摘要
利用小波分析和神经网络智能技术,针对凸轮轴铸造充型凝固过程的温度场数值求解问题,提出了小波神经网络算法。用热电偶对凸轮轴铸造温度场进行了实测,并以实测数据为样本进行小波神经网络学习和训练,由训练后的神经网络仿真了凸轮轴铸造过程的温度分布。实践表明,小波神经网络数值仿真快速、准确、合理,仿真结果与实测数据相比最大相对误差为1.83%,可为铸造工艺参数确定提供理论依据。
With the technique of wavelets analysis and neural network intelligence, aiming at numerical calculation of temperature field in casting process of camshafts, the arithmetic of wavelet neural network is described. The solidifying temperature of camshafts is tested by thermo-couples, the data of specimens obtained by the testing results of temperature field is trained by back- propagation neural network, the temperature distribution during filling and solidification is simulated. By contrasting the data of simulation with those of testing, the maximum relative errors of simulation is 1.83 %, and the theory basis is presented for technological parameters.
出处
《铸造技术》
CAS
北大核心
2010年第2期233-235,共3页
Foundry Technology
关键词
凸轮轴
铸造过程
小波神经网络
数值仿真
Camshaft
Casting process
Wavelet neural network
Numerical simulation