Computers & Chemical Engineering最新文献

Computer-aided mixture design using molecule superstructures 基于分子超结构的计算机辅助混合设计

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-07-05 DOI: 10.1016/j.compchemeng.2025.109232

Philipp Rehner, Johannes Schilling, André Bardow

{"title":"Computer-aided mixture design using molecule superstructures","authors":"Philipp Rehner, Johannes Schilling, André Bardow","doi":"10.1016/j.compchemeng.2025.109232","DOIUrl":"10.1016/j.compchemeng.2025.109232","url":null,"abstract":"<div><div>Computer-aided molecular and process design determines the best molecules together with their optimal process for a given objective function. The nonlinearity of typical thermodynamic models and the discrete nature of molecules lead to the challenge of solving a mixed-integer nonlinear programming problem. The optimization is even more demanding for a mixture design, in which two or more molecules and their composition are degrees of freedom. At the same time, the quality of the solution strongly depends on the accuracy of the thermodynamic model used to predict the thermophysical properties required to determine the process-based objective function and constraints. Today, most molecular design methods employ thermodynamic models based on group counts, resulting in a loss of structural information of the molecule during the optimization. The present work extends the integrated design of mixtures and processes in three areas: (1) Molecule superstructures represent chemical families by graphs that preserve the full adjacency matrix to unlock property prediction methods beyond first-order group-contribution methods. (2) Implicit automatic differentiation of process models determines Jacobians and Hessians needed for the optimization algorithm within machine precision. (3) A fine-tuned outer approximation algorithm efficiently calculates rankings of candidate mixtures for the non-convex integrated molecular and process design problem. In a case study, the design method is used to determine the optimal working fluid mixture for an Organic Rankine cycle.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"201 ","pages":"Article 109232"},"PeriodicalIF":3.9,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144570958","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 approach to wastewater valorization in the cassava value chain through biorefineries based on anaerobic digestion 基于厌氧消化的生物精炼厂在木薯价值链中实现废水增值的方法

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-07-05 DOI: 10.1016/j.compchemeng.2025.109274

Tatiana Agudelo-Patiño , Mariana Ortiz-Sanchez , Oscar Daniel Sanchez-Godoy , Leonardo Alonso-Gomez , Carlos Ariel Cardona Alzate

{"title":"An approach to wastewater valorization in the cassava value chain through biorefineries based on anaerobic digestion","authors":"Tatiana Agudelo-Patiño , Mariana Ortiz-Sanchez , Oscar Daniel Sanchez-Godoy , Leonardo Alonso-Gomez , Carlos Ariel Cardona Alzate","doi":"10.1016/j.compchemeng.2025.109274","DOIUrl":"10.1016/j.compchemeng.2025.109274","url":null,"abstract":"<div><div>The cassava value chain (VC) is essential for food security in developing countries. During cassava agro-industrial processing, wastewater (WW) is the main residue generated. Anaerobic digestion (AD) is an effective treatment for this WW, and modified AD (MAD) can produce valuable intermediates such as volatile fatty acids (VFAs). Although several studies have explored the valorization of cassava waste in the context of the circular economy, limited work has combined experimental results with techno-economic and environmental assessments of integrated AD-based biorefineries within the cassava VC. This study evaluates the feasibility and environmental impacts of incorporating AD-based biorefineries into the cassava VC. Experimental results from conventional AD (CAD) and MAD were used to simulate and assess multiple integration scenarios. Biorefineries were evaluated economically and environmentally, using cassava starch production as the base case. A biogas yield and mixed VFAs concentration of 5.57 ml/ml WW and 42.18 mg/ml WW was evidenced in the conventional AD (CAD) and MAD, respectively. Acetic acid was the most representative VFAs. The base case presented a payback period (PBP) of 10 years. CAD integration enhances economic performance by enabling the recovery of unconsumed mixed VFAs. MAD integration allowed a reduction of 18 % of the PBP. The cassava VC was found to have a carbon footprint of 2.63 kg CO₂ and a water depletion of 11.20 m³ per kilogram of WW. However, a 54.4 % reduction was achieved by integrating AD-based biorefineries. These results elucidate the potential of MAD-based biorefineries, showing favorable economic results, while environmental impact is reduced.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"201 ","pages":"Article 109274"},"PeriodicalIF":3.9,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144580358","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

Continuous learning of the value function utilizing deep reinforcement learning to be used as the objective in model predictive control 利用深度强化学习对值函数进行持续学习，作为模型预测控制的目标

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-07-05 DOI: 10.1016/j.compchemeng.2025.109262

