Pub Date : 2024-10-20DOI: 10.1016/j.compchemeng.2024.108900
Ibrahim Shomope , Muhammad Tawalbeh , Amani Al-Othman , Fares Almomani
The focus on sustainable energy has increased interest in biohydrogen production through dark fermentation of organic waste biomass, offering dual benefits of energy production and waste management. Optimizing this process is challenging due to complex interactions among substrate composition, microbial consortia, and fermentation parameters. A multilayer perceptron artificial neural network model was developed to predict biohydrogen yield from organic waste. The model, trained on 180 data points from 35 studies, uses inputs, such as substrate type, inoculum type, concentration, pH, and temperature, with hydrogen yield as the output. The multilayer perceptron artificial neural network model achieved high accuracy, with a root mean square error of 0.3838, a mean absolute percentage error of 0.1938, and a coefficient of determination of 0.8381. These results demonstrate the model's effectiveness in predicting biohydrogen production, providing a valuable tool for optimizing the fermentation process and advancing sustainable energy solutions.
{"title":"Predicting biohydrogen production from dark fermentation of organic waste biomass using multilayer perceptron artificial neural network (MLP–ANN)","authors":"Ibrahim Shomope , Muhammad Tawalbeh , Amani Al-Othman , Fares Almomani","doi":"10.1016/j.compchemeng.2024.108900","DOIUrl":"10.1016/j.compchemeng.2024.108900","url":null,"abstract":"<div><div>The focus on sustainable energy has increased interest in biohydrogen production through dark fermentation of organic waste biomass, offering dual benefits of energy production and waste management. Optimizing this process is challenging due to complex interactions among substrate composition, microbial consortia, and fermentation parameters. A multilayer perceptron artificial neural network model was developed to predict biohydrogen yield from organic waste. The model, trained on 180 data points from 35 studies, uses inputs, such as substrate type, inoculum type, concentration, pH, and temperature, with hydrogen yield as the output. The multilayer perceptron artificial neural network model achieved high accuracy, with a root mean square error of 0.3838, a mean absolute percentage error of 0.1938, and a coefficient of determination of 0.8381. These results demonstrate the model's effectiveness in predicting biohydrogen production, providing a valuable tool for optimizing the fermentation process and advancing sustainable energy solutions.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"192 ","pages":"Article 108900"},"PeriodicalIF":3.9,"publicationDate":"2024-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572553","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}
Pub Date : 2024-10-18DOI: 10.1016/j.compchemeng.2024.108890
Ashfaq Iftakher , Ty Leonard , M.M. Faruque Hasan
We integrate equilibrium and rate-based models to formulate a hybrid optimization scheme for designing an ionic liquid-based extractive distillation process for mixed-refrigerant separation. The equilibrium model assumes vapor–liquid equilibrium at each stage but challenges arise with low-volatility, high-viscosity solvents, which drive the system away from equilibrium. The rate-based approach considers mass and heat transfer rates, giving more accurate representation. We compare the two models for separating R-410A, an azeotropic mixture of R-32 and R-125, using [EMIM][SCN] ionic liquid as entrainer. Analyzing over 4300 simulations with various dimensionality reduction and topological analysis techniques, we find that predictions from the two models exhibit similar trends, but the overestimation in equilibrium-based purities sometimes leads to infeasible process designs. The proposed optimization algorithm thus combines the strengths of the two models to locate feasible and optimal designs.
