基于GA-LSSVM的粮情预警方法研究  

Research on grain situation warning method based on GA-LSSVM

作　　者：黄琦兰[1] 李玉强[1] HUANG Qi-lan;LI Yu-qiang(School of Electrical Engineering and Automation,Tianjin Polytechnic University,Tianjin 300387,China)

机构地区：[1]天津工业大学电气工程与自动化学院,天津300387

出　　处：《粮食与油脂》2021年第8期66-69,共4页Cereals & Oils

摘　　要：为了保障粮食储藏安全,提出了一种采用遗传算法优化最小二乘支持向量机判断粮情安全等级的方法。选取对粮仓安全影响因素较大的6个参数(仓气温、仓气湿、粮温、水分、二氧化碳、虫害)作为模型的输入,通过遗传算法优化最小二乘支持向量机的核参数和惩罚因子,输出当前的粮仓安全等级。方法经过仿真数据的验证,具有较高的准确率和良好的泛化能力,应用前景很好。In order to ensure the security of grain storage,a method of using genetic algorithm to optimize the least square support vector machine to judge the security level of grain was proposed.Six parameters were selected(granary temperature,granary humidity,grain temperature,moisture,carbon dioxide and insect pest)which have great influence on the safety of the granary as the input of the model.The kernel parameters and penalty factors of least square support vector machine were optimized by genetic algorithm to output the current granary safety level.The simulation results showed that the method had high accuracy and good generalization ability,and had a good application prospect.

关 键 词：遗传算法 最小二乘支持向量机 粮情安全 

分 类 号：TS201.6[轻工技术与工程—食品科学]