{"title":"Designing a centralized storage hydrogen supply chain network with multi-period and bi-objective optimization","authors":"Linfei Feng, Hervé Manier, Marie-Ange Maniera","doi":"10.1016/j.compchemeng.2024.108820","DOIUrl":"10.1016/j.compchemeng.2024.108820","url":null,"abstract":"<div><p>This study introduces a multi-period centralized storage optimization model aimed at designing an efficient hydrogen supply chain system, considering cost and emissions as dual objectives. It integrates multiple energy sources, production and storage methods, transport combinations, demand scenarios, and carbon capture systems, offering a comprehensive decision-making approach for hydrogen network design. Employing the mixed-integer linear programming methodology, the proposed model resolves these complexities. The research applies this model to a case study in France, generating six unique scenarios for 10 and 15 cities, and compares them against two distinct decentralized models. The findings consistently highlight the centralized storage model’s cost benefits across various demand scenarios, including cases of unrestricted emissions as well as cases with limited emission targets. The cost-effectiveness of this proposed model enhances its feasibility within the current context of decarbonization.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"190 ","pages":"Article 108820"},"PeriodicalIF":3.9,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141978000","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}
Daniel Beahr , Debangsu Bhattacharyya , Douglas A. Allan , Stephen E. Zitney
{"title":"Development of algorithms for augmenting and replacing conventional process control using reinforcement learning","authors":"Daniel Beahr , Debangsu Bhattacharyya , Douglas A. Allan , Stephen E. Zitney","doi":"10.1016/j.compchemeng.2024.108826","DOIUrl":"10.1016/j.compchemeng.2024.108826","url":null,"abstract":"<div><p>This work seeks to allow for the online operation and training of model-free reinforcement learning (RL) agents but limit the risk to system equipment and personnel. The parallel implementation of RL alongside more conventional process control (CPC) allows for the RL algorithm to learn from CPC. The past performance of both methods are assessed on a continuous basis allowing for a transition from CPC to RL and, if needed, transitioning back to CPC from RL. This allows for the RL algorithm to slowly and safely assume control of the process without significant degradation in control performance. It is shown that the RL can derive a near optimal policy even when coupled with a suboptimal CPC. It is also demonstrated that the coupled RL-CPC algorithm learns at a faster rate than traditional RL methods of exploration while the algorithm’s performance does not deteriorate below CPC, even when exposed to an unknown operating condition.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"190 ","pages":"Article 108826"},"PeriodicalIF":3.9,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141985090","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}
Daniel Mayfrank , Alexander Mitsos , Manuel Dahmen
{"title":"End-to-end reinforcement learning of Koopman models for economic nonlinear model predictive control","authors":"Daniel Mayfrank , Alexander Mitsos , Manuel Dahmen","doi":"10.1016/j.compchemeng.2024.108824","DOIUrl":"10.1016/j.compchemeng.2024.108824","url":null,"abstract":"<div><p>(Economic) nonlinear model predictive control ((e)NMPC) requires dynamic models that are sufficiently accurate and computationally tractable. Data-driven surrogate models for mechanistic models can reduce the computational burden of (e)NMPC; however, such models are typically trained by system identification for maximum prediction accuracy on simulation samples and perform suboptimally in (e)NMPC. We present a method for end-to-end reinforcement learning of Koopman surrogate models for optimal performance as part of (e)NMPC. We apply our method to two applications derived from an established nonlinear continuous stirred-tank reactor model. The controller performance is compared to that of (e)NMPCs utilizing models trained using system identification, and model-free neural network controllers trained using reinforcement learning. We show that the end-to-end trained models outperform those trained using system identification in (e)NMPC, and that, in contrast to the neural network controllers, the (e)NMPC controllers can react to changes in the control setting without retraining.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"190 ","pages":"Article 108824"},"PeriodicalIF":3.9,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0098135424002424/pdfft?md5=b8942e7813913b046ed7ab32d3f23e7e&pid=1-s2.0-S0098135424002424-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141938877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Strategic and tactical planning model for the design of perishable product supply chain network in Ethiopia","authors":"Asnakech Biza , Ludovic Montastruc , Stéphane Negny , Shimelis Admassu","doi":"10.1016/j.compchemeng.2024.108814","DOIUrl":"10.1016/j.compchemeng.2024.108814","url":null,"abstract":"<div><p>This article discusses the challenges associated with ensuring food security for a growing global population and emphasizes the critical role of the Agri Fresh Food Supply Chain in addressing these challenges such as mitigating food insecurity and reducing wastes. The economic repercussions of inefficiencies in perishable supply chains impact businesses' profit margins and consumers' access to essential goods. The focus is on the effective