Article
Computer Science, Interdisciplinary Applications
Zhendong Guo, Qineng Wang, Liming Song, Jun Li
Summary: The study introduces a new infill criterion called Filter-GEI for addressing sample assignment issue in multi-fidelity optimization. By considering correlations between HF and LF models and adding an adaptive filter function on top of the GEI acquisition function, Filter-GEI efficiently allocates HF and LF samples to achieve a good balance between local and global search, with further improvement in efficiency through infilling multiple HF and LF samples in each iteration along with parallel computing. Tests on mathematical toy problems and an engineering problem demonstrate the effectiveness of the proposed algorithm.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2021)
Article
Computer Science, Interdisciplinary Applications
Leshi Shu, Ping Jiang, Yan Wang
Summary: This work proposes a multi-fidelity Bayesian optimization approach that utilizes hierarchical Kriging to reduce optimization costs, quantifies the impact of high and low-fidelity samples based on expected further improvement, and introduces a novel acquisition function to determine the location and fidelity level of the next sample simultaneously. The proposed approach is compared with state-of-the-art methods for multi-fidelity global optimization and shows that it can achieve global optimal solutions with reduced computational costs.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2021)
Article
Computer Science, Interdisciplinary Applications
Youwei He, Jinju Sun, Peng Song, Xuesong Wang
Summary: This paper presents two variable-fidelity hypervolume-based expected improvement criteria for adaptive selection of LF/HF samples in the multi-objective EGO method. The proposed methods are demonstrated to be effective and efficient in engineering examples, outperforming other methods with higher efficiency.
ENGINEERING WITH COMPUTERS
(2022)
Article
Computer Science, Interdisciplinary Applications
Haizhou Yang, Seong Hyeong Hong, Yi Wang
Summary: This paper presents a novel computation-aware multi-fidelity surrogate-based optimization methodology and a new sequential and adaptive sampling strategy based on expected improvement reduction. It improves the exploration and convergence rate of the optimization process under a fixed computational budget.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2022)
Article
Computer Science, Interdisciplinary Applications
Hanyan Huang, Zecong Liu, Hongyu Zheng, Xiaoyu Xu, Yanhui Duan
Summary: This paper proposes a Co-kriging-based multi-fidelity sequential optimization method named proportional expected improvement (PEI), which aims to be more efficient for global optimization and to evaluate the costs and benefits of candidate points from different levels of fidelity more reasonably. Experiments show that the proposed method can better search for the global optimum, and the KL divergence can more significantly describe the relationship between high and low fidelity.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2023)
Article
Engineering, Aerospace
Youwei He, Jinju Sun, Peng Song, Xuesong Wang
Summary: The paper proposes a strategy to deal with simulation failures in variable-fidelity surrogate-based sequential optimization method, and develops new infill criteria to ensure the effectiveness and efficiency of the method.
AEROSPACE SCIENCE AND TECHNOLOGY
(2021)
Article
Engineering, Aerospace
Remy Charayron, Thierry Lefebvre, Nathalie Bartoli, Joseph Morlier
Summary: This paper proposes a multi-fidelity Bayesian optimization method for solving multi-objective problems. By combining multiple fidelity levels and objectives, this method efficiently explores the solution space and identifies the set of Pareto-optimal solutions.
AEROSPACE SCIENCE AND TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Jie Liu, Huachao Dong, Peng Wang
Summary: A new Multi-Fidelity Global Optimization algorithm MFGO is proposed in this paper, using a data-mining strategy to improve optimization efficiency and achieve a balance between exploitation and exploration on the HF surrogate model. Three versions of MFGO were verified to show superior computational efficiency and robustness compared to five well-known methods on benchmark cases and an engineering problem.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Agronomy
Yaohui Li, Junjun Shi, Hui Cen, Jingfang Shen, Yanpu Chao
Summary: The proposed method improves the GEI criterion into dual objectives and utilizes multi-objective PSO method to optimize these objectives, producing the Pareto frontier for updating the Kriging model. Test results show that this method outperforms other classical optimization methods in terms of convergence and accuracy.
AGRICULTURAL WATER MANAGEMENT
(2021)
Article
Computer Science, Information Systems
Rajitha Meka, Adel Alaeddini, Chinonso Ovuegbe, Pranav A. Bhounsule, Peyman Najafirad, Kai Yang
Summary: This study introduces a method called BREI for the global optimization of computer experiments, which adaptively adjusts the balance between exploration and exploitation, improving efficiency in low noise conditions. A multi-armed bandit strategy based on Thompson sampling is developed for adaptive optimization of the tuning parameter of BREI, and the proposed method's performance is validated through extensive simulation studies.
