67
PROGNOSIS HEALTH MONITORING MACHINE LEARNING GAS TURBINE COMPRESSOR PROGNOSIS HEALTH MONITORING MACHINE LEARNING GAS TURBINE COMPRESSOR

PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

  • Upload
    others

  • View
    1

  • Download
    0

Embed Size (px)

Citation preview

Page 1: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

PROGNOSIS HEALTH MONITORING – MACHINE LEARNING

GAS TURBINE COMPRESSOR

PROGNOSIS HEALTH MONITORING – MACHINE LEARNING

GAS TURBINE COMPRESSOR

Page 2: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Prognosis Health Monitoring

• Prognostics is the ability to assess and predict into the future health condition of the engine or one of its components for a fixed time horizon or predict the time to failure • Anomaly Detection• Forecast Time to Failure

Page 3: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Agenda

INTRODUCTION TO MACHINE LEARNING

Category : Supervised, Classic,

Unsupervised

Algorithm :SVR, ANN, One Class

SVM,etc

01METHODOLOGY

CRISP-DM

Business Understanding

Data Understanding

Data Preparation

Modelling

Evaluation

Deployment

02MACHINE LEARNING USE CASE

Anomaly Detection

Forecast RUL

Tuning Model

Server Performance

03

Page 4: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

PART-1INTRODUCTION TO MACHINE LEARNING

Page 5: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

What’s Machine Learning ?

It’s a subset of AI which uses mathematical methods to enable machines to improve with experience

It enables a computer to act and take data driven decisions to carry out a certain task

These programs or algorithms are designed in such a way that they can learn and improve over time when exposed to new data

Machine Learning is all about data

Page 6: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Types of Machine Learning

• Supervised Learning

• Unsupervised Learning

• Reinforcement Learning

Page 7: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Supervised Learning

• In Supervised learning, an AI system is presented with data which is labeled, which means that each data tagged with the correct label

• The goal is to approximate the mapping function so well that when you have new input data (x) that you can predict the output variables (Y) for that data

Supervised Learning

Classification

Regression

Page 8: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Supervised Learning - Classification

Page 9: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Supervised Learning - Regression

Page 10: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE
Page 11: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Supervised Learning

Page 12: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Unsupervised Learning

• In unsupervised learning, an AI system is presented with unlabeled, uncategorized data and the system’s algorithms act on the data without prior training

Unsupervised Learning

Clustering

Association

Discover the inherent groupings in the data, ie. grouping customers by purchasing behavior

Discover rules that describe large portions of your data, ie. people that buy X also tend to buy Y

Page 13: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Unsupervised Learning - Clustering

Page 14: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Unsupervised Learning

Page 15: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Machine Learning Algorithms

Page 16: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Machine Learning Applications(examples)

• Prediction — Machine learning can also be used in the prediction systems. Considering the loan example, to compute the probability of a fault, the system will need to classify the available data in groups.

• Image Recognition - Machine learning can be used for face detection in an image as well. There is a separate category for each person in a database of several people

• Medical Diagnoses — ML is trained to recognize cancerous tissues

• Financial Industry and Trading — companies use ML in fraud investigations and credit checks

Page 17: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Machine Learning Applications

• Industrial Predictive Maintenance

• Downtime prevention

• Remaining Useful Life of Asset estimation

Page 18: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Machine Learning Applications

Page 19: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Machine Learning Applications

Precision Drilling

• Helps control drilling equipment's

• human drill operator can better understand the operating environment, which leads to "faster results and less wear, tear and damage to machinery."

Page 20: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Machine Learning Applications

Page 21: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

PART – 2METHODOLOGY

Page 22: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

CRISP-DM1

•Monitor Actual Running Hour to next inspection/Engine Exchange schedule

2

•Early Warning System

•Anomaly detection

•Forecast RUL (Remaining Useful Life)

3

• Identify & Data collection

•Determine Predictive & Predictor parameters

4

•Tools :

