Review
Chemistry, Physical
Zhiming Feng, Jian Huang, Shan Jin, Guanqi Wang, Yi Chen
Summary: Proton exchange membrane fuel cells (PEMFCs) have promising properties for converting chemical energy into electrical energy, and artificial intelligence (AI) based multi-objective optimisation (AI-MOO) has been employed to support their design and applications. This review systematically summarizes the application of AI-MOO in the PEMFC field through literature survey and discusses the related research challenges and implications for future investigations.
JOURNAL OF POWER SOURCES
(2022)
Article
Computer Science, Artificial Intelligence
Abubakr Awad, George M. Coghill, Wei Pang
Summary: We proposed a novel Physarum-inspired competition algorithm (PCA) to solve discrete multi-objective optimization (DMOO) problems. Our algorithm is based on hexagonal cellular automata (CA) as a representation of problem search space and reaction-diffusion systems that control the Physarum motility. We have implemented a novel restart procedure to select the global Pareto frontier based on both personal experience and shared information. Extensive experimental and statistical analyses were conducted to assess the performance of our PCA against other evolutionary algorithms.
Article
Computer Science, Artificial Intelligence
Derya Deliktas, Ender Ozcan, Ozden Ustun, Orhan Torkul
Summary: The study introduces evolutionary algorithms to solve the bi-objective flexible job shop scheduling problem and compares their performance across various configurations. The transgenerational memetic algorithm using weighted sum method outperforms others and achieves the best-known results for almost all instances of bi-objective flexible job shop cell scheduling.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Information Systems
Yule Wang, Wanliang Wang, Ijaz Ahmad, Elsayed Tag-Eldin
Summary: This paper proposes a multi-objective quantum-inspired seagull optimization algorithm (MOQSOA) to optimize the convergence and distribution of solutions in multi-objective optimization problems. The algorithm utilizes opposite-based learning, seagull behavior simulation, and principles of quantum computing to enhance the performance of MOPs in terms of distribution and convergence.
Article
Biochemistry & Molecular Biology
Sohvi Luukkonen, Helle W. van den Maagdenberg, Michael T. M. Emmerich, Gerard J. P. van Westen
Summary: The factors determining a drug's success are diverse, making drug design a multi-objective optimisation problem. With the emergence of machine learning and optimisation methods, there has been a rapid increase in developments and applications in the field of multi-objective compound design. Population-based metaheuristics and deep reinforcement learning are commonly used methods, but conditional learning methods are gaining popularity. This article provides a brief overview of the field and the latest innovations.
CURRENT OPINION IN STRUCTURAL BIOLOGY
(2023)
Article
Engineering, Multidisciplinary
YingBo Xie, Ding Wang, JunFei Qiao
Summary: Wastewater treatment is vital for addressing water shortages and protecting the environment. This paper proposes a two-objective model and an intelligent optimal controller based on GD-MOEA/D to improve the efficiency of wastewater treatment by reducing energy consumption and ensuring effluent quality.
SCIENCE CHINA-TECHNOLOGICAL SCIENCES
(2022)
Article
Computer Science, Interdisciplinary Applications
Tom De Weer, Nicolas Lammens, Karl Meerbergen
Summary: Multi-scale topology optimization has the potential for increased mechanical performance and improved additive manufacturing capabilities. This work proposes a multi-objective framework to redefine the problem of optimal metamaterials and demonstrates the capability of accurately capturing every Pareto-optimal performance through a compromise space in a lattice unit cell.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2023)
Article
Engineering, Multidisciplinary
Noha Essam, Laila Khodeir, Fatma Fathy
Summary: Construction scheduling is a complex process that requires population-based optimization algorithms to reach optimal solutions. However, the efficiency of these algorithms degrades when optimizing more than three objectives, requiring trade-offs among conflicting objectives. Recent attempts have integrated Building Information Modelling (BIM) with Multi-Objective Optimization (MOO) algorithms to solve construction problems. This paper assesses the potential of combining information systems and optimization methods for better decision-making in construction and proposes recommendations for future research development.
