Computers & Chemical Engineering最新文献_第7页

Oscillation analysis using Retrieval-Augmented Generation 基于检索增广生成的振荡分析

IF 3.9 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Chemical Engineering

Pub Date : 2026-03-01 Epub Date: 2025-11-22 DOI: 10.1016/j.compchemeng.2025.109489

Abhijeet Singh , Mohammadhossein Modir Rousta , Biao Huang

Industrial control system oscillations pose significant operational challenges, causing economic losses through energy waste, equipment degradation, and reduced product quality. Traditional detection methods rely heavily on manual expert analysis, creating scalability constraints in facilities with thousands of control loops. This paper presents a novel framework integrating Large Language Models (LLMs) with specialized oscillation detection toolboxes through Retrieval-Augmented Generation (RAG). The system features a command-line interface enabling seamless programmatic interaction between LLMs and analytical tools, eliminating GUI dependencies. A domain-specific RAG architecture combines real-time analytical outputs with technical knowledge repositories, while natural language processing capabilities allow industrial personnel to query systems using everyday language. The framework incorporates triangle-like shape detection algorithms enhanced by intelligent LLM interpretation. Validation using industrial datasets from refinery operations, the International Stiction Database, and the Tennessee Eastman Process benchmark demonstrates substantial performance improvements, achieving excellent classification accuracy and correlation values exceeding 0.96, effectively democratizing access to advanced oscillation analysis capabilities.

工业控制系统振荡带来了重大的操作挑战，通过能源浪费、设备退化和产品质量降低造成经济损失。传统的检测方法严重依赖于人工专家分析，在具有数千个控制回路的设施中产生可扩展性限制。本文提出了一种通过检索增强生成（RAG）将大型语言模型（llm）与专门的振荡检测工具箱集成在一起的新框架。该系统具有命令行界面，可实现llm和分析工具之间的无缝编程交互，消除了对GUI的依赖。特定于领域的RAG体系结构将实时分析输出与技术知识库结合在一起，而自然语言处理功能允许工业人员使用日常语言查询系统。该框架结合了由智能LLM解释增强的类三角形形状检测算法。使用来自炼油厂作业的工业数据集、国际粘度数据库和田纳西伊士曼过程基准进行验证，证明了显著的性能改进，实现了出色的分类精度和超过0.96的相关值，有效地实现了高级振荡分析功能的大众化。

{"title":"Oscillation analysis using Retrieval-Augmented Generation","authors":"Abhijeet Singh , Mohammadhossein Modir Rousta , Biao Huang","doi":"10.1016/j.compchemeng.2025.109489","DOIUrl":"10.1016/j.compchemeng.2025.109489","url":null,"abstract":"<div><div>Industrial control system oscillations pose significant operational challenges, causing economic losses through energy waste, equipment degradation, and reduced product quality. Traditional detection methods rely heavily on manual expert analysis, creating scalability constraints in facilities with thousands of control loops. This paper presents a novel framework integrating Large Language Models (LLMs) with specialized oscillation detection toolboxes through Retrieval-Augmented Generation (RAG). The system features a command-line interface enabling seamless programmatic interaction between LLMs and analytical tools, eliminating GUI dependencies. A domain-specific RAG architecture combines real-time analytical outputs with technical knowledge repositories, while natural language processing capabilities allow industrial personnel to query systems using everyday language. The framework incorporates triangle-like shape detection algorithms enhanced by intelligent LLM interpretation. Validation using industrial datasets from refinery operations, the International Stiction Database, and the Tennessee Eastman Process benchmark demonstrates substantial performance improvements, achieving excellent classification accuracy and correlation values exceeding 0.96, effectively democratizing access to advanced oscillation analysis capabilities.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"206 ","pages":"Article 109489"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145594796","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

A fairness-guided supply chain framework for polyester production from biomass 生物质聚酯生产的公平导向供应链框架

IF 3.9 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Chemical Engineering

Pub Date : 2026-03-01 Epub Date: 2025-11-28 DOI: 10.1016/j.compchemeng.2025.109504

Bo-Xun Wang, Victor M. Zavala

Supply chains are complex systems involving many assets and stakeholders that need to be carefully orchestrated to conduct a variety of functions (e.g., meeting demands, ensuring robust operations, and cut down costs). Traditional optimization models that maximize total profit often lead to unfair profit distribution among stakeholders, which could discourage stakeholder collaboration and impede sustainable business development (e.g., activate new market/economies). In this work, we propose a fairness-guided optimization framework for supply chain design. To motivate our developments, we consider the production of a valuable polyester known as polybutylene adipate terephthalate (PBAT) from biomass in the State of Wisconsin. Specifically, we aim to design a supply chain (a bioeconomy) that harnesses biomass from different counties (stakeholders) and that processes this in chemical facilities to produce PBAT. We study the total cost and greenhouse gas (GHG) emissions in the system with the optimal allocation of supplies and facilities installed. We introduce different optimization formulations that maximize the total profit and that maximize a fairness measure of the profit distribution. Our results demonstrate that the fairness-driven formulation can achieve a more equitable distribution of profit but at the expense of a lower total profit, highlighting the inherent trade-off between fairness and economic efficiency. This study aims to provide insights for decision-makers that aim to balance economy development, sustainability, and fairness when designing supply chains.

