Design of Online Soft Sensors based on Combined Adaptive PCA and DMLP Neural Networks
An accurate on-line measurement of important quality variables is essential for successful monitoring and controlling of chemical process. However, these variables are usually difficult to measure on-line due to the limitations such as the time delay, high cost and reliability considerations. To overcome this problem, two online soft sensors are proposed based upon a combined adaptive principal component analysis (PCA) and a dynamic multi-layered perceptron (DMLP) artificial neural network (ANN). For this purpose, a recursive PCA and a PCA based on a sliding window are presented to adaptively extract the inherent features inside the measurements with high dimensions. The extracted low-dimension features are then used recursively as the main inputs to the DMLP networks. The developed online soft sensors are finally tested on a highly nonlinear distillation column benchmark problem to illustrate their comparative performances. The simulation results demonstrate the superiority of the soft sensor based on the recursive PCA and the DMLP network.
soft sensor Industrial distillation column PCA Neural network
Karim Salahshoor Mojtaba Kordestani Majid .S. Khoshro
Department of Instrumentation and Automation, Petroleum University of Technology Department of Control Engineering, Islamic Azad University South Tehran branch
国际会议
2009年中国控制与决策会议(2009 Chinese Control and Decision Conference)
广西桂林
英文
3481-3486
2009-06-17（万方平台首次上网日期，不代表论文的发表时间）