Computers & Chemical Engineering最新文献

英文中文

Planning strategies in the energy sector: Integrating bayesian neural networks and uncertainty quantification in scenario analysis & optimization

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

Computers & Chemical Engineering

Pub Date : 2025-03-17 DOI: 10.1016/j.compchemeng.2025.109097

Funda Iseri , Halil Iseri , Harsh Shah , Eleftherios Iakovou , Efstratios N. Pistikopoulos

The global energy market faces significant challenges due to increasing demand, growing competition, and the ongoing shift toward renewable sources. Addressing these complexities requires advanced methodologies that can effectively navigate uncertainty and optimize investment and operational decisions. This study presents a flexible scenario-based framework for capacity-related decision making and investment planning in energy systems comprising solar, wind, and natural gas facilities. The proposed framework integrates Bayesian Neural Networks (BNNs) into an optimization problem to address uncertainties in energy generation and demand forecasts. By leveraging posterior distributions from BNNs, the framework generates probabilistic, data-driven scenarios that capture future uncertainties. These scenarios are incorporated into a two-stage stochastic multi-period mixed-integer linear optimization model. The first stage optimizes investment decisions for new facilities prior to the realization of uncertainty, while the second stage incorporates operational costs, capacity expansions, and penalties for unmet demand across multiple future scenarios. We present a case study in Texas, demonstrating the applicability of the proposed framework. The results indicate the details on the capacity expansion and investment strategies for natural gas, wind and solar power plants to meet the increasing energy demand in the state. The model accounts for real-world considerations such as construction and expansion lag times, capacity constraints, and scenario-dependent demands. This methodology enhances the flexibility of energy systems, enabling planners to make cost-effective future investments and operational decisions through the complexities of the modern energy landscape. The proposed framework offers significant advantages over traditional methods by capturing nuanced uncertainty distributions and enabling flexible decision-making.

{"title":"Planning strategies in the energy sector: Integrating bayesian neural networks and uncertainty quantification in scenario analysis & optimization","authors":"Funda Iseri , Halil Iseri , Harsh Shah , Eleftherios Iakovou , Efstratios N. Pistikopoulos","doi":"10.1016/j.compchemeng.2025.109097","DOIUrl":"10.1016/j.compchemeng.2025.109097","url":null,"abstract":"<div><div>The global energy market faces significant challenges due to increasing demand, growing competition, and the ongoing shift toward renewable sources. Addressing these complexities requires advanced methodologies that can effectively navigate uncertainty and optimize investment and operational decisions. This study presents a flexible scenario-based framework for capacity-related decision making and investment planning in energy systems comprising solar, wind, and natural gas facilities. The proposed framework integrates Bayesian Neural Networks (BNNs) into an optimization problem to address uncertainties in energy generation and demand forecasts. By leveraging posterior distributions from BNNs, the framework generates probabilistic, data-driven scenarios that capture future uncertainties. These scenarios are incorporated into a two-stage stochastic multi-period mixed-integer linear optimization model. The first stage optimizes investment decisions for new facilities prior to the realization of uncertainty, while the second stage incorporates operational costs, capacity expansions, and penalties for unmet demand across multiple future scenarios. We present a case study in Texas, demonstrating the applicability of the proposed framework. The results indicate the details on the capacity expansion and investment strategies for natural gas, wind and solar power plants to meet the increasing energy demand in the state. The model accounts for real-world considerations such as construction and expansion lag times, capacity constraints, and scenario-dependent demands. This methodology enhances the flexibility of energy systems, enabling planners to make cost-effective future investments and operational decisions through the complexities of the modern energy landscape. The proposed framework offers significant advantages over traditional methods by capturing nuanced uncertainty distributions and enabling flexible decision-making.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"198 ","pages":"Article 109097"},"PeriodicalIF":3.9,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808535","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

Integrating solid direct air capture systems with green hydrogen production: Economic benefits and curtailment reduction

