Abstract
Industrial batch processes employ similar or identical equipment to manufacture various specification products, hence multi-batch data exhibit common characteristics. Additionally, complex characteristics exist within each batch. In this paper, a multi-level monitoring method based on slow independent component analysis-tensor decomposition (SICA-TD) is proposed considering the characteristics of industrial batch processes. In the first-level monitoring model, SICA is used to identify whether the current batch is faulty. An integrated control limit is constructed to enhance robustness. When a fault is detected, fault and normal data features are combined into a tensor. Subsequently, the second-level monitoring model extracts common features through TD. The disparity in common feature distribution between normal and fault conditions is measured via Bhattacharyya distance (BD) statistics to ascertain whether the fault affects all batches. The method is validated through an actual hot strip mill process (HSMP) and implemented in a process monitoring platform for a steel manufacturing company.
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.
