Multiple-target Optimization Design Of Pre-forging For Gear Blank

With the rapid development of automotive industry especially the car, the demand for gear has increased tremendously. In actual production, the process planning of gear blank relies on expert experiences and is optimized by trial and error. CAE software is also used to simulate the process of gear blank, which can shorten product design period and reduce the product cost. However, owing to the complexity of finish forging process, the times of trying dies is also inevitable by adopting CAE software. Besides, the optimization design of pre-forging for gear blank isn't obtained. If we can make full use of numerical simulation analysis together with new artificial intelligence algorithms including ANN and GA, we can get the optimization of gear blank automatically.The design of pre-forging is very important during multistage forging process of gear blank. It directly affects the behavior of metal flowing, filled situation of die cavity of finish forging, quality of products and die life.This thesis tries to present a suitable method for practical designation of pre-forging for gear blank by proposing an improved algorithm, which combines Back Propagation neural network and Genetic Algorithm. Firstly, the mathematical model was established associating the size parameters of pre-forging and maximum forming force, maximum die stress of finish forging by using Back Propagation neural network which has the advantage of processing highly nonlinear problems. Secondly, the established model was set as the fitness function of Genetic Algorithm. At last, the most superior pre-forging shape and the size parameters were solved by using the Genetic Algorithm with the function of overall situation optimization. These can lead to lower cost and time in the stages of designing pre-forging for gear blank.The thesis also presents the optimization design system of pre-forging for gear blank. The thesis shows the programming, the database access mode, the net truss, the equipment of the hardware and the function of this system. MATLAB and VC were used as developing tool. The implement of Mixed Programming is by VC++ calling MATLAB engine. Data Exchange with CAPP Environment is by using ADO technology. According to the optimization method, the optimal shape and size parameters of pre-forging were obtained. And qualified gear blank was produced by this method. This method provide scientific basis for the design of pre-forging for gear blank.