DataSource
- Channels to monitor signals from various sources
- Queues to store incoming samples
- Registration allows components to subscribe to updates
ProcessingEngine
- Applies signal processing techniques
- Subscribes to DataSource for raw signals
- Processes and returns processed signals
UserInterface
- Allows selection of processing techniques
- Displays processed signals for analysis
- Notifies user of faults or anomalies
The software architecture supports flexible routing of signals from multiple sources to processing techniques. Object-oriented design allows new processing techniques and data sources to be added dynamically. This enables online condition monitoring of variable state machinery using intelligent signal processing.
3. Problem Overview
Maintenance options have advanced considerably from
reactive policies
Modern sensors, computers and algorithms have set
the stage
Health monitoring of steady machinery widely available
Few techniques are available for monitoring unsteadily
operating equipment
Techniques required for advanced equipment such as
electromechanical shovel, variable duty hoists, etc.
Subject to variable loads, speed,
temperatures, etc.
3
4. Problem Definition
Enable condition monitoring (CM) of mobile
underground mining machinery
Multiple Artificial Intelligence (AI) techniques
• As validated on laboratory test bench
– gearbox and bearing faults
• Extensible to real-world applications?
Administration issues of automated computerized
monitoring systems
• Sporadic network availability
• Bandwidth limited environments
• Enterprise level integration
Extensible Software Engineering Architecture
4
5. Outline
Background
Condition Monitoring (CM)
Artificial Intelligence (AI) for CM
Monitoring of Variable-State Machinery
Methodology and Limitations
Statistical Parameterization
Augmented Novelty Detection
System Identification
Cross-Correlation
Software Architecture
Conclusion
5
7. Maintenance Management
Machinery Maintenance Policy driven by:
Availability of resources (spare parts, pers., capital)
Importance of equipment
Availability of technology and expertise
Modern Maintenance Policy evolved through:
Run-to-Failure
Periodic Maintenance
• Only 15% of failures follow MTBF model (Lihovd, 1998)
– Naval/air study
Predictive Maintenance
• Maintenance is delayed until some monitored parameter of the
equipment becomes erratic
• Proactive
• Balances resources
7
8. Condition Monitoring
Thrust
State of equipment determined by variations in
monitored parameters
Benefits
Environment
Safety
Production
Staff Shortages/Costs
Scheduling
Spare Parts (JIT)
Insurance
8 Life Extension
9. AI for CM
Savvy technicians employ(ed) a screw driver
set atop a vibrating machine
Resultant vibration of screw driver used by
technician to classify health
AUTOMATE THIS!
More sensitive
Earlier detection of faults
Consistent, reliable measurements
• Consistent, reliable classification
9
10. Pattern Recognition
One branch of AI domain
Patterns used to compute decision rule
Generalization
(Double) Curse of Dimensionality
10
11. Pattern Recognition
• Accelerometers, tachometers, acoustic emission sensors, thermocouples, etc.
Sensing
• Choose time intervals for division of data
• Synchronous intervals (fixed # of samples)
• Asynchronous intervals (fixed # of shaft rotations)
Segments
• N Parameters combined to form “patterns” or “feature vectors”
Feature • Statistics, Auto-regressive (AR) models, MUSIC Spectrum, etc.
Extraction
• Generate decision rules from training data
• Apply decision rules to test data
Classify • Fault detection: Novelty Detection (support vectors, neural networks, etc.)
• Diagnostics, prognostics
• Health reporting
Post- • Sensor failure analysis
Processing • Etc.
11
12. Monitored Parameters
Vibration, Thermography,
Oil Analysis, NDT, et
Vibration
Heavily used in literature
Non-destructive, online,
sensitive
Faults in rotating machinery
have strongly representative
features in the frequency
domain
Diagram: (Randall, 2004)
12
13. Novelty Detection
Motivation: addresses imbalance of data from one
class in relation to that of others
Data from faulted states are difficult to collect (economics,
operations)
Sub problem of pattern recognition
train on the “normal” class and then signal error when
behaviour deviates from the decision boundary
A wide variety of techniques available
Examine two:
Boundaries containing a certain quantile of data (i.e. a
statistical discordance test)
Boundaries derived by Support Vectors
13
14. Support Vectors
Support Vector Technique: Tax’s Support Vector
Data Description (for Novelty Detection)
Attempts to fit a sphere of minimal radius around normal
data
But a in a higher dimensional space (using the “kernel trick”)
• Generates a very flexible decision boundary in the input space
14
15. Variable-State Machinery
Primary aggravators: load and speed
Referred to as nuisance variables in the literature (Gelman,
2005)
In vibration monitoring
Power of vibration a product of the effects of load and speed
• Relation between power and speed non-linear
• Resonances!
