View
219
Download
2
Category
Preview:
Citation preview
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS TREATMENT CASE
PROACTIVELY PREDICT COLLAPSE OF AN AMINE PROCESSING CONTACTOR
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
2
AMINE GAS CASE PREDICT COLLAPSE OF PROCESSING CONTACTOR
Save
$200M USD
per year
Foaming / Flooding events:
• 2 to 4 events per contactor per year
• Costing $250,000 per event
• 200 contactors worldwide
• Impact:
• Lost revenue
• High unplanned maintenance costs
• Poor amine utilization
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE SAS DAY AT TEXAS A&M:
PREDICT COLLAPSE OF PROCESSING CONTACTOR
• Project Objectives
• Data Overview
• Analytical Approach
• Summary of Analytical Findings
• Lessons Learned
• Requirements for Big Data Predictive Analytics
Agenda
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE AMINE GAS TREATMENT CASE OBJECTIVES
Business Challenge
• Reduce collapse of Amine processing contactor due to foaming and flooding
Business Impact
• Proactively predict foaming and flooding events
• Predict and monitor processing liquid levels
• Optimize Amine utilization
Value Driver
• Improve up-time and processing efficiency
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE GOAL: PROACTIVELY PREDICT PROCESSING FAULTS
Low Amine Gas Pickup
Foaming/Flooding Event
Excess Amine Pickup
Lean Amine to Contactor
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE PROCESSING CONTACTOR SYSTEM OVERVIEW
CO2 treated
CO2 feed gas
Storage Tanks
41, 42 & 43
C-101 C-102
Contactor
C101
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE ANALYTICAL APPROACH
SAMPLE EXPLORE MODIFY MODEL ASSESS
• Consolidate
multiple data
sources
• Quality Check
• Cleanse
• Visualize sensor
and fault data
• Collaborate with
subject matter
experts
• Identify
candidate
anomalies
• Transform
variables
• Filter outliers
• Cluster similar
acting groups
• Variable
selection
• Identify early
fault indicators
Root cause analysis
• Generate
predictive
models
Decision trees
Logistic regression
Neural networks
• Review results
with subject
matter experts
• Score new data
• Automate
ongoing
assessment of
prediction
accuracy
• Flag model
needing tuning
• Alert when
operation
becomes
unstable
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE DATA OVERVIEW
• Source: PI System
• Systems:
• Contactor C-101: 22 sensor variables & 18 calculated variables
• Contactor C-201: 22 sensor variables & 18 calculated variables
• Contactor Feed Flow: 1 sensor variable
• Storage tanks: 3 sensor variables (1 per tank)
• Time range:
• January 1, 2010 to April 12, 2014
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
© Copyr i g h t 2014 OS Iso f t , LLC . 9
OSIsoft Overview
Employees Developers
One Product. Singular Focus. Agnostic
# of Sites Of Global Fortune 500
16,00065%
Founded
Customer Support
1000 250+
Privately held software company
Leader in Operational Intelligence
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
© Copyr i g h t 2014 OS Iso f t , LLC . 10
OSIsoft is trusted by the world’s leading companies
Innovative uses to monitor complex IT environments Connected Services, Smart Cities,
Transportation, Healthcare, Academia
Pha rm a c e utic a ls,
Food & Life Sc ie nc e s
Critic a l Fa c ilitie s,
Da ta Ce nte rs & IT
Oil & Ga s
Pulp & Pa pe r
De ve loping Ma rke ts &
Industrie s
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
© Copyr i g h t 2014 OS Iso f t , LLC .
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d . © Copyr i g h t 2014 OS Iso f t , LLC .
