摘要
由于缺乏稳定可靠的水质在线分析仪表,污水处理厂很难实现实时水质闭环控制和操作优化.通过选择污水过程中容易获得的进水流量和水质、溶解氧浓度、曝气氧量等辅助变量,提出一种基于PLS的多变量非线性动态多模型软测量建模方法.该方法基于有源自回归(Auto-Re-gressive with extra inputs,ARX)模型与模糊C-均值(Fuzzy C-Means,FCM)聚类方法识别操作工况,在不同操作工况分别采用神经网络偏最小二乘法NNPLS(Neural Net Partial Least Square),建立多个非线性子模型拟和系统全局非线性.所提方法应用于某污水处理厂出水水质组分浓度软测量,仿真试验结果表明:该方法建立的多变量出水水质指标模型精度优于传统线性PLS模型.
Due to the lack of widely stable and reliable water quality parameters on-line instrumentation,it is difficult to implement closed-loop control of water quality and optimize the operation in wastewater treatment plant.A multi-variable nonlinear dynamic multi-model soft-sensing model based on PLS,by using water flow and quality,the dissolved oxygen,the oxygen aeration and other auxiliary variables to receive easily as parameters is proposed to solve the problem of multi-variable,non-linear and time-varying uncertainty in wastewater treatment process.The methodology that integrates dynamic ARX with Fuzzy C-means identifies operating conditions of time-varying and uncertainty in the wastewater treatment process.NNPLS is used to establish a number of non-linear model in different operating conditions and the whole non-linear system.The proposed method is applied in soft-sensing of effluent quality component concentration in wastewater treatment plant.Simulation results indicate that the method which establishes a multi-variable model of water quality indicators for precision is better than traditional linear PLS model.
出处
《沈阳化工学院学报》
2009年第3期258-265,共8页
Journal of Shenyang Institute of Chemical Technolgy
基金
辽宁省教育厅科技研究项目资助(05L346
2008563)
