基于双向多层门控循环神经网络的奶牛乳脂率预测模型研究  

Study on the Prediction Model of Milk Fat Rate of Dairy Cows Based on Bidirectional Multilayer Gated Recurrent Neural Network

作　　者：朱孟宇 由楚川 赵军[3] ZHU Mengyu;YOU Chuchuan;ZHAO Jun(School of Information Engineering,Ningxia University,Yinchuan 750021,China;School of Electronic and Information Engineering,Liaoning University of Science and Technology,Benxi 1170043,China;School of Economics and Management,Ningxia University,Yinchuan 750021,China)

机构地区：[1]宁夏大学信息工程学院,宁夏银川750021 [2]辽宁科技学院电子与信息工程学院,辽宁本溪117004 [3]宁夏大学经济管理学院,宁夏银川750021

出　　处：《宁夏工程技术》2024年第1期65-72,共8页Ningxia Engineering Technology

基　　金：宁夏自然科学基金项目(2020AAC03028)。

摘　　要：通过对奶牛乳脂率进行数据预测以及结合随机森林算法对环境数据进行精准特征选择,确定了对乳脂率影响较大的环境因素。在此基础上,提出了将随机森林算法与双向多层门控循环神经网络相结合的乳脂率预测模型(RF-BiGRU)并进行了相关实验。结果表明,该模型能够提高预测的准确性及效率。Through data prediction of the milk fat rate of cows and precise feature selection of environmental data using the random forest algorithm,the ecological factors that significantly impact the milk fat rate were determined.On this basis,a milk fat rate prediction model(RF-BiGRU)that combines random forests with bidirectional gated recurrent neural networks was proposed,and related experiments were conducted.The results show that the model can improve the accuracy and efficiency of prediction.

关 键 词：奶牛生理预测模型 随机森林算法 双向多层门控循环神经网络模型 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]