Computers & Chemical Engineering最新文献_第5页

Sensitivity-based scenario selection for multi-stage MPC along principal components

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-01-02 DOI: 10.1016/j.compchemeng.2024.108992

Zawadi Mdoe, Johannes Jäschke

{"title":"Sensitivity-based scenario selection for multi-stage MPC along principal components","authors":"Zawadi Mdoe, Johannes Jäschke","doi":"10.1016/j.compchemeng.2024.108992","DOIUrl":"10.1016/j.compchemeng.2024.108992","url":null,"abstract":"<div><div>The robustness, degree of conservativeness, and computational efficiency in robust multi-stage MPC are affected by scenario selection. This study explores the advantages of employing multivariate data analysis, nonlinear optimization theory, and sensitivity analysis in scenario selection to reduce conservativeness and computational burden. A novel scenario selection approach is proposed, which integrates principal component analysis and sensitivity analysis, aiming to enhance computational efficiency and mitigate conservativeness in multi-stage MPC. This method advances and extends the previously quite conservative framework of sensitivity-assisted multi-stage nonlinear MPC. Assuming that the constraints are monotonic in the parameters, the approach identifies scenarios based on sensitivities along principal components derived from analyzing large process data. The optimization problem is reformulated using the principal components to determine parameter values for critical scenarios, providing a more accurate representation of the process. The efficacy of the controller is demonstrated through various numerical examples, including a detailed thermal energy storage case study, which showcases a reduction in peak heating requirements.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108992"},"PeriodicalIF":3.9,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comprehensive crop allocation model: Balancing profitability, environmental impact, and occupational health

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-31 DOI: 10.1016/j.compchemeng.2024.108996

Francisco Javier López-Flores , Maritza E. Cervantes-Gaxiola , Oscar M. Hernández-Calderón , José M. Ponce-Ortega , Jesús Raúl Ortiz-del-Castillo , Eusiel Rubio-Castro

{"title":"Comprehensive crop allocation model: Balancing profitability, environmental impact, and occupational health","authors":"Francisco Javier López-Flores , Maritza E. Cervantes-Gaxiola , Oscar M. Hernández-Calderón , José M. Ponce-Ortega , Jesús Raúl Ortiz-del-Castillo , Eusiel Rubio-Castro","doi":"10.1016/j.compchemeng.2024.108996","DOIUrl":"10.1016/j.compchemeng.2024.108996","url":null,"abstract":"<div><div>This paper presents an innovative mathematical optimization model, formulated as a Mixed-Integer Nonlinear Programming problem, for sustainable crop allocation across a set of available parcels. The model not only maximizes the economic benefits derived from crop sales but also optimizes the use of water and fertilizers, minimizes environmental impact, and assesses health and safety risks to workers using the Process Route Health Index, adapted from the chemical industry. The adaptation methodology is designed and presented step-by-step to highlight its applicability and relevance in the agricultural context. The integration of mass networks for the use, reuse, and regeneration of water and fertilizers allows for significant optimization of resources, reducing both operating costs and environmental waste. A case study involving the allocation of four crops across 12 parcels over three sowing cycles demonstrates the model's applicability under different scenarios, evaluating profits, Eco-indicator 95, water footprint, and occupational health. The results obtained demonstrate the model's ability to balance economic benefits with environmental sustainability and labor safety.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108996"},"PeriodicalIF":3.9,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Success-Based Optimization Algorithm (SBOA): Development and enhancement of a metaheuristic optimizer

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-30 DOI: 10.1016/j.compchemeng.2024.108987

Oscar Daniel Lara-Montaño , Fernando Israel Gómez-Castro , Claudia Gutiérrez-Antonio , Elena Niculina Dragoi

{"title":"Success-Based Optimization Algorithm (SBOA): Development and enhancement of a metaheuristic optimizer","authors":"Oscar Daniel Lara-Montaño , Fernando Israel Gómez-Castro , Claudia Gutiérrez-Antonio , Elena Niculina Dragoi","doi":"10.1016/j.compchemeng.2024.108987","DOIUrl":"10.1016/j.compchemeng.2024.108987","url":null,"abstract":"<div><div>This paper presents the development of the Success-Based Optimization Algorithm (SBOA), a novel metaheuristic inspired by success attribution theory, designed to address complex, high-dimensional optimization problems. SBOA balances exploration and exploitation by utilizing high-performing solutions and average-performing candidates to guide the search process, dynamically adjusting based on solution quality. The algorithm is evaluated against seven well-established optimization methods using CEC 2017 benchmark functions in 10, 30, and 50 dimensions. It is applied to a real-world engineering problem involving the optimal design of shell-and-tube heat exchangers (STHEs). The results demonstrate that SBOA consistently surpasses most competing algorithms, especially in higher-dimensional cases, achieving lower objective values and faster convergence. Statistical analyses, including the Wilcoxon signed-rank test, confirm the significant advantages of SBOA in benchmark performance and cost-effectiveness in practical engineering applications. These findings position SBOA as a highly adaptable and efficient optimization tool for addressing complex tasks.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108987"},"PeriodicalIF":3.9,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing arsenic removal in water supply: A mathematical approach for plant location, technology selection, and network synthesis

