GA-BP神经网络在铜合金海洋腐蚀预测中的应用

目的充分利用海洋腐蚀数据,深入分析数据规律。方法在BP神经网络的基础上引入遗传算法,以克服神经网络模型固有缺陷,提高预测精度和训练速度。结果对GA-BP人工神经网络进行了简要阐述,并以铜合金在海水中的腐蚀数据为例,应用GA-BP人工神经网络建立了海水腐蚀预测模型,对预测结果进行了评价。结论预测结果表明,模型能满足设计要求,具有较好的泛化能力。

Application of GA-BP Artificial Neural Network in Seawater Corrosion Prediction of Copper Alloys

This paper aims to take full advantage of corrosion data and deeply analyze corrosion law. The genetic algorithm (GA) was introduced to improve the back propagation (BP) artificial neural network (ANN), with a view to overcome the inherent defect of ANN and increase prediction accuracy and training speed. In this paper, a brief interpretation of GA-BP artificial neural network was given. And based on the corrosion data of copper in marine environment, the GA-BP artificial neural network method was applied to the building process of marine corrosion prediction model. The experimental results showed that the model can meet the design requirements and had good generalization ability.