Research On Life Prediction Of Honing Oilstone Based On Characteristic Parameters

The wear state of the honing oilstone has a greater effect on the final quality of the product.In order to predict the cutting life of oilstone,easy to replace it,according to comparing the wear of the oilstone and the blunt standard to determine whether replacement of oilstone.Therefore,the grey neural network is introduced,and the wear quantity of the oilstone is predicted by using the honing process parameters as the model input.Finally,the prediction model of the honing oilstone wear is established to predict the life of the oilstone.So as to provide a theoretical basis for the early replacement of oilstone,in ensuring the stable operation of the machine to improve the quality of processed products,saving manufacturing systems in the production costs and other aspects of great significance.The main contents of this thesis include:(1)The neural network and gray neural network prediction model algorithm are studied.Because the neural network has a high degree of non-linear fitting ability and honing itself can be seen as a gray system,through the analysis of a variety of forecasting model,the final selection of the above two models.And the selection of the model structure and the setting of the key parameters are described in detail.The basis of the accuracy and stability of the evaluation model is given.(2)The use of intelligent algorithms in model optimization is studied.The advantages and disadvantages of Particle Swarm Optimization(PSO),Genetic Algorithm(GA)and Ant Colony Algorithm(ACO)are compared.Because PSO algorithm has the advantages of fast convergence speed and few parameters to be adjusted,the algorithm is used to optimize the model.According to the shortcomings of the algorithm,this paper proposes to use the mutation factor to optimize the standard PSO algorithm,and the objective functions are used to compare the search ability and convergence of the algorithm.(3)The forecasting model suitable for the forecast of honing oilstone wear is studied.Based on the data of strong honing,the forecasting model of honing oilstone wear based on BPNN was established,and the MPSO algorithm and GA algorithm were used to optimize it.As the honing process itself can be seen as a gray system,first,the gray correlation degree is used to analyze the influence of the honing characteristic parameters on the honing oilstone wear.Secondly,the GNN-basedoilstone wear combination forecasting model is established and the gray parameters in the model are optimized by MPSO algorithm.The MPAE values based on the MPSO-GNN model are smaller than those of the simulation model.The results show that the model is more accurate and the prediction is more stable.Therefore,the model has certain advantages in the prediction of honing oilstone wear,which can be used to predict the wear state of oilstone in actual processing,and then replace the oilstone.