1. Department of Electrical Engineering
Neural-Fuzzy Pattern Recognition Algorithm for Classifying the Events in Power System Networks
Slavko Vasilic
Department of Electrical Engineering
Texas A&M University

2. Outline Problem, Goal, Objectives Protective relaying
Neural network (NN) algorithm
Process modeling and simulation
Algorithm implementation
Fuzzyfication of NN outputs
Algorithm Testing
Conclusion, Future Work

3. Problem
Traditional relay settings are computed ahead of time based on worst case fault conditions and related phasors
The settings may be incorrect for the unfolding events
The actual transients may cause a measurement error that can cause a significant impact on the phasor estimates

4. Goal
Design a new relaying strategy that does not have traditional relay setting
Optimize the algorithm performance in each prevailing network conditions
Improve simultaneously both, dependability and security of the relay operation
Demonstrate the benefits using realistic network and fault events

5. Objectives
Implement a new pattern recognition based protection algorithm
Use a neural network and apply it directly to the samples of voltage and current signals
Produce the fault type and zone classification in real time
Study various approaches for preprocessing NN inputs and fuzzyfication of NN outputs

6. The different parts of the fault clearance chain
Protective Relaying
The different parts of the fault clearance chain

7. The principle of distance protection relays
Protective Relaying
The principle of distance protection relays

8. Mho fault characteristic of distance relay
Protective Relaying
Mho fault characteristic of distance relay

9. Neural Network Algorithm The principle of multilayer neural networks

10. Neural Network Algorithm Pattern classification of faulted events
Class decision boundaries
Patterns

11. Neural Network Algorithm Characteristic of the used neural network
Direct use of samples (no feature extraction)
Hidden layer of competitive neurons
Self-organizing
Unsupervised and supervised learning
Outputs are prototypes of typical patterns
Adaptability for non-stationary inputs

12. Neural Network Algorithm
Training steps

13. Process Modeling and Simulation RE HL&P Stp-Sky power network model

14. Process Modeling and Simulation Scenario cases: general fault events
All types of fault (11 types)
Fault location variation (0-100% of the line length)
Fault impedance variation (0-100 Ohms)
Fault inception angle variation (0-360 deg)

15. Process Modeling and Simulation
Example of patterns for various fault parameters

16. Algorithm Implementation
Training and testing
Power network model is used to simulate various fault events
Fault events are determined with varying fault parameters: type, location, impedance and inception time
The simulation results are used for forming the inputs for algorithm training and evaluation

17. Algorithm Implementation Training and testing (cont’d)
Training tasks are aimed at recognizing fault type and location
Test patterns correspond to a new set of previously unseen scenarios
Test patterns are classified according to their similarity to the prototypes by applying K-nearest neighbor classifier (decision rule)

18. Algorithm Implementation Properties of input signal processing
Data selected for training: currents, voltages or both
Sampling frequency
Moving data window length
Analog filter characteristics
Scaling ratio between voltage and current samples

19. Algorithm Implementation Moving data window for taking the samples

20. Algorithm Implementation
Example of the patterns for various scaling ratios

21. Algorithm Implementation
Prototype
Training patterns

22. Algorithm Implementation
The outcome of training are pattern prototypes

23. Fuzzyfication of NN Outputs Fuzzyfied classification of a test pattern

24. Fuzzyfication of NN Outputs Fuzzyfied classification of a test pattern
Determine appropriate number of nearest prototypes to be taken into account
Include the weighted distances between a pattern and selected prototypes
Include the size of selected prototypes

25. Fuzzyfiaction of NN Outputs

26. Fuzzyfication of NN Outputs Fuzzy K-NN parameter optimization

27. Algorithm Testing
Test
pattern
Nearest prototypes

28. Propagation of classif. error during testing
Algorithm Testing
Propagation of classif. error during testing

29. Algorithm sensitivity versus data used for training
Algorithm Testing
Algorithm sensitivity versus data used for training

30. Conclusion
Protection algorithm is based on unique self­organized neural network and uses voltages and currents as inputs
Tuning of input signal preprocessing steps significantly affects algorithm behavior during training and testing
Fuzzyfication of NN outputs improves algorithm selectivity for previously unseen events

31. Conclusion
The algorithm establishes prototypes of typical patterns (events)
Proposed approach enables accurate fault type and fault location classification
The power network model is used to simulate a variety of fault and normal events

32. Future Work
Perform comprehensive algorithm training for extended set of training patterns
Perform extensive algorithm testing and performance optimization
Study algorithm sensitivity versus various input signal preprocessing steps
Implement algorithm on-line learning