Research On Tool Wear And Prediction Of Surface Roughness In Spiral Surface Milling

Screw drilling tools are widely used in oil extraction and other fields,and the screw rotor,as the core component of the drilling tool equipment,plays a vital role in the operation of the whole machine.During the machining process,the tool wear state is directly related to whether the surface roughness value of the workpiece can reach the standard of qualified use,so it is necessary to monitor the tool wear amount.In thesis,the tool wear and rotor surface roughness during milling screw rotors are studied,the relationship between process parameters,tool wear and surface roughness values is explored,and the tool wear mechanism is analyzed.Surface roughness and material removal rate are used as optimization objects to provide theoretical guidance for effective improvement of machining quality and cutting efficiency.The main research contents are as follows:(1)The machining process of milling rotors with disc milling cutters is analyzed,and a prediction model for the wear rate of disc milling cutters is established by linear regression method,so as to achieve the prediction of the normal use time of tools and provide theoretical reference for timely tool replacement.The wear mechanism of disc milling cutters is analyzed,and the influence rule of process parameters on tool wear rate is obtained by using extreme difference analysis.(2)According to the machining characteristics of milling screw rotors with disc cutter milling tools,a simplified surface roughness model for milling rotors with the introduction of wear coefficients is established and the model is validated.The effect of disc milling cutter wear on surface roughness is further analyzed by rotor milling tests using correlation analysis.(3)A prediction method(INGO-BP)for optimizing BP neural networks with an improved Northern Goshawk search algorithm is proposed to predict the surface roughness of rotors machined by the transient-free envelope method.The improved Northern Goshawk search algorithm optimized BP neural network is compared with the unimproved Northern Goshawk search algorithm optimized BP neural network and artificial neural network(ANN)algorithm,respectively,to verify the superiority of the proposed improved algorithm.Test samples are used to verify the accuracy of the proposed prediction method,and the method is used to analyze the influence law of different process parameters on the surface roughness of the rotor.(4)In order to further optimize the machining quality and improve the machining efficiency,an optimization model is established with surface roughness and material removal rate as the objectives,and an improved multi-objective African Vulture algorithm(MOEAVOA)is proposed to solve the optimization model,and the optimal solution set of Pareto frontier is obtained,so as to the optimal process parameters of screw rotor milling under the dual objective constraints of surface roughness value and material removal rate are obtained.The prediction of wear rate of disc milling cutter can provide theoretical reference for timely tool replacement in actual machining,and the prediction of surface roughness of screw rotor can solve the problem of difficult prediction of surface roughness of spiral surface,and help to analyze the influence law of process parameters on the surface roughness of screw rotor.Using surface roughness and material removal rate as optimization targets,the optimal parameters are determined by intelligent optimization algorithms that are important for efficient and high-precision machining of screw rotors.