Computers & Chemical Engineering最新文献_第9页

Integration of planning, scheduling, and control of no-wait batch plant 一体化的计划，调度，和控制的无等待批次工厂

IF 4.3 2区工程技术

Computers & Chemical Engineering Pub Date : 2023-10-16 DOI: 10.1016/j.compchemeng.2023.108467

Nan Ji, Xingsheng Gu

{"title":"Integration of planning, scheduling, and control of no-wait batch plant","authors":"Nan Ji, Xingsheng Gu","doi":"10.1016/j.compchemeng.2023.108467","DOIUrl":"https://doi.org/10.1016/j.compchemeng.2023.108467","url":null,"abstract":"<div><p>The batch process plays an important role in industrial production. Among them, production processes that have specific requirements for operational continuity in each processing stage should consider the no-wait constraint to meet the production reality. The batch process with a no-wait constraint is a typical NP-hard problem. In this work, we propose a framework for the integration of planning, scheduling, and control. We also propose a decomposition method with an improved genetic algorithm to solve the integration problem of scheduling and control for the no-wait batch process. The integrated formulation represents a typical mixed-logic dynamic optimization (MLDO) problem, which involves logical disjunctions and operational dynamics. Then, we address the integrated problem as a grey-box optimization problem, using data-driven feasibility analysis and surrogate models to approximate the unknown black-box constraints. Finally, we test specific production instances to demonstrate the feasibility and superiority of the proposed integration model of the no-wait batch process and optimization algorithm.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"180 ","pages":"Article 108467"},"PeriodicalIF":4.3,"publicationDate":"2023-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S009813542300337X/pdfft?md5=6637c2e57f813a97299172aab91293e4&pid=1-s2.0-S009813542300337X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91964511","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

Feasibility/Flexibility-based optimization for process design and operations 基于可行性/灵活性的工艺设计和操作优化

IF 4.3 2区工程技术

Computers & Chemical Engineering Pub Date : 2023-10-14 DOI: 10.1016/j.compchemeng.2023.108461

Huayu Tian , Jnana Sai Jagana , Qi Zhang , Marianthi Ierapetritou

引用次数: 1

A novel state-of-health notion and its use for battery aging monitoring of zinc-air batteries 一种新的健康状态概念及其在锌-空气电池老化监测中的应用

IF 4.3 2区工程技术

Computers & Chemical Engineering Pub Date : 2023-10-14 DOI: 10.1016/j.compchemeng.2023.108465

Woranunt Lao-atiman , Pornchai Bumroongsri , Sorin Olaru , Soorathep Kheawhom

{"title":"A novel state-of-health notion and its use for battery aging monitoring of zinc-air batteries","authors":"Woranunt Lao-atiman , Pornchai Bumroongsri , Sorin Olaru , Soorathep Kheawhom","doi":"10.1016/j.compchemeng.2023.108465","DOIUrl":"https://doi.org/10.1016/j.compchemeng.2023.108465","url":null,"abstract":"<div><p>Accurate monitoring of battery aging is pivotal for optimizing the performance of zinc-air batteries (ZABs). To obtain precise information about battery aging, an appropriate definition of state-of-health (SOH) is essential. However, the definition of SOH for ZABs has not been well-defined. This work introduces a novel SOH concept based on energy efficiency and integrates it with an underlying linear parameter varying (LPV) model. Crucially, the LPV model is chosen for its capability to represent nonlinear behavior, making it apt for capturing the intricacies of battery aging dynamics. With SOH defined as the scheduling parameter, electrochemical impedance spectroscopy (EIS) is employed to assess the influence of SOH. The results validate the model's robustness, as its predictions align closely with the empirical data. This newly proposed SOH definition exhibits a strong association with the model parameters. Furthermore, the efficacy of the LPV technique, especially when paired with the proposed SOH, suggests significant potential for refining battery aging monitoring in ZABs.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"180 ","pages":"Article 108465"},"PeriodicalIF":4.3,"publicationDate":"2023-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67736822","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

Process operations: from models and data to digital applications 流程操作：从模型和数据到数字应用

IF 4.3 2区工程技术

Computers & Chemical Engineering Pub Date : 2023-10-14 DOI: 10.1016/j.compchemeng.2023.108463

Constantinos C. Pantelides , Frances E. Pereira , Penelope J. Stanger , Nina F. Thornhill

