Research On Milling Performance Of Asymmetric Edge Passivation Too

With the continuous development of science and technology,advanced manufacturing technology incorporates various high-tech achievements and plays an important role in the manufacturing industry.Cutting processing technology is an important part of advanced manufacturing technology,and tools as direct performers play an important role in product quality,production cost and production efficiency.Therefore,the research on cutting tools is getting more and more intensive.Tool passivation is effective in removing microscopic defects from the tool surface,improving the surface quality of the tool,thereby enhancing cutting performance,and significantly changing the micro-geometry of the tool edge,which has a significant impact on cutting forces,tool wear and surface quality.The edge shape of tool passivation is complex and may be symmetrical or asymmetrical,not a regular circular arc,with an edge size in the micron range.Therefore,it is of great scientific significance and practical value to study the effect of asymmetric edge passivation on cutting performance.In this thesis,the effects of asymmetric edge passivation on cutting forces,tool wear and surface quality were investigated.Firstly,the orthogonal experiments of tool passivation were carried out by using the double-disk magnetic passivation method to study the influence of disk spacing,disk speed,tool speed and passivation time on the amount of passivation on the tool surface before and after the edge,which provides a basis for the preparation of tools with different shape factors in subsequent studies.Secondly,in view of the complexity of the asymmetric edge shape of the tool,the method of using two standard arcs for characterization is proposed,and considering the plowing force generated by the action of the edge,the method of replacing the rear face arc with a straight line as the equivalent rear face is proposed.The asymmetrical cutting edge model was established by comparing the correlation and error with the milling experiments and analyzing the ratio of shear force to plowing force to verify the correctness of the milling force model.Then,the influence law of shape factor on rear tool face wear was studied by milling experiments,and the mechanisms of edge chipping,adhesive wear and oxidation wear of tools with different shape factors were analyzed by scanning electron microscopy(SEM)inspection and energy spectrum analysis(EDS);according to the characteristics of milling processing,the machined surface profile was obtained,and the influence law of shape factor on machined surface roughness and The influence law of shape factor on surface roughness and residual stress is studied by analyzing the tool tip trajectory.Finally,based on the machine learning method,a stacked sparse self-coding network model is used to extract features from the cutting force signal containing tool wear information during the cutting process,and the extracted data features and the corresponding tool backface wear values are used as the data set to establish a stacked sparse self-coding network model(SSAE+BPNN)based on BP neural network,which effectively realizes the asymmetric wear prediction of blunt edge tools.The superiority of the proposed model(SSAE+BPNN)was verified by comparing it with the traditional BPNN and support vector regression(SVR)models based on manual extraction of data features.