基于BP神经网络的农机总动力预测

Prediction of Total Power in Agriculture Machinery Based on BP Neural Network

分析了BP神经网络用于预测时存在的不足,进而对基于BP神经网络的时间序列的预测问题进行了探讨。根据BP神经网络结构的特点,依据Z变换理论,提出了这一类预测问题可选用y=x作为传递函数,并分析指出了在BP神经网络中,以y=x作为传递函数与y=a+bx作为传递函数等价的结论,同时指出了网络结构应为两层网络。在此基础上,推导了相应的计算公式,并分别以单极性S型函数和y=x作为传递函数,对于具有增长趋势的农机总动力预测问题进行了实例计算。计算结果表明,以y=x作为传递函数的BP神经网络在外推效果、训练样本的数据处理区间影响方面明显优于S型传递函数的BP神经网络,并且克服了S型传递函数的BP神经网络在预测问题中存在的不足。

Based on analysis of the deficiencies of the BP neural network used in prediction,the time series prediction based on BP neural network was discussed.According to the characteristics of BP network structure and Z transform theory,function y=x was put forward to be the transfer function in this kind of prediction.Besides,the conclusion that function y=x and y=a＋bx were equivalent in the BP network was proposed.It was pointed out that the layer of network structure should be two.On basis of this,the corresponding formula was derived.With the unipolar S-function and function y=x as the transfer function respectively,the total power of agriculture machinery was calculated.The results showed that the performance of function y=x in BP neural network was better than S-transfer function in external push effect and influences of training sample data processing interval.It also overcame the shortcomings of S-function used in BP neural network.