Computers & Chemical Engineering最新文献_第5页

Capturing uncertainty in black-box chromatography modelling using conformal prediction and Gaussian processes 利用保形预测和高斯过程捕捉黑箱色谱建模中的不确定性

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-04-18 DOI: 10.1016/j.compchemeng.2025.109136

Tien Dung Pham , Robert Bassett , Uwe Aickelin

引用次数: 0

Distributing Chemical Reactions between Cell Populations: Exemplar Studies 在细胞群之间分布化学反应：范例研究

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-04-18 DOI: 10.1016/j.compchemeng.2025.109110

Sameer Sekhri, Chinmay K. Haritas, J. Krishnan

{"title":"Distributing Chemical Reactions between Cell Populations: Exemplar Studies","authors":"Sameer Sekhri, Chinmay K. Haritas, J. Krishnan","doi":"10.1016/j.compchemeng.2025.109110","DOIUrl":"10.1016/j.compchemeng.2025.109110","url":null,"abstract":"<div><div>The distribution of chemical reactions between different reactors or reaction compartments is foundational to chemical reaction engineering. It is also of relevance to both systems and synthetic biology. In this study we examine sample reaction systems distributed between two cell populations which have significant interactions between each other. We examine two scenarios motivated by specific studies in the experimental synthetic biology literature, one which involves a sequential distribution of reactions/components and one which involves a parallel distribution. We develop a modelling and systems framework to assess the overall production rate of product and how it depends on various parameters: intrinsic kinetic parameters, as well as cell population growth/death/interaction parameters. We use computational, analytical and semi-analytical methods to analyse the associated model and isolate insights both structural and parameter dependent qualitative insights. We then expand the modelling framework to assess the potential effect of external resources on systems behaviour. Overall, our analysis reveals how significant nonlinear interactions between cells and across levels has a profound effect on the distribution of chemical reactions.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"200 ","pages":"Article 109110"},"PeriodicalIF":3.9,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937377","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

Incorporating Physical Constraints inside Neural Networks to Improve their Accuracy and Physical Reliability for Chemical Engineering Unit Operations Modeling 在神经网络中引入物理约束以提高化学工程单元操作建模的准确性和物理可靠性

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-04-18 DOI: 10.1016/j.compchemeng.2025.109156

Jana Mousa, Stéphane Negny, Rachid Ouaret, Alessandro Di Pretoro, Ludovic Montastruc

{"title":"Incorporating Physical Constraints inside Neural Networks to Improve their Accuracy and Physical Reliability for Chemical Engineering Unit Operations Modeling","authors":"Jana Mousa, Stéphane Negny, Rachid Ouaret, Alessandro Di Pretoro, Ludovic Montastruc","doi":"10.1016/j.compchemeng.2025.109156","DOIUrl":"10.1016/j.compchemeng.2025.109156","url":null,"abstract":"<div><div>Neural networks are machine learning models structured in interconnected layers of nodes, or neurons, designed to process and learn complex data patterns by adjusting connections based on the input data and desired output. A common challenge with these networks lies in their limited ability to incorporate fundamental physical principles, as they typically prioritize data pattern recognition over adherence to system-specific laws and constraints. This research introduces an advanced modeling framework that integrates physics-informed neural networks with data reconciliation techniques, embedding physical constraints directly into the neural network's learning process. By enforcing consistency with foundational physical laws, this hybrid approach effectively combines data-driven insights with physics-based accuracy, enhancing the model’s reliability for complex engineering applications. The study further assesses the performance of traditional neural networks, physics-informed networks, and data reconciliation methods, focusing on their application in the design and optimization of unit operations, revealing the advantages of this physics-augmented approach in bridging theoretical principles and practical modeling.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"199 ","pages":"Article 109156"},"PeriodicalIF":3.9,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143868232","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

Data augmentation for forecasting industrial aging processes via conditional multimodal generative time-series models 通过条件多模态生成时间序列模型预测工业老化过程的数据增强

