Article
Computer Science, Hardware & Architecture
Chunyan Ling, Way Kuo, Min Xie
Summary: This study reviews the advantages and disadvantages of using surrogate models to streamline reliability-based design optimization (RBDO), as well as discussing the problems that need to be solved.
IEEE TRANSACTIONS ON RELIABILITY
(2023)
Article
Computer Science, Artificial Intelligence
Weixi Chen, Huachao Dong, Peng Wang, Xinjing Wang
Summary: Surrogate models are useful for studying system performance in engineering projects, but new projects often require constructing surrogate models from scratch, leading to unsatisfactory optimization results. To address this, a new surrogate-assisted global transfer optimization (SGTO) framework is proposed, which facilitates information transfer across projects and significantly reduces the computational burden. The framework consists of three stages: space division, adaptive samples estimation, and dynamic transfer allocation. Through experiments, the framework shows an average performance improvement of 12.8%.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Jolan Wauters, Ivo Couckuyt, Joris Degroote
Summary: This paper presents a novel scheme for reliability-based design optimization, utilizing surrogate-assisted asymptotic reliability analysis to obtain gradient and Hessian information. The sub-optimization problem is reformulated as a set of constraints using the Karush-Kuhn-Tucker conditions, leading to an efficient single-loop approach.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2021)
Article
Computer Science, Artificial Intelligence
Hao Chen, Weikun Li, Weicheng Cui
Summary: Fitness functions of real-world optimization problems often require expensive experiments or numerical simulations for analysis. Integrating these into optimization algorithms directly leads to high computational costs. Surrogate-assisted evolutionary algorithms (SAEAs) have gained attention for their high efficiency in solving real world optimization problems. However, with the increase in dimension, the computational cost of constructing surrogates increases and their prediction accuracy may degrade. This paper proposes a surrogate-assisted evolutionary algorithm with hierarchical surrogate technique and adaptive infill strategy (SAEA-HAS) to address these challenges. Experimental results validate the effectiveness of SAEA-HAS.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Interdisciplinary Applications
Tengfei Wang, Weihang Chen, Taifeng Li, David P. Connolly, Qiang Luo, Kaiwen Liu, Wensheng Zhang
Summary: This paper proposes a hybrid modeling framework to incorporate soil property uncertainty into embankment settlement calculations. The framework includes uncertainty modeling, finite element method, surrogate modeling, and probabilistic analysis. It uses a neural network with Monte Carlo dropout to correlate soil properties and predict post-construction settlements. The framework is validated through a case study and a cost-effective improved ground is designed using an exhaustive search approach.
COMPUTERS AND GEOTECHNICS
(2023)
Article
Physics, Multidisciplinary
Jeng-Shyang Pan, Li-Gang Zhang, Shu-Chuan Chu, Chin-Shiuh Shieh, Junzo Watada
Summary: This paper proposes an efficient surrogate-assisted hybrid meta-heuristic algorithm, SAGD, which combines the surrogate-assisted model with GOA and DE algorithms to solve the problem of long solution time for fitness function in high-complexity problems.
Article
Engineering, Civil
Debiao Meng, Tianwen Xie, Peng Wu, Chao He, Zhengguo Hu, Zhiyuan Lv
Summary: This study proposes a multidisciplinary design optimization strategy based on random and interval variables (UBMDO-RIV) to address the uncertainties in engineering systems, and introduces the classic decoupling strategy for UBMDO to reduce computational burden.
Article
Computer Science, Information Systems
Guodong Chen, Yong Li, Kai Zhang, Xiaoming Xue, Jian Wang, Qin Luo, Chuanjin Yao, Jun Yao
Summary: The study proposes a novel and efficient hierarchical surrogate-assisted differential evolution (EHSDE) algorithm for high-dimensional expensive optimization problems. By balancing exploration and exploitation using a hierarchical framework and utilizing global and local surrogate models to accelerate convergence speed, the algorithm demonstrates effectiveness and efficiency on benchmark functions and production optimization problems.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Jeng-Shyang Pan, Nengxian Liu, Shu-Chuan Chu, Taotao Lai
Summary: Surrogate-assisted evolutionary algorithms (SAEAs) combine the searching capabilities of evolutionary algorithms with the predictive capabilities of surrogate models, and an efficient SAHO algorithm integrates TLBO and DE algorithms, alternating between global exploration and local exploitation when better solutions cannot be found, with a new prescreening criterion selecting promising candidates for evaluations, and using a local RBF surrogate model to mimic the target function landscape.
INFORMATION SCIENCES
(2021)
Article
Energy & Fuels
Ruxin Zhang, Hongquan Chen
Summary: This paper proposes a multi-objective global and local surrogate-assisted particle swarm optimization (MO-GLSPSO) method for polymer flooding, aiming to balance the conflicting objectives of oil production and polymer injection. By using generalized regression neural network (GRNN) for global population prescreen and radial basis function (RBF) for local population search, optimal trade-off solutions are obtained. The MO-GLSPSO method adjusts the rates and concentration of wells to maximize cumulative oil production and minimize cumulative polymer injection. The method shows improved sweep efficiency, polymer utility, and a better pareto-front compared to other methods.