{"title":"Integrating different fidelity models for process optimization: A case of equilibrium and rate-based extractive distillation using ionic liquids","authors":"Ashfaq Iftakher , Ty Leonard , M.M. Faruque Hasan","doi":"10.1016/j.compchemeng.2024.108890","DOIUrl":"10.1016/j.compchemeng.2024.108890","url":null,"abstract":"<div><div>We integrate equilibrium and rate-based models to formulate a hybrid optimization scheme for designing an ionic liquid-based extractive distillation process for mixed-refrigerant separation. The equilibrium model assumes vapor–liquid equilibrium at each stage but challenges arise with low-volatility, high-viscosity solvents, which drive the system away from equilibrium. The rate-based approach considers mass and heat transfer rates, giving more accurate representation. We compare the two models for separating R-410A, an azeotropic mixture of R-32 and R-125, using [EMIM][SCN] ionic liquid as entrainer. Analyzing over 4300 simulations with various dimensionality reduction and topological analysis techniques, we find that predictions from the two models exhibit similar trends, but the overestimation in equilibrium-based purities sometimes leads to infeasible process designs. The proposed optimization algorithm thus combines the strengths of the two models to locate feasible and optimal designs.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"192 ","pages":"Article 108890"},"PeriodicalIF":3.9,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533123","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}
Pub Date : 2024-10-17DOI: 10.1016/j.compchemeng.2024.108893
Tobias Keßler , Christoph Plate , Jessica Behrens , Carl J. Martensen , Johannes Leipold , Lothar Kaps , Andreas Seidel-Morgenstern , Sebastian Sager , Achim Kienle
Power-to-methanol processes use green hydrogen, which is generated by electrolysis using regenerative energy, e.g. wind or solar energy. In this paper a novel control concept is proposed to handle fluctuations in the hydrogen feed due to unavoidable fluctuations in the energy supply. Focus is on a robust multistage reactor, with variable feed distribution as additional degrees of freedom. The controller uses dynamic optimization with a hybrid model for feedforward control of the feed distribution and simple PI control of the total carbon feed to compensate plant model mismatch and unforeseen disturbances. The hybrid model combines modeling from first principles with a neural network to capture the influence of catalyst dynamics on the reaction rates. The concept is validated with a simulation study using a detailed reference model.
电能转化甲醇工艺使用绿色氢气，这种氢气是利用风能或太阳能等可再生能源通过电解产生的。本文提出了一种新颖的控制概念，用于处理因能源供应不可避免的波动而导致的氢气进料波动。重点是稳健的多级反应器，将可变进料分布作为额外的自由度。控制器采用动态优化和混合模型对进料分布进行前馈控制，并对总碳进料进行简单的 PI 控制，以补偿工厂模型不匹配和不可预见的干扰。混合模型将第一原理建模与神经网络相结合，以捕捉催化剂动态对反应速率的影响。利用详细的参考模型进行的模拟研究验证了这一概念。
{"title":"Two degrees of freedom control of a multistage power-to-methanol reactor","authors":"Tobias Keßler , Christoph Plate , Jessica Behrens , Carl J. Martensen , Johannes Leipold , Lothar Kaps , Andreas Seidel-Morgenstern , Sebastian Sager , Achim Kienle","doi":"10.1016/j.compchemeng.2024.108893","DOIUrl":"10.1016/j.compchemeng.2024.108893","url":null,"abstract":"<div><div>Power-to-methanol processes use green hydrogen, which is generated by electrolysis using regenerative energy, e.g. wind or solar energy. In this paper a novel control concept is proposed to handle fluctuations in the hydrogen feed due to unavoidable fluctuations in the energy supply. Focus is on a robust multistage reactor, with variable feed distribution as additional degrees of freedom. The controller uses dynamic optimization with a hybrid model for feedforward control of the feed distribution and simple PI control of the total carbon feed to compensate plant model mismatch and unforeseen disturbances. The hybrid model combines modeling from first principles with a neural network to capture the influence of catalyst dynamics on the reaction rates. The concept is validated with a simulation study using a detailed reference model.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"192 ","pages":"Article 108893"},"PeriodicalIF":3.9,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533124","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}
Pub Date : 2024-10-15DOI: 10.1016/j.compchemeng.2024.108889
Pedro M. Castro
This paper presents a continuous-time formulation for the management of deep-sea floating production storage and offloading (FPSO) units, which process and store crude oil from nearby oil platforms while waiting for a shuttle tanker to arrive and collect it. A heterogeneous fleet of tanker vessels travelling between the FPSO units and a port refinery is available, with the optimization deciding on the number and type of vessels to use, their route and travelling speed. The goal is to achieve an environmentally friendly solution featuring vessels travelling at lower speeds to minimize fuel consumption (a quadratic function of speed), which may require renting additional shuttle tankers to maintain production. The resulting mixed-integer quadratically constrained problems (MIQCP) can be solved by GUROBI, but not to global optimality, whereas a mixed-integer linear programming (MILP) relaxation that underestimates the total operating cost can tackle moderate problem sizes (5 FPSOs and 4 shuttle tankers).
