In the complex and harsh environment of agriculture, rolling bearings, as the key transmission components in agricultural machinery, are very prone to failure, so research on the intelligent fault diagnosis of agricultural machinery components is critical. Therefore, this paper proposes a new method based on SVD-EDS-GST and ResNet-Vision Transformer (ResViT) for the fault diagnosis of rolling bearings in agricultural machines. Firstly, an experimental platform for rolling bearing failure in agricultural machinery is built, and one-dimensional vibration signals are obtained using acceleration sensors. Next, the signal is preprocessed for noise reduction using singular value decomposition (SVD) combined with the energy difference spectrum (EDS) to solve for the interference of complex noise and redundant components in the vibration signal. Secondly, generalized S-transform (GST) is used to process vibration signals into images. Then, the ResViT model is proposed, where the ResNet34 network is used to replace the image chunking mechanism in the original Vision Transformer model for feature extraction. Finally, an improved Vision Transformer (ViT) is utilized to synthesize global and local information for fault classification. The experimental results show that the proposed method’s average accuracy in rolling bearing fault classification for agricultural machinery reaches 99.08%. In addition, compared with SVD-EDS-GST-CNN, SVD-EDS-GST-LSTM, STFT-ViT, GST-ViT, and SVD-EDS-GST-ViT, the accuracy rate was improved by 3.5%, 3.84%, 4.8%, 8.02%, and 0.56%, and the standard deviation was also minimized.

Electric motors play a crucial role in ship systems. Detecting potential issues with electric motors is a critical aspect of ship fault diagnosis. Fault diagnosis in motors is often challenging due to limited and noisy vibration signals. Existing deep learning methods struggle to extract the underlying correlation between samples while being susceptible to noise interference during the feature extraction process. To overcome these issues, this study proposes an intelligent bimodal fusion attention residual model. Firstly, the vibration signal to be encoded undergoes demodulation and is divided into high and low frequencies using the IEEMD (Improved Ensemble Empirical Mode Decomposition) composed of the EEMD (Ensemble Empirical Mode Decomposition) and the MASM (the Mean of the Standardized Accumulated Modes). Subsequently, the high-frequency component is effectively denoised using the wavelet packet threshold method. Secondly, current data and vibration signals are transformed into two-dimensional images using the Gramian Angular Summation Field (GASF) and aggregated into a bimodal Gramian Angle Field diagram. Finally, the proposed model incorporates the Self-Attention Squeeze-and-Excitation Networks (SE) mechanism with the Swish activation function and utilizes the ResNeXt architecture with a Dropout layer to identify and diagnose faults in the multi-mode fusion dataset of motors under various working conditions. Based on the experimental results, a comprehensive discussion and analysis were conducted to evaluate the performance of the proposed intelligent bimodal fusion attention residual model. The results demonstrated that, in comparison to traditional methods and other deep learning models, the proposed model effectively utilized multimodal data, thereby enhancing the accuracy and robustness of fault diagnosis. The introduction of attention mechanisms and residual learning enable the model to focus more effectively on crucial modal data and learn the correlations between modalities, thus improving the overall performance of fault diagnosis.

Aiming at rolling bearing fault diagnosis, the collected vibration signal contains complex noise interference, and one-dimensional information cannot be used to fully mine the data features of the problem. This paper proposes a rolling bearing fault diagnosis method based on SVD-GST combined with the Vision Transformer. Firstly, the one-dimensional vibration signal is preprocessed to reduce noise using singular value decomposition (SVD) to obtain a more accurate and useful signal. Then, the generalized S-transform (GST) is used to convert the processed one-dimensional vibration signal into a two-dimensional time–frequency image and make full use of the advantages of deep learning in image classification with higher recognition accuracy. In order to avoid the problem of limited sensory fields in CNN and the need for an RNN to compute step by step over time when processing sequence data, the use of a Vision Transformer model for pattern recognition classification is proposed. Finally, an experimental platform for the fault diagnosis of rolling bearings is built. The model is experimentally validated, achieving an average accuracy of 98.52% over multiple tests. Additionally, compared with the SVD-GST-2DCNN, STFT-CNN-LSTM, SVD-GST-LSTM, and GST-ViT fault diagnosis models, the proposed method has higher diagnostic accuracy and stability, providing a new method for rolling bearing fault diagnosis.

