Big Data and Machine Learning for Predictive Maintenance

Transcription

1 Big Data and Machine Learning for Predictive Maintenance Paul Peeling 2015 The MathWorks, Inc. 1

2 Agenda The Predictive Maintenance Opportunity Exploring Big Data Machine Learning Approaches Deep Learning Fault Modelling Deploying to the Edge and the Cloud 2

3 React or Prevent? Aaron tango Tang on Flicker 3

4 Predictive Maintenance software Sense Temperature sensors Pressure sensors Vibration sensors Perceive Decide & Plan Act Total of 25 sensors - but which ones were the best predictors? 4

5 Predictive Maintenance software Sense Perceive Decide & Plan Act 5

6 What do we mean by Predictive Maintenance? Monitor equipment to avoid future failure. Schedule maintenance when it s needed. Identify the root cause of issues. How? Predictive models and sensor data. Deploying to the equipment and cloud. 6

7 Why is Predictive Maintenance Important? 7

8 Why is Predictive Maintenance Important? Source: GE Oil & Gas 8

9 Deploying Predictive Maintenance Algorithms 9

10 Aside: What if? I m not in the business of Predictive Maintenance I don t have big data I don t have any data I don t have a computing cluster I need a simpler solution 10

11 Workflow Access and Explore Data Preprocess Data Develop Predictive Models Integrate Analytics with Systems Files Visualizing Data Machine learning Embedded Devices/Hardware Sensors Data Reduction/ Transformation Model Validation Enterprise Scale Systems 11

12 Workflow Access and Explore Data Files Sensors 12

13 Predictive Maintenance of Turbofan Engine Sensor data from 100 engines of the same model Maintenance scheduled every 125 cycles Only 4 engines needed maintenance after 1 st round Predict and fix failures before they arise Import and analyze historical sensor data Train model to predict when failures will occur Deploy model to run on live sensor data Predict failures in real time Data provided by NASA PCoE 13

14 Working with Big Data Where is the data? How big is the data? What code can I write? 14

15 Tall Arrays Scaling your code to big data Automatically optimize data access bottlenecks Write code the same way you've always written it MATLAB automatically reorders operations to minimize disk access Machine Memory Applicable when: Data is columnar with many rows Overall data size is too big to fit into memory Operations are mathematical/statistical in nature Statistical and machine learning applications Hundreds of functions supported in MATLAB and Statistics and Machine Learning Toolbox Tall Data 15

16 Filtering Data 16

17 Workflow Access and Explore Data Preprocess Data Develop Predictive Models Integrate Analytics with Systems Files Visualizing Data Machine learning Embedded Devices/Hardware Sensors Data Reduction/ Transformation Model Validation Enterprise Scale Systems 17

18 Visualizing Big Data Using tall Support for: histogram histogram2 ksdensity plot scatter binscatter 18

19 Visualizing Big Data Using tall scatter binscatter 19

20 Standardizing Data 20

21 Deferred evaluation and gathering What does gather do? 1. Evaluate any pending operations 2. Collect the partitioned data into MATLAB main memory 3. Unwrap the data into an array or table 21

22 Workflow Access and Explore Data Preprocess Data Develop Predictive Models Integrate Analytics with Systems Files Visualizing Data Machine learning Embedded Devices/Hardware Sensors Data Reduction/ Transformation Model Validation Enterprise Scale Systems 22

23 Traditional Approaches 23

24 Live Historical Use historical data to predict when failures will occur Initial Use/ Prior Maintenance Recording Starts Failure Maintenance Engine 1? Engine 2 Engine 100 Engine X? Cycles (Time) Schedule Maintenance 24

25 Principal Components Analysis 25

26 Dimensionality Reduction with PCA 26

27 Early Warning System 27

28 Preprocessing and Classifying our Input Data Start of Recorded Engine Life Data Recording Starts Engine 1 Failure Engine 2 Engine 3 Engine 100 Cycle 0 Cycles (Time) 28

29 Classification Learner App 29

30 Convolutional Neural Network 30

31 Pretrained Networks 31

32 LSTM Network 32

33 Useful Life Estimation Simulink Model 33

34 Workflow Access and Explore Data Preprocess Data Develop Predictive Models Integrate Analytics with Systems Files Visualizing Data Machine learning Embedded Devices/Hardware Sensors Data Reduction/ Transformation Model Validation Enterprise Scale Systems 34

35 Internet of Things 35

36 Using Tall Arrays Run in parallel on compute clusters MATLAB Distributed Computing Server Local disk Shared folders Databases Compute Clusters Spark + Hadoop Tall arrays MATLAB 100 s of functions supported MATLAB Statistics and Machine Learning Toolbox Run in parallel Parallel Computing Toolbox Run in parallel on Spark clusters MATLAB Distributed Computing Server Deploy MATLAB applications as standalone applications on Spark clusters MATLAB Compiler 36

37 Working with GPU Coder: Deep Learning Workflow Access Data Preprocess Select Network Train Deploy Image Acquisition Tbx Image Processing Tbx Computer Vision System Tbx Neural Network Parallel Computing Tbx GPU Coder 37

38 Machine Learning on MATLAB Production Server Shell analyses big data sets to detect events and abnormalities at downstream chemical plants using predictive analytics with MATLAB. Multivariate statistical models running on MATLAB Production Server are used to do real-time batch and process monitoring, enabling real-time interventions when abnormalities are detected. 38

39 Where Next? Talks MatConvNet: Deep Learning Research in MATLAB Introduction to Machine & Deep Learning Scaling MATLAB for your Organisation and Beyond Demo Stations Big Data with MATLAB Deep Learning with MATLAB Predictive Maintenance with MATLAB and Simulink Deploying Video Processing Algorithms to Hardware Using MATLAB and ThingSpeak to Explore the Internet of Things 39

40 Thank You! 40