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

Computers & Chemical Engineering

Pub Date : 2025-03-17 DOI: 10.1016/j.compchemeng.2025.109102

Sunwoo Kim , Joungho Park , Jay H. Lee

The transition to a low-carbon energy system has positioned green hydrogen as a key clean energy carrier. However, the intermittent nature of renewable energy sources introduces significant challenges, such as substantial electricity curtailment, which affects both the economic feasibility and grid stability. Solid sorbent-based direct air capture systems, known for their high operational flexibility, offer a promising complementary solution to effectively utilize curtailed renewable power from green hydrogen production. This study examines the economic viability of integrating green hydrogen systems with solid direct air capture technology. The findings indicate that the integration can reduce curtailed renewable energy by up to 40 %, subsequently decreasing total annualized costs by approximately 6 % compared to operating these systems independently. Further economic improvements could be realized by optimizing the CO₂ capture-to-H₂ production ratio, capitalizing on anticipated cost reductions in direct air capture technology, and enhancing heat pump flexibility. With these improvements—including a 50 % reduction in direct air capture costs, an optimized CO₂-to-H₂ ratio, and enhanced heat pump flexibility—the economic benefits could increase from 6 % to 12 %. These results underscore the transformative potential of sector coupling in addressing the scalability challenges of green hydrogen, reducing renewable energy curtailment, and accelerating progress towards achieving net-zero and net-negative emissions goals.

{"title":"Integrating solid direct air capture systems with green hydrogen production: Economic benefits and curtailment reduction","authors":"Sunwoo Kim , Joungho Park , Jay H. Lee","doi":"10.1016/j.compchemeng.2025.109102","DOIUrl":"10.1016/j.compchemeng.2025.109102","url":null,"abstract":"<div><div>The transition to a low-carbon energy system has positioned green hydrogen as a key clean energy carrier. However, the intermittent nature of renewable energy sources introduces significant challenges, such as substantial electricity curtailment, which affects both the economic feasibility and grid stability. Solid sorbent-based direct air capture systems, known for their high operational flexibility, offer a promising complementary solution to effectively utilize curtailed renewable power from green hydrogen production. This study examines the economic viability of integrating green hydrogen systems with solid direct air capture technology. The findings indicate that the integration can reduce curtailed renewable energy by up to 40 %, subsequently decreasing total annualized costs by approximately 6 % compared to operating these systems independently. Further economic improvements could be realized by optimizing the CO<sub>2</sub> capture-to-H<sub>2</sub> production ratio, capitalizing on anticipated cost reductions in direct air capture technology, and enhancing heat pump flexibility. With these improvements—including a 50 % reduction in direct air capture costs, an optimized CO<sub>2</sub>-to-H<sub>2</sub> ratio, and enhanced heat pump flexibility—the economic benefits could increase from 6 % to 12 %. These results underscore the transformative potential of sector coupling in addressing the scalability challenges of green hydrogen, reducing renewable energy curtailment, and accelerating progress towards achieving net-zero and net-negative emissions goals.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"198 ","pages":"Article 109102"},"PeriodicalIF":3.9,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143685168","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

Design of modular electrolysis and modular high-efficiency fuel cell systems for green hydrogen production and power generation with low emission of carbon dioxide

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

Computers & Chemical Engineering

Pub Date : 2025-03-15 DOI: 10.1016/j.compchemeng.2025.109101

Waraporn Kongjui , Weerawat Patthaveekongka , Chuttchaval Jeraputra , Pornchai Bumroongsri

This study presents a system model of the process for converting water and sunlight into green hydrogen which is then used to generate electrical energy with low emission of carbon dioxide. The proposed system model incorporates modular electrolysis cells for green hydrogen production and modular high-efficiency fuel cells for power generation. The results show that modular electrolysis cells can produce hydrogen at 149 tons/day. The produced hydrogen can be used to generate 100 MW of electricity. The carbon dioxide emission index is 0.206 tons/MWh which is lower than conventional technologies. The proposed systems have excellent performance in terms of efficiency and environmental pollution reduction. The results in this paper can be used in the process design for green hydrogen production and power generation.

