利用改进BP神经网络预测初产奶牛产奶量的方法

Prediction Methods for Primary Production of a Milch Cow by Improved BP Neural Network Approach

针对传统BP算法的缺陷,提出了一种采用L-M训练法的BP神经网络。在此基础上建立了基于改进BP神经网络非线性系统的奶牛305d产奶量预测模型,此模型可以提前215d预测初产奶牛305d产奶量,从而实现提早进行选择,加速奶牛育种工作进程。并通过具体的实验验证了改进BP神经网络预测模型的有效性。

Aiming at the shortage of conventional BP algorithm, a BP neural improved by L- M algorithm is put forward. On the basis of the network, a predictive model for 305 days＇ milk productions was set up. The model can forecast 305 days milk quantitive production of the first birth cow ahead of 215 days. The validity of the improved BP neural network predictive model was validated through the experiments.