论文部分内容阅读
为了有效地控制激光铣削层质量,建立了激光铣削层质量(铣削层深度、铣削层宽度)与铣削层参数(激光功率、扫描速度和离焦量)之间的反向传播(BP)神经网络预测模型。利用遗传算法(GA)优化了BP神经网络的权值和阈值,构建了基于遗传算法神经网络的质量预测模型。用GA-BP算法对激光铣削层质量进行了仿真预测,并将仿真结果与BP神经网络模型仿真结果进行了对比。仿真结果表明,两种网络模型的平均误差较小,网络训练后检验精度较高,说明两种网络模型用于激光铣削层质量预测是可行的,并且遗传算法优化BP神经网络能够有效地提高网络的收敛性和预测精度。
In order to control the quality of the laser milling layer, a back propagation (BP) neural network between laser milling layer quality (milling depth, milling width) and milling parameters (laser power, scanning speed and defocusing amount) Predictive model. The weights and thresholds of BP neural network are optimized by genetic algorithm (GA), and the quality prediction model based on genetic algorithm neural network is constructed. The GA-BP algorithm is used to predict the quality of the laser milling layer. The simulation results are compared with those of the BP neural network model. The simulation results show that the average error of the two network models is small, and the accuracy of the network training is high, which shows that the two network models are feasible to predict the quality of the laser milling layer. Moreover, the genetic algorithm to optimize BP neural network can effectively improve the network Convergence and prediction accuracy.