Exploiting data in smart factories: Real-time state estimation and model improvement in metal forming mass production

    Research output: Contribution to journalArticleAcademicpeer-review

    12 Downloads (Pure)

    Abstract

    Modern production systems have numerous sensors that produce large amounts of data. This data can be exploited in many ways, from providing insight into the manufacturing process to facilitating automated decision making. These opportunities are still underexploited in the metal forming industry, due to the complexity of these processes. In this work, a probabilistic framework is proposed for simultaneous model improvement and state estimation in metal forming mass production. Recursive Bayesian estimation is used to simultaneously track the evolution of process state and to estimate the deviation between the physics-based model and the real process. A sheet bending mass production process is used to test the proposed framework. A metamodel of the process is built using proper orthogonal decomposition and radial basis function interpolation. The model is extended with a deviation model in order to account for the difference between model and real process. Particle filtering is used to track the state evolution and to estimate the deviation model parameters simultaneously. The approach is tested and analysed using a large number of simulations, based on pseudo-data obtained from a numerical sheet bending model.
    Original languageEnglish
    Pages (from-to)1-11
    Number of pages11
    JournalInternational journal of material forming
    DOIs
    Publication statusE-pub ahead of print/First online - 24 Jul 2019

    Fingerprint

    Metal forming
    State estimation
    Industrial plants
    Interpolation
    Physics
    Decision making
    Decomposition
    Sensors
    Industry

    Keywords

    • UT-Hybrid-D

    Cite this

    @article{3574816eb6b64a44a2ae58b2702cf21b,
    title = "Exploiting data in smart factories: Real-time state estimation and model improvement in metal forming mass production",
    abstract = "Modern production systems have numerous sensors that produce large amounts of data. This data can be exploited in many ways, from providing insight into the manufacturing process to facilitating automated decision making. These opportunities are still underexploited in the metal forming industry, due to the complexity of these processes. In this work, a probabilistic framework is proposed for simultaneous model improvement and state estimation in metal forming mass production. Recursive Bayesian estimation is used to simultaneously track the evolution of process state and to estimate the deviation between the physics-based model and the real process. A sheet bending mass production process is used to test the proposed framework. A metamodel of the process is built using proper orthogonal decomposition and radial basis function interpolation. The model is extended with a deviation model in order to account for the difference between model and real process. Particle filtering is used to track the state evolution and to estimate the deviation model parameters simultaneously. The approach is tested and analysed using a large number of simulations, based on pseudo-data obtained from a numerical sheet bending model.",
    keywords = "UT-Hybrid-D",
    author = "Jos Havinga and Mandal, {Pranab K.} and {van den Boogaard}, {Antonius H.}",
    note = "Springer deal",
    year = "2019",
    month = "7",
    day = "24",
    doi = "10.1007/s12289-019-01495-2",
    language = "English",
    pages = "1--11",
    journal = "International journal of material forming",
    issn = "1960-6206",
    publisher = "Springer",

    }

    TY - JOUR

    T1 - Exploiting data in smart factories

    T2 - Real-time state estimation and model improvement in metal forming mass production

    AU - Havinga, Jos

    AU - Mandal, Pranab K.

    AU - van den Boogaard, Antonius H.

    N1 - Springer deal

    PY - 2019/7/24

    Y1 - 2019/7/24

    N2 - Modern production systems have numerous sensors that produce large amounts of data. This data can be exploited in many ways, from providing insight into the manufacturing process to facilitating automated decision making. These opportunities are still underexploited in the metal forming industry, due to the complexity of these processes. In this work, a probabilistic framework is proposed for simultaneous model improvement and state estimation in metal forming mass production. Recursive Bayesian estimation is used to simultaneously track the evolution of process state and to estimate the deviation between the physics-based model and the real process. A sheet bending mass production process is used to test the proposed framework. A metamodel of the process is built using proper orthogonal decomposition and radial basis function interpolation. The model is extended with a deviation model in order to account for the difference between model and real process. Particle filtering is used to track the state evolution and to estimate the deviation model parameters simultaneously. The approach is tested and analysed using a large number of simulations, based on pseudo-data obtained from a numerical sheet bending model.

    AB - Modern production systems have numerous sensors that produce large amounts of data. This data can be exploited in many ways, from providing insight into the manufacturing process to facilitating automated decision making. These opportunities are still underexploited in the metal forming industry, due to the complexity of these processes. In this work, a probabilistic framework is proposed for simultaneous model improvement and state estimation in metal forming mass production. Recursive Bayesian estimation is used to simultaneously track the evolution of process state and to estimate the deviation between the physics-based model and the real process. A sheet bending mass production process is used to test the proposed framework. A metamodel of the process is built using proper orthogonal decomposition and radial basis function interpolation. The model is extended with a deviation model in order to account for the difference between model and real process. Particle filtering is used to track the state evolution and to estimate the deviation model parameters simultaneously. The approach is tested and analysed using a large number of simulations, based on pseudo-data obtained from a numerical sheet bending model.

    KW - UT-Hybrid-D

    U2 - 10.1007/s12289-019-01495-2

    DO - 10.1007/s12289-019-01495-2

    M3 - Article

    SP - 1

    EP - 11

    JO - International journal of material forming

    JF - International journal of material forming

    SN - 1960-6206

    ER -