Fault diagnosis in rolling bearings is an indispensable part of maintaining the normal operation of modern machinery, especially under the varying operating conditions. In this paper, an end-to-end adaptive anti-noise neural network framework (AAnNet) is proposed to solve the bearing fault diagnosis problem under heavy noise and varying load conditions, which takes the raw signal as input without requiring manual feature selection or denoising procedures. The proposed AAnNet employs the random sampling strategy and enhanced convolutional neural networks with the exponential linear unit as the activation function to increase the adaptability of the neural network. Moreover, the gated recurrent neural networks with attention mechanism improvement are further adopted to learn and classify the features processed by the convolutional neural networks part. Besides, we try to explain how the network works by visualizing the intrinsic features of the proposed framework. And we explore the effect of the attention mechanism in the proposed framework. Experiments show that the proposed framework achieves state-of-the-art results on two datasets under varying operating conditions.
Aiming at the problem of low recognition accuracy of maneuvering trajectories, this paper constructs a relatively complete maneuvering unit library by analyzing the characteristics of maneuvering trajectory, and expresses complex trajectories with simple units; Combine the coyote optimization algorithm(COA) with the Least Squares Support Vector Machine (LSSVM) classifier, and use the COA algorithm to adaptively adjust the width factor and the penalty factor δ of the kernel function in the LSSVM according to the error; Five classification algorithms, LSSVM, SSA-LSSVM, HHO-LSSVM, AOA-LSSVM, and AEO-LSSVM are selected for comparative experiments. The results show that the method proposed in this paper has higher accuracy in maneuvering trajectory recognition.