Just-in-Time Learning-Based Soft Sensor for Mechanical Properties of Strip Steel via Multi-Block Weighted Semisupervised Models

Mechanical properties are important indexes to evaluate the quality of hot rolling strips. It is a research hotspot in the field of hot rolling that realizing timely and accurate soft sensing of mechanical properties. Traditional soft sensing methods have poor performance in the application of strong nonlinearity and multiple working conditions. Moreover, the utilization rate of data is relatively low, which limit the improvement of prediction accuracy. To solve the problems above, a just-in-time learning (JITL) based multi-block weighted semisupervised Gaussian mixture regression (JMWSSGMR) soft sensor is proposed in the paper. There are two stages in the soft sensor: off-line variable blocking and on-line local modeling. In the off-line phase, process variables are divided into different sub-blocks by partial least square (PLS) according to distinct principal component directions. In each sub-block, original variables with high contribution rate are retained. In the on-line phase, optimized Mahalanobis distance is constructed to select the most similar historical samples to the query sample. Next, various real-time semisupervised sub-models are built to estimate the output of the query sample. Finally, predicted values of sub-models are fused and ultimate prediction of mechanical properties is obtained. Case studies are carried out on a numerical example and a hot rolling process. The feasibility and effectiveness of proposed soft sensor are verified by the predicted results.