Wang Daichao

TL;DR: A multiscale learning neural network that contains one-dimension (1D) and two- dimension (2D) convolution channels is proposed that can learn the local correlation of adjacent and nonadjacent intervals in periodic signals, such as vibration data.

TL;DR: In this paper, the authors proposed an attention-based multidimensional concatenated convolutional neural network (MDCNN) for the fault diagnosis of bearing failures, which can learn global information and assign different weights to feature maps to highlight important features.

TL;DR: In this article, the authors proposed an electromechanical equipment-oriented intelligent fault diagnosis method and system, and the method comprises the steps: obtaining the previous fault data of a target machine, and forming training data; acquiring real-time acquisition data of the target machine to form test data; constructing a domain adaptive network model, training the network model and marking the output of different data, minimizing the difference between the training data and the test data, and extracting and classifying the features of training data.

TL;DR: Wang et al. as discussed by the authors proposed a fault diagnosis method and system based on convolutional neural network cost-sensitive learning, which comprises the steps of constructing a CNN model with a cost sensitive layer, and carrying out the feature learning of a mechanical vibration training data set through a costsensitive learning method.