论文部分内容阅读
基于人工神经网络所体现出的良好的非线性逼近特性,运用遗传算法优化BP网络的权值和阈值,避免BP网络陷入局部极小点,同时通过灰色关联分析优化网络的结构,使网络具有更好的泛化性和收敛速度。运用改进的BP网络发掘油管接箍加工中各个加工参数对最终加工圆度误差的潜在关系,从而实现对油管接箍加工圆度误差的预测。结果表明改进型BP神经网络具有较快的收敛速度和较好的泛化性能够准确预测油管接箍加工圆度误差。
Based on the good non-linear approximation characteristic of artificial neural network, genetic algorithm is used to optimize the weights and thresholds of BP network to avoid the BP network getting into local minima. At the same time, the network structure is optimized by gray relational analysis Good generalization and convergence speed. The improved BP network is used to find out the potential relationship between the processing parameters and the roundness error of the final machining in the process of the tubing coupling, so as to predict the roundness error of the tubing coupling. The results show that the improved BP neural network has faster convergence rate and better generalization ability to accurately predict the roundness error of the tubing coupling.