基于GSA-SVM的畜禽舍废气监测缺失数据恢复方法  

Method of missing data recovery of waste gases monitoring in animal buildings based on GSA-SVM

作　　者：刘金明[1] 谢秋菊[1] 王雪[1] 马铁民[1] 

机构地区：[1]黑龙江八一农垦大学信息技术学院,黑龙江大庆163319

出　　处：《东北农业大学学报》2015年第5期95-101,共7页Journal of Northeast Agricultural University

基　　金：黑龙江省青年科学基金项目(QC2013C065)

摘　　要：针对畜禽舍内废气监测过程中因传感器故障等原因造成部分监测数据缺失的问题,将遗传模拟退火算法与支持向量机相结合,提出一种基于GSA-SVM的缺失数据恢复方法。该方法综合考虑畜禽舍废气监测值对应的时间、空间和环境等多种影响因素,建立支持向量机回归预测模型对缺失的监测数据进行恢复性估算;为获得更好的预测结果,使用遗传模拟退火算法对模型参数进行优化。以氨气浓度数据的恢复为例,随机选取某养殖场3 d的监测数据验证。结果表明,缺失数据估算最大相对误差为6.69%,平均相对误差为1.87%,估算数据与监测数据误差很小,可有效对缺失性数据进行恢复,为畜舍废气监测提供可行数据恢复处理方法。In order to solve the data missing problem caused by sensor faults during the waste gas monitoring in animal buildings, a method for missing data recovery was presented based on support vector machine （SVM） combined with genetic simulated annealing algodthm（GSA）. Multiple factors that influenced monitoring values of the waste gas in animal buildings, such as temporal, spatial and environmental, were considered to established a SVM regression prediction model to estimate the missing data of the waste gas monitoring. Meanwhile, to obtain a better prediction accuracy, model parameters were optimized by the GSA. The data processing of the ammonia concentration was taken as an example, monitodng data of 3 d were randomly selected in a farm to test the presented model in this paper. The results showed that there was a very little error between the estimated data and monitoring data, the maximal relative error was 6.69%, the average relative error was 1.87%. It was an effective method for missing data recovery and a practical way of data processing for waste gases monitoring in animal buildings.

关 键 词：遗传模拟退火算法 支持向量机 畜禽舍 废气监测 数据恢复 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]