Research on a monitoring model of revolute pair clearance based on dynamic features and thermal imaging fusion

Abstract

The revolute pair is an essential structure. The running of the revolute pair with clearance leads to energy loss due to collision. Partial energy loss is distributed in the form of heat energy. This provides the possibility for using thermal imaging to determine the clearance size of the revolute pair. A clearance monitoring method for revolute pairs fusing dynamic and thermal image features is proposed. The penetration depth and energy loss caused by collision are calculated as dynamic data, and dynamic features are extracted from the dynamic data by a multilayer perceptron. The convolutional block attention module embedded with a convolutional neural network is used to extract thermal imaging features. Clearance monitoring of revolute pairs is conducted based on fusion features of dynamic features and thermal image features. The experimental results on the test bench for revolute pair clearance show that the revolute pair clearance monitoring method based on fusion features can effectively monitor the revolute pair clearance.