Article
Engineering, Chemical
Xuezhi Zhao, Haoan Fan, Gaobo Lin, Zhecheng Fang, Wulong Yang, Mian Li, Jianghao Wang, Xiuyang Lu, Bolong Li, Ke-Jun Wu, Jie Fu
Summary: This study proposed an efficient optimization strategy based on computational fluid dynamics, machine learning, and the multi-objective genetic algorithm to predict and optimize the performance of a stirred tank. Single-factor analysis was conducted to study the effects of structural parameters on power consumption and mixing time. XGB coupled NSGA-II were utilized to further optimize the stirred tank geometries and maximize the integrated performance. The accuracy and reliability of the machine learning-based optimization method were confirmed.
Article
Chemistry, Physical
Ja-Ryoung Han, Jong Min Lee
Summary: This study proposes a multi-objective optimization approach to design a steam methane reforming (SMR) reactor and maximize the efficiency of the hydrogen production process. Only 50 iterations were performed, identifying three Pareto optimal designs with significant reactor size reductions and slight variations in process efficiency compared to the reference case. The results offer practical insights for planning on-site distributed hydrogen production systems and demonstrate the possibility of increasing overall process efficiency with a reduced reactor size.
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY
(2023)
Article
Chemistry, Physical
Mohammad Osat, Faryar Shojaati, Ali Hafizi
Summary: For the first time, a multi-objective optimization approach is used to optimize energy efficiency with other conflicting objectives for tri-reforming of methane. A 2-D axisymmetric model over nickel based catalysts is established to maximize the energy efficiency, syngas production and CO2 conversion. The attained results revealed different optimal conditions for maximizing H2/CO ratio and energy efficiency, CO2 conversion and energy efficiency, and CH4 conversion.
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY
(2023)
Article
Engineering, Marine
Hao Chen, Weikun Li, Weicheng Cui, Ping Yang, Linke Chen
Summary: In this paper, a multi-objective multidisciplinary design optimization (MMDO) strategy named IDF-DMOEOA is proposed for the conceptual design of a three-joint robotic fish system. By combining an efficient multidisciplinary design optimization approach and a novel multi-objective optimization algorithm, the optimized robotic fish shows better performance than the initial design.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Interdisciplinary Applications
Tom Savage, Nausheen Basha, Jonathan Mcdonough, Omar K. Matar, Ehecatl Antonio del Rio Chanona
Summary: This article presents a framework to solve the nonlinear, computationally expensive, and derivative-free problem of optimizing complex reactor geometries. The framework uses Gaussian processes to learn a multi-fidelity model of reactor simulations and explores the search space of reactor geometries through lower fidelity simulations.
COMPUTERS & CHEMICAL ENGINEERING
(2023)
Article
Computer Science, Interdisciplinary Applications
Trupen Parikh, Michael Mansour, Dominique Thevenin
Summary: This study uses multi-objective optimization to find the optimal geometry of pump inducers that can provide high performance over a wide range of flow rates. Computational fluid dynamics and a non-dominated sorting genetic algorithm are used to optimize the inducer parameters, taking into account different flow conditions. The results suggest that short blade length, low sweep angle, small tip clearance gap, and thin blade thickness are preferred for optimal performance in this application.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2022)
Article
Acoustics
Xun Sun, Ze Yang, Xuesong Wei, Yang Tao, Grzegorz Boczkaj, Joon Yong Yoon, Xiaoxu Xuan, Songying Chen
Summary: This study for the first time identifies optimal structures of the cavitation generation units of a representative advanced rotational hydrodynamic cavitation reactor by combining genetic algorithm and computational fluid dynamics, leading to significant improvements in vapor volume and rotor torque.
ULTRASONICS SONOCHEMISTRY
(2021)
Article
Engineering, Environmental
S. S. Hoseini, G. Najafi, B. Ghobadian, A. H. Akbarzadeh
Summary: This study investigates the importance of mixing in the chemical industry and proposes a computational framework for optimizing power consumption and impeller stress in stirred-tank reactors. By using Computational Fluid Dynamic (CFD) analysis, the study examines three types of impellers and utilizes Multi-objective Genetic Algorithm (MOGA) to optimize the geometrical parameters of the blades. The results show a decrease in power consumption with V- and U-shape impellers compared to the 6-blade Rushton turbine, and indicate differences in turbulent kinetic energy and stress distribution among different impeller designs.
