This chapter addresses the issue of sample value imbalance in process monitoring by developing a fault detection approach that integrates variable selection and support vector data description (SVDD) for enhanced efficiency. Initially, KLD is employed as the variable selection algorithm to identify the most informative variables related to specific faults. These selected variables are then segmented into blocks to prevent fault information from being obscured within a single monitoring space, ensuring that relevant variables and critical information are concentrated within the same block. Subsequently, kernel principal component analysis is conducted within each block to manage the challenges posed by high-dimensional and nonlinear variables. The monitoring outcomes are derived using the proposed SVDD, which incorporates a restructured radius index that exhibits heightened sensitivity to faults. Experimental results on the Tennessee Eastman process demonstrate the efficacy of this method, highlighting its superior mean fault detection rate compared to existing approaches.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Relevant Variable Selection and SVDD for Processes Fault Detection with Incremental Redundant Data


    Additional title:

    eng. Applications of Computational Methods


    Contributors:
    Yin, Hongpeng (author) / Zhou, Han (author) / Chai, Yi (author) / Tang, Qiu (author)


    Publication date :

    2025-04-16


    Size :

    19 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Fault Monitoring of Batch Process Based on Moving Window SVDD

    Xie, Yanhong / Sun, Chengao / Li, Yuan | British Library Online Contents | 2015


    Redundant IMU Fault Detection

    Li, Xuefeng / Xu, Fan / Xu, Guoqiang | Springer Verlag | 2022



    PCA-SVDD-based production line lifting appliance intelligent fault diagnosis method and system

    TENG RAN / HAO YUNRUI / XU CHI et al. | European Patent Office | 2024

    Free access

    Abnormality detection via SVDD technique of motor-generator system in HEV

    Na, S. G. / Yang, I. B. / Heo, H. | Online Contents | 2014