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-04-17 DOI: 10.1016/j.compchemeng.2025.109109

Mihail Bogojeski , Nataliya Yakut , Sasho Nedelkoski , Shinichi Nakajima , Klaus-Robert Müller

{"title":"Data augmentation for forecasting industrial aging processes via conditional multimodal generative time-series models","authors":"Mihail Bogojeski , Nataliya Yakut , Sasho Nedelkoski , Shinichi Nakajima , Klaus-Robert Müller","doi":"10.1016/j.compchemeng.2025.109109","DOIUrl":"10.1016/j.compchemeng.2025.109109","url":null,"abstract":"<div><div>Data augmentation has shown to be effective for improving generalization performance of deep neural networks, especially in the regime of high noise and scarce data. However, this approach has not been applied to industrial aging processes (IAP) forecasting, where observed data are multimodal time-series, and therefore existing augmentation methods are not suitable for data generation. In this paper, we propose Seq-MVAE, a generative architecture that can generate complex time-series data consisting of multiple heterogeneous modalities. Seq-MVAE is capable of conditional generation, i.e., Seq-MVAE learns the joint distribution across the modalities, and allows users to generate a part of the modalities that are coherent with the other (given) modalities. This enables not only missing value imputation but also conditional generation, which is known to be crucial for data augmentation. We evaluate the generative performance and other aspects of Seq-MVAE on an artificial dataset generated based designed to simulate an industrial aging process, and show the effectiveness of data augmentation by Seq-MVAE on a real-world dataset acquired from an industrial plant.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"199 ","pages":"Article 109109"},"PeriodicalIF":3.9,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143886509","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

Integrated thermo-economic organic Rankine cycle and working fluid design – On the accuracy of molecular-based computer-aided methodologies 综合热经济有机朗肯循环和工作流体设计。基于分子的计算机辅助方法的准确性

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-04-14 DOI: 10.1016/j.compchemeng.2025.109151

Matthias Mersch , Dominik Tillmanns , Paul Sapin , Johannes Schilling , André Bardow , Christos N. Markides

{"title":"Integrated thermo-economic organic Rankine cycle and working fluid design – On the accuracy of molecular-based computer-aided methodologies","authors":"Matthias Mersch , Dominik Tillmanns , Paul Sapin , Johannes Schilling , André Bardow , Christos N. Markides","doi":"10.1016/j.compchemeng.2025.109151","DOIUrl":"10.1016/j.compchemeng.2025.109151","url":null,"abstract":"<div><div>The performance of Organic Rankine cycle (ORC) systems is defined by the system design as well as working fluid selection. Integrated thermo-economic optimisation of both can unlock maximum system potential in terms of power generation at a minimal cost. However, such optimisation is associated with uncertainties related to the underlying thermodynamic fluid models, ORC system models, and equipment cost correlations. In this paper, the main sources of uncertainty are quantified and their impact on optimal system design and working fluid selection is analysed. A computer-aided molecular and process design (CAMPD) optimisation framework based on first-law system design models is developed and validated with experimental data. Results reveal that the developed framework can identify promising working fluid candidates with high probabilities, even considering the most important sources of uncertainty. In a case study of industrial waste-heat utilisation, it was found that while uncertainties challenge the strict discrimination of the most promising working fluids, they mainly affect absolute performance values, rather than the overall ranking of working fluids. Propane was identified as having a 94-% probability of being among the best 3 working fluids. Furthermore, although the overall specific investment costs are highly uncertain (mean: 3810 £/kW, standard deviation: 720 £/kW), the results are less sensitive to uncertainties in fluid equilibrium and transport properties (standard deviation: 160 £/kW), with the impact of equipment cost uncertainties being dominant. The analysis of uncertainties in working fluid selection also applies to other CAMPD problems, and other applications of group-contribution-based equations of state.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"199 ","pages":"Article 109151"},"PeriodicalIF":3.9,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895254","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