management of the complex perishable product supply chains, considering the economic significance of this sector and the need for advanced strategies to optimize the flow of time-sensitive products. The study discusses the limited consideration of product intrinsic characteristics in strategic and tactical planning decisions. The research aims to contribute to supply chain management by proposing a mathematical model (multi echelon, multi product, and multi period) for designing a perishable product supply chain network, considering factors like perishability, quantity discount policy, souring strategies and business continuity. The study explores the impact of these factors on the Agri Fresh Food Supply Chain design and its overall performances. Although the proposed model is designed to be applicable to any country or region, but its capabilities are shown through a real case study in Ethiopia. Results show that a agri-food supply chain design model that considers the intrinsic characteristics of the product, processing capacity level, and quantity discount leads to improved configurations of the food supply chain regardless of adding the associated cost.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"190 ","pages":"Article 108814"},"PeriodicalIF":3.9,"publicationDate":"2024-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141998015","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}
{"title":"Zonewise surrogate-based optimization of box-constrained systems","authors":"Srikar Venkataraman Srinivas, Iftekhar A. Karimi","doi":"10.1016/j.compchemeng.2024.108821","DOIUrl":"10.1016/j.compchemeng.2024.108821","url":null,"abstract":"<div><p>Complex physical or numerical systems may exhibit distinct behaviors in various zones of their design spaces. We present an algorithm that uses multiple cluster-based surrogates for optimizing such box-constrained systems. It partitions the design space into multiple clusters using K-means clustering and develops a separate surrogate for each cluster. It then uses these surrogates to sample additional points in the design space whose function evaluations guide the search for a global optimum. Clustering, surrogate construction, and smart sampling are employed iteratively to add sample points until a pre-defined threshold. The best solution from these points estimates a global optimum. An extensive test bed of 52 box-constrained functions was used to evaluate and compare the algorithm's performance and computational requirements with sixteen derivative-free optimization solvers. The best version of our algorithm surpassed all sixteen solvers in optimization accuracy for a fixed number of evaluations and demanded lower computational effort than fifteen.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"189 ","pages":"Article 108821"},"PeriodicalIF":3.9,"publicationDate":"2024-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141938878","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}
Kozue Okamura, Kota Oishi, Sara Badr, Akira Yamada, Hirokazu Sugiyama
{"title":"Data-driven parameterization and development of mechanistic cell cultivation models in monoclonal antibody production processes: Shifts in cell metabolic behavior","authors":"Kozue Okamura, Kota Oishi, Sara Badr, Akira Yamada, Hirokazu Sugiyama","doi":"10.1016/j.compchemeng.2024.108822","DOIUrl":"10.1016/j.compchemeng.2024.108822","url":null,"abstract":"<div><p>Representative kinetic models to describe monoclonal antibody (mAb) production processes are needed for effective process design. The development of mechanistic models can be impeded by the lack of complete understanding of changes in cell metabolism, e.g., lactate metabolic shifts. State-estimation-based methods were applied to assess the fit of available kinetic models over experimental runs. The results indicated the regions where model parameter updates were required. Different clustering strategies were applied to isolate the variations in the culture environment and correlate them to the lactate shifts. Alternative formulations for the specific lactate consumption/production term were provided for each identified phase. Two case studies are presented for pilot-scale data in different reactor types. The results show the improvement in modeling accuracy and highlight the role of oxygen and nutrient levels on the shifts. The approach showcases the use of data-driven insights to effectively utilize limited experimental data to develop robust mechanistic models.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"191 ","pages":"Article 108822"},"PeriodicalIF":3.9,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0098135424002400/pdfft?md5=7997adf5ee2030eb9c80b9ddacea1b76&pid=1-s2.0-S0098135424002400-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142049601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Novel terminal region computation method for quasi-infinite horizon NMPC","authors":"Guilherme Augusto Silva de Souza, Darci Odloak","doi":"10.1016/j.compchemeng.2024.108819","DOIUrl":"10.1016/j.compchemeng.2024.108819","url":null,"abstract":"<div><p>An algorithm for invariant region characterization for a nonlinear system controlled by an LQR is proposed. The quasi-infinite horizon nonlinear model predictive controller formulation is extended for zone control with optimizing targets. The novel invariant region characterization proposed promotes hypervolume gains of up to two orders of magnitude for an unstable CSTR. Extension of the NMPC formulation to the case of zone control with optimizing targets improves the formulation’s practical deployment capability. A comparison between QIH-NMPC and NMPC with a terminal equality constraint is drawn, showing considerable closed-loop performance loss when employing a terminal equality constraint. The proposed invariant region shows feasibility set gains from the proposed invariant region characterization, when compared to a recent approach. Closed-loop simulations of both controllers from the enlarged feasibility set show how sensible the closed-loop performance is to one infeasible controller iteration.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"189 ","pages":"Article 108819"},"PeriodicalIF":3.9,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141938879","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}