Article
Computer Science, Artificial Intelligence
Dawei Zhan, Yun Meng, Huanlai Xing
Summary: This study proposes a novel fast multipoint expected improvement (EI) criterion that is easier to implement and compute than the classical multipoint EI criterion. The proposed criterion uses only univariate normal cumulative distributions, resulting in significantly reduced computational time compared to the classical approach. Additionally, cooperative coevolutionary algorithms (CCEAs) are introduced to solve the inner optimization problem of the proposed criterion, leading to improved performance compared to standard evolutionary algorithms.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Interdisciplinary Applications
Youwei He, Jinju Sun, Peng Song, Xuesong Wang
Summary: The paper proposes a novel strategy to prevent the premature halt of the multi-objective efficient global optimization method by introducing an additional Kriging model to predict the success possibility of simulations. Experimental results suggest that this method consistently performs well on analytic and practical problems.
ENGINEERING WITH COMPUTERS
(2022)
Article
Engineering, Mechanical
Derbal Salh Eddine, Khalfallah Smail, Cerdoun Mahfoudh, Tarabet Lyes
Summary: This paper proposes a new strategy to improve the cost-effectiveness of multi-fidelity meta-model-based optimization. The strategy features the mutual adaptive refinement of high fidelity models (HFM) and low fidelity models (LFM) design of experiment sets, resulting in significant reduction in computation time while maintaining solution accuracy.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART E-JOURNAL OF PROCESS MECHANICAL ENGINEERING
(2023)
Article
Engineering, Civil
Cheng Chen, Yanlin Yang, Hetao Hou, Changle Peng, Weijie Xu
Summary: This study explores the use of Co-Kriging metamodeling for global response prediction under the presence of structural uncertainties in real-time hybrid simulation (RTHS). The results demonstrate that Co-Kriging can effectively reduce the number of RTHS tests in the laboratory and significantly improve metamodel accuracy for global prediction of structural response under uncertainties.
EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS
(2022)
Article
Computer Science, Interdisciplinary Applications
Long Wang, Theodore T. Allen, Michael A. Groeber
Summary: Methods based on Gaussian stochastic process models and expected improvement functions are promising for solving box-constrained expensive optimization problems. The proposed tabu EGO algorithm maintains a tabu list to avoid repeating past experimental points, resulting in improved computational performance. Comparative results show that tabu EGO offers promising convergence speed and solution quality for all types of black-box optimization.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2021)
Article
Chemistry, Multidisciplinary
Atthaphon Ariyarit, Masahiro Kanazaki
APPLIED SCIENCES-BASEL
(2017)
Article
Engineering, Aerospace
Yuki Kish, Shinya Kitazaki, Atthaphon Ariyarit, Yoshikazu Makino, Masahiro Kanazaki
AEROSPACE SCIENCE AND TECHNOLOGY
(2019)
Article
Multidisciplinary Sciences
Atthaphon Ariyarit, Tharathep Phiboon, Masahiro Kanazaki, Sujin Bureerat
Article
Computer Science, Information Systems
Vorapong Suppakitpaisarn, Atthaphon Ariyarit, Supanut Chaidee
Summary: The study introduces a method to automatically calculate suitable point positions for land-use optimization using semidefinite programming and gradient descent. Application to a practical case at Chiang Mai University shows that the proposed method is significantly faster than traditional algorithms, although it may result in slightly larger errors.
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
(2021)
Article
Engineering, Mechanical
Attasit Wiangkham, Atthaphon Ariyarit, Prasert Aengchuan
Summary: Artificial intelligence is increasingly used in materials testing for tasks such as new material design and predicting materials properties. In this particular study, artificial neural networks and adaptive neuro-fuzzy inference systems were used to predict fracture toughness of PMMA. The models showed high accuracy in predicting fracture toughness under different conditions, although there were slight discrepancies when compared to experimental values.