Hierarchical matrix completion for the prediction of properties of binary mixtures 二元混合物性质预测的层次矩阵补全

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-04-12 DOI: 10.1016/j.compchemeng.2025.109122

Dominik Gond , Jan-Tobias Sohns , Heike Leitte , Hans Hasse , Fabian Jirasek

{"title":"Hierarchical matrix completion for the prediction of properties of binary mixtures","authors":"Dominik Gond , Jan-Tobias Sohns , Heike Leitte , Hans Hasse , Fabian Jirasek","doi":"10.1016/j.compchemeng.2025.109122","DOIUrl":"10.1016/j.compchemeng.2025.109122","url":null,"abstract":"<div><div>Predicting the thermodynamic properties of mixtures is crucial for process design and optimization in chemical engineering. Machine learning (ML) methods are gaining increasing attention in this field, but experimental data for training are often scarce, which hampers their application. In this work, we introduce a novel generic approach for improving data-driven models: inspired by the ancient rule ”similia similibus solvuntur” (Latin, English: like dissolves like), we lump components that behave similarly into chemical classes and model them jointly in the first step of a hierarchical approach. While the information on class affiliations can stem in principle from any source, we demonstrate how classes can reproducibly be defined based on mixture data alone by agglomerative clustering. The information from this clustering step is then used as an informed prior for fitting the individual data. We demonstrate the benefits of this approach by applying it in connection with a matrix completion method (MCM) for predicting isothermal activity coefficients at infinite dilution in binary mixtures. Using clustering leads to significantly improved predictions compared to an MCM without clustering. Furthermore, the chemical classes learned from the clustering give exciting insights into what matters on the molecular level for modeling given mixture properties.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"199 ","pages":"Article 109122"},"PeriodicalIF":3.9,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143948266","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

Limeade: Let integer molecular encoding aid Limeade：让整数分子编码辅助

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-04-11 DOI: 10.1016/j.compchemeng.2025.109115

Shiqiang Zhang , Christian W. Feldmann , Frederik Sandfort , Miriam Mathea , Juan S. Campos , Ruth Misener

引用次数: 0

Optimal investment and bidding strategies for wind power in electricity and green certificates markets 风电在电力和绿色证书市场中的最优投资与投标策略

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-04-11 DOI: 10.1016/j.compchemeng.2025.109139

Maria Kanta, Christos N. Dimitriadis, Evangelos G. Tsimopoulos, Michael C. Georgiadis

{"title":"Optimal investment and bidding strategies for wind power in electricity and green certificates markets","authors":"Maria Kanta, Christos N. Dimitriadis, Evangelos G. Tsimopoulos, Michael C. Georgiadis","doi":"10.1016/j.compchemeng.2025.109139","DOIUrl":"10.1016/j.compchemeng.2025.109139","url":null,"abstract":"<div><div>The transition to Renewable Energy (RE) is essential for addressing the growing energy demand and meeting the global sustainability goals. Following market trends, this work simultaneously investigates two key aspects: the strategic investment and bidding decisions of an RE producer, and the hourly coordination of Green Certificates Market (GCM) and Electricity Market (EM). To address these aspects a bilevel optimization model is developed. The upper-level problem seeks to maximize the strategic investor's profits, while the lower-level problems sequentially clear the EM and GCM. The model links electricity demand with green certificates demand, and the share of RE in the energy mix with the availability of green certificates. Employing Karush-Kuhn-Tucker conditions, binary expansion, and duality theory, makes the model solvable by commercial solvers. Applied to a modified Pennsylvania-New Jersey-Maryland (PJM) 5-bus system and the IEEE 24-bus test system; the model shows that GCM encourages new RE investments. Strategic bidding in EM enhances these investments by driving down EM prices, securing a growing market share for the RE producer. This price reduction is combined with capacity withholding when needed to prevent zero-price scenarios. Moreover, higher Renewable Portfolio Standard (RPS) targets or increased rival offering prices boost GCM and EM profitability, thereby positively impacting investment decisions. Contrarily, lower wind capacity factors negatively impact new investments as they lead to higher EM and GCM prices.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"199 ","pages":"Article 109139"},"PeriodicalIF":3.9,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143828337","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

