Distribution Network Fault Identification Based on Wavelet Packet Transform and Semi-supervised Support Vector Machine
- Resource Type
- Conference
- Authors
- Liu, Yinliang; Pan, Shi; Yuan, Zhiyong; Bi, Ran; Zhang, Huiquan; Wu, Shilin; Wang, Shanxiang; He, Jinliang; Hu, Jun
- Source
- 2023 3rd International Conference on Energy Engineering and Power Systems (EEPS) Energy Engineering and Power Systems (EEPS), 2023 3rd International Conference on. :957-960 Jul, 2023
- Subject
- Components, Circuits, Devices and Systems
Computing and Processing
Power, Energy and Industry Applications
Support vector machines
Fault diagnosis
Training
Time-frequency analysis
Training data
Distribution networks
Switches
component
Wavelet packet transform
Semi-supervised learning
Support vector machine
Distribution network fault
- Language
This paper proposes a distribution network fault identification method based on wavelet packet transform and semi-supervised support vector machine. Using wavelet packet transform obtain the zero-sequence current time-frequency matrix of power signals in each section of distribution network. Using the zero-sequence current time-frequency matrix and three-phase current signals construct the feature data. The semi-supervised support vector machine is trained by feature data with partial labels. The highest fault classification accuracy rate can reach 99.7%. When the proportion of valid label data is about 50%, the classification accuracy can reach 99.5%. The robustness of the algorithm is also verified.