o Filling all blanks
o To calculate the values for
unknown values from machine
learning models

1/31/20 10:41:43 AM 13
Results
• Data Processing
Ø Pressure
o Recognize the ‘0’ values as errors
o Correct the responding values by
machine learning models
o Much more errors in wellhead
pressure data, due to the device
failures

1/31/20 10:41:43 AM 14
Results
• Data Processing
Ø Downhole temperature
correction and filling
o Recognize the temperature
values of downhole could not
be zeros
o Get the right values by
machine learning models

1/31/20 10:41:43 AM 15
Results
• Data Processing
Ø Other pressure and
temperature

o Remove all
outliers
o Put the calculated
values

1/31/20 10:41:43 AM 16
Results
• Data Prediction
Ø Production of Oil/gas
o Convert the processed data to daily
data
o Use the machine learning module
Prophet to predict
o Oil /gas will always decline in the
whole life-span of the wells

1/31/20 10:41:43 AM 17
Results Gas
Oil
• Data Prediction water

Ø Production of Water
o Oil reservoir driven by bottom
water will produce more and
more water
o The prediction can show this
characteristic

1/31/20 10:41:43 AM 18
Results
• Data Prediction
Ø Pressure
Surface pressure
o Pressure means the energy of the
reservoirs, which drives the fluids out
o Both downhole and surface pressure
will drop along the production

Downhole pressure

1/31/20 10:41:43 AM 19
Results
• Data Prediction
Ø Temperature
Surface temperature
o Temperature is controlled by
geothermal energy
o It is considered as a constant
o The predictions shows it is stable all
the time
o Surface temperature has some
vibrations due to environment
temperature changes
downhole temperature
1/31/20 10:41:45 AM 20
Discussion

• Machine learning provides lots of industries with intelligence,


knowledge, profits and more…

• People use physical rules of petroleum engineering, physics models to


do calculations and simulations to get the results they want

1/31/20 10:41:45 AM 21
Discussion

• Data science provides an alternative to finish the work when physical


models are not available

• More comparisons should be done to prove the effectiveness and


availability of machine learning results.

• The key word in "Data Science" is not Data, it is Science.

----Jeff Leek,2013.
1/31/20 10:41:45 AM 22
Thank you!

1/31/20 10:41:45 AM 23

You might also like