This paper develops a fixture failure diagnostic method based on the fixture geometry and in-line measurements. The proposed solution, based on the fixture geometry and measurement locations, is generic enough to apply to multi-fixture systems such as an autobody assembly. In this paper a generic model of variation pattern for 3-2-1 fixtures and fault mapping mechanism are proposed. The model of the variation pattern is based solely on the fixture configuration and measurement location. The relations between layout of tooling elements and measurements are developed and used for modeling of the fault variation pattern. Additionally, hypothetical tooling faults as well as their manifestation through dimensional sensors are thoroughly discussed. A major advantage of the proposed model is that the variation pattern of faults can be predetermined based only on the CAD data available during tooling design. In addition, a model can be created during the development cycle for all fixtures. Fault mapping includes two tasks: (1) estimation of the dominant direction of the fault variation pattern, and (2) fault classification of the dominant direction using a minimum distance classifier. A minimum distance classifier determines the unknown fault based on its distance from the predetermined variation pattern described in the model. The variation pattern of the unknown fault is described through Principal Component Analysis. The verification of the proposed method is presented through a series of computer simulations and one case study based on production data. These simulations and the one case study have demonstrated that dimensional faults can be isolated by using the proposed approach in the noisy production environment. The simulation results show that the presented approach is robust in 45 percent noise environment.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Fixture failure diagnosis for autobody assembly using pattern recognition


    Additional title:

    Fehlerdiagnose bei Vorrichtungen für die Karosseriemontage mittels Mustererkennung


    Contributors:
    Ceglarek, D. (author) / Shi, J. (author)


    Publication date :

    1996


    Size :

    12 Seiten, 10 Bilder, 6 Tabellen, 23 Quellen




    Type of media :

    Article (Journal)


    Type of material :

    Print


    Language :

    English





    Smart autobody assembly system

    PARK JONG AN / PARK YONG SEOK | European Patent Office | 2025

    Free access

    Dynamic denting of autobody panels

    Burley,C.E. / Niemeier,B.A. / Koch,G.P. et al. | Automotive engineering | 1976


    Technoeconomic evaluation of autobody materials

    George, S.C.H. / Evans, M. / Lowe, K. | Tema Archive | 1997


    Autobody stamping technology progress : papers

    Society of Automotive Engineers / Ferrous Committee | TIBKAT | 1991