Optimization Design Method Of Fatigue Fixation Life Of Parts Based On Data Driver

In recent years,the research and design of the parts life of the manufacturing industry has not stopped at the high durability.How to keep the life of the parts consistent with the overall life of the product,to realize the discarding of the parts and products at the same time,and to save a large amount of resources to reduce the cost,has become the key point of the research direction of the fatigue life of parts.Because it is difficult to construct the relationship between the structural parameters and the fatigue life of the parts,with the emergence of the data thinking,it is possible to use the deep relationship between the data mining products and the technology for the construction of the functional relationship between them.Therefore,on the premise of ensuring the life of the parts and improving the economy of the use and maintenance of parts,the structure optimization design of the parts is studied from the point of view of data driven,and an optimization design method for fatigue life structure of parts based on data driven is proposed.Aiming at the optimization design method of part structure proposed in this paper,the main works are as follows:(1)Using the powerful nonlinear mapping ability of artificial neural network,the complex relationship between the structural parameters and fatigue life values of the object is studied,and the suitable parameter values are obtained by constant debugging of the parameters of the neural network,and the mapping relation between the structural parameters and fatigue life of the parts is established,and the establishment of the relationship between the parameters and the fatigue life is established.The life prediction model of artificial neural network(artificial neural network)is used.Because the relationship between the structural parameters and fatigue life is more complex,and the neural network constraint function model has no specific function expressions,the traditional optimization method is difficult to optimize it.It is not aware of the specific constraint function expression by using the special point which is independent of the problem domain and the fast random search is found by the genetic algorithm.The process and method of modeling and optimization of crankshaft geometric parameters are determined.(2)Using OPTIMUS to integrate UG geometric modeling,ANSYS test simulation and MATLAB numerical simulation,the complicated process of geometric modeling and test simulation is shortened,and the parameterized modeling of parts,data integration,and the flow of numerical results analysis are realized.(3)According to the data,the prediction accuracy of the neural network prediction model and the nonlinear regression prediction method is analyzed,and the artificial neural network prediction model is a constraint function.Based on the genetic algorithm structure parameter optimization solution model,the optimization design of three structural parameter variables under the fixed life of the crankshaft is realized,and the method is verified.Effectiveness.The optimization design method based on data driven life structure based on data driven can greatly improve the utilization of product resources,reduce the cost,and conform to the design idea of the structural optimization of the parts.The optimization design method based on data driven life structure based on data driven can greatly improve the utilization of product resources,reduce the cost,and meet the new concept of part design.