• Vibration a function of health and mechanical state (speed,
load, etc.)
15
16. • When machine is healthy,
deviations in consequent
vibrations are small
• When health is poor,
deviations due to speed
become significant
• Stack: Damping in
undamaged machinery is
largely insensitive to
speed/load changes –
damaged machine
Diagram: (Stack, 2003)
16
19. Limitations
Test bench realism
Mass of shaft
• Inertia of rotor system
– Signal-to-Noise Ratio (SNR) of fault signals
Gear type
• Helical gears
– Increased mesh strength
» SNR of fault signals
Lack of complexity
• Variable Frequency Drive (VFD) and/or particle break
control on load/speed
– Torsional vibrations (typical in diesel engines) not
evaluated
19
20. Limitations
Challenging control
problem
Closed loop on speed
VFD
Open loop on load VFD
Torque profile fed forward
to speed VFD
Torque control
superimposed on speed
control
Noisy torque signal
Inconsistent effect on
20 algorithms
21. Limitations
Applicability to Underground Environment
Harsh conditions not present in laboratory
Temperatures
• Degradation of lubricants
• Thermal expansion of components
– Alters vibratory signature
– Time-varying parameter not considered
Heavy shock/vibration
• Noise for vibration-based CM
– Inclusion in training
» Overly broad decision boundary
– Exclusion
» Additionally processing required
21
24. Statistical Parameterization
Established technique from the literature
(Worden, 2001)
Motivation:
Distribution of vibration parameters will change
according to time-varying parameters
Experiments with variable speed only
24
25. Statistical Parameterization
Established Thrust:
Develop a decision boundary that changes according to
speed
Double Curse of Dimensionality *C30
Restrictive Gaussian assumption
*C20
y
* C10
x
25
27. Statistical Parameterization:
Improvement
Contribution:
Develop a rule to first center and whiten data
• Eigenvalue problem
Center/whiten all training data
• Train SVDD
Center/whiten test data according to rule
• Apply SVDD decision boundary to determine faults
Faulted Data
*C30
y
*C20 Healthy Data
y
for all Speeds
x
* C10
x
27
28. Statistical Parameterization
Choice of AR Model Order with Standard Statistical Parameterization
(Interpolation)
28
34. Augmented Novelty Detection
Previous limitations
Varying degrees of curse of dimensionality
Gaussian Assumption
Motivation
Intuition gained from Statistical Parameterization
• Include time-varying parameter in feature vector
– Trivial but not established in the literature
Problem reduced to standard novelty detection
Experiments with variable speed only
34
35. Background: Order Tracking
Ordinarily: Vibration sampled at constant intervals
Order tracking: vibration sampled at constant shaft
rotational intervals
Use pulse train from tachometer to indicate sampling
interval
Irregular resampling
Question:
How many samples per shaft rotation are
appropriate to gain good classification results?
35
44. System Identification
Shifts problem to the feature vector
rather than adapting decision boundary
Feature vector composed of elements of a
gear’s transfer functions
Analysis with both varying speed and load
44
45. System Identification
Assume a gear can be modeled as a
torsional spring
mx cx kx f (t )
Use system identification to model the
transfer function with MIMO
x Ax Bu B1 ( z ) B2 ( z )
V ( z) S ( z) T ( z)
y C x Du A1 ( z ) A2 ( z )
System:
Speed
Gearbox
Vibration
Load
45
46. Omitting Time-Varying Parameters
Employing Multi-Modal Novelty Detection
No Adaptation for Speed or Load No Adaptation for Load
46
51. Cross-Correlation Analysis
SysID Failings
Must measure all time-varying parameters
Must develop transfer functions for each
• Susceptibility to the double curse of dimensionality?
