Article
Computer Science, Information Systems
Jingliang Lin, Haiyan Li, Yunbao Huang, Junjie Liang, Sheng Zhou, Zeying Huang, Guiming Liang
Summary: This paper proposes a multi-objective surrogate modeling (MSM) method based on closed-loop transfer learning to address the challenges in simulation and optimization methods for forklift design. The MSM method improves the stability and accuracy of the surrogate model by pre-training a deep neural network model and transferring it with measurement data. Experimental results demonstrate the superiority of the MSM method and its valuable reference for simulation optimization of complex electromechanical products.
Article
Engineering, Aerospace
Quan Lin, Jiexiang Hu, Qi Zhou
Summary: This paper proposes two parallel multi-objective Bayesian optimization (MOBO) approaches based on multi-fidelity surrogate modeling to improve the optimization efficiency. The approaches utilize cheap auxiliary low-fidelity data for better performance. The modified hypervolume expected improvement function is used to determine the updating points and fidelity levels, and two parallel computing strategies are developed for multi-point sampling. Additionally, a constraint handling strategy is introduced for constrained problems. The proposed approaches are validated through numerical benchmark examples and real-world applications, showing significant improvements in terms of efficiency and overall performance compared to state-of-the-art MOBO methods.
AEROSPACE SCIENCE AND TECHNOLOGY
(2023)
Article
Water Resources
Ali A. Besalatpour, Mohsen Pourreza-Bilondi, Amirhosein Aghakhani Afshar
Summary: The calibration process for hydrological models is crucial and this study used parallel processing to speed up calculations and reduce running time, resulting in significantly reduced computational time for parameter calibration. A 4-objective function strategy provided an efficient tool to decide the best simulation based on the investigated objective functions, with potential application in hydrological and water quality models worldwide.
APPLIED WATER SCIENCE
(2023)
Article
Engineering, Mechanical
Alberto Gabrielli, Mattia Battarra, Emiliano Mucchi, Giorgio Dalpiaz
Summary: This paper proposes a procedure to estimate the unknown values of a lumped parameter model of a defective rolling element bearing using a multi-objective optimization technique. The procedure minimizes global indicators that measure the discrepancy between signal features computed from a numerical model and experimental data. The estimated values show good agreement with experimental results under various test conditions.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Artur Leandro da Costa Oliveira, Andre Britto, Rene Gusmao
Summary: This study aims to propose a framework that combines an inverse modeling approach with multi-objective evolutionary algorithms to enhance the capability of solving many-objective optimization problems. The results show that the proposed framework outperforms or performs equally well as traditional methods in various scenarios, including benchmark problems and real-world problems.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Yi Zhao, Jianchao Zeng, Ying Tan
Summary: The proposed method combines reference vector guided evolutionary algorithm and radial basis function networks to optimize individuals and introduces an infill strategy, showing competitive performance in solving computationally expensive many-objective optimization problems.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Qinghua Gu, Qian Wang, Xuexian Li, Xinhong Li
Summary: A new algorithm, RFMOPSO, is proposed in this paper to optimize constrained combinatorial optimization problems by combining multi-objective particle swarm optimization with a random forest model. Adaptive ranking strategy and novel rule are employed to improve search speed and adaptively update particle states for better objective balance and feasible solutions. Experimental results show promising performance on benchmark problems with discrete variables varying from 10 to 100.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Engineering, Multidisciplinary
Cheng-Wei Fei, Huan Li, Cheng Lu, Lei Han, Behrooz Keshtegar, Osman Taylan
Summary: A synchronous modeling concept is proposed to improve the computational cost and accuracy for the multi-objective reliability design of complex structures. The Vectorial Surrogate Modeling (VSM) method is developed for synchronously establishing an overall model with multiple objectives. The VSM method shows superior performances in computational efficiency and accuracy for high-dimensional nonlinear problems.
APPLIED MATHEMATICAL MODELLING
(2022)
Article
Environmental Sciences
Ruochen Sun, Qingyun Duan, Xueli Huo
Summary: Parameter optimization is crucial for accurate environmental model simulations and predictions. The MO-ASMOGS method proposed in this study efficiently constructs a surrogate model of the original model by using both parameter and spatial grid sampling, significantly improving simulation results with only a small portion of total grid cells sampled for a given PFT.