Graph-to-SFILES: Control structure prediction from process topologies using generative artificial intelligence 图到sfiles：使用生成式人工智能从过程拓扑中预测控制结构

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-04-10 DOI: 10.1016/j.compchemeng.2025.109121

Lukas Schulze Balhorn, Kevin Degens, Artur M. Schweidtmann

{"title":"Graph-to-SFILES: Control structure prediction from process topologies using generative artificial intelligence","authors":"Lukas Schulze Balhorn, Kevin Degens, Artur M. Schweidtmann","doi":"10.1016/j.compchemeng.2025.109121","DOIUrl":"10.1016/j.compchemeng.2025.109121","url":null,"abstract":"<div><div>Control structure design is an important but tedious step in P&ID development. Generative artificial intelligence (AI) promises to reduce P&ID development time by supporting engineers. Previous research on generative AI in chemical process design mainly represented processes by sequences. However, graphs offer a promising alternative because of their permutation invariance. We propose the Graph-to-SFILES model, a generative AI method to predict control structures from flowsheet topologies. The Graph-to-SFILES model takes the flowsheet topology as a graph input and returns a control-extended flowsheet as a sequence in the SFILES 2.0 notation. We compare four different graph encoder architectures, one of them being a graph neural network (GNN) proposed in this work. The Graph-to-SFILES model achieves a top-5 accuracy of 73.2% when trained on 10,000 flowsheet topologies. In addition, the proposed GNN performs best among the encoder architectures. Compared to a purely sequence-based approach, the Graph-to-SFILES model improves the top-5 accuracy for a relatively small training dataset of 1,000 flowsheets from 0.9% to 28.4%. However, the sequence-based approach performs better on a large-scale dataset of 100,000 flowsheets. These results highlight the potential of graph-based AI models to accelerate P&ID development in small-data regimes but their effectiveness on industry relevant case studies still needs to be investigated.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"199 ","pages":"Article 109121"},"PeriodicalIF":3.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143948265","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

Leveraging graph neural networks and multi-agent reinforcement learning for inventory control in supply chains 利用图神经网络和多智能体强化学习进行供应链库存控制

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2025-04-10 DOI: 10.1016/j.compchemeng.2025.109111

Niki Kotecha, Antonio del Rio Chanona

{"title":"Leveraging graph neural networks and multi-agent reinforcement learning for inventory control in supply chains","authors":"Niki Kotecha, Antonio del Rio Chanona","doi":"10.1016/j.compchemeng.2025.109111","DOIUrl":"10.1016/j.compchemeng.2025.109111","url":null,"abstract":"<div><div>Inventory control in modern supply chains has attracted significant attention due to the increasing number of disruptive shocks and the challenges posed by complex dynamics, uncertainties, and limited collaboration. Traditional methods, which often rely on static parameters, struggle to adapt to changing environments. This paper proposes a Multi-Agent Reinforcement Learning (MARL) framework with Graph Neural Networks (GNNs) for state representation to address these limitations.</div><div>Our approach redefines the action space by parameterizing heuristic inventory control policies, into an adaptive, continuous form where parameters dynamically adjust based on system conditions and avoid combinatorial explosion typical of discrete actions. By leveraging the inherent graph structure of supply chains, our framework enables agents to learn the system’s topology, and we employ a centralized learning, decentralized execution scheme that allows agents to learn collaboratively while overcoming information-sharing constraints. Additionally, we incorporate global mean pooling and regularization techniques to enhance performance.</div><div>We test the capabilities of our proposed approach on four different supply chain configurations and conduct a sensitivity analysis. This work paves the way for utilizing MARL-GNN frameworks to improve inventory management in complex, decentralized supply chain environments.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"199 ","pages":"Article 109111"},"PeriodicalIF":3.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143948263","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