Chong Liu , Chengyu Han , Chenxi Gu , Wei Sun , Jingde Wang , Xun Tang
{"title":"Operating condition design with a Bayesian optimization approach for pharmaceutical intermediate batch concentration","authors":"Chong Liu , Chengyu Han , Chenxi Gu , Wei Sun , Jingde Wang , Xun Tang","doi":"10.1016/j.compchemeng.2024.108813","DOIUrl":"10.1016/j.compchemeng.2024.108813","url":null,"abstract":"<div><p>In the synthesis of pharmaceutical intermediates, concentration is commonly employed to separate the product and recycle the solvents. To achieve a cost-effective manufacturing, operating parameters shall be adjusted over time, which could traditionally be achieved based on dynamic simulation, but with significant computation cost. In this work, we introduced a Bayesian optimization approach to design the optimal operating condition of a pharmaceutical intermediate in the production of Lamivudine. Using a Gaussian process regression as the surrogate model, the approach tremendously reduced the computational cost in searching for the optimal design. In comparison to other commonly used intelligent optimization algorithms, the results demonstrate that the presented approach confers evident advantages, especially in reducing the tendency of getting trapped in local optima and in improving the speed of convergence to an optimal solution.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"189 ","pages":"Article 108813"},"PeriodicalIF":3.9,"publicationDate":"2024-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141839626","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}
{"title":"Recurrent neural network-based prediction of O-GlcNAcylation sites in mammalian proteins","authors":"Pedro Seber, Richard D. Braatz","doi":"10.1016/j.compchemeng.2024.108818","DOIUrl":"10.1016/j.compchemeng.2024.108818","url":null,"abstract":"<div><p>O-GlcNAcylation has the potential to be an important target for therapeutics, but a motif or an algorithm to reliably predict O-GlcNAcylation sites is not available. Current predictive models are insufficient as they fail to generalize, and many are no longer available. This article constructs recurrent neural network models to predict O-GlcNAcylation sites based on protein sequences. Different datasets are evaluated separately and assessed in terms of strengths and issues. Within a given dataset, results are robust to changes in cross-validation and test data as determined by nested validation. The best model achieves an F<span><math><msub><mrow></mrow><mrow><mn>1</mn></mrow></msub></math></span> score of 36% (more than 3.5-fold greater than the previous best model) and a Matthews Correlation Coefficient of 35% (more than 4.5-fold greater than the previous best model), and, for the F<span><math><msub><mrow></mrow><mrow><mn>1</mn></mrow></msub></math></span> score, 7.6-fold higher than when not using any model. Shapley values are used to interpret the model’s predictions and provide biological insight into O-GlcNAcylation.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"189 ","pages":"Article 108818"},"PeriodicalIF":3.9,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141963120","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}
{"title":"Toward understandable semi-supervised learning fault diagnosis of chemical processes based on long short-term memory ladder autoencoder (LSTM-LAE) and self-attention (SA)","authors":"Yang Jing , Xiaolong Ge , Botan Liu","doi":"10.1016/j.compchemeng.2024.108817","DOIUrl":"10.1016/j.compchemeng.2024.108817","url":null,"abstract":"<div><p>Fault diagnosis and localization play vital role in chemical process monitoring. Finding the root cause of fault accurately and timely is the key to avoid serious accidents and ensure process safety. Unfortunately, most deep learning-based models only involves in predicting fault state and interpretability is still not fully explored. Besides, lack of labeled samples in practical situations makes supervised learning difficult to implement. To circumvent the obstacle, semi-supervised learning based on long short-term memory ladder autoencoder is combined with self-attention mechanism, which is intended to establish interpretable model by explicitly clarifying the corresponding relationship between abnormal variables and faults. Using Tennessee Eastman process and practical high-purity carbonate production process as benchmark, fault diagnosis and identification performance of proposed LSTM-LAE-SA is validated, and interpretability analysis is performed to demonstrate its capabilities in abnormal variable locations. The developed understandable model could improve operator's trust and industrial application in fault diagnosis system.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"189 ","pages":"Article 108817"},"PeriodicalIF":3.9,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141950332","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}