{"title":"Maritime inventory routing with speed optimization: A MIQCP formulation for a tanker fleet servicing FPSO units","authors":"Pedro M. Castro","doi":"10.1016/j.compchemeng.2024.108889","DOIUrl":"10.1016/j.compchemeng.2024.108889","url":null,"abstract":"<div><div>This paper presents a continuous-time formulation for the management of deep-sea floating production storage and offloading (FPSO) units, which process and store crude oil from nearby oil platforms while waiting for a shuttle tanker to arrive and collect it. A heterogeneous fleet of tanker vessels travelling between the FPSO units and a port refinery is available, with the optimization deciding on the number and type of vessels to use, their route and travelling speed. The goal is to achieve an environmentally friendly solution featuring vessels travelling at lower speeds to minimize fuel consumption (a quadratic function of speed), which may require renting additional shuttle tankers to maintain production. The resulting mixed-integer quadratically constrained problems (MIQCP) can be solved by GUROBI, but not to global optimality, whereas a mixed-integer linear programming (MILP) relaxation that underestimates the total operating cost can tackle moderate problem sizes (5 FPSOs and 4 shuttle tankers).</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"192 ","pages":"Article 108889"},"PeriodicalIF":3.9,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533121","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}
Pub Date : 2024-10-11DOI: 10.1016/j.compchemeng.2024.108894
Ahmed Zouhir Kouache, Ahmed Djafour, Mohammed Bilal Danoune, Khaled Mohammed Said Benzaoui, Abdelmoumen Gougui
The present study introduces an efficient Self-Adaptive Bonobo Optimizer (SaBO) for identifying the unknown parameters of the proton exchange membrane fuel cell (PEMFC). A comparative analysis between recent robust approaches, such as Gradient-based Optimizer (GBO), Bald Eagle Search Algorithm, and Rime-Ice algorithm (RIME), has been introduced. The basic concept is to minimize the mean bias error between the measured and predicted stack voltage. The main results show that although the techniques were close, in contrast, the SaBO optimizer provides a better superiority than GBO, BES, and RIME for an optimum forecast of the PEMFCs model. Moreover, the best fitness was achieved with the SaBO at 0.0367 (V) for the Heliocentris FC-50, and 0.1150 (V) for Nexa® 1200, also, with the minimum deviation of 0.0027 & 0.0172, and high efficiency. These achievements denote that the SaBO algorithm is more stable and robust for PEMFC parameter estimation.
{"title":"Accurate key parameters estimation of PEM fuel cells using self-adaptive bonobo optimizer","authors":"Ahmed Zouhir Kouache, Ahmed Djafour, Mohammed Bilal Danoune, Khaled Mohammed Said Benzaoui, Abdelmoumen Gougui","doi":"10.1016/j.compchemeng.2024.108894","DOIUrl":"10.1016/j.compchemeng.2024.108894","url":null,"abstract":"<div><div>The present study introduces an efficient Self-Adaptive Bonobo Optimizer (SaBO) for identifying the unknown parameters of the proton exchange membrane fuel cell (PEMFC). A comparative analysis between recent robust approaches, such as Gradient-based Optimizer (GBO), Bald Eagle Search Algorithm, and Rime-Ice algorithm (RIME), has been introduced. The basic concept is to minimize the mean bias error between the measured and predicted stack voltage. The main results show that although the techniques were close, in contrast, the SaBO optimizer provides a better superiority than GBO, BES, and RIME for an optimum forecast of the PEMFCs model. Moreover, the best fitness was achieved with the SaBO at 0.0367 (V) for the Heliocentris FC-50, and 0.1150 (V) for Nexa® 1200, also, with the minimum deviation of 0.0027 & 0.0172, and high efficiency. These achievements denote that the SaBO algorithm is more stable and robust for PEMFC parameter estimation.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"192 ","pages":"Article 108894"},"PeriodicalIF":3.9,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142441803","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}
Pub Date : 2024-10-11DOI: 10.1016/j.compchemeng.2024.108892
Wilson Cardoso , Jussara V. Roque , Jeroen J. Jansen , Sin Yong Teng , Reinaldo F. Teófilo
Combinatorial Order Pre-processing Search (COPS), a novel approach for optimizing data pre-processing is proposed in this work. Unlike simultaneous hyperparameter optimization, COPS employs a priori optimization to reduce computational time while refining the search space for preprocessing sequences and combinations. It allows for setting a maximum number of pre-processing methods, while efficiently searching through combinations of methods with chemically relevant knowledge. In this work, 67 calibration datasets across various analytical techniques, including fluorescence spectroscopy, gas chromatography (GC), near-infrared spectroscopy (NIR), mid-infrared spectroscopy (MIR), visible-near-infrared spectroscopy (Vis-NIR), Raman spectroscopy, nuclear magnetic resonance (NMR) spectroscopy, and voltammetry were evaluated. COPS yielded significant improvements over existing methodologies based on design of experiment and compounded pre-processing approaches. The COPS outperformed the other methods, resulting in an average root mean square error of prediction (RMSEP) reduction of 31.7%, while also reduced the complexity (number of latent variables) of the model which allows for easier interpretation. This underscores the importance of combinatorial order set theory for the search of pre-processing method combinations (without fixing the sequence of pre-processing methods) to enhance model performance and interpretation. The novel COPS approach can be employed in process analytical technology (such as inline, online or at-line chemical sensing analytics) to enhance predictive accuracy and operational efficiency, fundamentally transforming the quality and reliability of chemical process monitoring and control.