{"title":"Process operations: from models and data to digital applications","authors":"Constantinos C. Pantelides , Frances E. Pereira , Penelope J. Stanger , Nina F. Thornhill","doi":"10.1016/j.compchemeng.2023.108463","DOIUrl":"https://doi.org/10.1016/j.compchemeng.2023.108463","url":null,"abstract":"<div><p>Digital Applications are complex software systems for decision support in process operations and for process control. Each such application involves one or more computational modules being executed in an arbitrary real-time schedule, and communicating with each other and the external environment within which they are deployed. Each module may involve a mathematical computation based on a process model derived from first-principles or via machine learning applied to plant data; alternatively, it may have a purely statistical basis derived directly from plant data. There has been much progress in the use of such digital applications in industrial practice. However, achieving true scalability and sustainability in this direction will require general platforms that will allow the essentially code-free development of new applications and their large-scale deployments. We describe one such, recently developed, platform. We also consider the potential role of digital applications in the context of major trends in process operations, such as autonomous plant operation and process plant modularization.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"180 ","pages":"Article 108463"},"PeriodicalIF":4.3,"publicationDate":"2023-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67736821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Graph attention network with Granger causality map for fault detection and root cause diagnosis 利用格兰杰因果图对注意力网络进行故障检测和根本原因诊断

IF 4.3 2区工程技术

Computers & Chemical Engineering Pub Date : 2023-10-10 DOI: 10.1016/j.compchemeng.2023.108453

Yingxiang Liu , Behnam Jafarpour

{"title":"Graph attention network with Granger causality map for fault detection and root cause diagnosis","authors":"Yingxiang Liu , Behnam Jafarpour","doi":"10.1016/j.compchemeng.2023.108453","DOIUrl":"https://doi.org/10.1016/j.compchemeng.2023.108453","url":null,"abstract":"<div><p>Unsupervised data-driven methods are widely used for fault detection and diagnosis in modern industrial processes. However, accurately distinguishing faults from normal feedback control system adjustments and promptly identifying their root causes are among unresolved challenges. To address these issues, we propose a neural network model consisting of one-dimensional convolutional neural networks and a graph attention network (CNN-GAT) that uses a causal map derived from fault-free data using conditional Granger causality analysis. The CNN-GAT model produces a monitoring index that accurately reflects the operating conditions of the process and distinguishes faults from normal control adjustments. Using the causal map and prediction results from the CNN-GAT model, the root cause diagnosis can be performed promptly after faults are detected, providing operators with more time to address the fault. We demonstrate the performance of the proposed framework using the benchmark Tennessee Eastman process case studies and through comparison with other fault detection methods.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"180 ","pages":"Article 108453"},"PeriodicalIF":4.3,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S009813542300323X/pdfft?md5=c89ad4552f0f5ee0f0c29d6c43433c2e&pid=1-s2.0-S009813542300323X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91993396","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

Dynamics, uncertainty and control in circular supply chains 循环供应链中的动态、不确定性和控制

IF 4.3 2区工程技术

Computers & Chemical Engineering Pub Date : 2023-10-07 DOI: 10.1016/j.compchemeng.2023.108441

Raymond Park , Erhan Kutanoglu , Michael Baldea

引用次数: 0

Entropy-maximizing TD3-based reinforcement learning for adaptive PID control of dynamical systems 基于熵最大化td3的自适应PID系统强化学习

IF 4.3 2区工程技术

Computers & Chemical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.compchemeng.2023.108393

Myisha A. Chowdhury, Saif S.S. Al-Wahaibi, Qiugang Lu

{"title":"Entropy-maximizing TD3-based reinforcement learning for adaptive PID control of dynamical systems","authors":"Myisha A. Chowdhury, Saif S.S. Al-Wahaibi, Qiugang Lu","doi":"10.1016/j.compchemeng.2023.108393","DOIUrl":"10.1016/j.compchemeng.2023.108393","url":null,"abstract":"<div><p>The proper tuning of proportional–integral–derivative (PID) control is critical for satisfactory control performance. However, existing tuning methods are often time-consuming and require system models that are difficult to obtain for complex processes. To this end, automatic PID tuning, particularly that based on deep reinforcement learning, eliminates the necessity of a system model by treating the PID tuning as a black-box optimization. However, these methods suffer from low sample efficiency. In this paper, we present an entropy-maximizing twin-delayed deep deterministic policy gradient (EMTD3) method for automatic PID tuning. In our method, an entropy-maximizing stochastic actor is deployed at the beginning to ensure sufficient explorations, followed by a deterministic actor to focus on local exploitation. Such a hybrid approach can enhance the sample efficiency to facilitate the PID tuning. Extensive simulation studies are provided to show the superior performance of the proposed method relative to other methods on data efficiency, adaptivity, and robustness.</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"178 ","pages":"Article 108393"},"PeriodicalIF":4.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73445974","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: 1

Prediction based fusion estimator-controller for an event-triggered multi-sensor cyber-physical systems 基于预测的事件触发多传感器网络物理系统融合估计控制器

IF 4.3 2区工程技术

Computers & Chemical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.compchemeng.2023.108397

Senthilkumar K., Srinivasan K.

