Abstract
This paper proposes an adaptive soft sensing method based on selective ensemble of local partial least squares models, referring to as the SELPLS, for quality prediction of nonlinear and time-varying chemical processes. To deal with the process nonlinearity, we partition the process state into local model regions upon which PLS models are constructed, through a statistical hypothesis testing based adaptive localization procedure. Two main delightful advantages of this localization strategy are that, redundant local models can be effectively detected and deleted and the local model set can be easily augmented online without retraining from scratch. In addition, a local model weighting mechanism is proposed to adaptively differentiate the contributions of local models by explicitly quantifying their generalization abilities for the current process dynamics. Finally, the selective ensemble learning strategy combines partial local models instead of all available models through Bayesian inference, which is able to reach a good equilibrium between the prediction bias and variance. The proposed SELPLS based soft sensor is applied to a simulated continuous stirred tank reactor and a real-life industrial sulfur recovery unit. Extensive simulation results demonstrate the effectiveness of the proposed scheme in contrast with several state-of-the-art adaptive soft sensing approaches.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have