生物氧化预处理过程中进气量预测智能集成模型的建立  

Establishment of Intelligent Integrated Model for Predicting Air Input in Process of Bio-oxidation Pretreatment

作　　者：蔡鑫[1] 南新元[1] 高丙朋[1] 陈星志 

机构地区：[1]新疆大学电气工程学院,新疆乌鲁木齐830047

出　　处：《湿法冶金》2016年第4期288-292,共5页Hydrometallurgy of China

基　　金：国家自然科学基金资助项目(61463047)

摘　　要：针对生物氧化预处理过程中进气量调节的时滞性以及传统离线预测存在的不足,提出一种基于最优加权的进气量智能集成预测模型。首先根据生物氧化预处理机制,建立氧化槽耗氧机制模型;然后根据预处理过程各变量建立基于在线支持向量机的智能预测模型;最后根据集成思想,采用最优加权法将上述2个单一模型加权集成,建立进气量智能集成预测模型。试验结果表明:该模型能够很好地在线预测氧化槽进气量,相比单一预测模型具有更高的预测精度,可满足工业生产在线优化控制要求。Considering the time delay of operation air input and the deficiency in the traditional off-line prediction in the process of bio-oxidation pretreatment,an intelligent integrated model for predicting air input of oxidation tank online based on optimal weight was proposed.First,oxygen consumption mechanism model in the biological pretreatment process was built based on bio-oxidation pretreatment mechanism.Then,an air input intelligent prediction model based on online support vector regression was built according to the collected data from oxygen tank.Last,with the idea of system integration,the intelligent integrated model was built by weighted summation of the two prediction models.The weight coefficient can be solved by optimal weighting method.Using the real data collected from the pretreatment process,the experimental results show that the prediction accuracy of the intelligent integrated model is better than any single prediction model.The proposed model can predict air input of each oxidation tank efficiently and can meet the requirements of online optimal control in practical industrial production.

关 键 词：生物氧化 进气量 预测 在线支持向量机 智能集成模型 建立 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TF18[自动化与计算机技术—控制科学与工程]