{"title":"Combinatorial Order Pre-processing Search (COPS): A new pre-processing strategy for large-scale interpretable data analysis in process analytical technologies","authors":"Wilson Cardoso , Jussara V. Roque , Jeroen J. Jansen , Sin Yong Teng , Reinaldo F. Teófilo","doi":"10.1016/j.compchemeng.2024.108892","DOIUrl":"10.1016/j.compchemeng.2024.108892","url":null,"abstract":"<div><div>Combinatorial Order Pre-processing Search (COPS), a novel approach for optimizing data pre-processing is proposed in this work. Unlike simultaneous hyperparameter optimization, COPS employs <em>a priori</em> optimization to reduce computational time while refining the search space for preprocessing sequences and combinations. It allows for setting a maximum number of pre-processing methods, while efficiently searching through combinations of methods with chemically relevant knowledge. In this work, 67 calibration datasets across various analytical techniques, including fluorescence spectroscopy, gas chromatography (GC), near-infrared spectroscopy (NIR), mid-infrared spectroscopy (MIR), visible-near-infrared spectroscopy (Vis-NIR), Raman spectroscopy, nuclear magnetic resonance (NMR) spectroscopy, and voltammetry were evaluated. COPS yielded significant improvements over existing methodologies based on design of experiment and compounded pre-processing approaches. The COPS outperformed the other methods, resulting in an average root mean square error of prediction (RMSE<sub>P</sub>) reduction of 31.7%, while also reduced the complexity (number of latent variables) of the model which allows for easier interpretation. This underscores the importance of combinatorial order set theory for the search of pre-processing method combinations (without fixing the sequence of pre-processing methods) to enhance model performance and interpretation. The novel COPS approach can be employed in process analytical technology (such as inline, online or at-line chemical sensing analytics) to enhance predictive accuracy and operational efficiency, fundamentally transforming the quality and reliability of chemical process monitoring and control.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"192 ","pages":"Article 108892"},"PeriodicalIF":3.9,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533122","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}
Pub Date : 2024-10-03DOI: 10.1016/j.compchemeng.2024.108887
Cheng Ji , Fangyuan Ma , Jingde Wang , Wei Sun , Ahmet Palazoglu
Although deep autoencoders excel at extracting intricate features, their application in process monitoring is limited by the requirement for large sample sizes and interpretability of latent representations. This work presents a special deep learning structure named Siamese network to detect abnormal deviations in nonlinear dynamic processes. By leveraging the capability of Siamese architecture to process multiple inputs simultaneously, the training sample size expands exponentially, which enhances the learning potential of the model. Furthermore, a long short-term memory unit is integrated to enable the capture of long-term process dynamics. To refine the distribution of latent features extracted from diverse data types, a contrastive loss function is proposed, which strengthens the model's fault detection capabilities and enhances its interpretation of latent representations. Then T2 statistic is established on the latent space to perform fault detection. The effectiveness of the method is demonstrated through case studies on simulation processes and an industrial process.
