Search

• The initial measurement point is optimized, and the wavelet packet decomposition method is used to decompose and reconstruct the original measurement signal to realize the preprocessing of the data. Its main contributions include removing the DC component of the signal and reducing the non-stationarity and inconsistency of the sampled signal. • In view of the mode aliasing phenomenon caused by using EMD mode to analyze the signal, this paper uses VMD self-use segmentation technology to realize the adaptive segmentation of each component in the signal field, which effectively avoids the mode aliasing phenomenon, has stronger robustness, and effectively reduces the endpoint effect. At the same time, aiming at the problem that the grayscale map is not enough to visually express the deep features in the process of signal conversion to a grayscale map, this paper uses an SDPI diagram to display signal characteristics, and uses information entropy (IE) to select the optimal component after VMD decomposition to enhance the characteristics of symmetry point mode image (SDPI), and finally fuses the signal corresponding to the optimal component to generate a snowflake map, so as to display the changes between different vibration states simply, clearly and intuitively, and enhance the recognition ability of the image, and the image accuracy of the method is higher than the traditional sample accuracy. • Aiming at the phenomenon that the traditional SoftMax classification ability in convolutional neural network is not high, firstly, the convolutional neural network optimization is realized by adjusting the parameters of the CNN model, adding regularization, adjusting the hyperparameters, etc., and at the same time, the combined model combining SVM and CNN is used to replace the SoftMax classifier with the SVM classifier, and the results show that the method can improve the classification ability of images. • To verify the effectiveness and superiority of the proposed method, the proposed method is compared with the 1DCNN method, grey image-CNN method, SDPI-CNN, SDPI-SVM, and other methods, and the comparative results show that the model has good predictive performance and generalization ability, and verifies that the proposed signal picture establishment method and network improvement optimization model method are feasible for lead screw fault classification. The failure of the ball screw in the machine tool presents various types and complex coupling characteristics, which pose challenges in extracting fault features from vibration signals and lead to decreased accuracy in fault diagnosis classification. To tackle this issue, an improved intelligent fault diagnosis method based on enhanced CNN is proposed by optimizing the variational mode decomposition and symmetrized dot pattern image features. Initially, VMD is employed to decompose the preprocessed signals, incorporating information entropy for selecting decomposition layers to enhance accuracy. Different image features are generated using SDPI, and differential information is introduced to enhance feature expressive capability through fusion. Subsequently, considering the limited classification ability of traditional SoftMax classifiers in CNNs, SVM is integrated for classification purposes to optimize convolutional neural networks' structure and improve their classification performance. Finally, the proposed method was ultimately validated by means of comparative analysis of screw vibration signals, thereby affirming its exceptional accuracy in fault diagnosis and classification. [ABSTRACT FROM AUTHOR]

In motor drive system, Bearing fault detection through motor current signal (MCS) analysis has gained recognition for its cost-effectiveness and non-invasive nature. However, two-dimensional (2D) convolutional neural networks (CNNs) exhibit suboptimal performance when directly applied to raw stator current signals for fault detection. Meanwhile, the training of Recurrent Neural Networks (RNNs) for processing one-dimensional (1D) temporal sequence can be a time-consuming task due to the inherent procedures of the network structure. To balance time-consuming and accuracy, this paper presents a novel MCS-based bearing fault detection model utilizing a 1D CNN and corresponding pre-processing methods. In the early stages, a noise cancellation strategy termed time shifting is implemented. Subsequently, wavelet transform is employed to further refine the processed signal by eliminating components with minimal significance. By compressing homogenous signals, the resultant tensor, referred to as the "root map", is employed as the input for the proposed temporal causal network. Two groups of experimental results conducted on both laboratory and industrial conditions validate the effectiveness and convenience of the proposed methodology. • Bearing fault detection through motor current signals is considered cheap and non-invasive. • Deeper networks for extracting fault components from raw current signals leads to overfitting. • Causal CNNs are one-dimensional networks, which can process data in parallel. • Equipment paired with the motor adds noise, hindering fault identification. [ABSTRACT FROM AUTHOR]