基于支持向量机的啤酒企业能源消耗预测模型  

Prediction Model of Energy Consumption on Beer Enterprise Based on Support Vector Machine

作　　者：邢吉生[1] 武海巍[1,2] 

机构地区：[1]北华大学电气信息工程学院,吉林吉林132021 [2]吉林大学通信工程学院,长春130022

出　　处：《吉林大学学报（信息科学版）》2014年第6期664-669,共6页Journal of Jilin University（Information Science Edition）

基　　金：吉林省科技发展技术基金资助项目(20096035)

摘　　要：为提高啤酒企业包装车间生产耗电的预测精度,提出了一种基于支持向量机和粒子群优化算法的预测模型构建方法。该方法将radial basis function函数作为支持向量机的核函数构建预测模型,使用K-fold交叉验证方法,利用粒子群算法(PSO:Particle Swarm Optimization)对惩罚参数c和g值寻优。以28天的生产耗水和生产耗电数据作为训练集,以10天的生产耗水数据作为预测集,分别构建基于radial basis function函数与polynomial函数的生产耗电支持向量机预测模型对生产耗电数据进行预测。实验结果表明,以radial basis function函数作为核函数与以polynomial函数作为核函数相比,该支持向量机预测模型对生产耗电的预测精度提高了51.495%,该方法具有一定的实用性。To improve the prediction accuracy on consumed electricity of manufacturing in beer enterprise, we design a method on constructing prediction model based on support vector machine and PSO （Particle Swarm Optimization） algorithm. The radial basis function is used as the kernel function in SVM （Support Vector Machine）. The paper uses K-fold cross validation and optimizes the penalty parameter c and the parameter g based on PSO （Particle Swarm Optimization）. Based on the training set, which is consist of consumed water in the process of manufacturing and consumed electricity in the process of manufacturing for 28 days, and the prediction set, which is consist of consumed water in the process of manufacturing for 10 days, the paper respectively constructs the SVM prediction model on consumed electricity in the process of manufacturing based on radial basis function and polynomial function to predict the consumed electricity in the process data. The test results show that the prediction accuracy of the Support Vector Machine prediction model is 51. 495 % based on radial basis function kernel higher than that based on polynomial kernel in predicting consumed electricity in the process and the method is practical.

关 键 词：支持向量机 生产耗电预测模型 核函数 粒子群算法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]