THEORETICAL AND APPLIED FRACTURE MECHANICS
(2021)
Article
Engineering, Mechanical
Tharathep Phiboon, Krittin Khankwa, Nutchanan Petcharat, Nattaphon Phoksombat, Masahiro Kanazaki, Yuki Kishi, Sujin Bureerat, Atthaphon Ariyarit
Summary: This study proposed a multi-fidelity surrogate model optimization method to solve the airfoil design problem by combining wind tunnel experiment and aerodynamic evaluation data. An RBF/Kriging hybrid multi-fidelity surrogate model and non-dominated sorting genetic algorithm II (NSGA-II) were used for optimization to minimize aerodynamic drag and maximize lift force, with the selected optimal airfoil shape having less than 10% error in aerodynamic lift and drag in wind tunnel testing.
JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY
(2021)
Article
Engineering, Mechanical
Attasit Wiangkham, Atthaphon Ariyarit, Prasert Aengchuan
Summary: This study created a model using artificial intelligence methods to predict the fracture toughness of sugarcane leaf composite materials. The Artificial Neural Network, Generalized Regression Neural Network, and Gaussian Process Regression models all showed good performance in predicting fracture toughness. Despite some decline in performance with changing predictive factors, the models remained within an acceptable range.
THEORETICAL AND APPLIED FRACTURE MECHANICS
(2022)
Article
Multidisciplinary Sciences
Wisanupong Takian, Supakit Rooppakhun, Atthaphon Ariyarit, Sedthawatt Sucharitpwatskul
Summary: This research proposes an optimal conformity design for the symmetric polyethylene tibial insert component in total knee arthroplasty, using Latin Hypercube Sampling and finite element analysis. By combining these methods, the study was able to predict wear volume and determine the best design to minimize wear in total knee replacement surgery.
Article
Energy & Fuels
Chalita Kaewbuddee, Somkiat Maithomklang, Prasert Aengchuan, Attasit Wiangkham, Niti Klinkaew, Atthaphon Ariyarit, Ekarong Sukjit
Summary: The study aims to investigate and compare the effects of blending waste plastic oil with n-butanol on diesel engines and exhaust gas emissions. The experimental results showed that the addition of n-butanol to waste plastic oil reduced engine efficiency and increased hydrocarbon and carbon monoxide emissions. An optimization process using a general regression neural network (GRNN) was conducted to find the suitable ratio of n-butanol blends, taking engine load and blend ratio as input factors and engine performance and emissions as output factors. The results showed high predictive performances of the optimization model. Rating: 8/10
Article
Chemistry, Physical
Attasit Wiangkham, Prasert Aengchuan, Rattanaporn Kasemsri, Auraluck Pichitkul, Suradet Tantrairatn, Atthaphon Ariyarit
Summary: Artificial intelligence plays a significant role in solving complex problems, including fracture mechanics. By combining experimental data with fracture criteria data, an artificial intelligence model was created, resulting in more accurate predictions compared to using only experimental data.
Article
Chemistry, Multidisciplinary
Attasit Wiangkham, Niti Klinkaew, Prasert Aengchuan, Pansa Liplap, Atthaphon Ariyarit, Ekarong Sukjit
Summary: This study investigates the impact of adding diethyl ether (DEE) to pyrolysis oil derived from mixed plastic waste on engine performance, combustion characteristics, and emissions. The addition of DEE resulted in decreased fuel properties and NOx emissions, while engine performance declined at low engine loads but improved at high engine loads with increasing DEE concentration. The NSGA-II algorithm with GRNNs model accurately predicted the optimal DEE percentage for maximizing engine efficiency and minimizing emissions.
Article
Materials Science, Multidisciplinary
Nutchanan Petcharat, Attasit Wiangkham, Auraluck Pichitkul, Suradet Tantrairatn, Prasert Aengchuan, Sujin Bureerat, Suwatjanee Banpap, Piyanat Khunthongplatprasert, Atthaphon Ariyarit
Summary: Composite materials play a crucial role in modern engineering, reducing weight while maintaining structural strength. 3D printing allows for the fabrication of complex composite parts with customizable mechanical properties. To improve efficiency and reduce experimental waste, this study proposes an optimization-based technique to determine the optimal 3D printing material proportions.
MATERIALS TODAY COMMUNICATIONS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Atthaphon Ariyarit, Patipan Katasila, Teerapat Srinaem, Worapong Sukkhanthong
PROCEEDINGS OF 2020 IEEE 11TH INTERNATIONAL CONFERENCE ON MECHANICAL AND INTELLIGENT MANUFACTURING TECHNOLOGIES (ICMIMT 2020)
(2020)
Article
Multidisciplinary Sciences
Atthaphon Ariyarit, Masahiro Kanazaki, Sujin Bureerat