A CEGD-FNN-based fault early warning system for hydroelectric generator set

By using a fault early warning system based on CEGD-FNN, combined with fuzzy systems and RBF neural networks, the complexity of fault early warning for hydro-generator units has been solved, enabling accurate prediction and probability assessment of faults, supporting equipment condition assessment and maintenance decisions, and improving the safety and stability of the power system.

CN116906246BActive Publication Date: 2026-06-02CHINA YANGTZE POWER
View PDF 5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA YANGTZE POWER
Filing Date
2023-07-26
Publication Date
2026-06-02

AI Technical Summary

Technical Problem

Hydropower generator sets operate in a complex manner, making it difficult to establish accurate mathematical models. Furthermore, the occurrence of faults involves a variety of uncertain factors, making it difficult for existing technologies to effectively provide fault early warning.

Method used

A fault early warning system based on CEGD-FNN is adopted, including modules for early fault signal feature extraction, fault diagnosis, condition assessment and fault prediction. Combining fuzzy system theory and RBF neural network, multiple feature vectors are fused using turbine operating data and vibration signals to achieve accurate fault prediction and probability assessment.

Benefits of technology

It enables accurate prediction and probability assessment of hydro-generator unit failures, provides real-time assessment of equipment status and maintenance decision support, and improves the safety and stability of the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116906246B_ABST
    Figure CN116906246B_ABST
Patent Text Reader

Abstract

This invention relates to a fault early warning system for hydro-generator units based on CEGD-FNN. The system includes: a feature extraction module for early fault signals of the hydro-generator unit, a fault diagnosis module for the hydro-generator unit, a status assessment module for the hydro-generator unit, a fault prediction module for the hydro-generator unit, and a human-machine interface module. These modules are sequentially connected. This invention employs a unified data platform integrating heterogeneous source information and a unified platform for open knowledge resource sharing. It can promptly obtain heterogeneous data from distributed systems and knowledge resources from different users, thereby achieving intelligent collaborative diagnosis of equipment faults and reducing losses caused by insufficient timely handling of emergency faults.
Need to check novelty before this filing date? Find Prior Art