Computers & Chemical Engineering最新文献

ARRTOC: Adversarially Robust Real-Time Optimization and Control

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-11-28 DOI: 10.1016/j.compchemeng.2024.108930

Akhil Ahmed, Ehecatl Antonio del Rio-Chanona, Mehmet Mercangöz

{"title":"ARRTOC: Adversarially Robust Real-Time Optimization and Control","authors":"Akhil Ahmed, Ehecatl Antonio del Rio-Chanona, Mehmet Mercangöz","doi":"10.1016/j.compchemeng.2024.108930","DOIUrl":"10.1016/j.compchemeng.2024.108930","url":null,"abstract":"<div><div>Real-Time Optimization (RTO) plays a crucial role in process operation by determining optimal set-points for lower-level controllers. However, tracking these set-points can be challenging at the control layer due to disturbances, measurement noise, and actuator limitations, leading to a mismatch between expected and achieved RTO benefits. To address this, we present the Adversarially Robust Real-Time Optimization and Control (ARRTOC) algorithm. ARRTOC addresses this issue by finding set-points which are both optimal and inherently robust to implementation errors at the control layers. ARRTOC draws inspiration from adversarial machine learning, offering a novel constrained Adversarially Robust Optimization (ARO) solution applied to the RTO layer. We present several case studies to validate our approach, including a bioreactor, a multi-loop evaporator process, and scenarios involving plant-model mismatch. These studies demonstrate that ARRTOC can improve realized RTO benefits by as much as 50% compared to traditional RTO formulations that do not account for control layer performance.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108930"},"PeriodicalIF":3.9,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747137","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

Distributionally robust CVaR optimization for refinery integrated production–maintenance scheduling under uncertainty

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-11-27 DOI: 10.1016/j.compchemeng.2024.108949

Ya Liu , Jiahao Lai , Bo Chen , Kai Wang , Fei Qiao , Hanli Wang

{"title":"Distributionally robust CVaR optimization for refinery integrated production–maintenance scheduling under uncertainty","authors":"Ya Liu , Jiahao Lai , Bo Chen , Kai Wang , Fei Qiao , Hanli Wang","doi":"10.1016/j.compchemeng.2024.108949","DOIUrl":"10.1016/j.compchemeng.2024.108949","url":null,"abstract":"<div><div>In the petroleum refining industry, efficient production planning and maintenance scheduling are crucial for economic performance and operational efficiency. Moreover, the production processes face significant uncertainties stemming from market fluctuations and equipment failures. However, traditional optimization methods often treat production and maintenance independently and neglect the risk management associated with uncertainties in the production process, leading to unreliable plans and suboptimal execution. To address these issues, this paper proposes an innovative data-driven distributionally robust conditional value-at-risk (DRCVaR) method to tackle the integrated production–maintenance optimization problem under crude oil price uncertainty. By constructing confidence sets with <span><math><msub><mrow><mi>L</mi></mrow><mrow><mn>2</mn></mrow></msub></math></span> norm constraints based on historical data, our approach directly links the model’s conservatism to the amount of available data, effectively managing risk. In addition, we propose robust linear transformation to simplify the min–max nonlinear problem into a conic constraint problem, enhancing solution efficiency and ensuring better operational stability. Refinery case studies demonstrate that the proposed DRCVaR consistently achieves a practical and acceptable solution, significantly outperforming state-of-the-art approaches.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108949"},"PeriodicalIF":3.9,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747015","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

Machine learning in PEM water electrolysis: A study of hydrogen production and operating parameters

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-11-27 DOI: 10.1016/j.compchemeng.2024.108954

Ibrahim Shomope , Amani Al-Othman , Muhammad Tawalbeh , Hussam Alshraideh , Fares Almomani

