采用优化特征子集选取和改进SVR的养殖禽舍温度预测算法

doi:10.13733/j.jcam.issn.2095-5553.2023.02.013

摘要/Abstract

摘要： 为提高养殖禽舍温度预测算精度，降低数据冗余度和差异性对预测结果的影响，提出一种基于智能优化特征子集选取和模糊聚类改进SVR（Support Vector Regression）的温度预测模型。首先，构建最优特征子集选取模型，通过设计最优特征子集选取指标，以降低特征之间冗余度和数据维度；采用改进的离散灰狼算法对特征子集选取模型进行求解，以实现最优特征子集选取。其次，建立模糊聚类改进SVR预测机制，通过设计多度量核FCM（Fuzzy C-means）算法，以实现数据样本自动分类；提出与数据样本分类相对应的SVR预测算法，并采用灰狼算法对SVR参数进行优化，最大程度降低样本数据差异性对预测精度的影响。最后，融合最优特征子集选取和模糊聚类改进SVR预测机制，以实现养殖禽舍温度高精度预测。仿真结果表明，该算法实现不同季节条件下养殖禽舍温度的高精度预测，相比于其他预测算法，预测精度提高约23.7%~37.8%。所提养殖禽舍温度预测算法具有良好的预测性能，具有一定的推广应用价值。

关键词: 养殖禽舍, 温度预测, 灰狼算法, SVR, FCM, 优化特征子集选取

Abstract: In order to improve the accuracy of temperature prediction for poultry houses and reduce the impact of data redundancy and difference on the prediction results, a temperature prediction model based on intelligent optimization feature subset selection and fuzzy clustering improved SVR (Support Vector Regression) is proposed. Firstly, the optimal feature subset selection model is constructed, and the optimal feature subset selection index is designed to reduce the redundancy and data dimension between features; The improved discrete Gray Wolf algorithm is used to solve the feature subset selection model to realize the optimal feature subset selection. Secondly, the fuzzy clustering improved SVR prediction mechanism is established, and the multicore FCM (Fuzzy Cmeans) algorithm is designed to realize the automatic classification of data samples; A SVR prediction algorithm corresponding to data sample classification is proposed, and the Gray Wolf algorithm is used to optimize the SVR parameters to minimize the impact of sample data differences on prediction accuracy. Finally, the optimal feature subset selection and fuzzy clustering are combined to improve the SVR prediction mechanism to realize the highprecision prediction of poultry house temperature. The simulation results show that the algorithm realizes the highprecision prediction of poultry house temperature in different seasons and different climatic conditions, and the prediction accuracy is improved by about 23.7%-37.8% compared with other prediction algorithms.

Key words: poultry house, temperature prediction, Gray Wolf algorithm, SVR, FCM, optimized feature subset selection

中图分类号:

TP391

李继东, 王强辉. 采用优化特征子集选取和改进SVR的养殖禽舍温度预测算法[J]. 中国农机化学报, 2023, 44(2): 91-98.

Li Jidong, Wang Qianghui.. Temperature prediction algorithm for poultry house based on optimized feature subset selection and improved SVR[J]. Journal of Chinese Agricultural Mechanization, 2023, 44(2): 91-98.

参考文献

［1］　
侯水生. 2018年度水禽产业发展现状、未来发展趋势与建议［J］. 中国畜牧杂志， 2019， 55(3)： 124-128.

［2］　
徐宇，冀荣华. 基于复数神经网络的智能温室温度预测研究［J］. 中国农机化学报， 2019， 40(4)： 174-178.

Xu Yu, Ji Ronghua. Research on temperature prediction of intelligent greenhouse based on complex neural network ［J］. Journal of Chinese Agricultural Mechanization, 2019, 40(4)： 174-178.

［3］　
Nayak J, Naik B, Kanungo D P, et al. A hybrid elicit teaching learning based optimization with fuzzy cmeans algorithm for data clustering ［J］. Ain Shams Engineering Journal， 2016.

［4］　
欧阳宏佳，杨博，陈文俊，等. 养殖环境主要因子对肉鹅生长性能的影响［J］. 畜牧与兽医， 2019， 51(4)： 34-38.

Ouyang Hongjia, Yang Bo, Chen Wenjun, et al. Effects of main factors of breeding environment on growth performance of meat geese ［J］. Animal Husbandry & Veterinary Medicine, 2019， 51(4)： 34-38.

［5］　
Xu Longqin, Liu Shuangyin, Li Diaoliang. Prediction of water temperature in prawn cultures based on a mechanism model optimized by an improved artificial bee colony ［J］. Computers and Electronics in Agriculture, 2017(140): 397-408.

［6］　
徐龙琴，张军，李乾川，等. 基于EMD和ELM的工厂化育苗水温组合预测模型［J］. 农业机械学报， 2016， 47(4)：265-271.

Xu Longqin, Zhang Jun, Li Qianchuan, et al. Combined prediction model of water temperature in industrialized cultivation based on empirical mode decomposition and extreme learning machine ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2016, 47(4)： 265-271.

［7］　
Graf R, Zhu Senlin, Sivakumar B. Forecasting river water temperature time series using a waveletneural network hybrid modelling approach ［J］. Journal of Hydrology, 2019, 578: 1-12.

［8］　
王珺，卫金茂，张璐. 基于保留分类信息的多任务特征学习算法［J］. 计算机研究与发展， 2017， 54（3）： 537-548.

