A regression model for matching parallel systems

Roger NIBLER

    Research output: Journal PublicationsJournal Article (refereed)

    Abstract

    Contends that parallel production sub-systems may be cost effective and, in some cases, they are the only technically feasible way to improve output quality. Operating in either a standby-redundancy or an ongoing capacity, parallel production sub-systems are likely to be most cost effective when placed in upstream operations, where the leverage effect on output quality is considerably higher. Although typical research in parallel systems assumes a known distribution to estimate the output reliability of the parallel configuration, explains how this study used a simulated production environment to develop a regression model for assigning parallel system components by monitoring their actual past performance, and was therefore distribution free. Applying variables monitored during a previous production run in which quality is measured in a binary manner (i.e. either as acceptable or unacceptable), the model was used to determine optimal pairs of parallel subsystems. Claims that this matching model was about 2.5 times more accurate than Markov analysis in predicting the output quality of a given pair of parallel systems. The inclusion of an additional variable in the regression resulted in the model explaining about 75 per cent of the output variability of the parallel configurations and thus could potentially predict quality in lieu of direct inspection.
    Original languageEnglish
    Pages (from-to)176-185
    Number of pages10
    JournalInternational Journal of Quality and Reliability Management
    Volume14
    Issue number2
    DOIs
    Publication statusPublished - 1 Jan 1997

    Fingerprint

    Regression model
    Subsystem
    Leverage effect
    Matching model
    Inspection
    Monitoring
    Redundancy
    Distribution-free
    Inclusion

    Keywords

    • Process efficiency
    • Quality
    • Reliability
    • Systems

    Cite this

    @article{7637176f201a4b3e9eb6dce57bc76035,
    title = "A regression model for matching parallel systems",
    abstract = "Contends that parallel production sub-systems may be cost effective and, in some cases, they are the only technically feasible way to improve output quality. Operating in either a standby-redundancy or an ongoing capacity, parallel production sub-systems are likely to be most cost effective when placed in upstream operations, where the leverage effect on output quality is considerably higher. Although typical research in parallel systems assumes a known distribution to estimate the output reliability of the parallel configuration, explains how this study used a simulated production environment to develop a regression model for assigning parallel system components by monitoring their actual past performance, and was therefore distribution free. Applying variables monitored during a previous production run in which quality is measured in a binary manner (i.e. either as acceptable or unacceptable), the model was used to determine optimal pairs of parallel subsystems. Claims that this matching model was about 2.5 times more accurate than Markov analysis in predicting the output quality of a given pair of parallel systems. The inclusion of an additional variable in the regression resulted in the model explaining about 75 per cent of the output variability of the parallel configurations and thus could potentially predict quality in lieu of direct inspection.",
    keywords = "Process efficiency, Quality, Reliability, Systems",
    author = "Roger NIBLER",
    year = "1997",
    month = "1",
    day = "1",
    doi = "10.1108/02656719710165437",
    language = "English",
    volume = "14",
    pages = "176--185",
    journal = "International Journal of Quality and Reliability Management",
    issn = "0265-671X",
    publisher = "Emerald Group Publishing Ltd.",
    number = "2",

    }

    A regression model for matching parallel systems. / NIBLER, Roger.

    In: International Journal of Quality and Reliability Management, Vol. 14, No. 2, 01.01.1997, p. 176-185.

    Research output: Journal PublicationsJournal Article (refereed)

    TY - JOUR

    T1 - A regression model for matching parallel systems

    AU - NIBLER, Roger

    PY - 1997/1/1

    Y1 - 1997/1/1

    N2 - Contends that parallel production sub-systems may be cost effective and, in some cases, they are the only technically feasible way to improve output quality. Operating in either a standby-redundancy or an ongoing capacity, parallel production sub-systems are likely to be most cost effective when placed in upstream operations, where the leverage effect on output quality is considerably higher. Although typical research in parallel systems assumes a known distribution to estimate the output reliability of the parallel configuration, explains how this study used a simulated production environment to develop a regression model for assigning parallel system components by monitoring their actual past performance, and was therefore distribution free. Applying variables monitored during a previous production run in which quality is measured in a binary manner (i.e. either as acceptable or unacceptable), the model was used to determine optimal pairs of parallel subsystems. Claims that this matching model was about 2.5 times more accurate than Markov analysis in predicting the output quality of a given pair of parallel systems. The inclusion of an additional variable in the regression resulted in the model explaining about 75 per cent of the output variability of the parallel configurations and thus could potentially predict quality in lieu of direct inspection.

    AB - Contends that parallel production sub-systems may be cost effective and, in some cases, they are the only technically feasible way to improve output quality. Operating in either a standby-redundancy or an ongoing capacity, parallel production sub-systems are likely to be most cost effective when placed in upstream operations, where the leverage effect on output quality is considerably higher. Although typical research in parallel systems assumes a known distribution to estimate the output reliability of the parallel configuration, explains how this study used a simulated production environment to develop a regression model for assigning parallel system components by monitoring their actual past performance, and was therefore distribution free. Applying variables monitored during a previous production run in which quality is measured in a binary manner (i.e. either as acceptable or unacceptable), the model was used to determine optimal pairs of parallel subsystems. Claims that this matching model was about 2.5 times more accurate than Markov analysis in predicting the output quality of a given pair of parallel systems. The inclusion of an additional variable in the regression resulted in the model explaining about 75 per cent of the output variability of the parallel configurations and thus could potentially predict quality in lieu of direct inspection.

    KW - Process efficiency

    KW - Quality

    KW - Reliability

    KW - Systems

    UR - http://commons.ln.edu.hk/sw_master/6947

    U2 - 10.1108/02656719710165437

    DO - 10.1108/02656719710165437

    M3 - Journal Article (refereed)

    VL - 14

    SP - 176

    EP - 185

    JO - International Journal of Quality and Reliability Management

    JF - International Journal of Quality and Reliability Management

    SN - 0265-671X

    IS - 2

    ER -