供应链是复杂的系统，涉及许多资产和利益相关者，需要精心安排以执行各种功能（例如，满足需求，确保稳健运营，并降低成本）。追求总利润最大化的传统优化模型往往导致利益相关者之间的利润分配不公平，这可能会阻碍利益相关者的合作，阻碍可持续的业务发展（例如，激活新的市场/经济）。在这项工作中，我们提出了一个公平导向的供应链设计优化框架。为了推动我们的发展，我们考虑从威斯康星州的生物质中生产一种有价值的聚酯，称为聚己二酸丁二酯（PBAT）。具体来说，我们的目标是设计一个供应链（生物经济），利用来自不同国家（利益相关者）的生物质，并在化学设施中处理这些生物质以生产PBAT。我们研究了在供应和设施配置最优的情况下，系统的总成本和温室气体排放。我们介绍了不同的优化公式，最大化总利润和最大化利润分配的公平措施。我们的研究结果表明，公平驱动的公式可以实现更公平的利润分配，但以降低总利润为代价，突出了公平与经济效率之间的内在权衡。本研究旨在为决策者在设计供应链时兼顾经济发展、可持续性和公平性提供参考。

{"title":"A fairness-guided supply chain framework for polyester production from biomass","authors":"Bo-Xun Wang, Victor M. Zavala","doi":"10.1016/j.compchemeng.2025.109504","DOIUrl":"10.1016/j.compchemeng.2025.109504","url":null,"abstract":"<div><div>Supply chains are complex systems involving many assets and stakeholders that need to be carefully orchestrated to conduct a variety of functions (e.g., meeting demands, ensuring robust operations, and cut down costs). Traditional optimization models that maximize total profit often lead to unfair profit distribution among stakeholders, which could discourage stakeholder collaboration and impede sustainable business development (e.g., activate new market/economies). In this work, we propose a fairness-guided optimization framework for supply chain design. To motivate our developments, we consider the production of a valuable polyester known as polybutylene adipate terephthalate (PBAT) from biomass in the State of Wisconsin. Specifically, we aim to design a supply chain (a bioeconomy) that harnesses biomass from different counties (stakeholders) and that processes this in chemical facilities to produce PBAT. We study the total cost and greenhouse gas (GHG) emissions in the system with the optimal allocation of supplies and facilities installed. We introduce different optimization formulations that maximize the total profit and that maximize a fairness measure of the profit distribution. Our results demonstrate that the fairness-driven formulation can achieve a more equitable distribution of profit but at the expense of a lower total profit, highlighting the inherent trade-off between fairness and economic efficiency. This study aims to provide insights for decision-makers that aim to balance economy development, sustainability, and fairness when designing supply chains.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"206 ","pages":"Article 109504"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145691685","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

On the impact of mechanistic model quality and data availability in hybrid model development 混合模型开发中机制模型质量和数据可用性的影响

IF 3.9 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Chemical Engineering

Pub Date : 2026-03-01 Epub Date: 2025-12-20 DOI: 10.1016/j.compchemeng.2025.109536

Margherita Geremia , Tiziana Marella , Elaheh Ardalani , Samira Beyramysoltan , Sayantan Chattoraj , Pierantonio Facco , Massimiliano Barolo , Fabrizio Bezzo

This work presents a methodology for evaluating the effectiveness of hybrid modelling under varying conditions of mechanistic model quality and information available for model training, that is typically expressed as the amount of data available. While hybrid models – which integrate mechanistic and data-driven components – have gained significant attention in process systems engineering, their advantages over purely mechanistic or data-driven alternatives remain inadequately quantified. We address this gap by investigating two critical factors: (i) the impact of mechanistic model fidelity on hybrid model performance, and (ii) the influence of calibration dataset size on prediction accuracy. Our methodology is validated through an in-silico case study of baker's yeast cultivation and a real-world industrial application of ion-exchange chromatography in biopharmaceutical manufacturing. Results demonstrate that hybrid models consistently outperform purely mechanistic and data-driven approaches when the mechanistic component captures fundamental process behaviours, even with structural simplifications. Notably, hybrid models maintain superior predictive capability in extrapolative scenarios; however, when mechanistic knowledge is severely limited and insufficient information is available for compensation, hybridisation benefits diminish substantially. The work provides quantitative guidance for practitioners to determine when hybrid modelling represents a justified investment of modelling resources in process engineering applications.

这项工作提出了一种方法，用于评估混合建模在不同条件下的有效性，这些条件下的机械模型质量和模型训练可用的信息，通常表示为可用的数据量。虽然混合模型-集成了机械和数据驱动的组件-在过程系统工程中得到了极大的关注，但它们相对于纯机械或数据驱动的替代方案的优势仍然没有充分量化。我们通过研究两个关键因素来解决这一差距：(i)机制模型保真度对混合模型性能的影响，以及（ii）校准数据集大小对预测精度的影响。我们的方法通过烘焙酵母培养的计算机案例研究和离子交换色谱在生物制药制造中的实际工业应用得到验证。结果表明，当机械组件捕获基本过程行为时，混合模型始终优于纯机械和数据驱动的方法，即使结构简化了。值得注意的是，混合模型在外推情景中保持了优越的预测能力；然而，当机械知识严重有限，并且可供补偿的信息不足时，杂交的好处就会大大减少。这项工作为实践者提供了定量指导，以确定混合建模何时代表过程工程应用中建模资源的合理投资。