AIN SHAMS ENGINEERING JOURNAL
(2023)
Article
Environmental Sciences
Mohammad Ehteram, Fatemeh Panahi, Ali Najah Ahmed, Yuk Feng Huang, Pavitra Kumar, Ahmed Elshafie
Summary: Evaporation is a crucial component in agriculture management and water engineering, and its prediction is essential for modeling researchers. In this study, the MLP model was used with three different multi-objective algorithms to predict daily evaporation at three stations in Malaysia. The results showed that the MLP-MOSSA model had the highest efficiency and accuracy compared to the other models.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Engineering, Industrial
M. Rivier, P. M. Congedo
Summary: This paper presents the SABBa method to address constrained multi-objective optimization problems under uncertainty, aiming to improve accuracy and reduce computational costs using bounding boxes and surrogate-assisting strategy. The method demonstrates good performance in several analytical test cases and is successfully applied to three engineering applications.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Engineering, Multidisciplinary
Zeou Hu, Kiarash Shaloudegi, Guojun Zhang, Yaoliang Yu
Summary: In this work, federated learning is formulated as multi-objective optimization and a new algorithm called FedMGDA+ is proposed, which guarantees fairness and robustness while maintaining individual performance for participating users.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Edgar Galvan, Fergal Stapleton
Summary: This study makes progress in neuroevolution for vehicle trajectory prediction by adopting rich artificial neural networks and two evolutionary multi-objective optimization algorithms. The underlying mechanisms and response to objective scaling of each algorithm are revealed. Additionally, certain objectives are found to be beneficial while others are detrimental to finding valid models.
APPLIED SOFT COMPUTING
(2023)
Article
Automation & Control Systems
Pengcheng Jiang, Yu Xue, Ferrante Neri
Summary: Dropout is an effective method for training deep neural networks by deactivating some neurons to mitigate overfitting. This paper proposes a novel approach to guide the dropout rate using an evolutionary algorithm, allowing for more flexibility in training. Experimental results demonstrate that this method consistently outperforms other dropout methods, including state-of-the-art techniques.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Rafal Szlapczynski, Joanna Szlapczynska
Summary: This paper proposes a method of incorporating decision maker preferences into multi-objective meta-heuristics, extending Pareto dominance. The results show that the proposed method outperforms other state-of-the-art multi-objective algorithms for selected benchmark problems.
SWARM AND EVOLUTIONARY COMPUTATION
(2021)
Article
Computer Science, Artificial Intelligence
Suyu Wang, Dengcheng Ma, Ze Ren, Yuanyuan Qu, Miao Wu
Summary: This paper proposes an adaptive multi-objective particle swarm optimization algorithm to improve the distribution and accuracy of the algorithm through optimizing the maintenance and update mechanism of the repository. The results of benchmark testing show that the proposed algorithm has better improvements in convergence and distribution, and has the best overall performance compared to other algorithms.
INTERNATIONAL JOURNAL OF BIO-INSPIRED COMPUTATION
(2022)
Article
Engineering, Environmental
Zainab Al Ani, Mohammed Thafseer, Ashish M. Gujarathi, G. Reza Vakili-Nezhaad
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2020)
Article
Engineering, Environmental
Debasish Tikadar, Ashish M. Gujarathi, Chandan Guria
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2020)
Article
Engineering, Environmental
Zainab Al Ani, Ashish M. Gujarathi, G. Reza Vakili-Nezhaad
Summary: The study focuses on minimizing CO2 emissions, energy consumption, and water content in the gas during the dehydration process of natural gas through multi-objective optimization. The process was simulated and validated using real plant data, and non-dominated sorting genetic algorithm was utilized to attain Pareto fronts for the decided MOO cases. Retrofitting the current process showed noticeable improvements and enhancements in the given process.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2021)
Article
Energy & Fuels
Mohammed Thafseer, Zainab Al Ani, Ashish M. Gujarathi, G. Reza Vakili-Nezhaad
Summary: This study optimized the acid gas removal process using NSGA-II and EMOO, considering economic and environmental objectives. Results showed that two-objective optimization performed better, but three-objective solutions would be more practical for industries operating around more than two objectives.
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING
(2021)
Article
Green & Sustainable Science & Technology
Debasish Tikadar, Ashish M. Gujarathi, Chandan Guria, Sulaiman Al Toobi
Summary: The study aimed to enhance the performance of the MDEA process plant through retrofitting the gas sweetening unit and subsequent multi-criteria optimization studies.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Energy & Fuels
Debasish Tikadar, Ashish M. Gujarathi, Chandan Guria
Summary: In this study, multi-objective optimization was conducted on the methyl di-ethanolamine-based industrial natural gas sweetening process using an improved multi-objective differential evolutionary algorithm to enhance plant performance. The involvement of conflicting objectives allowed for the successful optimization of environmental, process safety, and economic objectives, resulting in Pareto-optimal solutions. The most influential operating variables were found to be the temperature and pressure of the feed gas, flow rate of the feed gas, and temperature of the regenerator.