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-28 DOI: 10.1016/j.compchemeng.2024.108994

Angel Alfaro-Bernardino, César Ramírez-Márquez, José M. Ponce-Ortega, Fabricio Nápoles-Rivera

{"title":"Optimizing arsenic removal in water supply: A mathematical approach for plant location, technology selection, and network synthesis","authors":"Angel Alfaro-Bernardino, César Ramírez-Márquez, José M. Ponce-Ortega, Fabricio Nápoles-Rivera","doi":"10.1016/j.compchemeng.2024.108994","DOIUrl":"10.1016/j.compchemeng.2024.108994","url":null,"abstract":"<div><div>Arsenic contamination in groundwater presents significant health risks, demanding effective treatment solutions. This study introduces a mathematical programming method to determine the optimal location to place arsenic treatment plants, select the appropriate technology, and design large-scale water distribution networks. This work focuses on minimizing costs associated with pumping, piping, plant installation, and operation while complying with the regulations of arsenic levels in drinking water. The approach involves a nonlinear mixed-integer mathematical programming model coupled with a detailed procedure to find solutions. In the implementation of this model, the study not only explores the best strategies to reduce the arsenic found in drinking water to safer levels in affected wells, but it also works to design an efficient water network. An analysis of areas with wells that show a concentration of arsenic above permissible levels demonstrates how the proposed solutions can effectively lower arsenic levels to meet safety standards and optimize water supply systems. The findings highlight the potential of significantly improving water quality and public health through strategic infrastructure, planning, and technological application.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108994"},"PeriodicalIF":3.9,"publicationDate":"2024-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Computer-aided molecular design by aligning generative diffusion models: Perspectives and challenges

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-27 DOI: 10.1016/j.compchemeng.2024.108989

Akshay Ajagekar , Benjamin Decardi-Nelson , Chao Shang , Fengqi You

{"title":"Computer-aided molecular design by aligning generative diffusion models: Perspectives and challenges","authors":"Akshay Ajagekar , Benjamin Decardi-Nelson , Chao Shang , Fengqi You","doi":"10.1016/j.compchemeng.2024.108989","DOIUrl":"10.1016/j.compchemeng.2024.108989","url":null,"abstract":"<div><div>Deep generative models like diffusion models have generated significant interest in computer-aided molecular design by enabling the automated generation of novel molecular structures. This manuscript aims to highlight the potential of diffusion models in computer-aided molecular design (CAMD) while addressing key limitations in their practical implementation. Diffusion models trained for specific molecular design problems can suffer for design tasks with alternate desired property requirements. To address this challenge, we provide perspectives on the integration of generative diffusion models with optimization methods for CAMD. We examine how pretrained equivariant diffusion models can be effectively aligned with text-guided molecular generation through optimization in the latent space. Computational experiments targeting drug design demonstrate the framework's capability of generating valid molecular structures that satisfy multiple objectives. This work underscores the potential of combining pretrained generative models with gradient-free optimization methods like genetic algorithms to enhance molecular design precision without incurring significant computational costs associated with finetuning diffusion models. Beyond highlighting the practical utility of diffusion models in CAMD, we identify key challenges encountered while adopting these models and propose future research directions to address them, providing a comprehensive roadmap for advancing the field of computational molecular design.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108989"},"PeriodicalIF":3.9,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparative modeling and assessment of renewable hydrogen production and utilization in remote communities

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-27 DOI: 10.1016/j.compchemeng.2024.108995

Muhammed Iberia Aydin , Ibrahim Dincer

{"title":"Comparative modeling and assessment of renewable hydrogen production and utilization in remote communities","authors":"Muhammed Iberia Aydin , Ibrahim Dincer","doi":"10.1016/j.compchemeng.2024.108995","DOIUrl":"10.1016/j.compchemeng.2024.108995","url":null,"abstract":"<div><div>This study explores renewable energy transitions in remote communities by addressing the environmental and health impacts of fossil fuel dependency. Remote communities face unique challenges in terms of economic, social and cultural development because of their geographical isolation and limited access to infrastructure, resources and services. Considering Sandy Lake First Nation community in Ontario, Canada as a case study, a life cycle assessment investigation is comprehensively conducted to evaluate the environmental outcomes of implementing hydrogen-based renewable systems into community's infrastructure. The respective life cycle impact assessment studies are then carried out to compare the environmental impacts of different energy production methods. The results for Global Warming Potential (GWP) show 1.88 kg CO₂ eq./kWh for the diesel-only scenario, while the renewable-integrated scenarios result in ranges from 0.08 to 0.37 kg CO₂ eq./kWh. The results further show that renewable-integrated scenarios reduce global warming potential (GWP) by up to 98.7 %, compared to diesel-only systems. While renewable energy significantly lowers the most environmental indicators, the manufacturing of renewable and hydrogen technologies makes some contributions to ecotoxicity. The study findings emphasize the need for sustainable manufacturing, strategic policymaking, and incentives to accelerate renewable adoption in isolated settlements.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108995"},"PeriodicalIF":3.9,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Closed-loop identification of MIMO systems: An excitation-free approach