Article
Engineering, Aerospace
Mohammad Reza Setayandeh
Summary: The study utilizes the metamodeling concept to reduce costs in multidisciplinary design optimization, approximating the behavior of complex engineering systems using neural networks. The optimization results demonstrate a significant reduction in computational costs.
JOURNAL OF AEROSPACE ENGINEERING
(2021)
Article
Automation & Control Systems
Yue Gao, Junwei Wang, Shuang Gao, Yao Cheng
Summary: The article introduces an integrated robust design and robust control strategy for engineering systems, utilizing a genetic algorithm. This approach outperforms existing strategies in terms of system-level optimization and robustness.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Artificial Intelligence
Yi Zhao, Jian Zhao, Jianchao Zeng, Ying Tan
Summary: This paper proposes a two-stage infill strategy and surrogate-ensemble assisted optimization algorithm for solving expensive many-objective optimization problems. Experimental results demonstrate the superiority of this algorithm in solving computationally expensive many-objective optimization problems.
COMPLEX & INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jeng-Shyang Pan, Qingwei Liang, Shu-Chuan Chu, Kuo-Kun Tseng, Junzo Watada
Summary: This paper introduces a surrogate-assisted evolutionary algorithm (SACSO) for solving expensive optimization problems. SACSO combines different search strategies of global search, local search, and opposition-based search, and utilizes generalized surrogate model and elite surrogate model to enhance the optimal performance.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Ke Chen, Bing Xue, Mengjie Zhang, Fengyu Zhou
Summary: This article introduces a novel PSO-based feature selection approach that continuously improves population quality and performance through correlation-guided updating and surrogate technique. Experimental results demonstrate its outstanding performance in classification accuracy.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Article
Automation & Control Systems
Mehdi Moghadasian, Jafar Roshanian
OPTIMAL CONTROL APPLICATIONS & METHODS
(2018)
Article
Engineering, Aerospace
Mojtaba Alavipour, Amir A. Nikkhah, Jafar Roshanian
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART G-JOURNAL OF AEROSPACE ENGINEERING
(2018)
Article
Engineering, Mechanical
Jafar Roshanian, Ali A. Bataleblu, Masoud Ebrahimi
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE
(2018)
Article
Engineering, Electrical & Electronic
Jafar Roshanian, Shabnam Yazdani, Fahimeh Barzamini
IEEE SENSORS JOURNAL
(2018)
Article
Engineering, Aerospace
Foozieh Morovat, Ali Mozaffari, Jafar Roshanian, Hadi Zare
AEROSPACE SCIENCE AND TECHNOLOGY
(2019)
Article
Engineering, Marine
Farshad Somayehee, Amir Ali Nikkhah, Jafar Roshanian
JOURNAL OF NAVIGATION
(2019)
Article
Engineering, Aerospace
Mehdi Moghadasian, Jafar Roshanian
ADVANCES IN SPACE RESEARCH
(2019)
Article
Engineering, Aerospace
J. Roshanian, A. A. Bataleblu, M. Ebrahimi
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART G-JOURNAL OF AEROSPACE ENGINEERING
(2020)
Article
Engineering, Aerospace
Farshad Somayehee, Amir Ali Nikkhah, Jafar Roshanian, Sadegh Salahshoor
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
(2020)
Article
Computer Science, Artificial Intelligence
Arian Abedini, Ali Asghar Bataleblu, Jafar Roshanian
Summary: This paper introduces a novel concept of a hybrid drone called MICOPTER to address the challenges faced by delivery drones in reliably delivering packages. By comparing it to other UAVs and utilizing multi-objective optimization and control methods, the MICOPTER is optimized for flight performance and controllability. Results indicate the MICOPTER's capabilities as a novel configuration in terms of design performance and controllability.
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
(2022)
Proceedings Paper
Engineering, Electrical & Electronic
Arian Abedini, Ali Asghar Bataleblu, Jafar Roshanian
Summary: This study combines incremental control action with the backstepping design methodology to propose a robust nonlinear flight control strategy for a bi-copter drone. By gradually stabilizing or tracking the control variables of the nonlinear system, the proposed method reduces the dependency on the dynamic model and exhibits strong robustness in compensating for external disturbances.
2022 10TH RSI INTERNATIONAL CONFERENCE ON ROBOTICS AND MECHATRONICS (ICROM)
(2022)
Proceedings Paper
Engineering, Electrical & Electronic
Arian Abedini, Ali Asghar Bataleblu, Jafar Roshanian
Summary: This paper explores the position and attitude control of a Bi-copter drone, presents a robust controller design, and validates its performance on a circular flight path through simulation.
2021 9TH RSI INTERNATIONAL CONFERENCE ON ROBOTICS AND MECHATRONICS (ICROM)
(2021)
Proceedings Paper
Engineering, Aerospace
Fahimeh Barzamini, Shabnam Yazdani, Jafar Roshanian
FOURTH IAA CONFERENCE ON DYNAMICS AND CONTROL OF SPACE SYSTEMS 2018, PTS I-III
(2018)