{"title":"Machine learning in PEM water electrolysis: A study of hydrogen production and operating parameters","authors":"Ibrahim Shomope , Amani Al-Othman , Muhammad Tawalbeh , Hussam Alshraideh , Fares Almomani","doi":"10.1016/j.compchemeng.2024.108954","DOIUrl":"10.1016/j.compchemeng.2024.108954","url":null,"abstract":"<div><div>Proton exchange membrane water electrolysis (PEMWE) powered by renewable energy stands out as a promising technology for the sustainable production of high-purity hydrogen. This study employed three machine learning (ML) algorithms, random forest (RF), support vector machine (SVM), and eXtreme gradient boosting (XGBoost), to predict hydrogen production in PEMWE. Model performance was evaluated using root mean squared error (RMSE), coefficient of determination (<em>R²</em>), and mean absolute error (MAE) metrics. The top-performing models, RF and XGBoost, were further refined through hyperparameter tuning. The final models demonstrated high reliability in predicting hydrogen production rates, with RF consistently outperforming XGBoost. The RF model achieved a predictive accuracy of <em>R²</em> = 0.9898, RMSE = 19.99 mL/min, and MAE = 10.41 mL/min, while the XGBoost model achieved <em>R²</em> = 0.9894, RMSE = 20.43 mL/min, and MAE = 11.50 mL/min. Partial dependency plots (PDPs) emphasized the critical role of optimizing both cell voltage and current to maximize hydrogen production in PEMWE. These insights provide valuable guidance for operational adjustments, ensuring optimal system performance for high efficiency and productivity. The study suggests further research on the impact of parameters like temperature and power density on hydrogen production, incorporating them for better optimization.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108954"},"PeriodicalIF":3.9,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747016","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

Gas dispersion modeling in stereoscopic space with obstacles using a novel spatiotemporal prediction network

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-11-24 DOI: 10.1016/j.compchemeng.2024.108934

Shikuan Chen, Wenli Du, Xinjie Wang, Bing Wang, Chenxi Cao, Xin Peng

{"title":"Gas dispersion modeling in stereoscopic space with obstacles using a novel spatiotemporal prediction network","authors":"Shikuan Chen, Wenli Du, Xinjie Wang, Bing Wang, Chenxi Cao, Xin Peng","doi":"10.1016/j.compchemeng.2024.108934","DOIUrl":"10.1016/j.compchemeng.2024.108934","url":null,"abstract":"<div><div>Gas leakage can lead to catastrophic consequences on both the environment and human health. To mitigate these losses, it is imperative to develop accurate and efficient spatiotemporal models for gas dispersion. The gas diffusion process occurs in a 3-dimensional (3D) space, but most research has been confined to flat-plane scenarios, neglecting the stereoscopic distribution of gas concentrations. To address this issue, we propose a novel method that combines 3D convolution with a long short-term memory neural network (3DConvLSTM) to forecast the 3D spatiotemporal concentration distribution of gas leakage in obstructed scenes. The 3D convolutional filters fully operate in the spatial domain, capturing spatial features horizontally and vertically. To provide data for the experiment, ethane leak scenarios with different sources, rates and wind directions are simulated by computational fluid dynamics (CFD). The results demonstrate that the 3DConvLSTM exhibits higher accuracy and requires fewer parameters, highlighting the effectiveness of the proposed method.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108934"},"PeriodicalIF":3.9,"publicationDate":"2024-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142756623","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

Linear and neural network models for predicting N-glycosylation in Chinese Hamster Ovary cells based on B4GALT levels

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-11-23 DOI: 10.1016/j.compchemeng.2024.108937

Pedro Seber, Richard D. Braatz

引用次数: 0

Designing a sustainable-resilient vaccine cold chain network in uncertain environments

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-11-23 DOI: 10.1016/j.compchemeng.2024.108936

Yanju Chen , Mengxuan Chen , Tianran Hu

引用次数: 0

A robust batch-to-batch optimization framework for pharmaceutical applications

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-11-22 DOI: 10.1016/j.compchemeng.2024.108935

Ali Ghodba , Anne Richelle , Chris McCready , Luis Ricardez-Sandoval , Hector Budman

引用次数: 0

Real-time update of data-driven reduced and full order models with applications

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-11-22 DOI: 10.1016/j.compchemeng.2024.108923