{"title":"On the impact of mechanistic model quality and data availability in hybrid model development","authors":"Margherita Geremia , Tiziana Marella , Elaheh Ardalani , Samira Beyramysoltan , Sayantan Chattoraj , Pierantonio Facco , Massimiliano Barolo , Fabrizio Bezzo","doi":"10.1016/j.compchemeng.2025.109536","DOIUrl":"10.1016/j.compchemeng.2025.109536","url":null,"abstract":"<div><div>This work presents a methodology for evaluating the effectiveness of hybrid modelling under varying conditions of mechanistic model quality and information available for model training, that is typically expressed as the amount of data available. While hybrid models – which integrate mechanistic and data-driven components – have gained significant attention in process systems engineering, their advantages over purely mechanistic or data-driven alternatives remain inadequately quantified. We address this gap by investigating two critical factors: (<em>i</em>) the impact of mechanistic model fidelity on hybrid model performance, and (<em>ii</em>) the influence of calibration dataset size on prediction accuracy. Our methodology is validated through an <em>in-silico</em> case study of baker's yeast cultivation and a real-world industrial application of ion-exchange chromatography in biopharmaceutical manufacturing. Results demonstrate that hybrid models consistently outperform purely mechanistic and data-driven approaches when the mechanistic component captures fundamental process behaviours, even with structural simplifications. Notably, hybrid models maintain superior predictive capability in extrapolative scenarios; however, when mechanistic knowledge is severely limited and insufficient information is available for compensation, hybridisation benefits diminish substantially. The work provides quantitative guidance for practitioners to determine when hybrid modelling represents a justified investment of modelling resources in process engineering applications.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"206 ","pages":"Article 109536"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145836404","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 performance of stochastic and deep learning models in forecasting crude oil prices under market shocks 随机和深度学习模型在市场冲击下原油价格预测中的比较性能

IF 3.9 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Chemical Engineering

Pub Date : 2026-03-01 Epub Date: 2025-12-19 DOI: 10.1016/j.compchemeng.2025.109534

Busra Agan Celik, Murat Yulek, Serdar Celik

This study provides a comprehensive evaluation of crude oil price forecasting by systematically comparing stochastic models (GBM, FBM, BB), machine learning and time-series approaches (LSTM, ARIMA, VAR), and two hybrid strategies LSTM-GBM (time-varying drift estimation) and Bridge-ARIMA (terminal-level anchoring) across short-, medium-, and long-term horizons. Using daily price data spanning 34 years (1990–2024), the analysis encompasses major global crises, including the Asian Financial Crisis, Dot-com Bubble, Global Commodity Boom, Global Financial Crisis, Arab Spring, Oil Price Collapse, COVID-19 pandemic, and the Russia–Ukraine conflict. Stochastic models exhibited sensitivity to the number of simulation runs, with FBM yielding the most robust forecasts, BB demonstrating stability through mean-reversion, and GBM showing larger errors over extended horizons. LSTM consistently outperformed alternative methods, capturing nonlinear dynamics and long-term dependencies with high accuracy across all horizons. ARIMA performed adequately for short-term forecasts but declined over longer periods, whereas VAR consistently underperformed, reflecting its limited capacity to capture complex market dynamics. The hybrid methods further enhance performance: Bridge-ARIMA reduces bias by aligning simulated paths with an ARIMA-implied terminal, improving crisis-period tracking, whereas LSTM-GBM leverages learned drift to refine path forecasts and risk metrics (e.g., VaR). These results underscore the complementary advantages of stochastic and deep learning approaches and suggest that hybrid frameworks can enhance both volatility assessment and trend prediction. The findings offer practical insights for energy market planning, risk management, and strategic investment, particularly under crisis-driven volatility.

本研究通过系统地比较随机模型（GBM、FBM、BB）、机器学习和时间序列方法（LSTM、ARIMA、VAR），以及两种混合策略LSTM-GBM（时变漂移估计）和Bridge-ARIMA（终端级锚定），对原油价格预测进行了全面评估。该报告利用34年（1990年至2024年）的每日价格数据，分析了亚洲金融危机、互联网泡沫、全球大宗商品繁荣、全球金融危机、阿拉伯之春、油价暴跌、COVID-19大流行、俄乌冲突等重大全球危机。随机模型显示出对模拟运行次数的敏感性，其中FBM产生最稳健的预测，BB通过均值回归显示出稳定性，而GBM在较长时间内显示出较大的误差。LSTM始终优于其他方法，在所有视界以高精度捕获非线性动态和长期依赖关系。ARIMA在短期预测中表现良好，但在长期预测中表现下降，而VAR的表现一直不佳，反映出其捕捉复杂市场动态的能力有限。混合方法进一步提高了性能：Bridge-ARIMA通过将模拟路径与arima隐含的终端对齐来减少偏差，改善危机期跟踪，而LSTM-GBM利用学习漂移来优化路径预测和风险指标（如VaR）。这些结果强调了随机和深度学习方法的互补优势，并表明混合框架可以增强波动性评估和趋势预测。研究结果为能源市场规划、风险管理和战略投资提供了实用的见解，特别是在危机驱动的波动下。

{"title":"Comparative performance of stochastic and deep learning models in forecasting crude oil prices under market shocks","authors":"Busra Agan Celik, Murat Yulek, Serdar Celik","doi":"10.1016/j.compchemeng.2025.109534","DOIUrl":"10.1016/j.compchemeng.2025.109534","url":null,"abstract":"<div><div>This study provides a comprehensive evaluation of crude oil price forecasting by systematically comparing stochastic models (GBM, FBM, BB), machine learning and time-series approaches (LSTM, ARIMA, VAR), and two hybrid strategies LSTM-GBM (time-varying drift estimation) and Bridge-ARIMA (terminal-level anchoring) across short-, medium-, and long-term horizons. Using daily price data spanning 34 years (1990–2024), the analysis encompasses major global crises, including the Asian Financial Crisis, Dot-com Bubble, Global Commodity Boom, Global Financial Crisis, Arab Spring, Oil Price Collapse, COVID-19 pandemic, and the Russia–Ukraine conflict. Stochastic models exhibited sensitivity to the number of simulation runs, with FBM yielding the most robust forecasts, BB demonstrating stability through mean-reversion, and GBM showing larger errors over extended horizons. LSTM consistently outperformed alternative methods, capturing nonlinear dynamics and long-term dependencies with high accuracy across all horizons. ARIMA performed adequately for short-term forecasts but declined over longer periods, whereas VAR consistently underperformed, reflecting its limited capacity to capture complex market dynamics. The hybrid methods further enhance performance: Bridge-ARIMA reduces bias by aligning simulated paths with an ARIMA-implied terminal, improving crisis-period tracking, whereas LSTM-GBM leverages learned drift to refine path forecasts and risk metrics (e.g., VaR). These results underscore the complementary advantages of stochastic and deep learning approaches and suggest that hybrid frameworks can enhance both volatility assessment and trend prediction. The findings offer practical insights for energy market planning, risk management, and strategic investment, particularly under crisis-driven volatility.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"206 ","pages":"Article 109534"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145836366","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

