摘要
针对污水处理过程中关键水质参数无法在线监测的问题,提出了基于主元分析PCA时间延迟神经网络的污水水质BOD在线预测软测量方法。该方法由三部分组成:主元分析PCA、时间延迟神经网络、软测量模型的在线校正。其中离线模型采用GABP算法训练,仿真结果表明该方法可以实现污水水质的在线预测,具有实时性好,稳定性高,精度高,校正方便等特点。
In monitoring and controlling wastewater treatment processes, on-line information of some essential wastewater parameters is inaccessible. In this paper, a soft-measuring approach applied in wastewater quality measurement is put forward based on Principal Components Analysis(PCA) time-delay neural network. It is composed of three elements: PCA, time-delay neural network and model updating, where the offline model is trained through the algorithm GABP. This model, which is of good real-time property, good stability, high precision and easy updating, can be applied to on-line predict wastewater Biochemical Oxygen Demand(BOD).
出处
《电工技术学报》
EI
CSCD
北大核心
2004年第12期78-82,共5页
Transactions of China Electrotechnical Society
基金
国家自然科学基金资助项目(50274003 和 60304012)
北京市科技新星计划资助项目
关键词
软测量
时间延迟神经网络
主元分析
在线预测
Soft–measuring, time-delay neural network (TDNN), PCA, on-line predict