•Cause Effect, P&ID/PFD

•Alarm List

•Logix

•Historical data

5

•Data Validation / clean-up → Null, error, overshoot

•Noise reduction

•Correlation analysis of Predictor Parameters

6•Generate new attribute for analysis

7

•Develop Model : Linear Regression, SVM, ARIMA, ANN, etc

•Perform data training & test

8

• Evaluate Result of ML →Accuracy & Error

• Benchmark with others model

• Evaluate Predictors

• Evaluate Data

• Replace model

9

• Deploy at production environment with live data

Cross Industry Standard Process for Data Mining

Page 23: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

System ArchitectureSystem Architecture

Historian DB

MACHINE

LEARNING

CMMS (SAP-PM,Oracle

eAM,Maximo, etc)

Anomaly detection

Forecast Failure/

RUL

Forecast Inspection Schedule

Page 24: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

• Design• Cause Effect (Alarm, Cooldown & Fast Stop)

• Datasheet

• P&ID / PFD

• Manual

• Alarm Set Point

• Logix

• Historical Data • HMI

• Historian

Data Understanding

Data Preparation Choose Model Training Evaluation

Page 25: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Boundary Definition Gas Turbine

Data Understanding

Data Preparation Choose Model Training Evaluation

Page 26: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Equipment Sub Division - Gas Turbine

Data Understanding

Data Preparation Choose Model Training Evaluation

Page 27: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Data Understanding

Data Preparation Choose Model Training Evaluation

Boundary Definition Gas Compressor

Page 28: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Equipment Sub Division - Gas Compressor

Data Understanding

Data Preparation Choose Model Training Evaluation

Page 29: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Gas Turbine CompressorGas Turbine Compressor

Air Inlet

Air Compressor

Combustion

Fuel

Starting System

Fire & Gas Protection

Lube Oil

Exhaust Enclosure

Drive Compressor

1 2 3 4 5

6 7 8 9 10 11

1. T1, Air Inlet DP, Air Supply Press

2a. NGP, PCD, Guide Vane, Bleed Valve2b. Bearing Vibration : 1xy-3xy,2c. Bearing Temp : Drain (1,2/3) , GP Thrust2d. Vibration : GP Axial

3. T5, EGF (Cmd & Pos), Pilot Valve (Cmd & Pos) Fuel (P,T,F), BAM,

Seal Gas

4a. Power Turbine (NPT)4b. Bearing Temp : Drain (4/5), PT Thrust, 4c. Vibration :PT Axial

5a. Suction (P,T),5b. Discharge (P,T,F)5c. Anti Surge5d. Bearing Temp : Thrust & Journal5e. Vibration (DE,NDE)

6. V, I, P, Freq 7. Enclosure8a. Temp : Header, Cooler8b. Pressure : Header8c. Tank Level

9. Pressure10. Press &Temp

11. Press, DP, Valve

Data Understanding

Data Preparation Choose Model Training Evaluation

Page 30: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Data Understanding

Data Preparation Choose Model Training Evaluation

• Predictive parameter act as an output parameter to be analyzed

• The predictor parameter provides information on an associated dependent variable regarding a particular outcome

• Defines predictive parameter based on Cause Effect / Logic

• Fast Stop

• Cooldown

• Exclude states of Transmitter and I/O module failure / fault

White Board

Page 31: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Data Understanding

Data Preparation Choose Model Training Evaluation

1• Remove / delete non-numeric data → Bad , IO

timed-out, under/over-range, etc

2• Data Filtering →Wavelet

3• Correlation analysis → Pearson

Data Pre-processing

Page 32: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Data Understanding

Data Preparation Choose Model Training Evaluation

T5 - TC1

Wavelet

Page 33: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Data Understanding

Data Preparation Choose Model Training Evaluation

❖Predictive : Lube Oil Header Temp

❖Predictors : • Lube oil header press• Lube oil filter dp• Lube Oil cooler inlet temp• Lube Oil cooler outlet temp• Lube oil tank level• Lube oil tank press• T1 temp• Engine PCD• Engine Bearing 1 Drain temp• Engine Bearing 2/3 Drain temp• Engine Bearing 4/5 Drain temp

Page 34: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Data Understanding

Data Preparation Choose Model Training Evaluation

Select predictor@Correlation> 60%

Page 35: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Data Understanding

Prepare Data Choose Model Training Evaluation

Define Parameter : Predictive + Predictor

Define Model Parameter

Define Data Duration for Training & Test

Evaluate Model + Forecast

Supervised : Support Vector

Regression (SVR)