Study on explosion characteristics of premixed gas influenced by magnetic field based on product analysis 基于产物分析的磁场对预混气体爆炸特性影响研究

IF 3.9 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Chemical Engineering

Pub Date : 2026-03-01 Epub Date: 2025-11-29 DOI: 10.1016/j.compchemeng.2025.109516

Shoutao Hu , Zhiwei Zhang , Hao Gong , Zhong Guan , Meiqi Liu , Nana Wu

In order to investigate the effects and mechanisms of magnetic fields on the explosion characteristics of premixed gases, explosion experiments were conducted under both magnetic field and no-magnetic field conditions using CH₄-air and C₃H₈-air premixed combustible gases. Explosion product analysis revealed variations in component types and concentrations under both conditions. Additionally, simulation studies related to product formation were carried out. The experimental results showed that the magnetic fields reduced maximum explosion pressure and flame velocity for both mixtures, while the detection of alkane products significantly increased. Numerical simulations revealed that ·H, ·O, ·OH, and ·CH₃ play key roles in the generation of explosion products in CH₄-air and C₃H₈-air premixed gases. The magnetic field caused changes in multiple free radical chain reaction pathways during the explosions of methane and propane. By simulating key elementary reactions using Materials Studio, it was found that in the methane explosion process, the reactions C₂H₂+·H, ·C₃H₅+·H, and ·C₂H₅+·CH₃ exhibit the lowest energy gaps, with the minimum value being 0.043855 eV. In the case of propane explosion, the energy gaps of critical elementary reactions increase in the order of ·C₂H₃+·CH₃, C₂H₄+·O, C₂H₂+·O, ·CH₃+·H, and ·CH₃+·HCO, with the lowest being 0.012061 eV. These low energy barriers indicate that little energy is needed to affect key reactions during methane and propane explosions. The applied magnetic field reduces collisions between free radicals, thereby inhibiting the consumption of reaction intermediates and ultimately increasing the concentration of explosion products.

为了研究磁场对预混气体爆炸特性的影响及其机理，采用ch4 -空气和c3h8 -空气预混可燃气体进行了有磁场和无磁场条件下的爆炸实验。爆炸产物分析揭示了两种条件下成分类型和浓度的变化。此外，还进行了与产品形成相关的模拟研究。实验结果表明，磁场降低了两种混合物的最大爆炸压力和火焰速度，而烷烃产物的检出率显著提高。数值模拟结果表明，在ch4 -空气和c3h8 -空气预混气体中，·H、·O、·OH和·CH3对爆炸产物的生成起关键作用。在甲烷和丙烷爆炸过程中，磁场引起了多种自由基链反应途径的变化。通过Materials Studio模拟关键元素反应，发现在甲烷爆炸过程中，C2H2+·H、·C3H5+·H、·C2H5+·CH3反应的能隙最小，最小值为0.043855 eV。丙烷爆炸时，临界元素反应的能隙大小依次为·C2H3+·CH3、C2H4+·O、C2H2+·O、·CH3+·H、·CH3+·HCO，最低为0.012061 eV。这些低能垒表明，在甲烷和丙烷爆炸过程中，只需很少的能量就能影响关键反应。外加磁场减少了自由基之间的碰撞，从而抑制了反应中间体的消耗，最终提高了爆炸产物的浓度。

{"title":"Study on explosion characteristics of premixed gas influenced by magnetic field based on product analysis","authors":"Shoutao Hu , Zhiwei Zhang , Hao Gong , Zhong Guan , Meiqi Liu , Nana Wu","doi":"10.1016/j.compchemeng.2025.109516","DOIUrl":"10.1016/j.compchemeng.2025.109516","url":null,"abstract":"<div><div>In order to investigate the effects and mechanisms of magnetic fields on the explosion characteristics of premixed gases, explosion experiments were conducted under both magnetic field and no-magnetic field conditions using CH<sub>4</sub>-air and C<sub>3</sub>H<sub>8</sub>-air premixed combustible gases. Explosion product analysis revealed variations in component types and concentrations under both conditions. Additionally, simulation studies related to product formation were carried out. The experimental results showed that the magnetic fields reduced maximum explosion pressure and flame velocity for both mixtures, while the detection of alkane products significantly increased. Numerical simulations revealed that ·H, ·O, ·OH, and ·CH<sub>3</sub> play key roles in the generation of explosion products in CH<sub>4</sub>-air and C<sub>3</sub>H<sub>8</sub>-air premixed gases. The magnetic field caused changes in multiple free radical chain reaction pathways during the explosions of methane and propane. By simulating key elementary reactions using Materials Studio, it was found that in the methane explosion process, the reactions C<sub>2</sub>H<sub>2</sub>+·H, ·C<sub>3</sub>H<sub>5</sub>+·H, and ·C<sub>2</sub>H<sub>5</sub>+·CH<sub>3</sub> exhibit the lowest energy gaps, with the minimum value being 0.043855 eV. In the case of propane explosion, the energy gaps of critical elementary reactions increase in the order of ·C<sub>2</sub>H<sub>3</sub>+·CH<sub>3</sub>, C<sub>2</sub>H<sub>4</sub>+·O, C<sub>2</sub>H<sub>2</sub>+·O, ·CH<sub>3</sub>+·H, and ·CH<sub>3</sub>+·HCO, with the lowest being 0.012061 eV. These low energy barriers indicate that little energy is needed to affect key reactions during methane and propane explosions. The applied magnetic field reduces collisions between free radicals, thereby inhibiting the consumption of reaction intermediates and ultimately increasing the concentration of explosion products.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"206 ","pages":"Article 109516"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145691666","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

