s8714 Deploying Machine Learning On The Oilfield From The Labs To The Edge
s8714 Deploying Machine Learning On The Oilfield From The Labs To The Edge
s8714 Deploying Machine Learning On The Oilfield From The Labs To The Edge
…cars
…evil robots
Our Challenges
ENSURE TRUST
How can our customers trust ML
predictions?
EXTEND MODELS
Labeled « expert » data is rare, how to ensure that
our models will work for any « new » pump?
PRESENT
OPTIMIZATION
EXPERIENCE
80% of US
74 M RPC make 5-2.5 K
BPD BPD
less than 10
BPD
3 years 10 years
Insights /
Advice
Field
Services
Stop production /
Change equipment
Generate
costs
REALLY?
Source: http://petrowiki.org,
Schneider Electric
Expert
1) Training
It’s very
Data challenging to
Label
Model obtain very large
Data Label amount
of labeled data
2) Inference
+ =
+ =
Model: “Those parts of the dynacard Model: “Mostly because of those parts of
indicate mostly to me that this pump is the dynacard I think this pump works
grinding” perfectly well”
Confidential Property of Schneider Electric | Page 27
Not sure what kind of cat it is but for sure not a dog!
Siamese Network
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.
• 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
Reconstructed
Input image Latent space image
representation
encoder decoder
Fully-connected network
Latent space
representation
Model Label
Weights
CNN
pluid pound
gas interference
Siamese
solids grinding
Ensemble
gas lock
model normal
AAE+FCN
plunger stuck
0 0.5 1
HOG
Reduce
safety
risks
Reduce
downtime
RPC Data Cleaning /
Segmenting
Increase
Data Preprocessing Production
Reduce
maintenance
costs
• Internet connectivity is
unreliable and expensive
• Low bandwidth
• Customers require high
data privacy and
confidentiality
• Critical systems are
installed
Onsite deployment
Training
data
Transfer
“Feedback” labelled
Local dataset Back propagation