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING
(2021)
Article
Energy & Fuels
Mohammed Al-Aghbari, Ashish M. Gujarathi
Summary: This study successfully applies multi-objective differential evolution with hybrid local dynamic search algorithm and non-dominated sorting genetic algorithm in a real-world oil field model. The results show that the two algorithms generate different Pareto solutions in different ranges, and the best solutions can be selected using the net flow method.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Energy & Fuels
Mohammed Al-Aghbari, Ashish M. Gujarathi
Summary: The hybrid optimization method of using evolutionary neural network (EvoNN) and NSGA-II algorithms has been successfully applied in two case studies. The results show that the EvoNN guided NSGA-II algorithm outperforms the NSGA-II algorithm in terms of convergence, diversity, and optimal solutions. This hybrid approach has significant implications for decision-makers in managing production and injection in oil fields.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Engineering, Manufacturing
Ashish M. Gujarathi, Swaprabha P. Patel, Badria Al Siyabi
Summary: Lysine production via fermentation process is an economical method that involves conflicting objectives. Two multi-objective differential evolution algorithms, MODE-III and MODE-III-IMS, are used to optimize the control parameters of the lysine bioreactor. The yield and productivity objectives are studied, and the corresponding Pareto fronts are reported. Tournament selection and penalty constraint handling methods are compared for both algorithms. The higher bound of feeding rate (2.0 L/s) is found to be the most optimal. The MODE-III-IMS algorithm converges faster to the Pareto front. The COPRAS method is used for Pareto ranking, and the best optimal solution is reported using the decision tree method with acceptable accuracy.
MATERIALS AND MANUFACTURING PROCESSES
(2023)
Article
Engineering, Environmental
Debasish Tikadar, Ashish M. Gujarathi, Chandan Guria
Summary: Natural gas processing is facing challenges due to changes in oil prices and the development of alternative energy sources. Optimization of the processing unit is necessary to ensure profitability and environmental friendliness. The study focuses on optimizing the CO2 removal process in a natural gas treatment plant using the NSGA-II algorithm, considering factors such as payback period and damage index. The results show trade-offs between different objectives and demonstrate the effectiveness of lean vapor compression in achieving high H2S and CO2 removal rates.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2023)
Article
Energy & Fuels
Mohammed Al-Aghbari, Ashish M. Gujarathi
Summary: A new hybrid optimization approach utilizing the combination of bi-objective genetic programming (BioGP) algorithm and NSGA-II algorithm is proposed to improve diversity and convergence speed. The method is tested on benchmark and real oil-field models, demonstrating faster convergence speed and better diversity compared to NSGA-II alone. The optimal solutions achieved using BioGP guided NSGA-II algorithm have better diversity and faster convergence in comparison to NSGA-II.
GEOENERGY SCIENCE AND ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Ashish M. Gujarathi, Rashid Al-Hajri, Zainab Al-Ani, Mohammed Al-Abri, Nabeel Al-Rawahi
Summary: This study focuses on two ammonia synthesis processes, one using solar energy (green ammonia) and the other using natural gas (non-green ammonia). Multi-objective optimization is conducted to compare the two processes in terms of profit and CO2 emissions. The results show that the non-green process has higher profit but produces significant CO2 emissions.
Article
Engineering, Chemical
Ashish M. Gujarathi, Swaprabha P. Patel, Badria Al Siyabi
Summary: This study uses differential evolution (DE) algorithm and genetic algorithm (GA) to estimate kinetic parameters for lactic acid production from Arabic date juice. Different feeding approaches are used to obtain optimized parameters. The DE algorithm outperforms other algorithms in terms of performance.
DIGITAL CHEMICAL ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Mohammed Al-Aghbari, Majid Al-Wadhahi, Ashish M. Gujarathi
Summary: The study focuses on investigating different multi-objective functions for short-term and long-term waterflood management in the Brugge field benchmark model using the NSGA-II algorithm. For short-term management, three cases were studied, with Case-1 achieving the highest oil production and NPV. In long-term optimization (Case-4), NSGA-II algorithm showed higher NPV results compared to previous work, demonstrating convergence into different Pareto optimal solutions.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2022)
Article
Chemistry, Multidisciplinary
Zainab Al Ani, Ashish M. Gujarathi, G. Reza Vakili-Nezhaad, Talal Al Wahaibi
Summary: The study simulated a sulfuric acid plant and conducted multi-objective optimization, finding that air, steam, and water flow rates play a crucial role in reducing costs and emissions.