引用次数: 0

A synchronous data-driven hybrid framework for optimizing hydrotreating units and hydrogen networks under uncertainty 在不确定条件下优化加氢处理装置和氢气网络的同步数据驱动混合框架

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

Computers & Chemical Engineering

Pub Date : 2025-03-15 DOI: 10.1016/j.compchemeng.2025.109050

Shizhao Chen , Xin Peng , Chenglin Chang , Zhi Li , Weimin Zhong

Minimizing hydrogen consumption while maintaining the production quality in the refinery is increasingly important with more usage of heavy crude oil. However, the uncertainty of the impurity content in the input flow has led to the optimal solution losing efficacy. Therefore, a synchronous optimization framework for the hydrogen network and the production system is proposed. In this work, the relationship between the production state and the hydrogen demand is characterized by a hybrid model. Besides, a Wasserstein distributionally robust optimization module is inserted into the optimization of the hydrogen network, considering the uncertain condition of the impurity content in the input flow. The results show that the balance of hydrogen consumption and production quality could be improved. a lower hydrogen demand, reduced energy consumption, and higher product profit could be achieved with a stabler production state.

引用次数: 0

Prediction of internal corrosion rate for gas pipeline: A new method based on transformer architecture

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

Computers & Chemical Engineering

Pub Date : 2025-03-13 DOI: 10.1016/j.compchemeng.2025.109084

Li Tan , Yang Yang , Kemeng Zhang , Kexi Liao , Guoxi He , Jing Tian , Xin Lu

Accurate assessment of internal corrosion rates in steel natural gas pipelines is a critical process in oil and gas pipeline integrity management. However, the existing models used for predicting internal corrosion rates often suffer from various issues, such as low accuracy, poor generalization, and a lack of interpretability. In order to appropriately address these challenges, we propose CNN-BO-Transformer, and employ DeepSHAP for enhancing the interpretability of the model. The proposed CNN-BO-Transformer is used to predict the corrosion rate in natural gas pipelines, while DeepSHAP is utilized to analyze the causal relationships between input variables and model's predictions. The proposed model is validated by using a real pipeline excavation dataset obtained from a gas field located in Northwest China, achieving an average error of 0.21mm/y. This represents reductions of 69.74 % and 66.67 % as compared to the errors of support vector regression (SVR) and the Transformer model, respectively. The proposed method significantly improves the accuracy and reliability of corrosion rate predictions in natural gas gathering and transportation pipelines, thus providing an effective approach for predictive maintenance and repair of steel gathering in transmission pipelines in gas fields.

{"title":"Prediction of internal corrosion rate for gas pipeline: A new method based on transformer architecture","authors":"Li Tan , Yang Yang , Kemeng Zhang , Kexi Liao , Guoxi He , Jing Tian , Xin Lu","doi":"10.1016/j.compchemeng.2025.109084","DOIUrl":"10.1016/j.compchemeng.2025.109084","url":null,"abstract":"<div><div>Accurate assessment of internal corrosion rates in steel natural gas pipelines is a critical process in oil and gas pipeline integrity management. However, the existing models used for predicting internal corrosion rates often suffer from various issues, such as low accuracy, poor generalization, and a lack of interpretability. In order to appropriately address these challenges, we propose CNN-BO-Transformer, and employ DeepSHAP for enhancing the interpretability of the model. The proposed CNN-BO-Transformer is used to predict the corrosion rate in natural gas pipelines, while DeepSHAP is utilized to analyze the causal relationships between input variables and model's predictions. The proposed model is validated by using a real pipeline excavation dataset obtained from a gas field located in Northwest China, achieving an average error of 0.21mm/y. This represents reductions of 69.74 % and 66.67 % as compared to the errors of support vector regression (SVR) and the Transformer model, respectively. The proposed method significantly improves the accuracy and reliability of corrosion rate predictions in natural gas gathering and transportation pipelines, thus providing an effective approach for predictive maintenance and repair of steel gathering in transmission pipelines in gas fields.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"198 ","pages":"Article 109084"},"PeriodicalIF":3.9,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143685170","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