{"title":"Industrial Process Fault Detection Based on Siamese Recurrent Autoencoder","authors":"Cheng Ji , Fangyuan Ma , Jingde Wang , Wei Sun , Ahmet Palazoglu","doi":"10.1016/j.compchemeng.2024.108887","DOIUrl":"10.1016/j.compchemeng.2024.108887","url":null,"abstract":"<div><div>Although deep autoencoders excel at extracting intricate features, their application in process monitoring is limited by the requirement for large sample sizes and interpretability of latent representations. This work presents a special deep learning structure named Siamese network to detect abnormal deviations in nonlinear dynamic processes. By leveraging the capability of Siamese architecture to process multiple inputs simultaneously, the training sample size expands exponentially, which enhances the learning potential of the model. Furthermore, a long short-term memory unit is integrated to enable the capture of long-term process dynamics. To refine the distribution of latent features extracted from diverse data types, a contrastive loss function is proposed, which strengthens the model's fault detection capabilities and enhances its interpretation of latent representations. Then <em>T</em><sup>2</sup> statistic is established on the latent space to perform fault detection. The effectiveness of the method is demonstrated through case studies on simulation processes and an industrial process.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"192 ","pages":"Article 108887"},"PeriodicalIF":3.9,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142425305","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}
Pub Date : 2024-09-30DOI: 10.1016/j.compchemeng.2024.108886
Zikai Cheng , Zheng Li , Pengyang Zhou , Pei Liu
Absorption-tower-based carbon capture can decarbonize coal or natural gas power plants, but its large space requirement limits its applications. On-site carbon capture facilities using hollow fiber membrane contactor (HFMC) can be retrofitted in flue gas passes of power units, thus have great potential in reducing space requirement of carbon capture functional blocks. In this paper, we present a one-dimensional mathematical model of superhydrophobic-modified HFMC and conduct a case study on 660 MW coal-fired power plant to illustrate energy, cost and space requirements of full-scale flue gas carbon capture. Results show that by retrofitting HFMC in flue gas passes, HFMC has around 40 % removal efficiency with 4 % volume of absorption towers. Energy and economic wise, HFMC has 17.22 % lower energy penalty and 37.95 % lower total annual cost than absorption towers. By extending flue gas passes, minimal energy penalty and CO2 avoidance cost drops to 2.33 GJ/t CO2 and 108.37 USD/t CO2.
{"title":"Spacially affordable decarbonization of coal-fired power plants via membrane-based on-site CO2 absorption: A techno-economic analysis","authors":"Zikai Cheng , Zheng Li , Pengyang Zhou , Pei Liu","doi":"10.1016/j.compchemeng.2024.108886","DOIUrl":"10.1016/j.compchemeng.2024.108886","url":null,"abstract":"<div><div>Absorption-tower-based carbon capture can decarbonize coal or natural gas power plants, but its large space requirement limits its applications. On-site carbon capture facilities using hollow fiber membrane contactor (HFMC) can be retrofitted in flue gas passes of power units, thus have great potential in reducing space requirement of carbon capture functional blocks. In this paper, we present a one-dimensional mathematical model of superhydrophobic-modified HFMC and conduct a case study on 660 MW coal-fired power plant to illustrate energy, cost and space requirements of full-scale flue gas carbon capture. Results show that by retrofitting HFMC in flue gas passes, HFMC has around 40 % removal efficiency with 4 % volume of absorption towers. Energy and economic wise, HFMC has 17.22 % lower energy penalty and 37.95 % lower total annual cost than absorption towers. By extending flue gas passes, minimal energy penalty and CO<sub>2</sub> avoidance cost drops to 2.33 GJ/t CO<sub>2</sub> and 108.37 USD/t CO<sub>2</sub>.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"192 ","pages":"Article 108886"},"PeriodicalIF":3.9,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142425304","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}
Pub Date : 2024-09-26DOI: 10.1016/j.compchemeng.2024.108883
Limin Wang , Linzhu Jia , Tao Zou , Ridong Zhang , Furong Gao
Aiming at the characteristics of batch process changing along with time and batch directions, the existence of unmodeled dynamics, and the partial failure of actuators or/and sensors, we propose a novel 2D reinforcement learning (RL) fault tolerant control strategy without considering model parameters. Firstly, a two-Dimensional (2D) augmented state space model and 2D Q function-based fault tolerant control (FTC) framework is established. The 2D Bellman equation can be acquired by analyzing the relationship between the 2D value function and the 2D Q function. Based on the extended model and Q-learning concept of RL, a data-driven FTTC independent of model parameters is designed, and a 2D data-driven Q-learning algorithm is proposed. Finally, taking the pressure holding phase in the injection process as the experimental object, the control effect is compared with that of the traditional model-based FTC, and better tracking performance and unbiasedness to the probing noise can be proved.
