Data Mining Applied To Fault Detection

1
Data Mining Applied To Fault Detection

• Shinho Jeong
• Jaewon Shim
• Hyunsoo Lee

2
Abstract

• Aims of work
• Neural Network Implementation of the Non-linear
  PCA model using Principal Curve algorithm to
  increase both rapidity accuracy of fault
  detection.
• Data mining?
• Extracting useful information from raw data
• using statistical methods and/or AI
  techniques.
• Characteristics
• Maximum use of data available.
• Rigorous theoretical knowledge not required.
• Efficient for a system with deviation between
  actual process and first principal based model .
• Application
• Process monitoring
• Fault detection/diagnosis/isolation
• Process estimation
• Soft sensor

3
Fault Detection(1)
4
Fault Detection(2)

• Major concerns
• Rapidity
• Ability to detect fault situation at an earlier
  stage of fault introduction.
• Accuracy
• Ability to distinguish fault situation from
  possible process variations.
• Trade-off problem
• Solve through
• Frequent acquisition of process data.
• Derivation of efficient process model through
  data analysis using Data mining methodologies.

5
Fault Detection(3)

• Inherent problems
• Multi-colinearity problem
• Due to high correlation among variables.
• Likely to cause redundancy problem.
• Derivation of new uncorrelated feature variables
  required.
• Dimensionality problem
• Due to more variables than observations.
• Likely to cause over-fitting problem in
  model-building phase.
• Dimensional reduction required.
• Non-linearity problem
• Due to non-linear relation among variables.
• Pre-determination of degree of non-linearity
  required.
• Application of non-linear model required.
• Process dynamics problem
• Due to change of operating conditions with time.
• Likely to cause change of correlation structure
  among variables.

6
Fault Detection(4)

• Statistical data analysis
• Uni-variate SPC
• Conventional Shewart, CUSUM, EWMA, etc.
• Limitations
• Perform monitoring for each process variable.
• Inefficient for multi-variate system.
• More concerned with how variables co-vary.
• Need for multi-variate data analysis
• Multi-variate SPC
• PCA
• Most popular multi-variate data analysis method.
• Basis for regression modesl(PLS, PCR, etc).

7
Linear PCA(1)

• Features
• Creation of
• Fewer gt solve Dimensionality problem
• Orthogonal gt solve Multi-colinearity problem
• new feature variables(Principal components)
• through linear combination of original
  variables.
• Perform Noise reduction additionally.
• Basis for PCR, PLS.
• Limitation
• Linear model gt inefficient for nonlinear
  process.

8
Linear PCA(2)

• Theory

9
Linear PCA(3)

• ERM inductive principle
• Limitation
• Alternatives
• Extension of linear functions to non-linear ones
  using
• Neural networks.
• Statistical method.

10
Kramers Non-linear PCA

• Limitations
• Difficult to train the networks with 3 hidden
  layers.
• Difficult to determine the optimal of hidden
  nodes.
• Difficult to interpret the meaning of the
  bottle-neck layer.

11
Non-linear PCA(1)

• Principal curve(Hastie et al. 1989)
• Statistical, Non-linear generalization of the
  first linear Principal component.
• Self-consistency principle
• Projection step(Encoding)
• Conditional averaging(Decoding)

12
Non-linear PCA(2)

• Limitations
• Finiteness of data.
• Unknown density distribution.
• No priori information about data.
• Additional consideration
• Conditional averaging gt Locally weighted
  regression, Kernel regression
• Increasing flexibility(Span decreasing)
• Span fraction of data considered to be in the
  neighborhood.
• smoothness of fit
• generalization capacity

13
Proposed Approach(1)

• Creation of Non-linear principal scores

14
Proposed Approach(2)

• Implementation of Auto-associative N.N.

15
Conclusion

• Future works
• Implementation of the proposed Neural Network
  structure.
• Application for a case study