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-26 DOI: 10.1016/j.compchemeng.2024.108990

Zhi-Qiang Zhang, Chun-Qing Huang

引用次数: 0

Towards a machine learning operations (MLOps) soft sensor for real-time predictions in industrial-scale fed-batch fermentation

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-26 DOI: 10.1016/j.compchemeng.2024.108991

Brett Metcalfe , Juan Camilo Acosta-Pavas , Carlos Eduardo Robles-Rodriguez , George K. Georgakilas , Theodore Dalamagas , Cesar Arturo Aceves-Lara , Fayza Daboussi , Jasper J Koehorst , David Camilo Corrales

{"title":"Towards a machine learning operations (MLOps) soft sensor for real-time predictions in industrial-scale fed-batch fermentation","authors":"Brett Metcalfe , Juan Camilo Acosta-Pavas , Carlos Eduardo Robles-Rodriguez , George K. Georgakilas , Theodore Dalamagas , Cesar Arturo Aceves-Lara , Fayza Daboussi , Jasper J Koehorst , David Camilo Corrales","doi":"10.1016/j.compchemeng.2024.108991","DOIUrl":"10.1016/j.compchemeng.2024.108991","url":null,"abstract":"<div><div>Real-time predictions in fermentation processes are crucial because they enable continuous monitoring and control of bioprocessing. However, the availability of online measurements is limited by the availability and feasibility of sensing technology. Soft sensors - or software sensors that convert available measurements into measurements of interest (product yield, quality, etc.) - have the potential to improve efficiency and product quality. Machine learning (ML) based soft sensors have gained increased popularity over the years since they can incorporate variables that are measured in real-time, and exploit the intricate patterns embedded in such voluminous datasets. However, ML-based soft sensor requires more than just a classical ML learner with an unseen test set to evaluate the quality prediction of the model. When a ML model is deployed in production, its performance can deteriorate rapidly leading to an unanticipated decline in the quality of the output and predictions. Here a proof concept of Machine Learning Operations (MLOps) to automate the end-to-end soft sensor lifecycle in industrial scale fed-batch fermentation, from development and deployment to maintenance and monitoring is proposed. Using the industrial-scale penicillin fermentation (<em>IndPenSim)</em> dataset that includes 100 fermentation batches, to build a soft sensor based on Long Short Term Memory (LSTM) for penicillin concentration prediction. The batches containing deviations in the processes (91–100) were used to assess concept drift of the LSTM soft sensor. The evaluation of concept drift is evidenced by the soft sensor performance falling below the set threshold based on the Population Stability Index (PSI), which automatically triggers an alert to run the retraining pipeline.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108991"},"PeriodicalIF":3.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An integrated reinforcement learning framework for simultaneous generation, design, and control of chemical process flowsheets

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-21 DOI: 10.1016/j.compchemeng.2024.108988

Simone Reynoso-Donzelli, Luis A. Ricardez-Sandoval

{"title":"An integrated reinforcement learning framework for simultaneous generation, design, and control of chemical process flowsheets","authors":"Simone Reynoso-Donzelli, Luis A. Ricardez-Sandoval","doi":"10.1016/j.compchemeng.2024.108988","DOIUrl":"10.1016/j.compchemeng.2024.108988","url":null,"abstract":"<div><div>This study introduces a Reinforcement Learning (RL) approach for synthesis, design, and control of chemical process flowsheets (CPFs). The proposed RL framework makes use of an inlet stream and a set of unit operations (UOs) available in the RL environment to build, evaluate and test CPFs. Moreover, the framework harnesses the power of surrogate models, specifically Neural Networks (NNs), to expedite the learning process of the RL agent and avoid reliance on mechanistic dynamic models embedded within the RL environment. These surrogate models approximate key process variables and descriptive closed-loop performance metrics for complex dynamic UO models. The proposed framework is evaluated through case studies, including a system where more than one type of UO is considered for simultaneous synthesis, design and control. The results show that the RL agent effectively learns to maintain the dynamic operability of the UOs under disturbances, adhere to equipment design and operational constraints, and generate viable and economically attractive CPFs.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108988"},"PeriodicalIF":3.9,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Lyapunov-based distributed reinforcement learning control with stability guarantee

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-20 DOI: 10.1016/j.compchemeng.2024.108979

Jingshi Yao , Minghao Han , Xunyuan Yin

引用次数: 0