Application of a temporal multiscale method for efficient simulation of degradation in PEM Water Electrolysis under dynamic operating conditions 应用时间多尺度方法高效模拟 PEM 水电解在动态运行条件下的降解过程

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

Computers & Chemical Engineering

Pub Date : 2025-03-10 DOI: 10.1016/j.compchemeng.2025.109083

Dayron Chang Dominguez , An Phuc Dam , Shaun M. Alia , Thomas Richter , Kai Sundmacher

Hydrogen is emerging as a vital energy carrier, driven by the need to reduce carbon emissions. Proton Electrolyte Membrane Water Electrolysis (PEMWE) enables hydrogen production under fluctuating renewable power conditions but requires improved understanding and stability of the anode catalyst layer under dynamic operating conditions, especially with low noble metal loadings. Long-term degradation experiments are both time-consuming and costly; therefore, a systematic, model-aided approach is essential. In the present work, a temporal multiscale method is applied to reduce the computational effort of simulating long-term degradation processes in PEMWE, with an exemplary focus on catalyst dissolution. A mechanistic model incorporating the oxygen evolution reaction, catalyst dissolution, and hydrogen permeation from the cathode to the anode was hypothesized and implemented. In this way, the local periodicity of transport and reaction processes in dynamic PEMWE operation, which influence the gradual degradation of the catalyst layer, is captured. The temporal multiscale method significantly reduces the computational effort of simulation, decreasing processing time from hours to mere minutes. This efficiency gain is attributed to the limited evolution of Slow-Scale variables during each period of time P of the Fast-Scale variables. Consequently, simulation is required only until local periodicity is achieved within each Slow-Scale time step. Hence, the fully resolved dynamic problem is decoupled into these two scales, employing a heterogeneous multiscale technique. The developed approach effectively accelerates parameter estimation and predictive simulations, supporting systematic modeling of PEMWE degradation under dynamic conditions.

{"title":"Application of a temporal multiscale method for efficient simulation of degradation in PEM Water Electrolysis under dynamic operating conditions","authors":"Dayron Chang Dominguez , An Phuc Dam , Shaun M. Alia , Thomas Richter , Kai Sundmacher","doi":"10.1016/j.compchemeng.2025.109083","DOIUrl":"10.1016/j.compchemeng.2025.109083","url":null,"abstract":"<div><div>Hydrogen is emerging as a vital energy carrier, driven by the need to reduce carbon emissions. Proton Electrolyte Membrane Water Electrolysis (PEMWE) enables hydrogen production under fluctuating renewable power conditions but requires improved understanding and stability of the anode catalyst layer under dynamic operating conditions, especially with low noble metal loadings. Long-term degradation experiments are both time-consuming and costly; therefore, a systematic, model-aided approach is essential. In the present work, a temporal multiscale method is applied to reduce the computational effort of simulating long-term degradation processes in PEMWE, with an exemplary focus on catalyst dissolution. A mechanistic model incorporating the oxygen evolution reaction, catalyst dissolution, and hydrogen permeation from the cathode to the anode was hypothesized and implemented. In this way, the local periodicity of transport and reaction processes in dynamic PEMWE operation, which influence the gradual degradation of the catalyst layer, is captured. The temporal multiscale method significantly reduces the computational effort of simulation, decreasing processing time from hours to mere minutes. This efficiency gain is attributed to the limited evolution of Slow-Scale variables during each period of time P of the Fast-Scale variables. Consequently, simulation is required only until local periodicity is achieved within each Slow-Scale time step. Hence, the fully resolved dynamic problem is decoupled into these two scales, employing a heterogeneous multiscale technique. The developed approach effectively accelerates parameter estimation and predictive simulations, supporting systematic modeling of PEMWE degradation under dynamic conditions.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"198 ","pages":"Article 109083"},"PeriodicalIF":3.9,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predicting the temperature-dependent CMC of surfactant mixtures with graph neural networks

