论文部分内容阅读
提出了一种将遗传算法和BP算法相结合的学习算法来训练BP神经网络,实现网络结构的优化,并用优化后的BP人工神经网络建立了航空发动机的磨损预测模型。将该模型预测结果与BP算法和多元线性回归法的预测结果进行了比较。检验结果表明:基于遗传算法的BP神经网络优于BP算法及多元线性回归法,具有良好的预测效果。
A learning algorithm based on genetic algorithm and BP algorithm was proposed to train BP neural network to optimize the network structure. A wear prediction model of aeroengine was established with the optimized BP artificial neural network. The prediction results of this model are compared with those of BP and Multivariate linear regression. The test results show that the BP neural network based on genetic algorithm is better than the BP algorithm and multiple linear regression method, and has a good prediction effect.