Soft-Sensing of Burn-Through Point Based on Weighted Kernel Just-in-Time Learning and Fuzzy Broad-Learning System in Sintering Process
- 12 February 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (5) , 7316-7324
Abstract
Burn-through point (BTP) is an essential thermal state parameter in a sintering process, which is a direct reflection of the stability of this process. However, it cannot be measured online. Soft-sensing technology offers a reliable method for estimating unmeasurable variables in industrial processes. Here, a soft-sensing model for BTP based on weighted kernel just-in-time learning (WKJITL) and fuzzy broad-learning system (FBLS) is built. First, an abnormal production data detection and correction strategy is employed to process the production data, and the mechanism analysis and mutual information analysis are utilized to specify the detectable process variables that are directly related to BTP. Then, the WKJITL method is proposed to obtain historical production data similar to the query data of BTP for local learning modeling, and the FBLS is utilized as an efficient modeling method for the soft-sensing prediction of BTP. Finally, the results of simulation experiments based on actual sintering production data reveal that the developed soft-sensing model of BTP exhibits better prediction accuracy and efficiency compared with some advanced modeling methods. Furthermore, the proposed method is of general nature and can also be easily applied to other industrial processes.Keywords
Funding Information
- National Natural Science Foundation of China (62303431)
- Higher Education Discipline Innovation Project (B17040)
- Hubei Provincial Natural Science Foundation of China (2021CFB145)
- Key Program of Hubei Provincial Technical Innovation Project (2023BAB080)
- Fundamental Research Funds for the Central Universities, China University of Geosciences (CUG2106210)
This publication has 31 references indexed in Scilit:
- Long–short-term memory encoder–decoder with regularized hidden dynamics for fault detection in industrial processesJournal of Process Control, 2023
- Stacked supervised Poisson autoencoders-based soft-sensor for defects prediction in steelmaking processComputers & Chemical Engineering, 2023
- A Multi-Objective online streaming Multi-Label feature selection using mutual informationExpert Systems with Applications, 2022
- Customisation of green buildings assessment tools based on climatic zoning and experts judgement using K-means clustering and fuzzy AHPBuilding and Environment, 2022
- Monitoring multi-domain batch process state based on fuzzy broad learning systemExpert Systems with Applications, 2022
- A Robust Asymmetric Kernel Function for Bayesian Optimization, With Application to Image Defect Detection in Manufacturing SystemsIEEE Transactions on Automation Science and Engineering, 2021
- Prediction model of burn-through point with fuzzy time series for iron ore sintering processEngineering Applications of Artificial Intelligence, 2021
- NOx emissions prediction based on mutual information and back propagation neural network using correlation quantitative analysisEnergy, 2020
- Fault Detection for Nonlinear Process With Deterministic Disturbances: A Just-In-Time Learning Based Data Driven MethodIEEE Transactions on Cybernetics, 2016
- On a comparison between Mahalanobis distance and Choquet integral: The Choquet–Mahalanobis operatorInformation Sciences, 2012