Om Prakash, Biao Huang

引用次数: 0

Virtual sample generation for soft-sensing in small sample scenarios using glow-embedded variational autoencoder

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-11-22 DOI: 10.1016/j.compchemeng.2024.108925

Yan Xu , Qun-Xiong Zhu , Wei Ke , Yan-Lin He , Ming-Qing Zhang , Yuan Xu

{"title":"Virtual sample generation for soft-sensing in small sample scenarios using glow-embedded variational autoencoder","authors":"Yan Xu , Qun-Xiong Zhu , Wei Ke , Yan-Lin He , Ming-Qing Zhang , Yuan Xu","doi":"10.1016/j.compchemeng.2024.108925","DOIUrl":"10.1016/j.compchemeng.2024.108925","url":null,"abstract":"<div><div>In industrial processes, limitations of the physical environment, sensors drop-out, and repetitive sampling often lead to insufficient and unevenly distributed representative instances, which greatly hinders the accuracy of soft-sensing models. This paper presents a novel virtual sample generation method based on Glow-embedded variational autoencoder (GVAE-VSG), aimed at enhancing data richness and diversity to improve the modeling performance. Specifically, GVAE-VSG embeds the Glow model from flow transformations into the variational autoencoder. This allows for the derivation of a more generalized posterior distribution without reducing sample dimensionality, thereby ensuring the generation of higher-quality virtual input samples. Subsequently, a nonlinear iterative partial least squares regression framework, incorporating a sparse constrained error matrix, is employed to generate virtual output samples that more closely resemble actual data. Finally, by a synthetic nonlinear function and an actual purification terephthalic acid (PTA) solvent system, the generative and modeling performance of the proposed method are comprehensively assessed.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"193 ","pages":"Article 108925"},"PeriodicalIF":3.9,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743283","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

Multiscale optimization of formic acid dehydrogenation process via linear model decision tree surrogates

IF 3.9 2区工程技术

Computers & Chemical Engineering Pub Date : 2024-11-22 DOI: 10.1016/j.compchemeng.2024.108921

Ethan M. Sunshine , Giovanna Bucci , Tanusree Chatterjee , Shyam Deo , Victoria M. Ehlinger , Wenqin Li , Thomas Moore , Corey Myers , Wenyu Sun , Bo-Xun Wang , Mengyao Yuan , John R. Kitchin , Carl D. Laird , Matthew J. McNenly , Sneha A. Akhade

{"title":"Multiscale optimization of formic acid dehydrogenation process via linear model decision tree surrogates","authors":"Ethan M. Sunshine , Giovanna Bucci , Tanusree Chatterjee , Shyam Deo , Victoria M. Ehlinger , Wenqin Li , Thomas Moore , Corey Myers , Wenyu Sun , Bo-Xun Wang , Mengyao Yuan , John R. Kitchin , Carl D. Laird , Matthew J. McNenly , Sneha A. Akhade","doi":"10.1016/j.compchemeng.2024.108921","DOIUrl":"10.1016/j.compchemeng.2024.108921","url":null,"abstract":"<div><div>Multiscale optimization problems require the interconnection of several models of distinct phenomena which occur at different scales in length or time. However, the best model for any particular phenomenon may not be amenable to rigorous optimization techniques. For instance, molecular interactions are often modeled by computational chemistry software packages that cannot be easily converted into optimization constraints. Data-driven surrogate models can overcome this problem. By choosing surrogates with functional forms that are convertible to a mixed-integer linear model, one can connect and optimize these surrogates instead of the underlying models. We demonstrate the interconnection of linear model decision trees to optimize across three scales of a formic acid dehydrogenation process. We show that optimizing across all three scales simultaneously leads to a 40% cost savings compared to optimizing each model independently. Furthermore, the surrogates retain some relevant physical behaviors and provide insights into the optimal design of this process.</div></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"194 ","pages":"Article 108921"},"PeriodicalIF":3.9,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747138","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