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

Computers & Chemical Engineering

Pub Date : 2025-03-10 DOI: 10.1016/j.compchemeng.2025.109085

Christoforos Brozos , Jan G. Rittig , Elie Akanny , Sandip Bhattacharya , Christina Kohlmann , Alexander Mitsos

Surfactants are key ingredients in various industries such as personal and home care with the critical micelle concentration (CMC) being of major interest. Predictive models for CMC of pure surfactants have been developed based on recent ML methods, however, in practice surfactant mixtures are typically used due to performance, environmental, and cost reasons. Herein, we develop a graph neural network (GNN) framework for surfactant mixtures to predict the temperature-dependent CMC. We collect data for 108 surfactant binary mixtures, to which we add data for pure species from our previous work Brozos et al. (2024). We then develop and train GNNs and evaluate their accuracy across different prediction test scenarios for binary mixtures relevant to practical applications. The final GNN models demonstrate very high predictive performance when interpolating between different mixture compositions and for new binary mixtures with known species. Extrapolation to binary surfactant mixtures where either one or both surfactant species are not seen before, yields accurate results for the majority of surfactant systems. We further find superior accuracy of the GNN over a semi-empirical model based on activity coefficients, which has been widely used to date. We then explore if GNN models trained solely on binary mixture and pure species data can also accurately predict the CMCs of ternary mixtures. Finally, we experimentally measure the CMC of 4 commercial surfactants that contain up to four species and industrial relevant mixtures and find a very good agreement between measured and predicted CMC values.

{"title":"Predicting the temperature-dependent CMC of surfactant mixtures with graph neural networks","authors":"Christoforos Brozos , Jan G. Rittig , Elie Akanny , Sandip Bhattacharya , Christina Kohlmann , Alexander Mitsos","doi":"10.1016/j.compchemeng.2025.109085","DOIUrl":"10.1016/j.compchemeng.2025.109085","url":null,"abstract":"<div><div>Surfactants are key ingredients in various industries such as personal and home care with the critical micelle concentration (CMC) being of major interest. Predictive models for CMC of pure surfactants have been developed based on recent ML methods, however, in practice surfactant mixtures are typically used due to performance, environmental, and cost reasons. Herein, we develop a graph neural network (GNN) framework for surfactant mixtures to predict the temperature-dependent CMC. We collect data for 108 surfactant binary mixtures, to which we add data for pure species from our previous work Brozos et al. (2024). We then develop and train GNNs and evaluate their accuracy across different prediction test scenarios for binary mixtures relevant to practical applications. The final GNN models demonstrate very high predictive performance when interpolating between different mixture compositions and for new binary mixtures with known species. Extrapolation to binary surfactant mixtures where either one or both surfactant species are not seen before, yields accurate results for the majority of surfactant systems. We further find superior accuracy of the GNN over a semi-empirical model based on activity coefficients, which has been widely used to date. We then explore if GNN models trained solely on binary mixture and pure species data can also accurately predict the CMCs of ternary mixtures. Finally, we experimentally measure the CMC of 4 commercial surfactants that contain up to four species and industrial relevant mixtures and find a very good agreement between measured and predicted CMC values.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"198 ","pages":"Article 109085"},"PeriodicalIF":3.9,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Machine learning enabled multiscale model for nanoparticle margination and physiology based pharmacokinetics

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

Computers & Chemical Engineering

Pub Date : 2025-03-09 DOI: 10.1016/j.compchemeng.2025.109081

Sahil Kulkarni , Benjamin Lin , Ravi Radhakrishnan

This study presents a multiscale modeling framework for simulating and predicting the behavior and biodistribution of nanoparticles (

NPs

), focusing on applications such as targeted drug delivery. The framework encompasses two coupled models: (1) a DeepONet-enabled Fokker–Planck equation to model the NP drift–diffusion in the red-blood cell-free layer (RBCFL) that predicts NP margination and concentration profiles taking hematocrit and vessel radius as inputs, built on top of a hemorheological model of shear-induced blood flow and (2) a physiologically based pharmacokinetic (PBPK) model that uses the predicted concentration profiles in microvasculature to inform the biodistribution of NPs across different organ in the body.