Daniel Beahr, Elijah Hedrick, Debangsu Bhattacharyya

{"title":"Continuous learning of the value function utilizing deep reinforcement learning to be used as the objective in model predictive control","authors":"Daniel Beahr, Elijah Hedrick, Debangsu Bhattacharyya","doi":"10.1016/j.compchemeng.2025.109262","DOIUrl":"10.1016/j.compchemeng.2025.109262","url":null,"abstract":"<div><div>Reinforcement learning (RL) and model predictive control (MPC) possess an inherent synergy in the manner in which they function. The work presented here investigates integrating RL with existing MPC in order to provide a constrained policy for the RL while also creating an adaptable objective for the MPC. Selection of MPC for combination with RL is not arbitrary. Two specific aspects of MPC are advantageous for such a combination: the use of a value function and the use of a model. The use of a model in MPC is useful since, by solving for the optimal trajectory, a projected view of the expected reward is gained. While this information can be inaccurate based on the current value function, it can allow for accelerated learning. By combining this with a correction for state transitions, an MPC formulation is derived that obeys the constraints set forth, but can adapt to changing dynamics and correct for plant model mismatch without a required discrete update, an advantage over standard MPC formulations. We propose two algorithms for the proposed value-function model predictive controller (VFMPC): one denoted as VFMPC(0) where the one step return is utilized to learn the cost function, and the other denoted as VFMPC(n), where the optimal trajectory is used to learn the n-step return subject to the dynamics of the process model. An artificial network (ANN) model is introduced into VFMPC(n) to improve the controller performance under slowly changing dynamics and plant-model mismatch, called VFMPC(<span><math><msub><mrow><mi>N</mi></mrow><mrow><mi>P</mi></mrow></msub></math></span>). The developed algorithms are applied to two applications.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"201 ","pages":"Article 109262"},"PeriodicalIF":3.9,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144580357","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 hybrid Kalman filter and physics-informed neural network approach for leakage detection and localization in heat exchanger networks 一种混合卡尔曼滤波和物理信息神经网络方法用于热交换器网络的泄漏检测和定位

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-07-04 DOI: 10.1016/j.compchemeng.2025.109259

Ming Shi, Lin Sun, Zhongcheng Bi, Renchu He

{"title":"A hybrid Kalman filter and physics-informed neural network approach for leakage detection and localization in heat exchanger networks","authors":"Ming Shi, Lin Sun, Zhongcheng Bi, Renchu He","doi":"10.1016/j.compchemeng.2025.109259","DOIUrl":"10.1016/j.compchemeng.2025.109259","url":null,"abstract":"<div><div>Leakage in heat exchanger network poses a critical latent threat to energy efficiency and process safety in industrial operations. This paper presents an integrated detection framework that synergistically combines Kalman Filter with physics-informed neural networks enable real-time detection and localization of leakage events. Kalman Filter is employed to preprocess noisy sensor data and accurately estimate key parameters, most notably the heat transfer coefficient, which is highly sensitive to leakage-induced deviations. These refined estimates serve as inputs for physics-informed neural networks, whose training is constrained by fundamental physical laws, enhancing fault detection accuracy. Validation via extensive simulations and experimental case studies demonstrates that the proposed framework reliably detects leakage flows as low as 1%, with an average inference time of only 0.76ms per sample. Compared with benchmark models, the proposed framework reduces prediction RMSE by 7%–15% and increases F1-score by 3%–5%, while maintaining millisecond-level responsiveness suitable for industrial real-time monitoring and precisely localizes the affected unit within complex heat exchanger network configurations. The integration of advanced state estimation and physics-constrained learning offers a robust strategy for improving the reliability, safety, and energy efficiency of industrial heat exchanger systems.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"201 ","pages":"Article 109259"},"PeriodicalIF":3.9,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144571233","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 practical reinforcement learning control design for nonlinear systems with input and output constraints 具有输入输出约束的非线性系统的实用强化学习控制设计

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-07-03 DOI: 10.1016/j.compchemeng.2025.109248