A survey and tutorial of reinforcement learning methods in Process Systems Engineering 过程系统工程中强化学习方法的综述与教程

IF 3.9 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Chemical Engineering

Pub Date : 2026-03-01 Epub Date: 2025-11-27 DOI: 10.1016/j.compchemeng.2025.109515

Maximilian Bloor , Max Mowbray , Ehecatl Antonio del Rio Chanona , Calvin Tsay

Sequential decision making under uncertainty is central to many Process Systems Engineering (PSE) challenges, where traditional methods often face limitations related to controlling and optimizing complex and stochastic systems. Reinforcement Learning (RL) offers a data-driven approach to derive control policies for such challenges. This paper presents a survey and tutorial on RL methods, tailored for the PSE community. We deliver a tutorial on RL, covering fundamental concepts and key algorithmic families including value-based, policy-based and actor-critic methods. Subsequently, we survey existing applications of these RL techniques across various PSE domains, such as in fed-batch and continuous process control, process optimization, and supply chains. We conclude with PSE-focused discussion of specialized techniques and emerging directions. By synthesizing the current state of RL algorithm development and implications for PSE this work identifies successes, challenges, trends, and outlines avenues for future research at the interface of these fields.

不确定条件下的顺序决策是许多过程系统工程（PSE）挑战的核心，传统方法在控制和优化复杂和随机系统方面经常面临限制。强化学习（RL）提供了一种数据驱动的方法来推导针对此类挑战的控制策略。本文介绍了针对PSE社区量身定制的RL方法的调查和教程。我们提供关于强化学习的教程，涵盖基本概念和关键算法家族，包括基于价值的，基于政策的和行动者批评的方法。随后，我们调查了这些RL技术在各种PSE领域的现有应用，例如进料批和连续过程控制、过程优化和供应链。最后，我们以pse为重点讨论了专业技术和新兴方向。通过综合RL算法开发的现状和对PSE的影响，本工作确定了成功、挑战、趋势，并概述了这些领域界面的未来研究途径。

{"title":"A survey and tutorial of reinforcement learning methods in Process Systems Engineering","authors":"Maximilian Bloor , Max Mowbray , Ehecatl Antonio del Rio Chanona , Calvin Tsay","doi":"10.1016/j.compchemeng.2025.109515","DOIUrl":"10.1016/j.compchemeng.2025.109515","url":null,"abstract":"<div><div>Sequential decision making under uncertainty is central to many Process Systems Engineering (PSE) challenges, where traditional methods often face limitations related to controlling and optimizing complex and stochastic systems. Reinforcement Learning (RL) offers a data-driven approach to derive control policies for such challenges. This paper presents a survey and tutorial on RL methods, tailored for the PSE community. We deliver a tutorial on RL, covering fundamental concepts and key algorithmic families including value-based, policy-based and actor-critic methods. Subsequently, we survey existing applications of these RL techniques across various PSE domains, such as in fed-batch and continuous process control, process optimization, and supply chains. We conclude with PSE-focused discussion of specialized techniques and emerging directions. By synthesizing the current state of RL algorithm development and implications for PSE this work identifies successes, challenges, trends, and outlines avenues for future research at the interface of these fields.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"206 ","pages":"Article 109515"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145691667","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

Q-learning agent-based level control of surge tanks for improved continuous manufacturing of monoclonal antibodies 基于q学习智能体的调压罐液位控制，用于改进单克隆抗体的连续生产

IF 3.9 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Chemical Engineering

Pub Date : 2026-03-01 Epub Date: 2025-11-27 DOI: 10.1016/j.compchemeng.2025.109514

Naveen G Jesubalan , Saxena Nikita , Shantanu Banerjee , Navnath Deore , Keshari Gupta , Anurag S Rathore

During the continuous production of monoclonal antibodies, the optimal management of surge tanks is crucial for process scheduling and mitigating disruptions caused by potential process variations, equipment failures, or calibration errors. This study presents a Q-learning-based reinforcement learning (RL) agent designed to regulate surge tank levels, offering a more sophisticated alternative to the conventional ON/OFF control strategy. To ensure an accurate representation of real-world conditions, the RL training environment was modeled with all process limitations and scheduling dynamics in place. The Q-learning agent was trained using surge tank heights as observational inputs, with a reward policy designed to accommodate a wide range of scenarios, from steady-state conditions to process deviations. A replay buffer function was incorporated to enhance the model's robustness.