引用次数: 0

Health-aware optimal charging of lithium-ion batteries using deep-neural networks-based explicit constrained model predictive control 利用基于深度神经网络的显式约束模型预测控制，实现锂离子电池的健康感知优化充电

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

Computers & Chemical Engineering

Pub Date : 2025-03-09 DOI: 10.1016/j.compchemeng.2025.109096

Ahmed Shokry , Mehdi Abou El Qassime , Antonio Espuña , Eric Moulines

The use of Model Predictive Control (MPC) for optimal charging of batteries is attracting attention due to its superiority over empirical charging protocols. But, the intricate nature of physics-based battery models poses a challenge to MPC implementation, necessitating substantial computational resources. Hence, this paper presents a method for explicit MPC based on machine learning (ML) models, applied for optimal battery charging while accounting for linear health constraints. The method uses Deep Neural Networks (DNNs) to construct offline control law that precisely describe the optimal charging current as a function of the battery's state. This DNN-based control law is developed using data generated by solving the MPC problem several times while varying the battery's initial state. Then, the control law is applied online to regulate the charging by cheaply predicting the closed-loop current. The method is numerically validated by its application to two case studies, showing: i) high accuracy in predicting closed-loop charging current (a normalized root mean square error of less than 1.0 %), ii) robustness in handling random initial states of the battery, iii) capability to learn bound and linear constraints directly from the data without any knowledge of their mathematical formulations, achieving a maximum constraint violation of an order of magnitude equal to 10^-2, iv) applicability to distinct types of battery models, and v) a reduction in the required computational time compared to traditional MPC, which reaches up to 94.7%, in the lowest-performing testing scenario.

由于模型预测控制（MPC）优于经验充电协议，因此在电池优化充电方面的应用备受关注。但是，基于物理的电池模型错综复杂，这给 MPC 的实施带来了挑战，需要大量的计算资源。因此，本文提出了一种基于机器学习（ML）模型的显式 MPC 方法，用于优化电池充电，同时考虑线性健康约束。该方法利用深度神经网络（DNN）构建离线控制法，精确描述作为电池状态函数的最佳充电电流。这种基于 DNN 的控制法则是利用在改变电池初始状态的同时多次求解 MPC 问题所生成的数据来开发的。然后，在线应用该控制法则，通过低成本预测闭环电流来调节充电。该方法在两个案例研究中的应用对其进行了数值验证，结果表明：i) 预测闭环充电电流的准确性高（归一化均方根误差小于 1.0 %）；ii) 处理电池随机初始状态的鲁棒性；iii) 直接从数据中学习约束和线性约束的能力，而无需了解其数学公式，最大违反约束的数量级等于 10-2；iv) 适用于不同类型的电池模型；v) 与传统 MPC 相比，在性能最低的测试场景中，所需计算时间减少了 94.7%。

{"title":"Health-aware optimal charging of lithium-ion batteries using deep-neural networks-based explicit constrained model predictive control","authors":"Ahmed Shokry , Mehdi Abou El Qassime , Antonio Espuña , Eric Moulines","doi":"10.1016/j.compchemeng.2025.109096","DOIUrl":"10.1016/j.compchemeng.2025.109096","url":null,"abstract":"<div><div>The use of Model Predictive Control (MPC) for optimal charging of batteries is attracting attention due to its superiority over empirical charging protocols. But, the intricate nature of physics-based battery models poses a challenge to MPC implementation, necessitating substantial computational resources. Hence, this paper presents a method for explicit MPC based on machine learning (ML) models, applied for optimal battery charging while accounting for linear health constraints. The method uses Deep Neural Networks (DNNs) to construct offline control law that precisely describe the optimal charging current as a function of the battery's state. This DNN-based control law is developed using data generated by solving the MPC problem several times while varying the battery's initial state. Then, the control law is applied online to regulate the charging by cheaply predicting the closed-loop current. The method is numerically validated by its application to two case studies, showing: i) high accuracy in predicting closed-loop charging current (a normalized root mean square error of less than 1.0 %), ii) robustness in handling random initial states of the battery, iii) capability to learn bound and linear constraints directly from the data without any knowledge of their mathematical formulations, achieving a maximum constraint violation of an order of magnitude equal to 10<sup>-2</sup>, iv) applicability to distinct types of battery models, and v) a reduction in the required computational time compared to traditional MPC, which reaches up to 94.7%, in the lowest-performing testing scenario.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"199 ","pages":"Article 109096"},"PeriodicalIF":3.9,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143783226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Nonlinear pinch analysis targeting inspired by options valuation and Black-Scholes-Merton model