CHEMICAL ENGINEERING JOURNAL
(2021)
Article
Materials Science, Ceramics
Kensaku Nakamura, Naoya Otani, Tetsuya Koike
Summary: The study focuses on the trade-off between target properties of optical glass, using the ParEGO algorithm to find suitable glass compositions and optimize research components. The results show that ParEGO can effectively find compositions with low target property values, and normalization is necessary for search performance.
CERAMICS INTERNATIONAL
(2021)
Article
Environmental Sciences
Sayonara Vanessa de Medeiros Lima, Natan Padoin, Cintia Soares
Summary: This study focused on the photochemical degradation of tetracycline in the innovative photoreactor FluHelik, using computational fluid dynamics (CFD) simulations to optimize operational conditions and enhance reactor performance at the laboratory scale.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2021)
Article
Computer Science, Interdisciplinary Applications
Tengfei Tang, Lei Lei, Li Xiao, Yili Peng, Hongjian Zhou
Summary: An optimization framework based on Optimized Latin Hypercube Sampling and Bayesian optimization is proposed for efficient design of throttle elements. The framework is validated through numerical cases and shows good performance in engineering problems, with computational fluid dynamics error less than 5% compared to experimental data.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2023)
Article
Engineering, Marine
Ashkan Rafiee, Max Haase, Andrew Malcolm
Summary: Simulation-based design is crucial for improving hull form designs in naval architecture. This paper proposes a low dimensional shape morphing tool and an efficient design framework for high-speed craft, demonstrating significant reduction in total resistance compared to baseline hulls.
Article
Engineering, Chemical
Yanyan Ding, Jun Wang, Boyan Jiang, Zhiang Li, Qianhao Xiao, Lanyong Wu, Bochao Xie
Summary: This study introduces a new blade design method and neural network to predict the aerodynamic performance of low-pressure axial flow fans. A non-dominated sorting genetic algorithm is used for global optimization. The simulation results show that the optimized fan performance and efficiency are improved.
Article
Energy & Fuels
Jaeheon Sim, Balaji Mohan, Jihad Badra
Summary: In this study, the piston bowl geometry and injector design of a light-duty GCI engine were co-optimized using computational fluid dynamics (CFD) and advanced machine learning (ML) techniques. The results showed that the design parameters of the piston bowl and injector had a significant impact on engine performance under different load conditions.
Article
Nuclear Science & Technology
Emilian Popov, Richard Archibald, Briana Hiscox, Vladimir Sobes
Summary: This paper describes the application of machine learning, specifically deep learning and Gaussian processes, in optimizing the design of complex nuclear engineering systems. The approach combines reduced-order modeling, simulation, and machine learning to minimize computational and physical costs. The method utilizes high-fidelity simulations and Gaussian processes to provide accurate predictions of optimal designs.
NUCLEAR ENGINEERING AND DESIGN
(2022)
Article
Engineering, Chemical
Tae Hoon Oh, Hyun Min Park, Jong Woo Kim, Jong Min Lee
Summary: This article proposes an integrated algorithm using double-deep Q-network and model predictive control to optimize substrate feeding strategy in a bioreactor. The study finds that the proposed method outperforms other methods and can learn with fewer data.
Article
Engineering, Environmental
Sunkyu Shin, Solji Choi, Jonggeol Na, Ikhwan Jung, Min-Kyu Kim, Myung-June Park, Won Bo Lee
Summary: The study indicates that circulation flow pattern in industrial-scale reactors can result in a broad molecular weight distribution and bimodality of polymers, highlighting the importance of controlling the flow pattern to produce polymers with desired properties.
CHEMICAL ENGINEERING JOURNAL
(2022)
Article
Engineering, Environmental
Minsu Kim, Sunghyun Cho, Kyojin Jang, Seokyoung Hong, Jonggeol Na, Il Moon
Summary: The aim of the study was to reduce NOx emissions from military weapon system waste incineration by finding optimal operating conditions under parameter uncertainties using a robust optimization framework. Implementing this framework led to a stable reduction in NOx emissions, despite uncertainties in waste particle conditions, with mean reduction of NOx production rate by 13.6-13.9% and variance reduced by 36.1-36.3% compared to nominal optimum conditions.