The agent underwent extensive training with 100,000 episodes and was evaluated using 100 random episodes for kernel density estimation (KDE)and 10 random episodes for in-depth analysis. In addition, a comparative analysis was conducted between the RL-based controller and a rule-based controller. This assessment aimed to highlight the reliability and robustness of the proposed control strategy. During the agent construction phase, each episode lasted 70 min, accounting for single process cycle. After training and testing, the agent was deployed in real-time and integrated with the PLC and other sensors using Python middleware. The reliability of the built agent was further tested through two unforeseen events introduced during the campaign. The results demonstrate the resilience and effectiveness of the proposed approach towards maintaining surge tank stability, thereby underscoring the robustness it offers and its suitability for implementation in commercial manufacturing.

在单克隆抗体的连续生产过程中，调压罐的优化管理对于工艺调度和减轻由潜在的工艺变化、设备故障或校准错误引起的中断至关重要。本研究提出了一种基于q学习的强化学习（RL）代理，旨在调节调压箱液位，为传统的ON/OFF控制策略提供更复杂的替代方案。为了确保真实世界条件的准确表示，RL训练环境的建模包含了所有的过程限制和调度动态。Q-learning代理使用调压罐高度作为观察输入进行训练，其奖励策略旨在适应从稳态条件到过程偏差的各种场景。为了增强模型的鲁棒性，引入了重放缓冲函数。代理接受了100,000集的广泛训练，并使用100个随机集进行核密度估计（KDE）和10个随机集进行深度分析。此外，还对基于rl的控制器和基于规则的控制器进行了对比分析。该评估旨在强调所提出的控制策略的可靠性和鲁棒性。代建阶段，每集持续70分钟，占单工艺周期。经过培训和测试，该代理被实时部署，并使用Python中间件与PLC和其他传感器集成。通过在战役中引入的两个不可预见的事件，进一步测试了构建剂的可靠性。结果证明了所提出的方法在维持调压箱稳定性方面的弹性和有效性，从而强调了它提供的鲁棒性及其在商业制造中实施的适用性。

{"title":"Q-learning agent-based level control of surge tanks for improved continuous manufacturing of monoclonal antibodies","authors":"Naveen G Jesubalan , Saxena Nikita , Shantanu Banerjee , Navnath Deore , Keshari Gupta , Anurag S Rathore","doi":"10.1016/j.compchemeng.2025.109514","DOIUrl":"10.1016/j.compchemeng.2025.109514","url":null,"abstract":"<div><div>During the continuous production of monoclonal antibodies, the optimal management of surge tanks is crucial for process scheduling and mitigating disruptions caused by potential process variations, equipment failures, or calibration errors. This study presents a Q-learning-based reinforcement learning (RL) agent designed to regulate surge tank levels, offering a more sophisticated alternative to the conventional ON/OFF control strategy. To ensure an accurate representation of real-world conditions, the RL training environment was modeled with all process limitations and scheduling dynamics in place. The Q-learning agent was trained using surge tank heights as observational inputs, with a reward policy designed to accommodate a wide range of scenarios, from steady-state conditions to process deviations. A replay buffer function was incorporated to enhance the model's robustness.</div><div>The agent underwent extensive training with 100,000 episodes and was evaluated using 100 random episodes for kernel density estimation (KDE)and 10 random episodes for in-depth analysis. In addition, a comparative analysis was conducted between the RL-based controller and a rule-based controller. This assessment aimed to highlight the reliability and robustness of the proposed control strategy. During the agent construction phase, each episode lasted 70 min, accounting for single process cycle. After training and testing, the agent was deployed in real-time and integrated with the PLC and other sensors using Python middleware. The reliability of the built agent was further tested through two unforeseen events introduced during the campaign. The results demonstrate the resilience and effectiveness of the proposed approach towards maintaining surge tank stability, thereby underscoring the robustness it offers and its suitability for implementation in commercial manufacturing.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"206 ","pages":"Article 109514"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145749130","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

Dynamic simulation and operational optimization of dividing wall batch distillation columns based on rigorous models 基于严格模型的分壁间歇精馏塔动态仿真及操作优化

IF 3.9 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Chemical Engineering

Pub Date : 2026-03-01 Epub Date: 2025-12-24 DOI: 10.1016/j.compchemeng.2025.109542

Xing Qian , Jiayi Du , Gonghan Guo , Shengkun Jia , Chao Zhang

Batch distillation, as a widely applied separation technology, demonstrates significant advantages in small-scale, multi-component, and composition-variable separation tasks. Current research primarily focuses on two directions to enhance its overall performance, reduce energy consumption, and shorten separation time: development of novel process configurations and operational optimization. Among these, the dividing wall batch distillation column (DWBDC) remarkably improves separation efficiency of conventional batch distillation through its innovative batch dividing wall process intensification structure. However, as a highly nonlinear dynamic system, DWBDC presents considerable challenges in rigorous simulation and optimization, which is well worth further investigation. Bayesian optimization algorithms have gained extensive application in chemical engineering due to their efficient global search capability in recent years. This study innovatively applies Bayesian optimization to batch distillation processes, establishing an operational optimization framework based on this algorithm and implementing it in the optimal design of various batch distillation configurations. To systematically evaluate DWBDC's superiority, rigorous dynamic simulations were conducted on three configurations: conventional batch distillation column (BDC), middle vessel batch distillation column (MVBDC), and DWBDC, with corresponding concentration control systems developed. The research examined separation performances of these configurations for industrial waste solvents with different feed compositions (light-component-dominant, intermediate-component-dominant, and balanced light/intermediate-component feeds). Bayesian optimization was employed to optimize operational parameters for all three configurations, followed by comparative performance analysis under optimal conditions. Results demonstrate the superior performance of DWBDC in both operating time and economic efficiency, providing crucial theoretical foundations and practical guidance for industrial application of dividing wall batch distillation technology.

