基于神经网络与遗传算法的钢的锻造工艺优化OA
Optimization of steel forging process based on neural network and genetic algorithm
基于神经网络与遗传算法,以加热方式、锻造压力、始锻温度、终锻温度、预热温度、加热温度及锻造速度作为7个输入层参数,以抗拉强度、屈服强度和断后伸长率作为3个输出层参数,隐含层调用tansig函数,输出层调用purelin函数,设计了40Cr钢锻造工艺优化神经网络模型,其选用7 × 32 × 16×3共4层拓扑结构.经过训练、预测及验证后可知:该模型经过9113次迭代运算后收敛,模型输出的抗拉强度、屈服强度和断后伸长率均具有5%以内的相对预测误差,模型具有极高的预测精度和预测能力;相较于现有锻造工艺,采用神经网络-遗传算法优化工艺时,40Cr钢抗拉强度提高了82MPa、屈服强度提高了88MPa、断后伸长率小幅增大.因此,神经网络-遗传算法优化模型具有较佳的实用性能.
Based on neural network and genetic algorithm,an optimized neural network model for 40Cr steel forging process was constructed with heating method,forging pressure,initial forging temperature,final forging temperature,temperature of preheating,speed of forging and temperature of heating as seven input layer parameters,with tensile strength,yield strength,and elongation after fracture as three output layer parameters,moreover,the hidden and output layer were with tansig and purelin function,respectively.The model structure adopted a four-layer topology of 7 × 32 × 16 × 3.After training,prediction,and verification,it is found that the model converges after 9113 iterations,and the relative prediction errors of the tensile strength,yield strength,and elongation after fracture of model output are all less than 5%.The model has high prediction accuracy and predictive ability.Compared with the current forging process of 40Cr steel used by enterprises,the optimized forging process of 40Cr by the neural network-genetic algorithm results in an increase of 82MPa in tensile strength,88MPa in yield strength,and a slight increase in elongation after fracture within a small range.The neural network-genetic algorithm optimization model has better practical performance.
杨小华;王仁本;佘斌;李建巍;魏金前
国能大渡河检修安装有限公司 四川乐山 614000国能大渡河检修安装有限公司 四川乐山 614000国能大渡河检修安装有限公司 四川乐山 614000国能大渡河检修安装有限公司 四川乐山 614000国能大渡河检修安装有限公司 四川乐山 614000
神经网络遗传算法锻造工艺优化力学性能锻造工艺参数
neural networkgenetic algorithmoptimization of forging processmechanical propertyforging process parameter
《金属加工(热加工)》 2026 (9)
13-20,8
国家能源集团科技创新项目资助(CJNY-DDH-2024-023).
评论