Computers & Chemical Engineering最新文献_第10页

Bayesian optimization of gray-box process models using a modified upper confidence bound acquisition function

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-19 DOI: 10.1016/j.compchemeng.2024.108976

Joschka Winz, Florian Fromme, Sebastian Engell

引用次数: 0

Comparative framework of representative weeks selection methods for the optimization of power systems

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-17 DOI: 10.1016/j.compchemeng.2024.108985

Alma Yunuen Raya-Tapia , Francisco Javier López-Flores , Javier Tovar-Facio , José María Ponce-Ortega

{"title":"Comparative framework of representative weeks selection methods for the optimization of power systems","authors":"Alma Yunuen Raya-Tapia , Francisco Javier López-Flores , Javier Tovar-Facio , José María Ponce-Ortega","doi":"10.1016/j.compchemeng.2024.108985","DOIUrl":"10.1016/j.compchemeng.2024.108985","url":null,"abstract":"<div><div>Considering the reliability and flexibility to supply future energy demand, power grid planning models are composed of mathematical formulations that represent investments in the installation and operation of generation and storage systems to reduce costs and environmental impacts. However, these can be computationally intractable to solve for many periods. Hence, in this paper, three methods are compared to obtain representative weeks in terms of their accuracy in representing the net load duration curve (NLDC) of the 5 regions that compose the Mexican peninsular electric system and in the objective function domain of a proposed model. The selection methods used for representative weeks were k-means with Euclidean metric, k-means with dynamic time warping (DTW) metric and a combinatorial method. It was observed that the combinatorial method obtained a root mean square error (RMSE) in the representation of 2.80, followed by k-means with DTW metric with 3.21 and finally k-means with Euclidean metric with 5.49. K-means with DTW metric requires about 17 and 70 times more computational time than the combinatorial method and k-means with Euclidean metric, because it had no restrictions on the amount of deformation allowed. In terms of the objective function, the combinatorial method had higher total system costs with $ 4.4274 × 10<sup>10</sup>, while they were 0.1 % and 0.2 % lower in k-means with DTW and k-means with Euclidean metric, respectively. These lower costs are due to underestimation of the system cost, as the methods do not adequately reflect operational situations and generate less expensive scenarios than are actually the case.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108985"},"PeriodicalIF":3.9,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136626","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

Knowledge-enhanced data-driven modeling of wastewater treatment processes for energy consumption prediction

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-17 DOI: 10.1016/j.compchemeng.2024.108982

Louis Allen, Joan Cordiner

{"title":"Knowledge-enhanced data-driven modeling of wastewater treatment processes for energy consumption prediction","authors":"Louis Allen, Joan Cordiner","doi":"10.1016/j.compchemeng.2024.108982","DOIUrl":"10.1016/j.compchemeng.2024.108982","url":null,"abstract":"<div><div>Rising energy usage in wastewater treatment processes (WWTPs) poses pressing economic and environmental challenges. Machine learning approaches to model these complex systems have been limited by highly non-linear processes and high dataset noise. To address this, we introduce a novel Knowledge-Enhanced Graph Disentanglement framework for Energy Consumption Prediction (KEGD-EC) that leverages causal inference and graph neural networks. This work combines specific knowledge of causal relationships with a disentangled graph convolutional network architecture to facilitate accurate predictions. In a study on a WWTP in Melbourne, we demonstrate a 59.7% reduction in root mean squared error in energy consumption prediction using KEGD-EC compared to the next best model. We show that causal models built using domain knowledge outperform data-driven causal discovery models for complex systems. These results signify a step forward in applying machine learning to complex manufacturing processes, with the integration of causal knowledge into deep learning architectures posing a promising area of research for predictive analytics in manufacturing.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108982"},"PeriodicalIF":3.9,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136592","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

Model predictive control of purple bacteria in raceway reactors: Handling microbial competition, disturbances, and performance

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-17 DOI: 10.1016/j.compchemeng.2024.108981

Ali Moradvandi , Bart De Schutter , Edo Abraham , Ralph E.F. Lindeboom

{"title":"Model predictive control of purple bacteria in raceway reactors: Handling microbial competition, disturbances, and performance","authors":"Ali Moradvandi , Bart De Schutter , Edo Abraham , Ralph E.F. Lindeboom","doi":"10.1016/j.compchemeng.2024.108981","DOIUrl":"10.1016/j.compchemeng.2024.108981","url":null,"abstract":"<div><div>Purple Phototrophic Bacteria (PPB) are increasingly being applied in resource recovery from wastewater. Open raceway-pond reactors offer a more cost-effective option, but subject to biological and environmental perturbations. This study proposes a hierarchical control system based on Adaptive Generalized Model Predictive Control (AGMPC) for PPB raceway reactors. The AGMPC uses simple linear models updated adaptively to project the complex process dynamics and capture changes. The hierarchical approach uses the AGMPC controller to optimize PPB growth as the core of the system. The developed supervisory layer adjusts set-points for the core controller based on two operational scenarios: maximizing PPB concentration for quality, or increasing yield for quantity through effluent recycling. Lastly, due to competing PPB and non-PPB bacteria during start-up phase, an override strategy for this transition is investigated through simulation studies. The Purple Bacteria Model (PBM) simulates this process, and simulation results demonstrate the control system’s effectiveness and robustness.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108981"},"PeriodicalIF":3.9,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136591","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