Hesam Hassanpour , Brandon Corbett , Prashant Mhaskar

{"title":"A practical reinforcement learning control design for nonlinear systems with input and output constraints","authors":"Hesam Hassanpour , Brandon Corbett , Prashant Mhaskar","doi":"10.1016/j.compchemeng.2025.109248","DOIUrl":"10.1016/j.compchemeng.2025.109248","url":null,"abstract":"<div><div>In this work, a practically implementable reinforcement learning (RL)-based controller is designed to handle process input and output constraints. In a typical RL problem, an RL agent is employed to learn an optimal control policy through interactions with the environment. This is unimplementable in practical situations due to the excessive exploration needed by the RL-based controller and exacerbated by the possible violation of the input and output constraints. We previously proposed an implementable RL controller that can circumvent random exploration needs by leveraging existing model predictive control (MPC) to pre-train/warm start the RL agent. The pre-trained agent is subsequently employed in real-time to engage with the process to improve its performance by gaining more knowledge about the nonlinear behavior of the system. This work generalizes our previous method to handle constraints on the outputs and the rate of change of the inputs by modifying the reward function. The effectiveness of the proposed algorithm is illustrated through simulations conducted for control of a pH neutralization process. The findings indicate that the proposed RL method enhances closed-loop performance in comparison to the nominal MPC while satisfying all input and output constraints.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"201 ","pages":"Article 109248"},"PeriodicalIF":3.9,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144580359","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 multi-agent system for hybrid optimization 混合优化的多智能体系统

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-07-03 DOI: 10.1016/j.compchemeng.2025.109258

Eric S. Fraga, Veerawat Udomvorakulchai, Miguel Pineda, Lazaros G. Papageorgiou

{"title":"A multi-agent system for hybrid optimization","authors":"Eric S. Fraga, Veerawat Udomvorakulchai, Miguel Pineda, Lazaros G. Papageorgiou","doi":"10.1016/j.compchemeng.2025.109258","DOIUrl":"10.1016/j.compchemeng.2025.109258","url":null,"abstract":"<div><div>Optimization problems in process engineering, including design and operation, can often pose challenges to many solvers: multi-modal, non-smooth, and discontinuous models often with large computational requirements. In such cases, the optimization problem is often treated as a <em>black box</em> in which only the value of the objective function is required, sometimes with some indication of the measure of the violation of the constraints. Such problems have traditionally been tackled through the use of <em>direct search</em> and <em>meta-heuristic</em> methods. The challenge, then, is to determine which of these methods or combination of methods should be considered to make most effective use of finite computational resources. This paper presents a multi-agent system for optimization which enables a set of solvers to be applied simultaneously to an optimization problem, including different instantiations of any solver. The evaluation of the optimization problem model is controlled by a scheduler agent which facilitates cooperation and competition between optimization methods. The architecture and implementation of the agent system is described in detail, including the solver, model evaluation, and scheduler agents. A suite of direct search and meta-heuristic methods has been developed for use with this system. Case studies from process systems engineering applications are presented and the results show the potential benefits of automated cooperation between different optimization solvers and motivate the implementation of competition between solvers.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"202 ","pages":"Article 109258"},"PeriodicalIF":3.9,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144605378","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

Comparing generative process synthesis approaches with superstructure optimization for the conception of supercritical CO2 Brayton cycles 超临界CO2布雷顿循环概念生成过程综合方法与上层结构优化方法的比较

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-07-03 DOI: 10.1016/j.compchemeng.2025.109255

Antonio Rocha Azevedo , Tahar Nabil , Valentin Loubière , Romain Privat , Thibaut Neveux , Jean-Marc Commenge

{"title":"Comparing generative process synthesis approaches with superstructure optimization for the conception of supercritical CO2 Brayton cycles","authors":"Antonio Rocha Azevedo , Tahar Nabil , Valentin Loubière , Romain Privat , Thibaut Neveux , Jean-Marc Commenge","doi":"10.1016/j.compchemeng.2025.109255","DOIUrl":"10.1016/j.compchemeng.2025.109255","url":null,"abstract":"<div><div>In process synthesis, while heuristic-based approaches are most often used for proposing relevant alternatives (that must then be thoroughly analyzed), this strategy may not be the most efficient. When it comes to the search for innovative processes, prior domain knowledge may be scarce or may not effectively exploit the properties contributing to the process novelty. Generative synthesis approaches that can freely explore the search space and that do not rely on any previous knowledge, have been proposed in the literature. Yet, a lack of benchmarks on complex problems strongly hinders their use. In this work, we address this gap by comparing two generative approaches, based on Evolutionary Programming and Machine Learning, to a superstructure optimization (which serves as a baseline). They are applied to the synthesis of supercritical CO<sub>2</sub> Brayton cycles. Despite starting with no field of expertise, the generative approaches not only manage to identify multiple known heuristics of the domain, but also a counter-intuitive and new way of increasing the efficiency of sCO<sub>2</sub> cycles — by expanding the fluid at lower temperatures. The approaches’ use-cases are discussed, based on the amount of computational resources necessary, implementation difficulties and quality of the results.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"201 ","pages":"Article 109255"},"PeriodicalIF":3.9,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144570957","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

