Neural network-based hybrid modeling approach incorporating Bayesian optimization with industrial soft sensor application

Zhenhua Yu, Zhongyi Zhang, Qingchao Jiang, Xuefeng Yan

Abstract: Highlights•A novel hybrid modeling method that incorporates data and knowledge is proposed.•Model interpretability, model robustness, and prediction accuracy are improved.•Case studies on two application examples are provided.•Comparisons to state-of-the-arts show effectiveness of the proposed method.