Page 36: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Gathering Data Data Preparation Choose Model Training Evaluation

1Define Predictive &

Predictor

2Define Duration for

Training & Test

3Define Model

Parameter

4 Evaluate Model

1. MAPE = Mean Absolute Percentage Error)2. R square = Coefficient of determination3. Model Valid

• MAPE <<<• R square → 1

Page 37: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

PART – 3

MACHINE LEARNING – USE CASE

Page 38: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Machine Learning – Forecast Data Flow

Now

N1

F1

F2

History Future

Forecast 2 Days ahead using 2 Days historical data

1. MAPE (Mean Absolute Percentage Error)

2. MAPE = Forecast –Actual

3. Forecast Valid = MAPE <<<

H1H2 H0MAPE1 = F1-N1

= F(H0,H1,H2)

= F1 + F(H0,H1)

N2 MAPE2 = F1-N2 + MAPE1

Page 39: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

What Machine Leaning Do ?

• Perform Anomaly Detection

Data analysis to identify anomaly due process upset & anomaly

instrument reading

• Perform Forecast / Prediction

Data analysis to predict RUL (Remaining Useful Life) ✓ Predict reaches the shutdown limit ✓ Predict running hour reaches maintenance / engine exchange schedule

• Provides Early Warning System

Provides “Future Alarm” to notify Operator & Maintenance team to

prepare mitigation plans

Page 40: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Use Case - Model

No Description Predictor

1 Forecast : Lube Oil Header Temperature

a. Supervised : SVR (Support Vector Regression) Multi variable

b. Classic : Prophet Single variable

2 Forecast : Engine Vibration Displacement 3x

a. Classic : Prophet Single variable

3 Anomaly detection : Engine Bearing Drain Temperature

a. Un-Supervised : On-Class SVM (Support Vector Machine) Single variable

b. Supervised : SVR (Support Vector Regression) Multi variable

Page 41: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

LUBE OIL SYSTEM

Drain Temp

Header Temp

Page 42: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

T1

Average T5

NGP

NPT

Lube Oil Header Temperature

Lube Oil Tank Temperature

Lube Oil Engine Bearing Drain #1 delta temperature

Lube Oil Header Pressure

Lube Oil Inlet Temperature

Lube Oil Outlet Temperature

Lube Oil Tank Level

Lube Oil Engine Bearing Drain # 4 & #5 delta temperature

Predictive : Engine Bearing Drain Temp

Predictor

Page 43: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

T1

Average T5

NGP

NPT

Lube Oil Engine Bearing Drain # 2 & #3 delta temperature

Lube Oil Tank Temperature

Lube Oil Engine Bearing Drain #1 delta temperature

Lube Oil Header Pressure

Lube Oil Inlet Temperature

Lube Oil Outlet Temperature

Lube Oil Tank Level

Lube Oil Engine Bearing Drain # 4 & #5 delta temperature

Predictive : Lube Oil Header Temp

Predictor

Page 44: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Transmitter Healthy

Transmitter Un-Healthy, Spike reachs HH limit (125 degF) → Fast stop (Emergency Shutdown)

Trending Drain Temp #2 & 3

1 2 3 4 5 6 7 8 9 10

1 2 3 4 5 6 7 8 9 10

Page 45: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

ANOMALY DETECTION

MODEL : ONE CLASS SVM (SUPPORT VECTOR MACHINE)

CATEGORY : UN-SUPERVISED

Tag : LUBE OIL HEADER & ENG

BRN DRAIN TEMP

Page 46: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Spike Analysis- Develop alarm of total Spike occurred - Alarm of Spikes will be displayed at HMI

Engine Bearing Drain Delta Temp (Anomaly Instrument Reading) – Un Supervised –One Class SVM

1 2 3 4 5 6 7 8 9

Page 47: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Simulated anomaly (17-20 Aug)

Anomaly identified by

ML

Page 48: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Simulated anomaly (17-20

Agustus)

Anomaly identified by

ML

Page 49: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

ANOMALY DETECTION

MODEL : SVR (SUPPORT VECTOR REGRESSION)