Electric motors play a crucial role in self-driving vehicles. Therefore, fault diagnosis in motors is important for ensuring the safety and reliability of vehicles. In order to improve fault detection performance, this paper proposes a motor fault diagnosis method based on vibration signals. Firstly, the vibration signals of each operating state of the motor at different frequencies are measured with vibration sensors. Secondly, the characteristic of Gram image coding is used to realize the coding of time domain information, and the one-dimensional vibration signals are transformed into grayscale diagrams to highlight their features. Finally, the lightweight neural network Xception is chosen as the main tool, and the attention mechanism Convolutional Block Attention Module (CBAM) is introduced into the model to enforce the importance of the characteristic information of the motor faults and realize their accurate identification. Xception is a type of convolutional neural network; its lightweight design maintains excellent performance while significantly reducing the model’s order of magnitude. Without affecting the computational complexity and accuracy of the network, the CBAM attention mechanism is added, and Gram’s corner field is combined with the improved lightweight neural network. The experimental results show that this model achieves a better recognition effect and faster iteration speed compared with the traditional Convolutional Neural Network (CNN), ResNet, and Xception networks.

Electric motors play a pivotal role in the functioning of autonomous vehicles, necessitating accurate fault diagnosis to ensure vehicle safety and reliability. In this paper, a novel motor fault diagnosis approach grounded in vibration signals to enhance fault detection performance is presented. The method involves capturing vibration signals from the motor across various operational states and frequencies using vibration sensors. Subsequently, the signals undergo transformation into frequency domain representations through fast Fourier transform. This includes normalizing and concatenating the amplitude frequency and phase frequency signals into comprehensive frequency domain information. Leveraging Gramian image-encoding attributes, cross-domain fusion of time-domain and frequency-domain data is achieved. Finally, the fused Gram angle field map is fed into the ConvMixer deep learning model, augmented by the ECA mechanism to facilitate precise motor fault identification. Experimental outcomes underscore the efficacy of cross-domain data fusion, showcasing improved pattern recognition and recognition rates for the models compared to traditional time-domain methods. Additionally, a comparative analysis of various deep learning models highlights the superior performance of the ECA-ConvMixer model. This study makes significant contributions by introducing a cross-domain data fusion method, merging time-domain and frequency-domain information to enhance motor vibration signal analysis. Additionally, the incorporation of the ECA-ConvMixer deep learning model, equipped with attention mechanisms, effectively captures critical features, thus serving as a robust tool for motor fault diagnosis. These innovations not only enhance diagnostic accuracy but also have broad applications in areas like autonomous vehicles and industry, leading to reduced maintenance expenses and enhanced equipment reliability.

Three-phase asynchronous motors have a wide range of applications in the machinery industry and fault diagnosis aids in the healthy operation of a motor. In order to improve the accuracy and generalization of fault diagnosis in three-phase asynchronous motors, this paper proposes a three-phase asynchronous motor fault diagnosis method based on the combination of multiscale Weibull dispersive entropy (WB-MDE) and particle swarm optimization–support vector machine (PSO-SVM). Firstly, the Weibull distribution (WB) is used to linearize and smooth the vibration signals to obtain sharper information about the motor state. Secondly, the quantitative features of the regularity and orderliness of a given sequence are extracted using multiscale dispersion entropy (MDE). Then, a support vector machine (SVM) is used to construct a classifier, the parameters are optimized via the particle swarm optimization (PSO) algorithm, and the extracted feature vectors are fed into the optimized SVM model for classification and recognition. Finally, the accuracy and generalization of the model proposed in this paper are tested by adding raw data with Gaussian white noise with different signal-to-noise ratios and the CHIST-ERA SOON public dataset. This paper builds a three-phase asynchronous motor vibration signal experimental platform, through a piezoelectric acceleration sensor to discern the four states of the motor data, to verify the effectiveness of the proposed method. The accuracy of the collected data using the WB-MDE method proposed in this paper for feature extraction and the extracted features using the optimization of the PSO-SVM method for fault classification and identification is 100%. Additionally, the proposed model is tested for noise resistance and generalization. Finally, the superiority of the present method is verified through experiments as well as noise immunity and generalization tests.