Acoustic Vibration Approach for Detecting Faults in Hydroelectric Units: A Review

The acoustic-based approach is a prevalent way for non-contact fault diagnosis on Gas-Insulated Switch-gear (GIS). GIS always works under different voltages causing great diversity in acoustic frequency. However, based on the frequency principle, neural networks always focus on a specific frequency, which challenges robust fault detection on GIS. This paper introduces a novel multi-stage training method to improve the robustness of fault detection on GIS. The proposed method consists of three components: a Multi-Channel Based Frequency Regressor (MCBFR), an Audio Spectrogram Transformer Auto-Encoder (AST-AE), and a Feature Interaction Module (FIM). MCBFR and AST-AE are optimised to extract specific features from acoustics during the pre-training stage. The FIM fuses components extracted by MCBFR and AST when training the model that can indicate the final result. Also, we apply a multi-stage training strategy during the training stage to reduce the cost of potential model retraining. The efficacy of the proposed method was validated using experimental data from a real GIS, and it shows competitive performance in fault detection compared to existing methods.

Section: Transformermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Gas-insulated switch-gear mechanical fault detection based on acoustic feature analysis using a multi-state pre-trained neural network

Wang,

Zhang,

Shao

et al. 2024

“…To provide guidance and suggestions for the normal operation of HGUs, many scholars have conducted a lot of research on the early fault detection of HGUs [4]. For example, De Santis and Costa [5] performed anomaly detection based on an improved random forest model for small hydropower plant operation data to identify faults.…”

Section: Introductionmentioning

confidence: 99%

Operational risk assessment for hydroelectric generating units using multi-head spatio-temporal attention and adaptive fuzzy clustering

Liu,

Xu,

Liu

et al. 2023

A novel operational risk assessment method for hydroelectric generating units (HGUs) is presented in this article. First, a multi-head spatio-temporal attention gated network (MSTAGN) is proposed to establish an operation risk benchmark model (ORBM) for HGUs to reveal the intricate relationship between performance and its multiple influencing factors. In particular, MSTAGN learns complex interaction relationships among multiple influencing factors in both temporal and spatial dimensions and automatically extracts important features. Then, a nonlinear mapping function is constructed to extract the deviation of the current measured performance parameters from the predicted baseline performance parameters as the operation risk degree (ORD). On this basis, an adaptive fuzzy clustering (AFC) algorithm is proposed to achieve a clear classification of the operating risk level for HGUs. The proposed method is applied in a HGU in Sichuan province, China. The results of comparative experiments demonstrate its viability and efficacy.

“…The two-stage methodology of first extracting fault features from vibration signals by means of some signal processing methods, and then taking the extracted features as the * Author to whom any correspondence should be addressed. model input of machine learning algorithms to identify the exact fault types, is a common procedure for the fault diagnosis of hydropower units [3]. With the deepening of the research on vibration fault diagnosis, a variety of different fault diagnosis methods have been proposed.…”

Section: Introductionmentioning

confidence: 99%

An intelligent fault diagnosis scheme for hydropower units based on the pattern recognition of axis orbits

Liu¹,

Zheng²,

Ma³

et al. 2022

Fault diagnosis plays an important role in maintaining the safe and stable operation of hydropower units. This paper presents an intelligent fault diagnosis scheme for hydropower units based on the pattern recognition of axis orbits. Firstly, the vibration signals in X and Y directions which constitute the axis orbit of the unit shaft are processed by the denoising method based on VMD and PE entropy. Secondly, the relative position and distribution of the axis orbits for different samples in the image window are unified. Thirdly, the trained CNN is chosen as the classifier to recognize the axis orbit image for the fault type recognition. Through the analysis of the measured data of hydropower station, the influence of the sample number of training set and the size of axis orbit image on the performance of the proposed method and the necessity of denoising operation are studied. Compared with the existing methods, the proposed method has higher fault recognition accuracy and better generalization performance for different training sample sets. The results indicate that the proposed method is an effective alternative for the fault diagnosis of hydropower units.