Abstract
In this paper, a PLS-based fault-relevant reconstruction method is proposed for fault detection and identification. The PLS-based proposed method finds a set of latent variables to project the training data onto a process space to analyze the problem of reconstruction and is used to find the directions which can best characterize the fault effects relevant to normal status. According to the fault distribution directions, the PLS-based proposed method can eliminate the fault cause and bring faulty statistics under the control limits. The PLS-based proposed method is compared with partial least squares (PLS) to show the feasibility of the novel method, and is applied to two simulated processes. One is a simulated linear process and the other is the penicillin fermentation process. The simulated results show the improvement of the PLS-based proposed method in fault detection and identification.
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.
