Applying a robust heteroscedastic probabilistic neural network to analog fault detection and classification

Zheng Rong Yang, Mark Zwolinski, Chris D. Chalk, Alan Christopher Williams

    Research output: Contribution to journalArticle

    Abstract

    The problem of distinguishing and classifying the responses of analog integrated circuits containing catastrophic faults has aroused recent interest. The problem is made more difficult when parametric variations are taken into account. Hence, statistical methods and techniques such as neural networks have been employed to automate classification. The major drawback to such techniques has been the implicit assumption that the variances of the responses of faulty circuits have been the same as each other and the same as that of the fault-free circuit. This assumption can be shown to be false. Neural networks, moreover, have proved to be slow. This paper describes a new neural network structure that clusters responses assuming different means and variances. Sophisticated statistical techniques are employed to handle situations where the variance tends to zero, such as happens with a fault that causes a response to be stuck at a supply rail. Two example circuits are used to show that this technique is significantly more accurate than other classification methods. A set of responses can be classified in the order of 1 s.

    Original languageEnglish
    Pages (from-to)142-151
    Number of pages10
    JournalIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
    Volume19
    Issue number1
    DOIs
    Publication statusPublished - 2000

    Fingerprint

    Fault detection
    Neural networks
    Networks (circuits)
    Rails
    Statistical methods

    Cite this

    Yang, Zheng Rong ; Zwolinski, Mark ; Chalk, Chris D. ; Williams, Alan Christopher. / Applying a robust heteroscedastic probabilistic neural network to analog fault detection and classification. In: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2000 ; Vol. 19, No. 1. pp. 142-151.
    @article{5a306f290f024b00b76dba679ba71da0,
    title = "Applying a robust heteroscedastic probabilistic neural network to analog fault detection and classification",
    abstract = "The problem of distinguishing and classifying the responses of analog integrated circuits containing catastrophic faults has aroused recent interest. The problem is made more difficult when parametric variations are taken into account. Hence, statistical methods and techniques such as neural networks have been employed to automate classification. The major drawback to such techniques has been the implicit assumption that the variances of the responses of faulty circuits have been the same as each other and the same as that of the fault-free circuit. This assumption can be shown to be false. Neural networks, moreover, have proved to be slow. This paper describes a new neural network structure that clusters responses assuming different means and variances. Sophisticated statistical techniques are employed to handle situations where the variance tends to zero, such as happens with a fault that causes a response to be stuck at a supply rail. Two example circuits are used to show that this technique is significantly more accurate than other classification methods. A set of responses can be classified in the order of 1 s.",
    author = "Yang, {Zheng Rong} and Mark Zwolinski and Chalk, {Chris D.} and Williams, {Alan Christopher}",
    year = "2000",
    doi = "10.1109/43.822626",
    language = "English",
    volume = "19",
    pages = "142--151",
    journal = "IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems",
    issn = "0278-0070",
    publisher = "IEEE",
    number = "1",

    }

    Applying a robust heteroscedastic probabilistic neural network to analog fault detection and classification. / Yang, Zheng Rong; Zwolinski, Mark; Chalk, Chris D.; Williams, Alan Christopher.

    In: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, Vol. 19, No. 1, 2000, p. 142-151.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Applying a robust heteroscedastic probabilistic neural network to analog fault detection and classification

    AU - Yang, Zheng Rong

    AU - Zwolinski, Mark

    AU - Chalk, Chris D.

    AU - Williams, Alan Christopher

    PY - 2000

    Y1 - 2000

    N2 - The problem of distinguishing and classifying the responses of analog integrated circuits containing catastrophic faults has aroused recent interest. The problem is made more difficult when parametric variations are taken into account. Hence, statistical methods and techniques such as neural networks have been employed to automate classification. The major drawback to such techniques has been the implicit assumption that the variances of the responses of faulty circuits have been the same as each other and the same as that of the fault-free circuit. This assumption can be shown to be false. Neural networks, moreover, have proved to be slow. This paper describes a new neural network structure that clusters responses assuming different means and variances. Sophisticated statistical techniques are employed to handle situations where the variance tends to zero, such as happens with a fault that causes a response to be stuck at a supply rail. Two example circuits are used to show that this technique is significantly more accurate than other classification methods. A set of responses can be classified in the order of 1 s.

    AB - The problem of distinguishing and classifying the responses of analog integrated circuits containing catastrophic faults has aroused recent interest. The problem is made more difficult when parametric variations are taken into account. Hence, statistical methods and techniques such as neural networks have been employed to automate classification. The major drawback to such techniques has been the implicit assumption that the variances of the responses of faulty circuits have been the same as each other and the same as that of the fault-free circuit. This assumption can be shown to be false. Neural networks, moreover, have proved to be slow. This paper describes a new neural network structure that clusters responses assuming different means and variances. Sophisticated statistical techniques are employed to handle situations where the variance tends to zero, such as happens with a fault that causes a response to be stuck at a supply rail. Two example circuits are used to show that this technique is significantly more accurate than other classification methods. A set of responses can be classified in the order of 1 s.

    UR - http://www.scopus.com/inward/record.url?scp=0033908161&partnerID=8YFLogxK

    U2 - 10.1109/43.822626

    DO - 10.1109/43.822626

    M3 - Article

    VL - 19

    SP - 142

    EP - 151

    JO - IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

    JF - IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

    SN - 0278-0070

    IS - 1

    ER -