间歇精馏作为一种广泛应用的分离技术，在小规模、多组分、多组分的分离任务中具有显著的优势。目前的研究主要集中在两个方向，以提高其整体性能，降低能耗，缩短分离时间：开发新的工艺配置和操作优化。其中，分壁间歇精馏塔（DWBDC）通过其创新的间歇分壁过程强化结构，显著提高了常规间歇精馏的分离效率。然而，作为一个高度非线性的动态系统，DWBDC在严格的仿真和优化方面面临着相当大的挑战，值得进一步研究。近年来，贝叶斯优化算法以其高效的全局搜索能力在化工领域得到了广泛的应用。本研究创新性地将贝叶斯优化应用于间歇精馏过程，建立了基于该算法的操作优化框架，并将其应用于间歇精馏的各种配置优化设计中。为了系统地评价DWBDC的优越性，对常规间歇精馏塔（BDC）、中间容器间歇精馏塔（MVBDC）和DWBDC三种配置进行了严格的动态仿真，并开发了相应的浓度控制系统。研究考察了这些构型对不同原料组成（轻组分为主、中间组分为主、轻/中间组分平衡）的工业废溶剂的分离性能。采用贝叶斯优化方法对三种构型的运行参数进行优化，并在最优条件下进行性能对比分析。结果表明，DWBDC在操作时间和经济效率方面均具有优越的性能，为分壁间歇精馏技术的工业应用提供了重要的理论基础和实践指导。

{"title":"Dynamic simulation and operational optimization of dividing wall batch distillation columns based on rigorous models","authors":"Xing Qian , Jiayi Du , Gonghan Guo , Shengkun Jia , Chao Zhang","doi":"10.1016/j.compchemeng.2025.109542","DOIUrl":"10.1016/j.compchemeng.2025.109542","url":null,"abstract":"<div><div>Batch distillation, as a widely applied separation technology, demonstrates significant advantages in small-scale, multi-component, and composition-variable separation tasks. Current research primarily focuses on two directions to enhance its overall performance, reduce energy consumption, and shorten separation time: development of novel process configurations and operational optimization. Among these, the dividing wall batch distillation column (DWBDC) remarkably improves separation efficiency of conventional batch distillation through its innovative batch dividing wall process intensification structure. However, as a highly nonlinear dynamic system, DWBDC presents considerable challenges in rigorous simulation and optimization, which is well worth further investigation. Bayesian optimization algorithms have gained extensive application in chemical engineering due to their efficient global search capability in recent years. This study innovatively applies Bayesian optimization to batch distillation processes, establishing an operational optimization framework based on this algorithm and implementing it in the optimal design of various batch distillation configurations. To systematically evaluate DWBDC's superiority, rigorous dynamic simulations were conducted on three configurations: conventional batch distillation column (BDC), middle vessel batch distillation column (MVBDC), and DWBDC, with corresponding concentration control systems developed. The research examined separation performances of these configurations for industrial waste solvents with different feed compositions (light-component-dominant, intermediate-component-dominant, and balanced light/intermediate-component feeds). Bayesian optimization was employed to optimize operational parameters for all three configurations, followed by comparative performance analysis under optimal conditions. Results demonstrate the superior performance of DWBDC in both operating time and economic efficiency, providing crucial theoretical foundations and practical guidance for industrial application of dividing wall batch distillation technology.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"206 ","pages":"Article 109542"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145880239","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

Digital design of crystallization processes using statistical machine learning 使用统计机器学习的结晶过程的数字化设计

IF 3.9 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Chemical Engineering

Pub Date : 2026-03-01 Epub Date: 2025-12-10 DOI: 10.1016/j.compchemeng.2025.109518

Yash Barhate , Yung Shun Kang , Neda Nazemifard , C․Benjamin Renner , Yihui Yang , Charles Papageorgiou , Zoltan K. Nagy

This study presents a generic statistical machine learning (ML)-driven modeling workflow for designing crystallization processes, serving as a practical alternative in situations where traditional mechanistic population-balance modeling approaches are impractical. Key highlights of the proposed workflow include synthetic data augmentation to reduce dependency on extensive experimental datasets; the incorporation of active learning strategies to iteratively suggest experimental conditions and refine experimental datasets; and the successful deployment of ML models within the Quality-by-Digital-Design (QbDD) framework. The effectiveness of the proposed approach is demonstrated through two case studies: (1) an in-silico study involving an agrochemical compound, and (2) an experimental case study with an industrial pharmaceutical compound. ML models trained in these scenarios achieved prediction errors below 10 % when predicting critical quality attributes (CQAs). These models subsequently enabled deterministic and probabilistic design space analyses, followed by model-based process optimization, and were confirmed through experimental validation. While the approaches are exemplified using crystallization processes, it provides a generic and systematic framework for the ML model, development applicable to reactions and other complex process systems.

