smart alarm monitoring - university of albertaslshah/files/nserc_irc2007... · 2009. 6. 9. · 4...
TRANSCRIPT
Smart Alarm Monitoring
Iman Izadi, Research FellowDepartment of Chemical and Materials Engineering
University of Alberta
2
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Outline
MotivationFalse alarms, causes and remediesModel base performance monitoringMultivariate vs. univariate Error processingCase studiesConcluding remarks
3
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Why Monitoring?
Improving efficiency and reliabilityReducing unplanned downtimeAvoiding production lossPreventing equipment damage
Environment protectionSafety
MOREPROFIT
4
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
History
Traditionally, a limited number of variables are monitored.If a variables exceeds a certain limit, an alarm is raised.After an alarm is raised, the operator must understand and acknowledge the alarm, detect the event, and react accordingly.SPC (Statistical Process Control) and SQC (Statistical Quality Control) charts are used for performance monitoring (e.g., Shewhart chart).For overall performance of the process, a few “quality variables” or “key performance indicators (KPI)” are monitored.
5
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Old Control Room
Historically, alarms were expensive and difficult to implementEach alarm had to be hardwiredLimited space in control panelsResulting in careful design and review before implementation
6
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Modern Control Room
Today, hardware and software advances has made it easy to add alarms at minimal costLarge increase in the quantity of alarmsReducing the quality and efficiency of alarms
7
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Why False Alarms?
Thousands of alarms configured and continuously addedBad design, bad tuningDifferent operating statesProcesses change over time Equipments change and degradeSeasonal changesNoise
8
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Standards and Regulations
1999 EEMUA 191 v1World-wide standard
2007 EEMUA 191 v22008 ISA S18.02 - Management of Alarm Systems for the Process Industries2008 ANSI Adoption of ISA
9
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
EEMUA Benchmarks
EEMUA Oil & Gas PetroChem Power Other
Average Alarmsper hour <6 36 54 48 30
Average StandingAlarms 9 50 100 65 35
Peak Alarms/hour(10 Minutes) 60 1320 1080 2100 1080
Distribution %(Low/Med/High) 80/15/5 25/40/35 25/40/35 25/40/35 25/40/35
10
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
How to Reduce False Alarms
Can be addressed in different levels in the plant (design, operation, management)Improve the design
Multivariate instead of univariateMore accurate models Better configuration (tuning)Processing of data
Alarm Management
11
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Multivariate vs. Univariate
Pressure
0 20 40 60 80 100
92
94
96
98
100
102
104
Pre
ssur
e
Pressure versus Temperature
Temperature
0 20 40 60 80 10041
42
43
44
45
46
47
48
4941 42 43 44 45 46 47 48 49
92
94
96
98
100
102
104
12
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Why Multivariate Analysis
Hundreds to thousands of variables are measuredVariables are highly correlated with one another
It is not easy to understand the correlation between variablesStatistical rank of data is very lowRank is independent of the number of variables measuredThe behavior of the process can be expressed by a few independent variables (sources of variation in the in the process)
Low signal-to-noise ratio Little information in any one variable
13
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Model-based Performance Monitoring
The actual behavior of the process is compared with the behavior predicted by the model.(perfect model) and (no abnormalities)
(error is white noise)The prediction error is processed.The result is compared with a threshold.
Actual Process
Process Model
+_
errorprocessing alarm
14
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Modelling
First principles modelData-driven modeling
Dynamical modeling (system identification)Statistical modeling (PCA, PLS, CCA, …)
A new set of independent variables are created (from a combination of the original variables) that capture the variability of the process
Neural networks…
15
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Error Processing
After the error is generated, it should be processed to facilitate
Threshold designNoise reductiondetection delay and false alarm rate trade-offfalse alarm rate and missed alarm rate trade-off
16
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Reducing False Alarm Rate
False alarm rate can be reduced using simple processing techniques
FilteringReduces noiseRemoves spikesModifies distribution
Time delayDead-band
Reduces alarm chattering
17
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filtering
Filters are applied to variables to:reduce noiseremove bad or unwanted dataextract featuresmodify statistical distributionsseparate frequency components
Common filtersMoving averageMoving varianceMoving rangeEWMAFinite Impulse Response (FIR)
18
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
19
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
20
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
21
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
22
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
-2 0 2 40
0.1
0.2
0.3
0.4
false alarm = 102missed alarm = 157
23
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
24
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
0 500 1000 1500
-1
0
1
2
3
25
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
0 500 1000 1500
-1
0
1
2
3
-1 0 1 20
0.5
1
1.5
26
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
0 500 1000 1500
-1
0
1
2
3
-1 0 1 20
0.5
1
1.5
27
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
0 500 1000 1500
-1
0
1
2
3
-1 0 1 20
0.5
1
1.5
28
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
-1 0 1 20
0.5
1
1.5
false alarm = 39, missed alarm = 1
29
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
0 500 1000 1500
-1
0
1
2
3
-1 0 1 20
0.5
1
1.5
30
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
0 500 1000 1500
-1
0
1
2
3
-1 0 1 20
0.5
1
1.5
31
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Average
0 500 1000 1500
-2
0
2
4
6
-2 0 2 40
0.1
0.2
0.3
0.4
-1 0 1 20
0.5
1
1.5
32
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Variance
0 500 1000 1500-10
-5
0
5
10
33
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Variance
0 500 1000 1500-10
-5
0
5
10
-5 0 50
0.1
0.2
0.3
0.4
34
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Variance
0 500 1000 1500-10
-5
0
5
10
-5 0 50
0.1
0.2
0.3
0.4
35
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Variance
0 500 1000 1500-10
-5
0
5
10
-5 0 50
0.1
0.2
0.3
0.4
36
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Variance
0 500 1000 1500-10
-5
0
5
10
-5 0 50
0.1
0.2
0.3
0.4
0 500 1000 1500
0
5
10
15
20
37
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Variance
0 500 1000 1500-10
-5
0
5
10
-5 0 50
0.1
0.2
0.3
0.4
0 500 1000 1500
0
5
10
15
20
0 5 10 150
0.5
1
38
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Variance
0 500 1000 1500-10
-5
0
5
10
-5 0 50
0.1
0.2
0.3
0.4
0 500 1000 1500
0
5
10
15
20
0 5 10 150
0.5
1
39
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Filter: Moving Variance
0 500 1000 1500-10
-5
0
5
10
-5 0 50
0.1
0.2
0.3
0.4
0 5 10 150
0.5
1
40
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Time Delay
0 500 1000 1500
-2
0
2
4
6
41
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Time Delay
42
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Alarm Chattering - Deadband
43
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Alarm Chattering - Deadband
44
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Alarm Chattering - Deadband
45
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Alarm Chattering - Deadband
46
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Alarm Chattering - Deadband
47
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Alarm Chattering - Deadband
48
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Case Study 1
Performance Monitoring of a Pump
49
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Case Study 2
Performance Monitoring of Electric Motors
50
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Concluding Remarks
Alarm management and engineering is critical in today’s industries.Multivariate and model-based methods offer better monitoring performance than univariate and signal-based methods.False alarms can be avoided by processing the prediction error and applying simple techniques.The major trade-off in alarm design is between detection delay and false alarm rate.
51
NSERC-Matrikon-Suncor-iCORE IRC Seminar; 3 December 2007
Acknowledgements
Dr. Dave Shook from MatrikonDr. Sirish Shah and Dr. Tongwen ChenCPC Group MembersNSERC-Matrikon-Suncor-iCORE for financial support