Design of online soft sensors based on combined adaptive PCA and RBF neural networks

An accurate on-line measurement of important quality variables is essential for successful monitoring and controlling of chemical processes. However, these variables are usually difficult to measure on-line due to the practical 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 radial basis functions (RBF) artificial neural network. For this purpose, a recursive PCA and a PCA based on a sliding window scheme 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 RBF neural network. The developed online soft sensors are finally tested on a highly nonlinear distillation column benchmark problem to illustrate their effective performances. The simulation results demonstrate the superiority of the proposed soft sensor based on the combined recursive PCA and the RBF neural network.