Transductive transfer broad learning for cross-domain information exploration and multigrade soft sensor application

Without sufficient labeled data, the construction of accurate soft-sensor models for multigrade chemical processes is challenging. To alleviate the dilemma, a transductive transfer broad learning (TTBL) model for cross-domain information exploration is proposed. The features are extracted by the nodes of broad learning system. Then, similar sample information from the current and related domains is captured by the k nearest-neighbor graph and retained by the manifold regularization framework. By exploring the available cross-domain information, unlabeled data in the prediction domain can be utilized for modeling. Finally, a TTBL model is constructed assisted by the fast leave-one-out cross-validation strategy. TTBL can effectively exploit the useful information of cross-domain data to improve prediction performance. Experimental results on two multigrade chemical processes demonstrate its superiorities compared with several traditional methods. •A transductive transfer broad learning soft sensor model is proposed for quality prediction of multigrade processes.•By leveraging useful information from the related domain, unlabeled data is utilized effectively for modeling.•The model extracts and utilizes similar data information from the current and related domains.•The prediction results of two multigrade chemical processes show its effectness and practicality.