Exploring data augmentation: Multi-task methods for molecular property prediction 探索数据增强：分子性质预测的多任务方法

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-07-02 DOI: 10.1016/j.compchemeng.2025.109253

Muhammad bin Javaid , Timo Gervens , Alexander Mitsos , Martin Grohe , Jan G. Rittig

引用次数: 0

Building hybrid AI models in chemical engineering: A tutorial review 在化学工程中建立混合人工智能模型：教程回顾

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-07-02 DOI: 10.1016/j.compchemeng.2025.109236

Arijit Chakraborty , Naz Pinar Taskiran , Rishab Kottooru , Vipul Mann , Venkat Venkatasubramanian

{"title":"Building hybrid AI models in chemical engineering: A tutorial review","authors":"Arijit Chakraborty , Naz Pinar Taskiran , Rishab Kottooru , Vipul Mann , Venkat Venkatasubramanian","doi":"10.1016/j.compchemeng.2025.109236","DOIUrl":"10.1016/j.compchemeng.2025.109236","url":null,"abstract":"<div><div>Modern machine learning (ML) methods excel at learning from vast datasets and have demonstrated exceptional performance in conventional applications like text prediction, recommender systems, and chatbots. However, their application in science and engineering is constrained by challenges such as limited explainability, susceptibility to hallucinations, and a lack of grounding in first-principles knowledge. These limitations could be overcome by incorporating symbolic or classical artificial intelligence (AI) methods, which have been applied in chemical engineering for more than four decades. This paper outlines a systematic approach to incorporating domain knowledge into the AI/ML workflow, resulting in the development of hybrid AI models. Our proposed four-stage process includes (1) knowledge assessment, (2) domain-informed problem formulation, (3) selection of an appropriate AI/ML model, and (4) model validation. Additionally, we present six commonly used templates for hybrid AI development: feature engineering, customized knowledge representation, imposition of additional constraints, integration of these approaches, custom model architecture design, and end-to-end domain-specific AI models. These templates are organized by increasing levels of “hybridization”, reflecting progressively more advanced integration of domain knowledge. The goal is to migrate from the paradigm of large language models (LLMs) to large knowledge models (LKMs), which are better positioned to meet the unique demands of science and engineering applications.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"201 ","pages":"Article 109236"},"PeriodicalIF":3.9,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144570956","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

Structural constraint reduction in process simulator-based optimisation: Leveraging the P-graph framework 基于过程模拟器的优化中的结构约束减少：利用p图框架

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-07-01 DOI: 10.1016/j.compchemeng.2025.109254

Darrick Hillaby, Andrés Piña-Martinez, Laurent Falk, Jean-François Portha

{"title":"Structural constraint reduction in process simulator-based optimisation: Leveraging the P-graph framework","authors":"Darrick Hillaby, Andrés Piña-Martinez, Laurent Falk, Jean-François Portha","doi":"10.1016/j.compchemeng.2025.109254","DOIUrl":"10.1016/j.compchemeng.2025.109254","url":null,"abstract":"<div><div>In superstructure-based process synthesis, the same superstructure can be modelled with different levels of detail. Models can be characterised into three main categories: high-level aggregate models, shortcut models, and detailed rigorous models. If a detailed modelling level is required, process simulators offer a reliable and rigorous modelling environment. In this context, process simulator-based superstructure optimisation may be performed by postulating the superstructure: (1) in an external optimisation environment, or (2) as a flowsheet in the process simulator itself. This work is focused on the latter option.</div><div>To reduce the tedious mathematical writing of the logical constraints required to guarantee the structural coherence of a sequence of unit operations, a P-graph-based framework is proposed in the current work. The developed framework consists of three algorithms. The first algorithm transforms the superstructure flowsheet into a P-graph. The second algorithm gets process sub-flowsheets from the superstructure by searching for active units corresponding to a set of decisions made, for example, by an optimiser. The third one checks structural feasibility by verifying that the resulting process satisfies the five axioms of the original P-graph framework and two additional connectivity tests proposed in this work.</div><div>The methodology is tested on two different examples based on Organic Rankine Cycles. The first case study, based on a published article, consists in applying the methodology to build a superstructure implicitly equivalent to the original logic constraints formulation. The second case study is presented to implement the proposed framework into a Combined Heat and Power Cycle optimisation problem.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"201 ","pages":"Article 109254"},"PeriodicalIF":3.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144563667","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