s8714 deploying machine learning on the oilfield: from the labs … · 2018. 3. 30. · dynacard...
TRANSCRIPT
Deploying Machine Learning on the
Oilfield: From the Labs to the Edge.
S8714
Confidential Property of Schneider Electric
- Matthieu Boujonnier – Analytics Application Architect
- Bartosz Boguslawski – Data Scientist
- Loryne Bissuel-Beauvais – Data Scientist
Are you ready to
deploy your data scientists’
work on this pump?
Are you ready to
deploy your data scientists’
work on this pump?
Yes! Those guys!!!
Are you ready to
deploy your data scientists’
work on this pump?
Yes! Those guys!!!And that works also for
…cars
…evil robots
ENSURE TRUST
How can our customers trust ML
predictions?
EXTEND MODELSLabeled « expert » data is rare, how to ensure that
our models will work for any « new » pump?
Page 13Confidential Property of Schneider Electric |
Our Challenges
Page 14Confidential Property of Schneider Electric |
Realift: A Pilot on Rod Pumps
Page 15Confidential Property of Schneider Electric |
The Digital Oilfield AnatomyPast, Present and Future
Fewer and fewer
expertise available:
Local workforce needs to be
empowered
EXPERIENCE
OP
TIM
IZA
TIO
N
AUTOMATION
PRESENT
FUTUREDATA
Page 16Confidential Property of Schneider Electric |
Rod pump: facts
3 years 10 yearsAVERAGE RUN LIFE OF A RPC OPTIMAL RUN LIFE OF A RPC
74 MBPD
80% of US
RPC make
less than 10BPD
5-2.5 KBPD
CURRENT
GLOBAL OIL
PRODUCTION
DAILY
PRODUCTION
38% of the total production
750 000 Wells
CURRENT
SITUATION
Impact of downtime at
$65 per barrel of oil
Page 17Confidential Property of Schneider Electric |
Today’s SCADA solution
Page 18Confidential Property of Schneider Electric |
Customer’s confidence is key
© XKCD
ML Predictions
Insights / Advice
Field Services
Stop production / Change equipment
Generate costs
Page 19Confidential Property of Schneider Electric |
Customer’s confidence is key
© XKCD
REALLY?
Page 20Confidential Property of Schneider Electric |
Customer’s confidence is key
© XKCD
Let’s do like humans do !
Page 21Confidential Property of Schneider Electric |
A bit of mechanics and mathematics
Gibbs’s Wave Equation
Source: http://petrowiki.org,
Schneider Electric
Mile
s b
elo
w
the
su
rface
Page 22Confidential Property of Schneider Electric |
Easier with a little animation…
• Experts look at charts of failure patterns
• Experts use mostly their eyes, which interpret the image to a failure (but also look at the data)
Page 23Confidential Property of Schneider Electric |
Human expertise
Expert
Simplified Dynacards showing a failure pattern
Page 24Confidential Property of Schneider Electric |
1) Training: build model
2) Inference: use model
The way Machine Learning usually works
Modeldata label
Modeldata labelCat (0.86)
You (0.14)
Cat
(after this session)
Training
Inference
Page 25Confidential Property of Schneider Electric |
1) Training
2) Inference
The way Machine Learning usually works
It’s very
challenging to
obtain very large
amount
of labeled data
Model
Modeldata Label
Data
Data
Label
Label
Page 26Confidential Property of Schneider Electric |
Data augmentationUsing existing tagged cards to increase the size of the training dataset
One way to get around a lack of data is to augment the dataset. The model will often be more robust and
can even be simpler due to a better training set. This may prevent overfitting as well.
+ =
Pick images of the same class and combine them to get a new one:
gas lock 1 gas lock 2 new gas lock
+ =
worn pump 1 worn pump 2 new worn pump
Page 27Confidential Property of Schneider Electric |
Dynacards can be considered as an image, right?Convolutional Neural Networks
CNN typical architecture
Model: “Those parts of the dynacard
indicate mostly to me that this pump is
grinding”
Model: “Mostly because of those parts of
the dynacard I think this pump works
perfectly well”
Page 28Confidential Property of Schneider Electric |
When humans look at an object, they recognize its class not only because it’s similar to some object
but also because it’s different from some objects.
Not sure what kind of cat it is but for sure not a dog!
Conv. Neural Net
Conv. Neural Net
dense layer
concatenation
Binary Output
1: same
0: different
Image 1: gas lock
Image 2: pump grinding
Labeled at learning time
Unlabeled at inference time
• Training is done by comparing each image against all the images in dataset and checking if the
class is the same or different
• Data set is “augmented” by the combinations of pairs of all the images available
Siamese Network
Page 29Confidential Property of Schneider Electric |
Not enough labeled data? Use autoencoders!
Input image Latent space
representation
Reconstructed
image
encoder decoder
Self-supervised model - trained without labels!
Latent space
representation
Fully-connected network
Page 30Confidential Property of Schneider Electric |
Simplify image by extracting new features:
Gradients (x and y derivatives) of an image are large around contours (regions of abrupt intensity
changes) and we know that contours contain a lot more information about shape than flat regions
especially in our application!
Dynacards are shapes, right?Histogram of Oriented Gradients (HOG)
Reduced dimension
Extracted features
Model Label
Page 31Confidential Property of Schneider Electric |
Increase your odds! Use ensemble of models!Instead of having one model combine many of them and make our task a team work!
CNN
Siamese
AAE+FCN
Ensemble
model
Input data Run all models Final output
0 0.5 1
plunger stuck
normal
gas lock
solids grinding
gas interference
pluid pound
Weights
HOG
Closing the loop: the Edge deployment
Page 32Confidential Property of Schneider Electric |
From the labs to a solution ready to sell
Data Preprocessing
Data is collected from
local systemsDynacard Pattern recognition
Reduce
downtime
RPC immediate
diagnostics
Data Acquisition Data Exploration & Detection Results
Data Cleaning /
SegmentingRPC
Reduce
safety
risks
Increase
Production
Reduce
maintenance
costs
Dynacard Pattern evolution
Confidential Property of Schneider Electric | Page 33
Page 34Confidential Property of Schneider Electric |
The solution is deployed in
harsh environments where
• Internet connectivity is
unreliable and expensive
• Low bandwidth
• Customers require high
data privacy and
confidentiality
• Critical systems are
installed
As a result, Realift® is a full
Edge solution that does not
rely on “always available”
connectivity!
Onsite deployment
Realift Architecture, the marketing speech
Page 35Confidential Property of Schneider Electric |
Enhanced with Azure IoT Edge
GPRS not always-on
connectivity
Page 36Confidential Property of Schneider Electric |
Use transfer learning to adapt the models locally
“Feedback” labelled
Local dataset
Training
data
Frozen weights
Classifier
Transfer Learned knowledge
Feature Extractor
Transfer
Back propagation
Local screen
Page 37Confidential Property of Schneider Electric |
Questions and Answers
• Deep dive on the ML model:
https://tinyurl.com/devintersect
• WSJ article:
https://tinyurl.com/wsjpump
• Microsoft Customer Story:
https://tinyurl.com/mscuststory
Resources
Page 38Confidential Property of Schneider Electric |
Learn More
Realift™ installation in North Dakota