Physics-Based Gaussian Process Method for Predicting Average Product Lifetime in Design Stage

被引:6
作者
Wei, Xinpeng [1 ]
Han, Daoru [1 ]
Du, Xiaoping [2 ]
机构
[1] Missouri Univ Sci & Technol, Dept Mech & Aerosp Engn, 400 West 13th St, Rolla, MO 65409 USA
[2] Indiana Univ Purdue Univ, Dept Mech & Energy Engn, 723 W Michigan St, Indianapolis, IN 46202 USA
基金
美国国家科学基金会;
关键词
average lifetime; mean time to failure; Gaussian process model; adaptive training; supervised learning; machine learning for engineering applications; physics-based simulations; SYSTEM RELIABILITY-ANALYSIS; RESPONSE-SURFACE METHOD; LEARNING-FUNCTION; NEURAL-NETWORKS; OPTIMIZATION; MACHINE; MODEL;
D O I
10.1115/1.4049509
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The average lifetime or the mean time to failure (MTTF) of a product is an important metric to measure the product reliability. Current methods of evaluating the MTTF are mainly based on statistics or data. They need lifetime testing on a number of products to get the lifetime samples, which are then used to estimate the MTTF. The lifetime testing, however, is expensive in terms of both time and cost. The efficiency is also low because it cannot be effectively incorporated in the early design stage where many physics-based models are available. We propose to predict the MTTF in the design stage by means of a physics-based Gaussian process (GP) method. Since the physics-based models are usually computationally demanding, we face a problem with both big data (on the model input side) and small data (on the model output side). The proposed adaptive supervised training method with the Gaussian process regression can quickly predict the MTTF with a reduced number of physical model calls. The proposed method can enable continually improved design by changing design variables until reliability measures, including the MTTF, are satisfied. The effectiveness of the method is demonstrated by three examples.
引用
收藏
页数:9
相关论文
共 50 条
  • [41] Reliability-Based Geotechnical Design Method Using the Gaussian Process Regression-Based Differential Evolution Algorithm
    Wen, Kai
    Kuang, Zemin
    Zeng, Wei
    Zeng, Sanyou
    Qiu, Yue
    ADVANCES IN CIVIL ENGINEERING, 2024, 2024
  • [42] Research on lifetime degradation modeling and Gaussian stochastic process regression method for life prediction of photovoltaic modules
    Tang S.
    Song X.
    Li M.
    Yao S.
    Chen L.
    Sun Z.
    Taiyangneng Xuebao/Acta Energiae Solaris Sinica, 2022, 43 (12): : 41 - 49
  • [43] Extended physics-based wing mass estimation in early design stages applying automated model generation
    Dorbath, F.
    Nagel, B.
    Gollnick, V.
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART G-JOURNAL OF AEROSPACE ENGINEERING, 2014, 228 (07) : 1010 - 1019
  • [44] Online average-based system modelling method for batch process
    Cao, Zhixing
    Lu, Jingyi
    Zhang, Ridong
    Gao, Furong
    COMPUTERS & CHEMICAL ENGINEERING, 2018, 108 : 128 - 138
  • [45] Physics-informed sparse variational Gaussian process for predicting the wake flow field of underwater vehicles with limited data
    Zhao, Pu
    Xia, Linsheng
    Bian, Chao
    Ding, Jiaqi
    Wang, Xiaofang
    Liu, Haitao
    OCEAN ENGINEERING, 2024, 310
  • [46] Gaussian process regression-driven deep drawing blank design method
    Lee, Seungro
    Lim, Youngbin
    Galdos, Lander
    Lee, Taeyong
    Quagliato, Luca
    INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES, 2024, 265
  • [47] Physics-based simulation of electrochemical impedance spectroscopy of complex electrode microstructures using smoothed boundary method
    Qu, Danqi
    Malik, Affan
    Yu, Hui-Chia
    ELECTROCHIMICA ACTA, 2022, 432
  • [48] A diversity metric based on Gaussian process model for diverse and competitive design
    Zheng Li
    Heng Liu
    Gengdong Cheng
    Yiming Zhou
    Structural and Multidisciplinary Optimization, 2021, 64 : 2975 - 2997
  • [49] A method of implementing formalized multidisciplinary collaboration in product conceptual design process
    Yan, Xi-qiang
    Li, Yan
    Chen, Jian
    Li, Wen-qiang
    Xiong, Yan
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE, 2017, 231 (18) : 3342 - 3357
  • [50] An intelligent system based on concurrent engineering for innovative product design at the conceptual design stage
    Tseng, Kevin C.
    El-Ganzoury, Waleed
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2012, 63 (5-8) : 421 - 447