论文部分内容阅读
以模具加热温度、预热温度、始锻温度、终锻温度和锻压速度为输入层参数,以冲击性能、耐磨损性能为输出层参数,构建了汽车连杆锻压工艺优化的5×25×15×2四层神经网络模型。结果表明,神经网络模型的预测误差小于3%,具有较强的预测能力和较高的预测精度。与生产线原锻压工艺相比,采用优化工艺生产的汽车连杆冲击吸收功增大24%,磨损体积减小35%。使用优化工艺生产的汽车连杆冲击性能和耐磨损性能得到提高。
Taking the heating temperature, preheating temperature, initial forging temperature, final forging temperature and forging speed as the input layer parameters, the impact performance and wear resistance as the parameters of the output layer, the car linkage forging process optimization 5 × 25 × 15 × 2 four-layer neural network model. The results show that the prediction error of the neural network model is less than 3%, which has strong prediction ability and high prediction accuracy. Compared with the original forging process in the production line, the impact absorption power of the automotive connecting rod produced by the optimized process is increased by 24% and the wear volume is reduced by 35%. The impact and wear properties of the automotive connecting rod produced with the optimized process are improved.