Convolutional neural network has been widely used in fault diagnosis of mechanical devices. In particular, a 2-D convolutional neural network requires manual selection of multiscale transformation to transform vibration signal into the 2-D structure. Although a 1-D convolution neural network can directly use the vibration signal for convolution processing, it cannot make full use of the nonlinear information in the 1-D space. In order to make full use of the advantages of 1-D and 2-D convolutional neural networks, in this article, we develop a one-dimension in tandem with 2-D joint convolutional neural network (1D–2D JCNN) for rotating machinery fault diagnosis. More specifically, 1-D convolution is employed to adaptively obtain the multiscale feature vectors of the vibration signal, and these feature vectors are constructed into 2-D maps, and then these 2-D vectors are used as the input of the 2-D convolutions neural network. Take the cross-entropy loss function as the loss function and use the error back propagation algorithm to optimize the filter parameters of the 1D–2D JCNN model to obtain the final fault diagnosis model. Using the motor bearing dataset and the worm gearbox dataset, the experimental results show the excellent classification performance of bearings and gears under different working conditions. The average diagnostic accuracy of ten runs on Case Western Reserve University bearing dataset is 99.92%, and the variance is 3.96e-6. The average diagnostic accuracy of ten runs on the worm gear dataset is 99.82%, and the variance is 7.82e-6. Compared with the traditional fault diagnosis model and the latest convolution neural network method, the 1D–2D JCNN shows better diagnosis performance.

In order to realize equipment’s near-zero downtime and maximum productivity a rolling bearing performance degradation assessment is proposed, which is one of the most important techniques. The traditional feature extraction methods based on stationary and Gauss characteristics were unfit to handle non-stationary and non-Gauss signals when the rolling bearing performance begins to degrade. The higher-order statistics (HOS) are fit for handling the non-stationary and non-Gauss signals. Bispectrum not only possesses all the properties of HOS but also has a higher computational efficiency because of a lower order compared with other types of HOS. The support vector data description (SVDD) is a single value classification method which can overcome the problem of a lack of samples in the degradation process of the rolling bearing. A method is proposed in the paper which is based on the bispectrum and SVDD. Firstly, the rolling bearing data of normal state is collected and handled by bispectrum. Based on feature vectors extracted from normal data an SVDD model fitting a tight hypersphere around them is trained. The general distance of test data handled by the bispectrum to this hypersphere is used as the degradation index. In the end, through simulation and a rolling bearing’s accelerated life test, the effectiveness and feasibility of the proposed method is verified.

Vibration signals are used to monitor the running state of mechanical equipment, but always suffer from a lot of noise in the acquisition process. In order to eliminate noise interference as much as possible, a multilevel residual convolution autoencoder network based noise learning method (LN-MRSCAE) is proposed in this paper. The LN-MRSCAE consists of a deep convolutional autoencoder network and multilevel residual, in which the learning noise module encodes and decodes the noise components, combining with a residual module to obtain the denoised signal. The multilevel residual structure is designed to address the gradient disappearance in network learning and improve the training speed. In specific, the noise learning replaces the traditional clean signal learning. Instead of learning the characteristics of the original clean signal, just learn the characteristics of the noise signal. The effectiveness of LN-MRSCAE network denoising is verified by classic analog signal and actual bearing vibration signals with different faults. The results show that the LN-MRSCAE model is superior to the latest models, and the noise component of the signal is obviously suppressed.

The bispectrum of rolling element bearing compound faults contains abundant fault characteristic information, and how to extract the fault feature effectively is a key problem. The fault diagnosis method of rolling element bearing compound faults based on Sparse No-Negative Matrix Factorization (SNMF)-Support Vector Data Description (SVDD) is proposed in the paper. The figure handling method SNMF is used firstly in fault feature extraction of the bispectrums of rolling element bearing different kinds of compound faults and the sparse coefficient matrices of the bispectrums are obtained. The sparse coefficient matrices are used as training and test input vectors of SVDD. At last, the three kinds of rolling element bearing compound faults (inner race outer race compound faults, outer race rolling element compound faults and inner race outer race rolling element compound faults) are classified correctly. In order to verify the advantages of the proposed method, the diagnosis results of the same three kinds of rolling element bearing compound faults based on No-Negative Matrix Factorization (NMF)-SVDD is used as comparison. The proposed method provides a new idea for fault diagnosis of rolling element bearing compound faults.

In the intelligent fault diagnosis of rotating machinery, it is difficult to extract early weak fault impact features of rotating machinery under the interference of strong background noise, which makes the accuracy of fault identification low. In order to effectively identify the early faults of rotating machinery, an intelligent fault diagnosis method of rotating machinery based on an optimized adaptive learning dictionary and one-dimensional convolution neural network (1DCNN) is proposed in this paper. First of all, based on the original signal, a redundant dictionary with impact components is constructed by K-singular value decomposition (K-SVD), and the sparse coefficients are solved by an optimized orthogonal matching pursuit (OMP) algorithm. The sparse representation of fault impact features is realized, and the reconstructed signal with a concise fault impact feature structure is obtained. Secondly, the reconstructed signal is normalized, and the experimental dataset is divided into samples. Finally, the training set is input into the 1DCNN model for model training, and the test set is input into the trained model for classification and detection to complete the intelligent fault classification diagnosis of rotating machinery. This method is applied to the fault diagnosis of bearing data of Case Western Reserve University and worm gear reducer data of Shanghai University of Technology. Compared with other methods and models, the results show that the diagnosis method proposed in this paper can achieve higher diagnosis accuracy and better generalization ability than other diagnosis models under different datasets.