A risk-based maintenance planning in process industry using a bi-objective robust optimization model

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-16 DOI: 10.1016/j.compchemeng.2024.108984

Zohreh Alipour , Mohammadali Saniee Monfared , Sayyed Ehsan Monabbati

{"title":"A risk-based maintenance planning in process industry using a bi-objective robust optimization model","authors":"Zohreh Alipour , Mohammadali Saniee Monfared , Sayyed Ehsan Monabbati","doi":"10.1016/j.compchemeng.2024.108984","DOIUrl":"10.1016/j.compchemeng.2024.108984","url":null,"abstract":"<div><div>We have developed an innovative risk-based maintenance planning methodology using a bi-objective scenario-based robust optimization model. This approach determines robust, optimal maintenance intervals for process industries. Our methodology comprises two main phases: risk assessment and maintenance planning. In the initial phase, we identified critical items using a Bow-tie diagram, which is subsequently mapped into a Bayesian network to estimate the overall risk based on historical data and process knowledge. In the second phase, we developed a bi-objective scenario-based robust optimization model to Pareto-optimize both risk and cost under operational risks. This results in a robust maintenance plan capable of withstanding time, costs, and failure rate uncertainties inherent in process industries with considering decision-makers' attitudes to risk (risk-averse, risk-neutral, or hybrid attitude). The computational results demonstrate the significant impact of considering uncertainty of critical data, and robustness on the selected maintenance plan and system performance.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108984"},"PeriodicalIF":3.9,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136358","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

Smart Process Analytics for Process Monitoring

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-14 DOI: 10.1016/j.compchemeng.2024.108918

Fabian Mohr , Elia Arnese-Feffin , Massimliano Barolo , Richard D. Braatz

引用次数: 0

Phase stability criteria and fluid-phase equilibria in strong-electrolyte systems

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-13 DOI: 10.1016/j.compchemeng.2024.108977

Felipe A. Perdomo , George Jackson , Alexander Mitsos , Amparo Galindo , Claire S. Adjiman

{"title":"Phase stability criteria and fluid-phase equilibria in strong-electrolyte systems","authors":"Felipe A. Perdomo , George Jackson , Alexander Mitsos , Amparo Galindo , Claire S. Adjiman","doi":"10.1016/j.compchemeng.2024.108977","DOIUrl":"10.1016/j.compchemeng.2024.108977","url":null,"abstract":"<div><div>Although the presence of salts can significantly affect the fluid-phase equilibria, phase stability and equilibrium calculations remain challenging due to the nonlinearity of thermodynamic models and to the negligible amounts of ions that can be present in some phases. To address this, we introduce a new variable transformation and present the first formal proof of a stability criterion for strong (fully-dissociated) electrolyte solutions based on the tangent-plane distance under the electroneutrality constraint. The criterion can also be recast based on duality theory, yielding two alternative formulations with/without reformulation in the volume-composition space. We use these theoretical results to extend the Helmholtz free Energy Lagrangian Dual (HELD) algorithm (Pereira et al., Comput. Chem. Eng. 36 (2012) 99) to strong electrolyte mixtures. The resulting HELD2.0 algorithm provides reliable calculations of the nonideal phase behaviour of mixtures of organic molecules and water with alkali halide salts for a wide range of thermodynamic states.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108977"},"PeriodicalIF":3.9,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136779","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

Retraction notice to “Economic, reliability, environmental and operation factors to achieve optimal operations of multiple microgrids” [Computers & Chemical Engineering 176 (2023) 108279]

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-12 DOI: 10.1016/j.compchemeng.2024.108971

Aiqin Xu , Jing Wu , Guoliang Zhou , Sara Saeedi

引用次数: 0

Deep reinforcement learning enables conceptual design of processes for separating azeotropic mixtures without prior knowledge

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-12 DOI: 10.1016/j.compchemeng.2024.108975

Quirin Göttl , Jonathan Pirnay , Jakob Burger , Dominik G. Grimm

{"title":"Deep reinforcement learning enables conceptual design of processes for separating azeotropic mixtures without prior knowledge","authors":"Quirin Göttl , Jonathan Pirnay , Jakob Burger , Dominik G. Grimm","doi":"10.1016/j.compchemeng.2024.108975","DOIUrl":"10.1016/j.compchemeng.2024.108975","url":null,"abstract":"<div><div>Process synthesis in chemical engineering is a complex planning problem due to vast search spaces, continuous parameters and the need for generalization. Deep reinforcement learning agents, trained without prior knowledge, have shown to outperform humans in various complex planning problems in recent years. Existing work on reinforcement learning for flowsheet synthesis shows promising concepts. We further develop those concepts and present a general deep reinforcement learning approach for flowsheet synthesis. We demonstrate the adaptability of an agent to the general task of separating binary azeotropic mixtures. The agent is trained to set up the discrete process topology alongside choosing continuous specifications for the individual flowsheet elements (e.g., distillation columns and recycles). Without prior knowledge, it learns within one training cycle to craft flowsheets for multiple chemical systems, considering different feed compositions and conceptual approaches. The agent discovers autonomously fundamental process engineering paradigms as heteroazeotropic distillation or curved-boundary distillation.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108975"},"PeriodicalIF":3.9,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136741","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

Superstructure optimization with rigorous models via an exact reformulation

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-12-12 DOI: 10.1016/j.compchemeng.2024.108972

Smitha Gopinath , Claire S. Adjiman

引用次数: 0