基于遗传优化的BP神经网络水泥强度预测

Cement Strength Prediction of Optimized BP Neural Network Based on Genetic Algorithm

为了提高BP神经网络预测模型对水泥强度值的预测精度,通过结合BP神经网络与遗传算法各自的优势,提出一种采用遗传算法优化的BP神经网络的水泥强度预测算法.利用遗传算法具有的全局优化搜索能力优化BP神经网络的各层节点连接权值与阈值,训练BP神经网络预测模型以求得最优解,并将训练以外的样本数据用于模型的有效性验证.仿真结果表明,该算法对水泥强度值预测具有较高的预测精度,同时可缩短网络收敛时间.

In order to improve the prediction accuracy of BP neural network model for cement strength value, a genetic optimization BP neural network algorithm based on respective advantage of BP neural network and genetic algorithm was proposed, which made use of the advantage of genetic algorithm with the global optimization ability to optimize connection weights and threshold of BP neural network, then the BP neural network was trained to seek the optimal solution, the efficiency of the proposed prediction method was tested by the sample data different from the training samples. From the simulation results, it could be concluded that the proposed algorithm can offer high predicting accuracy and shorten the network convergence time.