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
© Copyr i g h t 2014 OS Iso f t , LLC . 13
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
© Copyr i g h t 2014 OS Iso f t , LLC . 14
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
© Copyr i g h t 2014 OS Iso f t , LLC . 15
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d . www.SAS.com
ANALYTICAL APPROACH
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE ANALYTICAL WORKFLOW
Identify
• Time periods to investigate
• Events to investigate
Explore
• See potential trends/areas to investigate
• Leading cause of failures
• Identify potential explanatory variables
Analyze
• Perform root cause analysis
• Statistical signatures for events
• Stability modeling and monitoring
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE EXPLORE SENSOR DATA AND FAILURE TIMES
February 10, 2013 to April 12, 2014
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE ANALYTICAL METHODS EMPLOYED
Pareto Analysis Correlation Analysis Variable Cluster
Analysis Principal Component
Analysis
Association Analysis Root Cause
Analysis Decision Trees Logistic Regression Stability Monitoring
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE CORRELATION ANALYSIS
Purpose:
• Measures strength of a linear relationship between numerical variables
Benefits:
Improves accuracy and performance of predictive models
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE VARIABLE CLUSTER ANALYSIS AND
PRINCIPAL COMPONENT ANALYSIS
Purpose:
• Identifies similar acting variables or groups
• Variable reduction technique
Benefits:
Identifies most meaningful sensor data and events to further analyze
Cluster Analysis
Principal Component Analysis
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE MULTIPLE LINEAR REGRESSION
Dependent Var: Gas Treating Area Pickup Ratio
Explanatory Var: Flash Drum Level
Feed Filter Separator Level
CO2 in treated gas
Tray 21 Level
Feed Gas Pressure
DSG Stripper Temp
D101 NGL Train Separator
Feed gas - Lean DGA temp
Contactor Level
Lean DGA % Strength
NGL Train Separator Level
Feed Gas Temp
Dependent Var: Contactor Level
Explanatory Var: DSG Stripper Temp
Feed Gas Temp
Feed gas – Lean DGA temp
D201 NGL Train Separator
D101 NGL Train Separator
Lean DGA % Strength
Feed Filter Separator Level
Tray 21 Level
Flash Drum Level
Dependent Var: Feed Gas Flow
Explanatory Var: Lean DGA % Strength
DGA Antifoam Tank Level
Contactor Level
Flash Drum Level
Lower Tray #5 Temp
NGL Train Separator Level
Purpose: • Predicts contactor processing liquid levels
• Explains variables or combination of
variables affecting contactor processing
liquid levels
Benefits:
Analyzes more information generating
greater predictive power
Generates better understanding of
relationships between variables
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE CONTACTOR FOAMING/FLOODING DECISION TREE
Purpose:
• Illustrates all possible outcomes and highlights typical path
Benefits:
Visually identifies variables considered relevant to target event occurrence or non-occurrence
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE ROOT CAUSE ANALYSIS & ASSOCIATION ANALYSIS
Foaming/Flooding Event
Period: Jan 1/2013
to Dec 31/2013
Analytical rule Lift PDI205_v_gt95p & PDI022_v_gt95p ==> TARGET_EVENT 17.86
PDI205_v_gt95p & PDI006_v_gt95p ==> TARGET_EVENT 16.76
TI028_v_gt95p & PDI205_v_gt95p ==> TARGET_EVENT 15.94
TI028_v_gt95p & FIC004_v_gt95p ==> TARGET_EVENT 15.59
PDI022_v_gt95p & FIC004_v_gt95p ==> TARGET_EVENT 15.52
TI026_v_gt95p & FIC004_v_gt95p ==> TARGET_EVENT 15.45
TI026_v_gt95p & PDI022_v_gt95p ==> TARGET_EVENT 15.12
Purpose:
• Helps understand why processing fault occurred
• Identifies variables potentially contributing to fault/failure event
Benefits:
Identifies association rules to predict occurrence of future faults/failures
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE ALERT FOAMING/FLOODING ROOT CAUSE PATTERN
RECOGNITION WARNING
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE CONTACTOR LEVEL STABILITY MONITORING MODELS
• Provides better forecasting accuracy
• Detects and accounts for daily and seasonal operational differences
ARIMA
• Provides better explanatory power
• Traditional approach used by engineers
REGRESSION
Purpose:
• Provides predictive
capability to show
current state and alert
of potential problems
Benefits:
Automatically alerts
when operation
becomes unstable
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE SCORE NEW DATA AGAINST PREDICTION MODELS
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE ALERT UNSTABLE OPERATION TO PREVENT FUTURE
FOAMING/FLOODING EVENTS
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE SUMMARY OF ANALYTICAL FINDINGS
Proactively predict foaming and
flooding events
Predict and monitor processing liquid
levels
Optimize Amine utilization
Discovered
foaming/flooding
fault signatures
Developed prediction
models and stability
monitoring forecast
models
Developed stability
model to feed
optimization model
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE LESSONS LEARNED
Sensor and fault data can easily be analyzed
Wide variety of analytical methods available
Tremendous business value discovering root
cause of faults and failure initiating variables
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AMINE GAS CASE REQUIREMENTS FOR BIG DATA PREDICTIVE ANALYTICS
Data:
Scalable Performance Data Server
High-Performance Architecture:
Analysis:
Copyr i g ht © 2012, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
32
AMINE GAS CASE PREDICT COLLAPSE OF PROCESSING CONTACTOR
Save
$200M USD
per year
Foaming / Flooding events:
• 2 to 4 events per contactor per year
• Costing $250,000 per event
• 200 contactors worldwide
• Impact:
• Lost revenue
• High unplanned maintenance costs
• Poor amine utilization
Recommended