WATER RESOURCES RESEARCH
(2021)
Article
Energy & Fuels
Jiawei Lu, Qiong Wang, Zhuxiu Zhang, Jihai Tang, Mifen Cui, Xian Chen, Qing Liu, Zhaoyang Fei, Xu Qiao
Summary: The study proposed an approach that incorporates surrogate modeling into multi-objective optimization, using RBF neural networks to construct surrogate models, adopting central composite design as a sampling strategy, and constructing surrogate models individually for different optimization objectives to improve prediction accuracy. The multi-objective bat algorithm was used to obtain the Pareto front in the design of dividing wall column and side-reactor column configuration, successfully achieving design options that balance capital and operating costs.
CHEMICAL ENGINEERING AND PROCESSING-PROCESS INTENSIFICATION
(2021)
Article
Computer Science, Artificial Intelligence
Junfeng Tang, Handing Wang, Lin Xiong
Summary: In preference-based multi-objective optimization, knee solutions are the implicit preferred promising solutions. However, finding knee solutions is difficult and computationally expensive. To address this issue, we propose a surrogate-assisted evolutionary multi-objective optimization algorithm that uses surrogate models to replace expensive evaluations. Experimental results show that our proposed algorithm outperforms state-of-the-art knee identification evolutionary algorithms on most test problems within a limited computational budget.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Interdisciplinary Applications
Qi Zhou, Jinhong Wu, Tao Xue, Peng Jin
Summary: The paper introduces a two-stage adaptive multi-fidelity surrogate model-assisted multi-objective genetic algorithm (AMFS-MOGA), which involves obtaining a preliminary Pareto frontier using low-fidelity model data in the first stage and constructing an initial MFS model based on samples selected from the preliminary Pareto set in the second stage. The fitness values of individuals are evaluated using the MFS model, which is adaptively updated according to prediction uncertainty and population diversity. The effectiveness of the proposed approach is demonstrated through benchmark tests and design optimization, showing comparable results to traditional methods while significantly reducing computational costs.
ENGINEERING WITH COMPUTERS
(2021)
Article
Computer Science, Interdisciplinary Applications
Ruochen Sun, Qingyun Duan, Xiyezi Mao
Summary: Many multi-objective optimization problems in integrated environmental modeling and management involve complex constraints and different types of decision variables. This study presents an algorithm called MO-ASMOCH that can effectively solve these hybrid problems by using fewer model evaluations and achieving high-quality solutions.
ENVIRONMENTAL MODELLING & SOFTWARE
(2022)
Article
Thermodynamics
Hongwei Li, Boshi Xu, Guolong Lu, Changhe Du, Na Huang
Summary: This paper presents a fast and systematic optimization approach for PEMFC by combining variance analysis, surrogate models, and NSGA-II. By optimizing power density, system efficiency, and oxygen distribution uniformity simultaneously, the study demonstrates the success of this method in solving time-consuming multi-optimization problems efficiently.
ENERGY CONVERSION AND MANAGEMENT
(2021)
Article
Engineering, Industrial
Cheng Lu, Da Teng, Jun -Yu Chen, Cheng-Wei Fei, Behrooz Keshtegar
Summary: In this paper, the concept of vectorial modeling is proposed by introducing matrix theory into the point modeling concept. An adaptive vectorial surrogate modeling framework (AVSMF) is developed based on this concept and adaptive modeling strategy. The effectiveness of AVSMF is demonstrated through three examples and comparison with other methods, showing its advantages in computational efficiency and precision.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Review
Engineering, Civil
Xiaomeng Song, Jianyun Zhang, Chesheng Zhan, Yunqing Xuan, Ming Ye, Chonggang Xu
JOURNAL OF HYDROLOGY
(2015)
Article
Meteorology & Atmospheric Sciences