{"title":"Two-dimensional reinforcement learning model-free fault-tolerant control for batch processes against multi- faults","authors":"Limin Wang , Linzhu Jia , Tao Zou , Ridong Zhang , Furong Gao","doi":"10.1016/j.compchemeng.2024.108883","DOIUrl":"10.1016/j.compchemeng.2024.108883","url":null,"abstract":"<div><div>Aiming at the characteristics of batch process changing along with time and batch directions, the existence of unmodeled dynamics, and the partial failure of actuators or/and sensors, we propose a novel 2D reinforcement learning (RL) fault tolerant control strategy without considering model parameters. Firstly, a two-Dimensional (2D) augmented state space model and 2D Q function-based fault tolerant control (FTC) framework is established. The 2D Bellman equation can be acquired by analyzing the relationship between the 2D value function and the 2D Q function. Based on the extended model and Q-learning concept of RL, a data-driven FTTC independent of model parameters is designed, and a 2D data-driven Q-learning algorithm is proposed. Finally, taking the pressure holding phase in the injection process as the experimental object, the control effect is compared with that of the traditional model-based FTC, and better tracking performance and unbiasedness to the probing noise can be proved.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"192 ","pages":"Article 108883"},"PeriodicalIF":3.9,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142425303","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}
Pub Date : 2024-09-26DOI: 10.1016/j.compchemeng.2024.108885
Maria Kanta, Evangelos G. Tsimopoulos, Christos N. Dimitriadis, Michael C. Georgiadis
Addressing global warming necessitates carbon emissions reduction and renewable energy integration within the energy sector. Gas-Fired Power Plants (GFPP) are appealing to investors due to their low emissions and operational flexibility, which are considered necessary characteristics within low-carbon power systems with increasing renewable energy uncertainty. Investing in GFPPs presents intricate challenges due to the increasingly interdependent electricity and natural gas markets, especially in the light of a low-carbon economy. This work addresses these challenges for a strategic agent by proposing a bi-level optimization framework. The upper-level model derives the optimal electricity portfolio management regarding new investments and strategic biddings, while in the lower-level model, the electricity and gas markets are cleared sequentially under a Carbon Emission Trading Scheme (CETS). Case studies on a Pennsylvania-New Jersey- Maryland (PJM) 5-bus power system and an IEEE 24-bus test system demonstrate the applicability and efficacy of the proposed model in capturing the impact of a transitional integrated market framework on GFPPs investments. Also, introducing stochasticity to the model provides a better insight into the contrasting effects of emission allowance trading and gas prices on investment and bidding strategies.
{"title":"Strategic investments and portfolio management in interdependent low-carbon electricity and natural gas markets","authors":"Maria Kanta, Evangelos G. Tsimopoulos, Christos N. Dimitriadis, Michael C. Georgiadis","doi":"10.1016/j.compchemeng.2024.108885","DOIUrl":"10.1016/j.compchemeng.2024.108885","url":null,"abstract":"<div><div>Addressing global warming necessitates carbon emissions reduction and renewable energy integration within the energy sector. Gas-Fired Power Plants (GFPP) are appealing to investors due to their low emissions and operational flexibility, which are considered necessary characteristics within low-carbon power systems with increasing renewable energy uncertainty. Investing in GFPPs presents intricate challenges due to the increasingly interdependent electricity and natural gas markets, especially in the light of a low-carbon economy. This work addresses these challenges for a strategic agent by proposing a bi-level optimization framework. The upper-level model derives the optimal electricity portfolio management regarding new investments and strategic biddings, while in the lower-level model, the electricity and gas markets are cleared sequentially under a Carbon Emission Trading Scheme (CETS). Case studies on a Pennsylvania-New Jersey- Maryland (PJM) 5-bus power system and an IEEE 24-bus test system demonstrate the applicability and efficacy of the proposed model in capturing the impact of a transitional integrated market framework on GFPPs investments. Also, introducing stochasticity to the model provides a better insight into the contrasting effects of emission allowance trading and gas prices on investment and bidding strategies.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"192 ","pages":"Article 108885"},"PeriodicalIF":3.9,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142425302","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号