Rotating machinery fault diagnosis based on a novel lightweight convolutional neural network

Abstract

The advancement of Industry 4.0 and Industrial Internet of Things (IIoT) has laid more emphasis on reducing the parameter amount and storage space of the model in addition to the automatic and accurate fault diagnosis. In this case, this paper proposes a lightweight convolutional neural network (LCNN) method for intelligent fault diagnosis of rotating machinery, which can largely satisfy the need of less parameter amount and storage space as well as high accuracy. First, light-weight convolution blocks are constructed through basic elements such as spatial separable convolutions with the aim to effectively reduce model parameters. Secondly, the LCNN model for the intelligent fault diagnosis is constructed via lightweight convolution blocks instead of the tradi-tional convolution operation. Finally, to address the “black box” problem, the entire network is visualized through Tensorboard and t-distribution stochastic neighbor embedding. The results demonstrate that when the number of lightweight convolutional blocks reaches 6, the diagnosis accuracy of the LCNN model exceeds 99.9%. And the proposed model has become the most robust with parameters significantly decreasing. Furthermore, the proposed LCNN model has realized accurate, automatic, and robust fault diagnosis of rotating machinery, which makes it more suitable for deployment under the IIoT context.

Mechanical Fault Diagnosis of High-Voltage Circuit Breakers with Dynamic Multi-Attention Graph Convolutional Networks Based on Adaptive Graph Construction

“…It can be seen that the weight function (11) causes very small weight differentiation of nodes with different distances such that the weights of most nodes are concentrated in a small interval. In addition, the weight function (16) increases the differentiation of the weights of nodes. Moreover, the calculation coefficient θ and weight coefficient γ are introduced to increase the generalization of the method and adjust the calculation cost of adding an edge.…”

“…Zhang et al [15] proposed multi-sensor information fusion which can achieve more accurate identification of mechanical faults for high-voltage circuit breakers with higher speed. Yan et al [16] proposed a lightweight CNN construction method that can achieve fault diagnosis of HVCBs under big data.…”

Fault Diagnosis of Rotating Machinery under Complex Conditions Based on Multi-Scale Convolutional Neural Networks

“…Yan et al conceived a lightweight convolutional neural network (LCNN) approach for intelligent rotating machinery fault diagnosis. This technique aptly fulfills requisites for modest parameter count, minimal storage space, and high diagnostic precision [6]. However, a comprehensive analysis unveils that while the previously proposed models showcase commendable health state identification prowess under ideal and constant operational conditions, they exhibit limitations when contending with noise interferences and the intricate dynamics of variable operational settings.…”

A Review of Fault Diagnosis Methods for Rotating Machinery Using Infrared Thermography

“…To improve the service life and safety of rotating machinery and reduce the shutdown loss, experts and scholars in related fields have studied and proposed a series of technical methods to diagnose the faults of rotating machinery. Common fault diagnosis methods for rotating machinery include fault diagnosis based on vibration signals [ 3 , 4 , 5 , 6 ], fault diagnosis based on acoustic emission technology [ 7 , 8 ], fault diagnosis based on temperature information [ 9 , 10 ], fault diagnosis based on oil analysis technology [ 11 , 12 , 13 , 14 ] and other non-destructive testing technologies [ 15 ]. For electric driven rotating machinery, fault diagnosis can also be carried out by collecting and analyzing the current and voltage signals [ 16 , 17 ].…”