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

Computers & Chemical Engineering

Pub Date : 2025-03-03 DOI: 10.1016/j.compchemeng.2025.109086

Akshay U․ Shenoy, Uday V․ Shenoy

A novel function-condition product (FCP) approach, where conditions are evaluated using Boolean logic, is proposed for pinch analysis targeting with two distinct advantages. First, a direct targeting formula with Boolean expressions coerced to numeric equivalents provides a superior alternative to a multi-step targeting algorithm with surplus/deficit resource loads cascaded across intervals. Second, the targeting formula allows direct calculation at any level to generate even a nonlinear grand composite curve (GCC) rather than a piecewise-linear GCC with constant slope segments within each interval. The FCP approach is initially developed for the valuation of financial derivatives (specifically, options), where the payoff and P&L (profit and loss) diagrams for option strategies at expiry are shown to be analogs of piecewise-linear GCCs. The pre-expiry P&L curves for options valued by the Nobel prize-winning Black-Scholes-Merton (BSM) model are then shown to be analogous to nonlinear GCCs. An FCP formula for targeting the minimum utilities in heat exchanger networks (HENs) and the optimum mass separating agent flowrates in mass exchanger networks (MENs) is finally derived based on formally demonstrating that each stream in a HEN / MEN is equivalent to a spread in an option strategy. To illustrate various aspects of the new methodology, examples of a crude oil option strategy (for a bull put spread, put ratio spread and butterfly spread), of HENs for both constant and variable specific heat capacity C_p, and of a reactive MEN with a general nonlinear equilibrium function are considered in detail.

{"title":"Nonlinear pinch analysis targeting inspired by options valuation and Black-Scholes-Merton model","authors":"Akshay U․ Shenoy, Uday V․ Shenoy","doi":"10.1016/j.compchemeng.2025.109086","DOIUrl":"10.1016/j.compchemeng.2025.109086","url":null,"abstract":"<div><div>A novel function-condition product (FCP) approach, where conditions are evaluated using Boolean logic, is proposed for pinch analysis targeting with two distinct advantages. First, a direct targeting formula with Boolean expressions coerced to numeric equivalents provides a superior alternative to a multi-step targeting algorithm with surplus/deficit resource loads cascaded across intervals. Second, the targeting formula allows direct calculation at any level to generate even a nonlinear grand composite curve (GCC) rather than a piecewise-linear GCC with constant slope segments within each interval. The FCP approach is initially developed for the valuation of financial derivatives (specifically, options), where the payoff and P&L (profit and loss) diagrams for option strategies at expiry are shown to be analogs of piecewise-linear GCCs. The pre-expiry P&L curves for options valued by the Nobel prize-winning Black-Scholes-Merton (BSM) model are then shown to be analogous to nonlinear GCCs. An FCP formula for targeting the minimum utilities in heat exchanger networks (HENs) and the optimum mass separating agent flowrates in mass exchanger networks (MENs) is finally derived based on formally demonstrating that each stream in a HEN / MEN is equivalent to a spread in an option strategy. To illustrate various aspects of the new methodology, examples of a crude oil option strategy (for a bull put spread, put ratio spread and butterfly spread), of HENs for both constant and variable specific heat capacity <em>C<sub>p</sub></em>, and of a reactive MEN with a general nonlinear equilibrium function are considered in detail.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"198 ","pages":"Article 109086"},"PeriodicalIF":3.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611621","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

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Computers & Chemical Engineering

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