Online Prediction Method of Broach Wear Based on Dense Convolutional Network
Broaching is an important process of automobile brake caliper bracket groove.However,in the process of processing,if the broach wear anomaly can not be found in time,it will lead to batch scrap of parts.In this paper,an online prediction method for broach wear is proposed,which uses the vibration characteristics of broach signal to distinguish broach process and broach gap effectively,and constructs an online recognition model for broach wear based on DenseNet.The results show that the method has good adaptive feature extraction effect,and both generali-zation and accuracy can realize online prediction of broaching wear in actual machining process,which is of great significance for improving production efficiency and reducing manufacturing cost.
万方数据
维普