CHEMICAL ENGINEERING JOURNAL
(2022)
Article
Engineering, Chemical
Hye Ji Lee, Shinje Lee, Jong Min Lee
Summary: The proposed method improves trajectory tracking performance and reduces tracking error by applying online alignment, selecting multiple models, and adaptively applying future reference based on current batch measurements. Additionally, the method adaptively decides batch duration, leading to improved overall performance in industrial penicillin production.
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH
(2022)
Article
Polymer Science
Min Jun Song, Sung Hyun Ju, Sungkyu Kim, Seung Hwan Oh, Jong Min Lee
Summary: This research paper presents a hybrid modeling approach that combines mechanistic modeling and machine learning to predict the melt index (MI) of an industrial polymerization process. The results indicate that the proposed hybrid model has an increased prediction accuracy and generalizability for MI prediction in an industrial polymerization process.
JOURNAL OF APPLIED POLYMER SCIENCE
(2022)
Article
Automation & Control Systems
Sang Hwan Son, Jong Woo Kim, Tae Hoon Oh, Dong Hwi Jeong, Jong Min Lee
Summary: We propose an improved offset-free model predictive control framework that combines the advantages of model-based and data-driven control strategies by learning and utilizing the intrinsic model-plant mismatch map. The map is approximated using artificial neural network modeling and a supplementary disturbance variable is introduced to handle transient state information. The proposed scheme effectively improves the closed-loop reference tracking performance of the control system.
JOURNAL OF PROCESS CONTROL
(2022)
Article
Automation & Control Systems
Tae Hoon Oh, Jong Woo Kim, Sang Hwan Son, Dong Hwi Jeong, Jong Min Lee
Summary: This paper proposes a multi-strategy control scheme to reduce computational load and extend the feasible region of robust model predictive control. The scheme stabilizes the system under a subset of disturbances and automatically switches to another control strategy for the rest of the disturbances, keeping the state within a predetermined bounded set. The existence of this set is proven, and an efficient algorithm is proposed to generate it. The proposed controller maintains the recursive feasibility and stability of the original RMPC.
JOURNAL OF PROCESS CONTROL
(2022)
Article
Chemistry, Physical
Shinyoung Bae, Hwangho Lee, Junseop Shin, Hyun Sub Kim, Yeonsoo Kim, Do Heui Kim, Jong Min Lee
Summary: In this study, a machine learning model based on a decision tree was used to investigate the causal relationship between features of zeolite-based SCR catalysts and NOx removal efficiency at low temperatures. Several synthesis guidelines for catalysts with superior low-temperature NOx removal performance were extracted based on the model. Experimental validation showed that newly synthesized catalysts using the proposed rules exhibited excellent performance in removing NOx at low temperatures.
CHEMISTRY OF MATERIALS
(2022)
Article
Computer Science, Interdisciplinary Applications
Jong Woo Kim, Tae Hoon Oh, Sang Hwan Son, Jong Min Lee
Summary: The main objective of this study is to develop a model-based reinforcement learning framework called primal-dual differential dynamic programming (DDP) that can handle constrained dynamic optimization problems. This framework, incorporating a modified augmented Lagrangian, can handle general nonlinear constraints and consider the optimal feasible policy under state perturbations.
COMPUTERS & CHEMICAL ENGINEERING
(2022)
Article
Thermodynamics
Suk Hoon Choi, Dong Hwi Jeong, Jong Min Lee
Summary: In order to provide stable and affordable city gas, the open rack vaporizer (ORV) is being studied as a heat exchanger for vaporizing LNG using seawater. A physics-based surrogate model for the ORV system is developed in this study, which has high accuracy and low computational load compared to a CFD model. The model is optimized to achieve both profit and desired LNG outlet temperature, and it is found that the two objectives are incompatible and the LNG and seawater flowrates are inversely proportional.