CATEGORY : SUPERVISED

TAG : ENG BRG DRN TEMP

Page 50: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Pearson Correlation• Data Duration : 2 weeks @ 1 h

• Predictor: 13 external + 1 self

Page 51: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Data Duration: 2 weeks-@interval 1 hKernel : PolynomialPredictor: 13 external + 1 self

1Define Predictive &

Predictor

2Define Duration for

Training & Test

3Define Model

Parameter

4 Evaluate Model

Page 52: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Data Duration: 2 weeks-@interval 1 hKernel : LinearPredictor: 13 external + 1 self

1Define Predictive &

Predictor

2Define Duration for

Training & Test

3Define Model

Parameter

4 Evaluate Model

Page 53: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Anomaly Detection : Engine Bearing Drain Temp

MAPE

Linear Poly RBF

2 weeks , 13 external + 1 Self 0.5 0.54 0.49

12 Normal + 3 days Anomaly,13 external + 1 Self 15.27 12.02 15.69

Forecast : Lube Oil Header Temp

MAPE

Linear Poly RBF

2 weeks , 5 external + 1 Self 0.33 0.51

2 weeks , 11 external + 1 Self 0.39 0.5

12 Normal + 3 days Anomaly,11 external + 1 Self 19.22 13.53 20.72

SUMMARY – TUNING THE MODEL

Page 54: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

FORECAST –TIME TO FAILURE

MODEL : PROPHET

CATEGORY : CLASSIC

TAG : LUBE OIL HEADER TEMP & ENG BRG VIBRATION

Page 55: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Shutdown limit – 165 degF

ML perform Forecast when Process Value reach Alarm

HH

Lube Oil Header Temperature

Page 56: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

SERVER PERFORMANCE

PART - 3

Page 57: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Computer Specification

• Processor Ryzen 9 3800X (8 of CPU Cores & 16 of Threads)

• RAM 64 GB

• SSD 1 TB

• GPU GeForce 2060 RTX

Page 58: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Machine Learning Model

• Support Vector Regression (SVR)

• Data training : 2 weeks, 1 hour interval,

• Lag features 48 hours + additional predictor (optional) → generate more than 48 features

• Data sample size : 481 rows with > 48 + 11 (optional) columns

• Model parameter tuning using GridSearch method

Page 59: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

CPU Utilization – Create 1 model

Page 60: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

CPU Utilization – Create 2 model

Page 61: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

CPU Utilization – Create 3 model

Page 62: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

CPU Utilization – Create 4 model

Page 63: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

CPU Utilization – Create 18 model

When all models are running, the CPU goes straight to 100%, then drops slowly as each model is finished

Page 64: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

CPU Utilization – Create 18 model

• It's been 1 hour, there are still 2 unfinished models →Models for Engine Bearing Vibration 1X and 1Y

Page 65: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Predictor Self Self+12 Self+9 Self+7

Training time 19min 47s 20min 1s 19min 40s 19min 45s

MAPE 0.23% 0.77% 0.66% 0.56%

MSE 0.02 0.19 0.13 0.09

R2 0.98 0.78 0.86 0.89

Predictor Self Self+12 Self+9 Self+7

Forecasting time

19min 47s 11min 41s 11min 31s 11min 31s

MAPE 1.98% 1.49% 1.30% 1.57%

MSE 1.59 0.88 0.43 1.15

R2 -0.80 0.05 -18.87 -0.30

Prediction

Forecasting

Comparison ML : 3 days @interval 1 minute

GTC : Engine, Gearbox, Dual stages of CompressorAnalog Tag : 220Alarm : 159 (Fast Stop) & Cooldown (21)

Predictive : 100Predictor : 1000

1 Model (Predictive +Forecast) = 30 min100 Model = 30 x 100 = 3,000 min = 50 hour

1 Model (Forecast) = 10 min100 Model = 10 x 100 = 1,000 min = 17 hour

Page 66: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE

Speed

Efficiency

Surge Line

Surge

Stonewall

Co

mp

ress

or

Pe

rfo

rman

ce M

ap

ML forecast possibility compressor to Surge / Stonewall

Page 67: PROGNOSIS HEALTH MONITORING – MACHINE LEARNING GAS TURBINE