基于遗传算法优化的BP神经网络研究应用

Research and application of BP neural network based on genetic algorithm optimization

为提高BP神经网络预测模型对超市大米日销售预测的准确性,提出一种基于遗传算法优化的BP神经网络预测方法。介绍了BP神经网络和遗传算法的特点以及存在的缺陷,并进一步研究了BP神经网络和遗传算法相结合的有关技术,利用遗传算法优化BP神经网络的权值和阈值,然后训练BP神经网络预测模型获取最优解,充分发挥了BP神经网络的局部搜索能力和遗传算法的全局搜索能力的优势。仿真结果证明,该方法对超市大米日销售预测具有更高的精度和更好的非线性拟合能力。

In order to improve the accuracy of daily rice sales forecast in the supermarket by means of BP neural network forecasting model,a BP neural network prediction method based on genetic algorithm optimization is proposed.The characteris-tics and defects of BP neural network and genetic algorithm are introduced.The relevant technology combining BP neural net-work and genetic algorithm is studied.The genetic algorithm is used to optimize the weight and threshold of BP neural network,and train the BP neural network prediction model to obtain the optimal solution.The advantages of the local search ability of BP neural network and global search ability of genetic algorithm are fully displayed.The simulation results show that the method has higher accuracy and better non-linear fitting ability for daily rice sales forecast in the supermarket.