Abrasive belt wear detection method based on multi-sensor information fusion

Abstract

The invention discloses an abrasive belt wear detection method based on multi-sensor information fusion, and belongs to the field of grinding machining. The method comprises the specific steps of firstly, defining the abrasive belt abrasion factor, building a grinding platform, setting multiple sets of grinding use amounts, and collecting various sensor signals; then, performing primary processing on the collected original sensor signals; performing cutting processing on the signal after the primary processing; training a deep convolutional neural network model; and finally, obtaining an abrasive belt wear sensor signal in actual grinding, inputting a grinding amount number, calling a corresponding model to judge a corresponding abrasive belt wear state, and outputting abrasive belt use time, residual life, wear factors and the like. According to the method, a plurality of deep convolutional neural network models are matched with one another, so that the accuracy of the models is improved, and more accurate abrasive belt wear information can be output.

Description

technical field [0001] The invention belongs to the field of grinding processing, and in particular relates to a method for detecting abrasive belt wear through multi-sensor information fusion. Background technique [0002] Grinding is generally used as the last process of mechanical processing, which can effectively eliminate the processing defects caused by the previous process and improve the surface quality of products. The grinding process is complex, and there are many factors that affect the grinding quality, among which the impact of abrasive tool wear is particularly prominent. The wear state of abrasive tools is affected by factors such as the type of abrasive tool, grinding object, service time, and process parameters. It is a typical time-varying, multi-factor coupling process, so it is difficult to detect the wear state. In the existing grinding process, it mainly relies on manual experience, and judges the state of the abrasive tool by observing the state of t...

AI Technical Summary

Problems solved by technology

However, in the field of abrasive belt grinding, as a flexible polishing tool, the abrasive belt has a small structural size. The structure of the abrasive belt is different from that of hard polishing tools such as grinding wheels. It is difficult to use digital quantities to represent the degree of wear. Therefore, many direct detection methods such as weighing are not applicable. For abrasive belt wear detection

For the indirect method, there are fewer types of monitoring signals currently used, and the response degree of each signal to the wear of the abrasive belt is not clear. The construction of the model requires a large amount of signal data support, and the accuracy of the model is high.

Therefore, there is still no relatively mature detection method for abrasive belt wear so far.

Images