Guoqing Wang, Jianyun Zhang, Thomas C. Pagano, Yueping Xu, Zhenxin Bao, Yanli Liu, Junliang Jin, Cuishan Liu, Xiaomeng Song, Sicheng Wan
THEORETICAL AND APPLIED CLIMATOLOGY
(2016)
Article
Environmental Sciences
Guoqing Wang, Jianyun Zhang, Junliang Jin, Josh Weinberg, Zhenxin Bao, Cuishan Liu, Yanli Liu, Xiaolin Yan, Xiaomeng Song, Ran Zhai
MITIGATION AND ADAPTATION STRATEGIES FOR GLOBAL CHANGE
(2017)
Article
Environmental Sciences
Kui Zhu, Zibo Xie, Yong Zhao, Fan Lu, Xinyi Song, Lu Li, Xiaomeng Song
Article
Engineering, Environmental
Chesheng Zhan, Rongrong Zhang, Xiaomeng Song, Baolin Liu
FRONTIERS OF ENVIRONMENTAL SCIENCE & ENGINEERING
(2015)
Article
Engineering, Environmental
Rongrong Zhang, Chesheng Zhan, Xiaomeng Song, Baolin Liu
FRONTIERS OF ENVIRONMENTAL SCIENCE & ENGINEERING
(2015)
Article
Meteorology & Atmospheric Sciences
Xiaomeng Song, Jianyun Zhang, Chunhua Zhang, Xianju Zou
ADVANCES IN METEOROLOGY
(2019)
Article
Meteorology & Atmospheric Sciences
Xiaomeng Song, Jianyun Zhang, Xianju Zou, Chunhua Zhang, Amir AghaKouchak, Fanzhe Kong
ATMOSPHERIC RESEARCH
(2019)
Article
Environmental Sciences
Xiaomeng Song, Xianju Zou, Chunhua Zhang, Jianyun Zhang, Fanzhe Kong
Article
Meteorology & Atmospheric Sciences
Xiaomeng Song, Chunhua Zhang, Jianyun Zhang, Xianju Zou, Yuchen Mo, Yimin Tian
THEORETICAL AND APPLIED CLIMATOLOGY
(2020)
Article
Meteorology & Atmospheric Sciences
Xiaomeng Song, Xianju Zou, Yuchen Mo, Jianyun Zhang, Chunhua Zhang, Yimin Tian
ATMOSPHERIC RESEARCH
(2020)
Article
Environmental Sciences
Xiaomeng Song, Yuchen Mo, Yunqing Xuan, Quan J. Wang, Wenyan Wu, Jianyun Zhang, Xianju Zou
Summary: The study shows distinct trends in precipitation over the past six decades in the greater Beijing-Tianjin-Hebei metropolitan region, with urbanization having a positive contribution to precipitation changes, particularly in autumn.
ENVIRONMENTAL RESEARCH LETTERS
(2021)
Article
Environmental Sciences
Yimin Tian, Yanqing Yang, Zhenxin Bao, Xiaomeng Song, Guoqing Wang, Cuishan Liu, Houfa Wu, Yuchen Mo
Summary: The long-term overexploitation of groundwater has led to significant changes in the runoff process of the hydrological cycle in the North China Plain. Evaluating the impact of groundwater overdraft on runoff generation is the focus of this study. A hydrological modeling framework based on the VIC model was proposed, and its parameters were calibrated using a combination of runoff, evaporation, and water storage. The VIC model showed good applicability and the calibrated optimal parameter revealed a close relationship with groundwater table and water storage levels.
Article
Environmental Sciences
Xiaomeng Song, Jiachen Qi, Xianju Zou, Jianyun Zhang, Cuishan Liu
Summary: Rapid urbanization has a significant impact on extreme precipitation in the Pearl River Delta region, leading to more frequent, intense, and higher amount of extreme precipitation in urban areas, especially in highly urbanized regions. Urbanization level plays a major role in temporal changes of precipitation extremes, while showing little effect on the spatial patterns of extreme precipitation.
Article
Green & Sustainable Science & Technology
Ying Zhang, Xiaomeng Song, Xiaojun Wang, Zhifeng Jin, Feng Chen
Summary: Water resources are essential for the ecological environment, social economy, and human survival. Water resource carrying capacity (WRCC) is an important indicator of sustainable development and has been used to assess the capacity of water resources to support development. This study investigated the WRCC in Xuzhou City from 2012 to 2020 and projected scenarios for 2025 and 2030. The results showed a decline in WRCC in 2019 but an overall improvement from 2012 to 2020. However, the projected assessment indicates continued pressure on water resources sustainable development in the future. Various measures, such as industrial restructuring and water conservation, should be implemented to enhance the carrying capacity of water resources and ensure sustainable regional development.