Novel Bayesian Framework for Dynamic Soft Sensor Based on Support Vector Machine With Finite Impulse Response

Conventional data-driven soft sensors commonly rely on the assumption that processes are operating at steady states. As chemical processes involve evident dynamics, conventional soft sensors may suffer from transient inaccuracy and poor robustness. In addition, the control performance is unsatisfactory when the outputs of soft sensors serve as the feedback signals for quality control. This brief develops a dynamic soft-sensing model combining finite impulse response and support vector machine to describe dynamic and nonlinear static relationships. The model parameters are then estimated within a Bayesian framework. The results from both the simulated and the industrial case show its superiority to conventional static models in terms of dynamic accuracy and practical applicability.