A bi-objective optimization approach to reducing uncertainty in pipeline erosion predictions

被引:4
|
作者
Dai, Wei [1 ]
Cremaschi, Selen [1 ]
Subramani, Hariprasad J. [2 ]
Gao, Haijing [2 ]
机构
[1] Auburn Univ, Dept Chem Engn, Auburn, AL 36849 USA
[2] Chevron Energy Technol Co, Houston, TX USA
关键词
epsilon-constrained approach; Bayesian optimization; Gaussian process modeling; Erosion-rate model discrepancy; BAYESIAN-INFERENCE; PARTICLE EROSION; MODEL; QUANTIFICATION; VALIDATION;
D O I
10.1016/j.compchemeng.2019.05.021
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Confidence in erosion model predictions is crucial for their effective use in design and operation of pipelines in upstream oil and gas industry. Accurate and precise estimates of the model discrepancy would increase the confidence in these predictions. We developed a Gaussian process (GP) model based framework to estimate erosion model discrepancy and its confidence interval. GP modeling, as a kernel-based approach, relies on the proper selection of hyperparameters. They are generally determined using the maximum marginal likelihood. Here, we present a bi-objective optimization approach, which uses minimization of mean squared error (MSE) and prediction variance (VAR) for training GP models. For this application, GP models trained using bi-objective optimization yielded lower MSE and VAR values than the ones trained using the maximum marginal likelihood. This paper is an extended version of a conference paper (Wei et al., 2018) presented at the 13th International Symposium on Process Systems Engineering. (C) 2019 Elsevier Ltd. All rights reserved.
引用
收藏
页码:175 / 185
页数:11
相关论文
共 50 条
  • [41] On efficiency of a single variable bi-objective optimization algorithm
    James M. Calvin
    Antanas Žilinskas
    Optimization Letters, 2020, 14 : 259 - 267
  • [42] On efficiency of a single variable bi-objective optimization algorithm
    Calvin, James M.
    Zilinskas, Antanas
    OPTIMIZATION LETTERS, 2020, 14 (01) : 259 - 267
  • [43] A model of anytime algorithm performance for bi-objective optimization
    Jesus, Alexandre D.
    Paquete, Luis
    Liefooghe, Arnaud
    JOURNAL OF GLOBAL OPTIMIZATION, 2021, 79 (02) : 329 - 350
  • [44] Bi-objective optimization for the container terminal integrated planning
    Liu, Ming
    Lee, Chung-Yee
    Zhang, Zizhen
    Chu, Chengbin
    TRANSPORTATION RESEARCH PART B-METHODOLOGICAL, 2016, 93 : 720 - 749
  • [45] TOTAL UNIMODULARITY APPLICATIONS IN BI-OBJECTIVE DISCRETE OPTIMIZATION
    KOUVELIS, P
    CARLSON, RC
    OPERATIONS RESEARCH LETTERS, 1992, 11 (01) : 61 - 65
  • [46] A Bi-objective Optimization Model for Interactive Face Retrieval
    Fang, Yuchun
    Cai, Qiyun
    Luo, Jie
    Dai, Wang
    Lou, Chengsheng
    ADVANCES IN MULTIMEDIA MODELING, PT II, 2011, 6524 : 393 - 400
  • [47] Bi-Objective Optimization for Indonesian Container Terminal Planning
    Rhomadona, Rizka
    Komarudin
    Hidayatno, Akhmad
    2017 2ND IEEE INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION ENGINEERING (ICITE), 2017, : 164 - 168
  • [48] Bi-objective optimization design of functionally gradient materials
    Huang, JH
    Fadel, GM
    Blouin, VY
    Grujicic, M
    MATERIALS & DESIGN, 2002, 23 (07) : 657 - 666
  • [49] A Branching Strategy for Exploring the Objective Space in Bi-objective Optimization Problems
    Hashem, Ihab
    De Buck, Viviane
    Seghers, Seppe
    Van Impe, Jan
    IFAC PAPERSONLINE, 2022, 55 (07): : 364 - 369
  • [50] Balancing and bi-objective optimization of robotic assemble lines
    Zhou B.-H.
    Wu Q.
    Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition), 2021, 51 (02): : 720 - 727