本研究提出了一个通用的统计机器学习（ML）驱动的建模工作流程，用于设计结晶过程，在传统的机械人口平衡建模方法不切实际的情况下，作为一种实用的替代方案。提出的工作流的关键亮点包括合成数据增强，以减少对大量实验数据集的依赖；结合主动学习策略，迭代提出实验条件，完善实验数据集；以及在数字设计质量（QbDD）框架内成功部署ML模型。通过两个案例研究证明了所提出方法的有效性：(1)涉及农业化学化合物的计算机研究，以及(2)涉及工业药物化合物的实验案例研究。在这些场景中训练的ML模型在预测关键质量属性（cqa）时实现了低于10%的预测误差。这些模型随后进行了确定性和概率设计空间分析，随后进行了基于模型的流程优化，并通过实验验证得到了证实。虽然这些方法是用结晶过程举例说明的，但它为ML模型提供了一个通用和系统的框架，开发适用于反应和其他复杂的过程系统。

{"title":"Digital design of crystallization processes using statistical machine learning","authors":"Yash Barhate , Yung Shun Kang , Neda Nazemifard , C․Benjamin Renner , Yihui Yang , Charles Papageorgiou , Zoltan K. Nagy","doi":"10.1016/j.compchemeng.2025.109518","DOIUrl":"10.1016/j.compchemeng.2025.109518","url":null,"abstract":"<div><div>This study presents a generic statistical machine learning (ML)-driven modeling workflow for designing crystallization processes, serving as a practical alternative in situations where traditional mechanistic population-balance modeling approaches are impractical. Key highlights of the proposed workflow include synthetic data augmentation to reduce dependency on extensive experimental datasets; the incorporation of active learning strategies to iteratively suggest experimental conditions and refine experimental datasets; and the successful deployment of ML models within the Quality-by-Digital-Design (QbDD) framework. The effectiveness of the proposed approach is demonstrated through two case studies: (1) an <em>in-silico</em> study involving an agrochemical compound, and (2) an experimental case study with an industrial pharmaceutical compound. ML models trained in these scenarios achieved prediction errors below 10 % when predicting critical quality attributes (CQAs). These models subsequently enabled deterministic and probabilistic design space analyses, followed by model-based process optimization, and were confirmed through experimental validation. While the approaches are exemplified using crystallization processes, it provides a generic and systematic framework for the ML model, development applicable to reactions and other complex process systems.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"206 ","pages":"Article 109518"},"PeriodicalIF":3.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145797290","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

The incorporation of qualitative knowledge in hybrid modeling 混合建模中定性知识的结合

IF 3.9 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Chemical Engineering

Pub Date : 2026-02-15 Epub Date: 2025-11-18 DOI: 10.1016/j.compchemeng.2025.109484

Elia Arnese-Feffin , Nidhish Sagar , Luis A. Briceno-Mena , Birgit Braun , Ivan Castillo , Caterina Rizzo , Linh Bui , Jinsuo Xu , Leo H. Chiang , Richard D. Braatz

Data-driven modeling enables the pursuit of model-based solutions when no or partial knowledge is available on the process of interest. The typically poor generalization performance of data-driven models can be improved by incorporating all available knowledge into the model development workflow, i.e. by hybrid modeling. However, how to incorporate this knowledge and what kind of knowledge to use have been strictly problem-dependent questions: whether a general framework for hybrid modeling can be devised remains an open research topic. In this article, we make the first step towards such an objective: we propose a method relying on theoretically sound modification of the objective function of data-driven models by incorporation of constraints derived from process knowledge, an approach that can be readily implemented in existing software packages with minimal overhead. We focus on an underutilized source of knowledge, i.e. qualitative knowledge. The proposed approach is demonstrated in two case studies, where we employ qualitative and quantitative process knowledge with varying degrees of complexity and discuss their effectiveness. Results show promising performance, paving the way for a truly general hybrid modeling framework.

当感兴趣的过程没有或只有部分知识可用时，数据驱动的建模支持追求基于模型的解决方案。通过将所有可用的知识合并到模型开发工作流中，即通过混合建模，可以改善数据驱动模型的典型的较差的泛化性能。然而，如何整合这些知识以及使用什么样的知识一直是严格依赖于问题的问题：是否可以设计出混合建模的通用框架仍然是一个开放的研究课题。在本文中，我们向这样一个目标迈出了第一步：我们提出了一种方法，该方法依赖于数据驱动模型的目标函数的理论上合理的修改，通过合并来自过程知识的约束，这种方法可以很容易地在现有软件包中以最小的开销实现。我们专注于未充分利用的知识来源，即定性知识。所提出的方法在两个案例研究中得到了证明，在这些案例研究中，我们采用了不同复杂程度的定性和定量过程知识，并讨论了它们的有效性。结果显示了良好的性能，为真正通用的混合建模框架铺平了道路。

{"title":"The incorporation of qualitative knowledge in hybrid modeling","authors":"Elia Arnese-Feffin , Nidhish Sagar , Luis A. Briceno-Mena , Birgit Braun , Ivan Castillo , Caterina Rizzo , Linh Bui , Jinsuo Xu , Leo H. Chiang , Richard D. Braatz","doi":"10.1016/j.compchemeng.2025.109484","DOIUrl":"10.1016/j.compchemeng.2025.109484","url":null,"abstract":"<div><div>Data-driven modeling enables the pursuit of model-based solutions when no or partial knowledge is available on the process of interest. The typically poor generalization performance of data-driven models can be improved by incorporating all available knowledge into the model development workflow, i.e. by hybrid modeling. However, how to incorporate this knowledge and what kind of knowledge to use have been strictly problem-dependent questions: whether a general framework for hybrid modeling can be devised remains an open research topic. In this article, we make the first step towards such an objective: we propose a method relying on theoretically sound modification of the objective function of data-driven models by incorporation of constraints derived from process knowledge, an approach that can be readily implemented in existing software packages with minimal overhead. We focus on an underutilized source of knowledge, i.e. <em>qualitative</em> knowledge. The proposed approach is demonstrated in two case studies, where we employ qualitative and quantitative process knowledge with varying degrees of complexity and discuss their effectiveness. Results show promising performance, paving the way for a truly general hybrid modeling framework.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"205 ","pages":"Article 109484"},"PeriodicalIF":3.9,"publicationDate":"2026-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145620087","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