APPLIED THERMAL ENGINEERING
(2023)
Article
Energy & Fuels
Minsu Kim, Areum Han, Jaewon Lee, Sunghyun Cho, Il Moon, Jonggeol Na
Summary: In modern chemical engineering, various derivative-free optimization (DFO) studies have been conducted to identify operating conditions for efficient operation of processes. The selection of DFO algorithms is crucial but nonintuitive due to uncertain performance. This study compares the performance of 12 algorithms in the early stage of optimization, and applies them to energy process optimization for hydrogen production, resulting in significant improvements in thermal efficiency.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2023)
Article
Green & Sustainable Science & Technology
Malik Sajawal Akhtar, Hafsa Khan, J. Jay Liu, Jonggeol Na
Summary: A social life cycle assessment (S-LCA) was conducted on green hydrogen production through water electrolysis powered by renewable energy in seven countries. The results indicate that South Africa poses the highest risk to social indicators, while other countries can reduce risk by manufacturing key equipment domestically. Compared to conventional hydrogen, green hydrogen performs poorly in various social indicators due to the complexity of the supply chain and outsourcing from countries with poor working conditions.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Thermodynamics
Dongju Kang, Doeun Kang, Sumin Hwangbo, Haider Niaz, Won Bo Lee, J. Jay Liu, Jonggeol Na
Summary: This article emphasizes the importance of energy management systems in utilizing renewable energy and solving complex problems. It proposes a method using deep reinforcement learning algorithm to achieve real-time optimal energy storage system planning. The performance comparison and action mapping results confirm the capability of deep reinforcement learning in handling uncertainty and large-scale problems.
Article
Chemistry, Physical
Dong Hyeon Mok, Daeun Shin, Jonggeol Na, Seoin Back
Summary: In recent years, the development of appropriate crystal representations for accurate prediction of inorganic crystal properties has been a crucial task to accelerate materials discovery. However, most existing models are designed for predicting properties of given structures, while predicting ground state structures using unrelaxed structures as inputs is more important for practical high-throughput virtual screening. To address this challenge, we propose a chemically inspired convolutional neural network, ESNet, which achieves the highest accuracy for predicting formation energy by utilizing density of states of unrelaxed initial structures as inputs.
JOURNAL OF MATERIALS CHEMISTRY A
(2023)
Article
Chemistry, Multidisciplinary
Suhyun Lee, Woong Choi, Jae Hyung Kim, Sohyeon Park, Yun Jeong Hwang, Jonggeol Na
Summary: This study evaluates the economic and environmental potential of direct electrochemical conversion of captured CO2 technology through techno-economic analysis and life cycle assessment. The results indicate that the technology has good economic potential if developed to the same level as the conventional CO2 reduction reaction process. Moreover, the environmental impact of the technology is positive, especially when using renewable electricity.
Article
Computer Science, Interdisciplinary Applications
Nohan Joemon, Melpakkam Pradeep, Lokesh K. Rajulapati, Raghunathan Rengaswamy
Summary: This paper introduces a smoothing-based approach for discovering partial differential equations from noisy measurements. The method is data-driven and improves performance by incorporating first principles knowledge. The effectiveness of the algorithm is demonstrated in a real system using a new benchmark metric.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Zhibin Lu, Yimeng Li, Chang He, Jingzheng Ren, Haoshui Yu, Bingjian Zhang, Qinglin Chen
Summary: This study proposes a new inverse design method using a physics-informed neural network to identify optimal heat sink designs. A hybrid PINN accurately approximates the governing equations of heat transfer processes, and a surrogate model is constructed for integration with optimization algorithms. The proposed method accelerates the search for Pareto-optimal designs and reduces search time. Comparing different scenarios facilitates real-time observation of multiphysics field changes, improving understanding of optimal designs.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Luca Gasparini, Antonio Benedetti, Giulia Marchese, Connor Gallagher, Pierantonio Facco, Massimiliano Barolo
Summary: In this paper, a method for batch process monitoring with limited historical data is investigated. The methodology utilizes machine learning algorithms to generate virtual data and combines it with real data to build a process monitoring model. Automatic procedures are developed to optimize parameters, and indicators and metrics are proposed to assist virtual data generation activities.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Julia Jimenez-Romero, Adisa Azapagic, Robin Smith
Summary: Energy transition is a significant and complex challenge for the industry, and developing cost-effective solutions for synthesizing utility systems is crucial. The research combines mathematical formulation with realistic configurations and conditions to represent utility systems and provides a basis for synthesizing energy-efficient utility systems for the future.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Samuel Adeyemo, Debangsu Bhattacharyya
