An online-offline prognosis model for fatigue life prediction under biaxial cyclic loading with overloads

Guoyi Li, Siddhant Datta, Aditi Chattopadhyay, Nagaraja Iyyer, Nam Phan

    Research output: Contribution to journalArticle

    Abstract

    This paper presents a robust online-offline model for the prediction of crack propagation under complex in-phase biaxial fatigue loading in the presence of overloads of different magnitudes. The online prognosis model comprises a combination of finite element analysis and data-driven regression to predict the crack propagation under constant loading, while the offline model is trained using experimental data to inform the post-overload crack growth retardation behavior to the online model. The developed methodology is validated by conducting biaxial fatigue experiments using aluminum AA7075-T651 alloy cruciform specimens. A close correlation is observed between the experimental results and model predictions. The results show that the model successfully predicts the crack retardation behavior under the influence of overloads with different magnitudes occurring at different stages of fatigue crack growth. Error analysis is conducted to investigate the sensitivities of the number of training points and crack increments to the prediction accuracy. In addition, the error propagation with respect to the crack length is studied, which provides constructive suggestions for further model improvement.

    Original languageEnglish (US)
    JournalFatigue and Fracture of Engineering Materials and Structures
    DOIs
    StatePublished - Jan 1 2019

    Fingerprint

    Fatigue of materials
    Crack propagation
    Cracks
    Fatigue crack propagation
    Aluminum
    Error analysis
    Finite element method
    Experiments

    Keywords

    • biaxial fatigue
    • crack propagation
    • Gaussian process machine learning
    • online-offline model
    • overload
    • prognosis

    ASJC Scopus subject areas

    • Materials Science(all)
    • Mechanics of Materials
    • Mechanical Engineering

    Cite this

    An online-offline prognosis model for fatigue life prediction under biaxial cyclic loading with overloads. / Li, Guoyi; Datta, Siddhant; Chattopadhyay, Aditi; Iyyer, Nagaraja; Phan, Nam.

    In: Fatigue and Fracture of Engineering Materials and Structures, 01.01.2019.

    Research output: Contribution to journalArticle

    @article{90eec12034b446e5b2944d1c0e328a3b,
    title = "An online-offline prognosis model for fatigue life prediction under biaxial cyclic loading with overloads",
    abstract = "This paper presents a robust online-offline model for the prediction of crack propagation under complex in-phase biaxial fatigue loading in the presence of overloads of different magnitudes. The online prognosis model comprises a combination of finite element analysis and data-driven regression to predict the crack propagation under constant loading, while the offline model is trained using experimental data to inform the post-overload crack growth retardation behavior to the online model. The developed methodology is validated by conducting biaxial fatigue experiments using aluminum AA7075-T651 alloy cruciform specimens. A close correlation is observed between the experimental results and model predictions. The results show that the model successfully predicts the crack retardation behavior under the influence of overloads with different magnitudes occurring at different stages of fatigue crack growth. Error analysis is conducted to investigate the sensitivities of the number of training points and crack increments to the prediction accuracy. In addition, the error propagation with respect to the crack length is studied, which provides constructive suggestions for further model improvement.",
    keywords = "biaxial fatigue, crack propagation, Gaussian process machine learning, online-offline model, overload, prognosis",
    author = "Guoyi Li and Siddhant Datta and Aditi Chattopadhyay and Nagaraja Iyyer and Nam Phan",
    year = "2019",
    month = "1",
    day = "1",
    doi = "10.1111/ffe.12983",
    language = "English (US)",
    journal = "Fatigue and Fracture of Engineering Materials and Structures",
    issn = "8756-758X",
    publisher = "Wiley-Blackwell",

    }

    TY - JOUR

    T1 - An online-offline prognosis model for fatigue life prediction under biaxial cyclic loading with overloads

    AU - Li, Guoyi

    AU - Datta, Siddhant

    AU - Chattopadhyay, Aditi

    AU - Iyyer, Nagaraja

    AU - Phan, Nam

    PY - 2019/1/1

    Y1 - 2019/1/1

    N2 - This paper presents a robust online-offline model for the prediction of crack propagation under complex in-phase biaxial fatigue loading in the presence of overloads of different magnitudes. The online prognosis model comprises a combination of finite element analysis and data-driven regression to predict the crack propagation under constant loading, while the offline model is trained using experimental data to inform the post-overload crack growth retardation behavior to the online model. The developed methodology is validated by conducting biaxial fatigue experiments using aluminum AA7075-T651 alloy cruciform specimens. A close correlation is observed between the experimental results and model predictions. The results show that the model successfully predicts the crack retardation behavior under the influence of overloads with different magnitudes occurring at different stages of fatigue crack growth. Error analysis is conducted to investigate the sensitivities of the number of training points and crack increments to the prediction accuracy. In addition, the error propagation with respect to the crack length is studied, which provides constructive suggestions for further model improvement.

    AB - This paper presents a robust online-offline model for the prediction of crack propagation under complex in-phase biaxial fatigue loading in the presence of overloads of different magnitudes. The online prognosis model comprises a combination of finite element analysis and data-driven regression to predict the crack propagation under constant loading, while the offline model is trained using experimental data to inform the post-overload crack growth retardation behavior to the online model. The developed methodology is validated by conducting biaxial fatigue experiments using aluminum AA7075-T651 alloy cruciform specimens. A close correlation is observed between the experimental results and model predictions. The results show that the model successfully predicts the crack retardation behavior under the influence of overloads with different magnitudes occurring at different stages of fatigue crack growth. Error analysis is conducted to investigate the sensitivities of the number of training points and crack increments to the prediction accuracy. In addition, the error propagation with respect to the crack length is studied, which provides constructive suggestions for further model improvement.

    KW - biaxial fatigue

    KW - crack propagation

    KW - Gaussian process machine learning

    KW - online-offline model

    KW - overload

    KW - prognosis

    UR - http://www.scopus.com/inward/record.url?scp=85061508314&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85061508314&partnerID=8YFLogxK

    U2 - 10.1111/ffe.12983

    DO - 10.1111/ffe.12983

    M3 - Article

    JO - Fatigue and Fracture of Engineering Materials and Structures

    JF - Fatigue and Fracture of Engineering Materials and Structures

    SN - 8756-758X

    ER -