Abstract
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.
Highlights
Mechanical properties refer to the mechanical characteristics of materials under various external loads in different environments, which are important indexes to evaluate the quality of materials
At the tolerance level of 15 MPa with tensile strength (TS), yield strength (YS) and 3% with EL, the prediction accuracy of JMWSSGMR is higher, which verifies its superiority. These results clearly show that the proposed soft sensor can effectively deal with various problems in hot rolling, and it can be successfully applied in the prediction of mechanical properties of strips
To monitoring the mechanical properties of hot rolled strips accurately, a just-in-time learning (JITL) based multi-block weighted semisupervised soft sensor is proposed in this paper
Summary
Mechanical properties refer to the mechanical characteristics of materials under various external loads (tension, compression, bending etc.) in different environments, which are important indexes to evaluate the quality of materials. There are two kinds of models in the soft sensor: metallurgical mechanism models and data-driven models [2] The former establish theoretical formulas for the evolution of strip structure and process parameters, and predict mechanical properties by revealing microstructure evolution of steel. Compared with complex mechanism models, datadriven ones have simpler structure, wider applicability and stronger learning ability These models can extract effective parts from numerous process information and provide precise prediction of mechanical properties. How to build responsive and accurate data-driven soft sensors is a research hotspot in the field of steel quality prediction and process control. As early as the 1990s, Liu et al [7] have applied ANN to predict the mechanical properties of hot rolled C-Mn steel, showing great learning and generation ability compared with traditional regression models.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