Computational expensive
Cross-correlation based feature vector
Sensors on disparate machinery components will
behave in a time-correlated manner
Use statistical correlation signal
*
• Generate feature vectors from it ( f g )(t ) f ( ) g (t )d
Eliminates failings of SysID *
( f g )[n] f [ m] g [ n m]
m
51
56. Challenge
No silver bullet for condition monitoring (pattern
recognition)
Multitude of techniques for multitude of problems
Wide variety of (transient) machinery
Similar CM problems: prognostics, sensor failure analysis
Extensible beyond rotating machinery
Pattern recognition problem generates multiple
possible combinations of
Sensing
Segmentation
Feature vector generation
Classification techniques
Post-processing requirements
56
57. Software Design
Structural
Monitoring
Measure Aircraft
while Drilling Monitoring
Design for Process
Monitoring
Stationary
Equipment
Monitoring
change!
Recognize Smart
Signal
Processing Seismicity
broader- Vehicle
Monitoring
Monitoring
in Mines
scoped
problem Automotive
Wind
Part and Test
• Intelligent Bench
Monitoring
Turbine
Monitoring
Signal Ship
Biomedical Propulsion
Processing Monitoring and Auxiliary
System
and Analysis
57
58. Scope of Present Work
Design Object-Oriented (OO) Data
Processing Layer
Online, flexible and dynamic routing of signals
Augmentable with user/programmer defined
techniques
Design for intelligent signal processing
• Implement for CM
Create MATLAB prototype
Review and make recommendations for
integration with mining enterprise systems
International Rock Excavation Data Exchange
58 Standard (IREDES)
59. Use Cases
Hand-held, portable monitoring system
Cheaper, economies of scale
Intermittent monitoring
Dedicated online monitoring system
Costly
Equivalent problem to intermittent monitoring
• Intermittent functionality/benefits achievable by “wheeling” this
system around
Capabilities to monitor more than one (physically proximate)
machine at a time
Data Connectivity
Limited bandwidth
Intermittent network connectivity
59
61. Design
Signal conditioning strategy
Typical signal processing techniques
“Signal” representing time intervals for segmentation
Signal conditioner
Does the actual work of
• getting sensor data
• passing it through selected algorithms
Feature generator
Requests conditioned signals from conditioner
Segments signals according to segmentation strategy
Combines multiple feature vectors into one
61
63. Design
FeatureGenerator
*
Intelligent
-SegStrategy
-SigConditioner
-Name
Analyzer Strategy 1
IntelligentAnalyzerStrategy
Requests feature DataSource
-ChannelQueues
vectors from -SampleRatesArray
-ChannelNames
-updateQueues
feature generator +DataSource()
+MonitorChannel() : <unspecified>
+getData()
Does the +clearData()
+updateQueue()
ExpertSystem FaultTree PatternRecognition
classification work
• Depending on 1 *
“state” of CombinationOfClassifiers NoveltyDetection
classification
problem
StatisticalParameterization SVDD
63
64. Integration with Enterprise Layer
IREDES in need of augmentation for CM
CM standards already exist
Don’t reinvent the wheel
Two options of differing granularity
Open Systems Architecture for Enterprise Application
Integration (OSA-EAI)
Open Systems Architecture for Condition-Base
Maintenance (OSA-CBM)
Wide industrial support
US Navy
Caterpillar
Rockwell Automation Systems
64
66. Conclusions
No silver bullet for CM
Wide variety of techniques for a wide variety of
applications
Advances in CM for variable-state machinery
• Must consider time-varying parameters to optimize
operations
Techniques
Limitations:
• Normal Distribution
• Double Curse of Dimensionality
• Sensors to measure time-varying parameters
Extensible to other mining and non-mining
66 applications
67. Conclusions
Software architecture
Recognize broader problem of Intelligent Signal Processing
• Subsumes CM, prognostics, sensor failure, etc.
Design for change
• Greater breadth of marketability
• Extensibility/Maintainability of Software Design
Integration at the Enterprise level
• Rich standard exists to augment IREDES
Future work
Take the solutions to the underground environment
Validate in harsh environment
67