Hydroelectric generating set bolt looseness monitoring method and device

By using non-invasive sensors and adaptive wavelet denoising technology in hydropower units, combined with conditional generative adversarial networks and support vector machines, the problems of difficult sensor installation, high noise, and operating condition interference in monitoring bolt loosening in hydropower units have been solved, achieving high-precision real-time monitoring and early warning.

CN121253142AActive Publication Date: 2026-01-02HUBEI ENERGY GRP CO LTD +1
10 Cites 2 Cited by

Patent Information

Application Number
CN202511812581.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-04
Publication Date
2026-01-02
Estimated Expiration
2045-12-04

AI Technical Summary

Technical Problem

Existing technologies struggle to achieve real-time, comprehensive, and reliable bolt loosening monitoring in hydropower units. This is due to limitations such as difficult sensor installation, high environmental noise, and operational interference, resulting in a high false alarm rate.

Method used

A diagnostic model is constructed by using non-invasive vibration and ultrasonic sensors, combined with an adaptive wavelet denoising algorithm, a conditional generative adversarial network (cGAN), and a support vector machine (SVM). By fusing time-domain and frequency-domain features, the model achieves condition-adaptive monitoring of bolt loosening.

Benefits of technology

It achieves high-precision bolt loosening monitoring in high-noise environments with a low false alarm rate, and can provide real-time, full-coverage bolt loosening early warning, reducing the impact of operating condition fluctuations.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a hydroelectric generating set bolt looseness monitoring method and device, and relates to the technical field of bolt looseness monitoring. The method comprises the following steps: arranging a vibration sensor and an ultrasonic sensor in a key area of a hydroelectric generating set, synchronously collecting a vibration signal and an ultrasonic signal, and recording the vibration signal and the ultrasonic signal as original signals; carrying out adaptive wavelet threshold noise reduction processing on the original signal to obtain a sound vibration signal to be diagnosed; building a diagnosis model based on the conditional generative adversarial network and a support vector machine; extracting a time domain feature and a frequency domain feature from the acoustic vibration signal to be diagnosed, obtaining a working condition parameter vector of the hydroelectric generating set, and splicing the time domain feature, the frequency domain feature and the working condition parameter vector to obtain a fusion feature vector; and inputting the fusion feature vector into a diagnosis model, and monitoring the loosening state of the bolt through the diagnosis model. According to the invention, effective, real-time and comprehensive bolt loosening state monitoring can be realized.
Need to check novelty before this filing date? Find Prior Art