Residual Life Prediction Of Micro-textured Ball-end Milling Cutter Based On Deep Learning

As a basic processing part in the manufacturing industry,the cutting tool has a significant impact on the manufacturing industry.The heat generated in the cutting process of titanium alloy material due to its low thermal conductivity can not be transmitted in time,which leads to the high surface temperature of the tool and affects the service life of the tool.Therefore,the prediction of the remaining useful life of the tool during the cutting process can not only avoid the huge impact on the surface quality of the product due to tool breakage or bluntness,but also avoid the waste of resources caused by excessive maintenance and frequent tool replacement and the reduction of processing efficiency caused by frequent shutdown.Based on the simulation and experimental research of milling titanium alloy with micro-texture ballend milling cutter,this paper analyzes the force characteristics,vibration characteristics and flank wear of micro-texture ball-end milling cutter.According to the change trend of force characteristics and vibration characteristics,the remaining service life of micro-texture ball-end milling cutter is predicted,which is of great significance for making full use of the tool and reducing the manufacturing cost.Firstly,based on Deform software,the dynamic simulation of milling titanium alloy with micro-texture ball-end milling cutter is carried out,and the heat conduction model and tool-chip friction model are established.Based on the orthogonal simulation test,the influence of different micro-texture parameters on the flank wear,milling force and milling temperature of ball-end milling cutter was studied.The influence factors of micro-texture parameters were studied by range analysis,and the microtexture parameters were optimized to provide data support for the subsequent construction of the remaining service life prediction model of micro-texture ball-end milling cutter.Secondly,the milling test platform is built to carry out the experimental study on the milling of titanium alloy with micro-texture ball-end milling cutter.The influence of tool condition monitoring signal,namely force signal and vibration signal,on the remaining service life of micro-texture ball-end milling cutter is analyzed,and the variation law of flank wear value of micro-texture ball-end milling cutter is explored.The tool condition monitoring signal preprocessing and feature extraction are carried out to extract the feature data which is more sensitive to the remaining service life of the micro-texture ball-end milling cutter,and the feature data related to the life cycle of the micro-texture ball-end milling cutter is discussed,which provides data support for the establishment of the remaining service life prediction model of the microtexture ball-end milling cutter.Finally,a residual service life prediction model of micro-textured ball-end milling cutter based on deep learning bidirectional long short-term memory neural network is established,and the attention mechanism is integrated into it.The extracted training set feature data is input into the prediction model,the prediction model is trained,and the verification set is brought into the prediction model to verify the validity of the prediction model.By comparing and analyzing the prediction models of different mechanisms,the superiority of the remaining useful life prediction model of microtexture ball-end milling cutter established in this paper is verified and evaluated.