Failure Detection of PEMFC Power Generation System Based on Locality Preserving Projection and Learning Vector Quantization Neural Network
- Resource Type
- Conference
- Authors
- Liu, Jiawei; Li, Qi; Tang, Quan; Li, Ting; Wang, Yunling; Liu, Fang; Su, Yunche; Yan, Yu; Chen, Weirong
- Source
- 2020 IEEE Sustainable Power and Energy Conference (iSPEC) Sustainable Power and Energy Conference (iSPEC),2020 IEEE. :283-288 Nov, 2020
- Subject
- Power, Energy and Industry Applications
Protons
Vector quantization
Conferences
Neural networks
Fuels
Data mining
Power generation
Proton exchange membrane fuel cell
failure detection
feature extraction
locality preserving projection
learning vector quantization neural network
- Language
To settle the failure detection conundrum of the PEMFC power generation system, a failure detection approach of the PEMFC power generation system ground on local reservation projection (LLP) and learning vector quantization neural network (LVQNN) is devised. In this method, normalized preprocessing and LLP algorithms are used to shorten the dimensionality of the primary data, and the LVQNN is used to identify the pre-processed data. The results of 600 groups of fault data of the PEMFC water management subsystem reveal that the proposed approach can diagnose the faults of the PEMFC power generation system with 98.33% accuracy and can apply to the failure detection field of PEMFC power generation system.