Wang Jun, Wei Jinmao, Zhang Lu. Multitask feature learning algorithm based on preserving classification information ［J］. Journal of Computer Research and Development, 2017, 54（3）： 537-548.

［9］　
杜晔，张亚丹，黎妹红，等. 基于改进FastICA算法的入侵检测样本数据优化方法［J］. 通信学报， 2016， 37（1）： 42-48.

Du Ye, Zhang Yadan, Li Meihong, et al. Improved FastICA algorithm for data optimization processing in intrusion detection ［J］. Journal on Communications, 2016, 37(1): 42-48

［10］　
仇利克，郭忠文，刘青，等. 基于冗余分析的特征选择算法［J］. 北京邮电大学学报， 2017， 40（1）： 36-41.

Qiu Like, Guo Zhongwen, Liu Qing,et al. Feature selection algorithm based on redundancy analysis ［J］. Journal of Beijing University of Posts and Telecommunications, 2017, 40(1): 36-41.

［11］　
孙广路，宋智超，刘金来，等. 基于最大信息系数和近似马尔科夫毯的特征选择方法［J］. 自动化学报， 2017， 43（5）：795-805.

Sun Guanglu,Song Zhichao,Liu Jinlai, et al. Feature selection method based on maximum information coefficient and approximate markov blanket ［J］. Acta Automatica Sinica, 2017, 43(5): 795-805.

［12］　
Teng Xianliang, Gao Zonghe, Zhang Yingyuan, et al. Key technologies and the implementation of wind, PV and storage cogeneration monitoring system ［J］. Journal of Modern Power Systems and Clean Energy, 2014, 2(2): 104-113.

［13］　
叶林，陈政，赵永宁，等. 基于遗传算法—模糊径向基神经网络的光伏发电功率预测模型［J］. 电力系统自动化， 2015， 39（16）： 16-22.

Ye Lin, Chen Zheng, Zhao Yongning, et al. Photovoltaic power forecasting model based on genetic algorithm and fuzzy radial basis function neural network ［J］. Automation of Electric Power Systems, 2015, 39(16): 16-22.

［14］　
王昕，黄柯，郑益慧，等. 基于PNN/PCA/SS-SVR的光伏发电功率短期预测方法［J］. 电力系统自动化， 2016， 40（17）： 156-162.

Wang Xin, Huang Ke, Zheng Yihui, et al. Shortterm forecasting method of photovoltaic output power based on PNN/ PCA/SS-SVR ［J］. Automation of Electric Power Systems, 2016, 40(17): 156-162.

［15］　
陈英义，程倩倩，方晓敏，等. 主成分分析和长短时记忆神经网络预测水产养殖水体溶解氧［J］. 农业工程学报， 2018， 34(17)： 183-191.

Chen Yingyi, Cheng Qianqian, Fang Xiaomin, et al. Principal component analysis and long shortterm memory neural network for predicting dissolved oxygen in water for aquaculture ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2018, 34(17)： 183-191.

［16］　
Mirjalili S, Mirjaliiis M, Lewis A. Grey wolf optimization ［J］. Advances in Engineering Software, 2014, 69(7): 46-61.

［17］　
向子权，杨家其，李慧琳，等. 基于离散灰狼算法的资源分配问题求解［J］. 华中科技大学学报(自然科学版)， 2021， 49(8): 81-85.

Xiang Ziquan, Yang Jiaqi, Li Huilin, et al. A solution to resource allocation problem based on discrete grey wolf optimizer ［J］. Journal of Huazhong University of Science and Technology (Nature Science Edition), 2021, 49(8): 81-85.

［18］　
殷豪，董朕，陈云龙. 基于CEEMD和膜计算优化支持向量机的风速预测［J］. 电力系统保护与控制， 2017， 45(21): 27-34.

Yin Hao, Dong Zhen, Chen Yunlong. Wind speed forecasting based on complementary ensemble empirical mode decomposition and support vector regression optimized by membrane computing optimization ［J］. Power System Protection and Control, 2017, 45(21): 27-34.

［19］　
Zhao Z, Wang L, Liu H, et al. On similarity preserving feature selection ［J］. IEEE Transactions on Knowledge and Data Engineering, 2011, 25(3): 619-632.

［20］　
李怀俊，谢小鹏. 基于核特征模糊聚类及模糊关联熵的齿轮故障模式识别［J］. 仪器仪表学报， 2015， 36(4): 848-855.

Li Huaijun, Xie Xiaopeng. Gear fault pattern recognition based on kernel feature fuzzy clustering and fuzzy association entropy ［J］. Chinese Journal of Scientific Instrument, 2015, 36(4): 848-855.

［21］　
刘双印，黄建德，徐龙琴，等. 基于PCA-SVR-ARMA的狮头鹅养殖禽舍气温组合预测模型［J］. 农业工程学报， 2020， 36(11): 225-233.

Liu Shuangyin, Huang Jiande, Xu Longqin, et al. Combined model for prediction of air temperature in poultry house for lionhead goose breeding based on PCA-SVR-ARMA ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(11): 225-233.

[1]	程鑫;徐晓辉;宋涛;宋卓研;赵睿;. 基于PSO-SVR模型的温室智能补光系统研究[J]. 中国农机化学报, 2020, 41(6): 64-68+82.
[2]	张舜;杨欣;魏津瑜;. 基于预防性维修的农机备件需求预测问题研究[J]. 中国农机化学报, 2020, 41(6): 225-230.