Fault Diagnosis of Rotating Machinery Based on Convolutional Neural Network and Singular Value Decomposition

Abstract

Vibration signal and shaft orbit are important features that reflect the operating state of rotating machinery. Fault diagnosis and feature extraction are critical to ensure the safety and reliable operation of rotating machinery. A novel method of fault diagnosis based on convolutional neural network (CNN), discrete wavelet transform (DWT), and singular value decomposition (SVD) is proposed in this paper. CNN is used to extract features of shaft orbit images, DWT is used to transform the denoised swing signal of rotating machinery, and the wavelet decomposition coefficients of each branch of the signal are obtained by the transformation. The SVD input matrix is formed after single branch reconstruction of the different branch coefficients, and the singular value is extracted to obtain the feature vector. The features extracted from both methods are combined and then classified by support vector machines (SVMs). The comparison results show that this hybrid method has a higher recognition rate than other methods.

Research on the shaft orbit of hydropower units based on convolutional neural network and the fine-grained indicators

“…Jiang Xiaomo proposed a multi-layer CNN framework for automatic fault diagnosis of various turbo-machines [12]. In the area of rotating machines, plenty of CNN models have been broadly implemented for fault diagnosis and pattern recognition [13][14][15][16][17]. However, these CNNbased methods are mostly focused on the features of vibration signals rather than the orbit images.…”