Summary: This work develops algorithms for estimating sparse interpretable data-driven models. The algorithms select the optimal basis functions and estimate the model parameters using Bayesian inferencing. The algorithms estimate the noise characteristics and model parameters simultaneously. The algorithms also exploit prior analysis and special properties for efficient pruning, and use a modified Akaike information criterion for model selection.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Abbasali Jafari-Nodoushan, Mohammad Hossein Dehghani Sadrabadi, Maryam Nili, Ahmad Makui, Rouzbeh Ghousi
Summary: This study presents a three-objective model to design a forward supply chain network considering interrelated operational and disruptive risks. Several strategies are implemented to cope with these risks, and a joint pricing strategy is used to enhance the profitability of the supply chain. The results show that managing risks and uncertainties simultaneously can improve sustainability goals and reduce associated costs.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
T. A. Espaas, V. S. Vassiliadis
Summary: This paper extends the concept of higher-order search directions in interior point methods to convex nonlinear programming. It provides the mathematical framework for computing higher-order derivatives and highlights simplified computation for special cases. The paper also introduces a dimensional lifting procedure for transforming general nonlinear problems into more efficient forms and describes the algorithmic development required to employ these higher-order search directions.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
David A. Linan, Gabriel Contreras-Zarazua, Eduardo Sanhez-Ramirez, Juan Gabriel Segovia-Hernandez, Luis A. Ricardez-Sandoval
Summary: This study proposes a parallel hybrid algorithm for optimal design of process flowsheets, which combines stochastic method with deterministic algorithm to achieve faster and improved convergence.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Xiaoyong Lin, Zihui Li, Yongming Han, Zhiwei Chen, Zhiqiang Geng
Summary: A novel GAT-LSTM model is proposed for the production prediction and energy structure optimization of propylene production processes. It outperforms other models and can provide the optimal raw material scheme for actual production processes.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Prodromos Daoutidis, Jay H. Lee, Srinivas Rangarajan, Leo Chiang, Bhushan Gopaluni, Artur M. Schweidtmann, Iiro Harjunkoski, Mehmet Mercangoz, Ali Mesbah, Fani Boukouvala, Fernando Lima, Antonio del Rio Chanona, Christos Georgakis
Summary: This paper provides a concise perspective on the potential of machine learning in the PSE domain, based on discussions and talks during the FIPSE 5 conference. It highlights the need for domain-specific techniques in molecular/material design, data analytics, optimization, and control.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Hesam Hassanpour, Prashant Mhaskar, Brandon Corbett
Summary: This work addresses the problem of designing an offset-free implementable reinforcement learning (RL) controller for nonlinear processes. A pre-training strategy is proposed to provide a secure platform for online implementations of the RL controller. The efficacy of the proposed approach is demonstrated through simulations on a chemical reactor example.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Hunggi Lee, Donghyeon Lee, Jaewook Lee, Dongil Shin
Summary: This study introduces an innovative framework that utilizes a limited number of sensors to detect chemical leaks early, mitigating the risk of major industrial disasters, and providing faster and higher-resolution results.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Sibel Uygun Batgi, Ibrahim Dincer
Summary: This study examines the environmental impacts of three alternative hydrogen-generating processes and determines the best environmentally friendly option for hydrogen production by comparing different impact categories. The results show that the solar-based HyS cycle options perform the best in terms of global warming potential, abiotic depletion, acidification potential, ozone layer depletion, and human toxicity potential.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
LaGrande Gunnell, Bethany Nicholson, John D. Hedengren
Summary: A review of current trends in scientific computing shows a shift towards open-source and higher-level programming languages like Python, with increasing career opportunities in the next decade. Open-source modeling tools contribute to innovation in equation-based and data-driven applications, and the integration of data-driven and principles-based tools is emerging. New compute hardware, productivity software, and training resources have the potential to significantly accelerate progress, but long-term support mechanisms are still necessary.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Daniel Cristiu, Federico d'Amore, Fabrizio Bezzo
Summary: This study presents a multi-objective mixed integer linear programming framework to optimize the supply chain for mixed plastic waste in Northern Italy. Results offer quantitative insights into economic and environmental performance, balancing trade-offs between maximizing gross profit and minimizing greenhouse gas emissions.
COMPUTERS & CHEMICAL ENGINEERING
(2024)