{"title":"Prediction based fusion estimator-controller for an event-triggered multi-sensor cyber-physical systems","authors":"Senthilkumar K., Srinivasan K.","doi":"10.1016/j.compchemeng.2023.108397","DOIUrl":"10.1016/j.compchemeng.2023.108397","url":null,"abstract":"<div><p><span>This article focusses on development of centralized fusion estimator-controller for event-triggered multi-variable(MV) multi-sensors(MS) cyber–physical systems. The unified mathematical model is developed, which is able to take care of simultaneous occurrences of packet loss<span> in S-E and C-A channels and event-triggered conditions. The model uses current measurements and state predictions to handle communication flaws and untriggered sensor measurements. The centralized fusion estimator is developed using </span></span>orthogonal projections<span><span> for augmented MV-MS system, offering a globally optimal solution. The proposed fusion estimator possesses linear minimum variance property and it is unbiased. Feedback control is designed and it ensures </span>mean square stability<span>. Zero estimate error concept is introduced to reduce the computation burden, network congestion and energy utilization. The novel residual-based cyber-attack detection algorithm is developed. The proposed method is validated for cruise control system and performance is compared with other popular works.</span></span></p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"178 ","pages":"Article 108397"},"PeriodicalIF":4.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73630143","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 model decision trees as surrogates in optimization of engineering applications 线性模型决策树在工程应用优化中的替代

IF 4.3 2区工程技术

Computers & Chemical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.compchemeng.2023.108347

Bashar L. Ammari , Emma S. Johnson , Georgia Stinchfield , Taehun Kim , Michael Bynum , William E. Hart , Joshua Pulsipher , Carl D. Laird

{"title":"Linear model decision trees as surrogates in optimization of engineering applications","authors":"Bashar L. Ammari , Emma S. Johnson , Georgia Stinchfield , Taehun Kim , Michael Bynum , William E. Hart , Joshua Pulsipher , Carl D. Laird","doi":"10.1016/j.compchemeng.2023.108347","DOIUrl":"https://doi.org/10.1016/j.compchemeng.2023.108347","url":null,"abstract":"<div><p><span>Machine learning models are promising as surrogates in optimization when replacing difficult to solve equations or black-box type models. This work demonstrates the viability of linear model decision trees as piecewise-linear surrogates in decision-making problems. Linear model decision trees can be represented exactly in mixed-integer linear programming (MILP) and mixed-integer quadratic constrained programming (MIQCP) formulations. Furthermore, they can represent discontinuous functions, bringing advantages over neural networks in some cases. We present several formulations using transformations from Generalized Disjunctive Programming (GDP) formulations and modifications of MILP formulations for gradient boosted decision trees (GBDT). We then compare the computational performance of these different MILP and MIQCP representations in an optimization problem and illustrate their use on </span>engineering applications. We observe faster solution times for optimization problems with linear model decision tree surrogates when compared with GBDT surrogates using the Optimization and Machine Learning Toolkit (OMLT).</p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"178 ","pages":"Article 108347"},"PeriodicalIF":4.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72248499","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: 3

Identification of sustainable carbon capture and utilization (CCU) pathways using state-task network representation 使用状态-任务网络表征的可持续碳捕获与利用(CCU)途径的识别

IF 4.3 2区工程技术

Computers & Chemical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.compchemeng.2023.108408

Wonsuk Chung , Sunwoo Kim , Ali S. Al-Hunaidy , Hasan Imran , Aqil Jamal , Jay H. Lee

{"title":"Identification of sustainable carbon capture and utilization (CCU) pathways using state-task network representation","authors":"Wonsuk Chung , Sunwoo Kim , Ali S. Al-Hunaidy , Hasan Imran , Aqil Jamal , Jay H. Lee","doi":"10.1016/j.compchemeng.2023.108408","DOIUrl":"10.1016/j.compchemeng.2023.108408","url":null,"abstract":"<div><p>Carbon capture and utilization (CCU) can be a pertinent solution to avoid millions of tons of carbon emission. The challenge is to identify, among numerous available options of carbon sources capture/utilization technologies, and products, the CCU pathways with best economic and/or CO<sub>2</sub> reduction potential. In this work, we propose a novel framework for identifying sustainable <em>CCU pathways</em><span>, i.e., combinations of sources, processes, and products, using a superstructure based on state-task network (STN) representation. STN allows incorporation of nonlinear models<span> including first-principles or surrogate models into the superstructure representation of potential CCU pathways. The proposed framework solves the superstructure optimization problem of mixed-integer nonlinear programming (MINLP) by introducing logic-based outer approximation (LOA), to reduce the computational time and improve the solvability greatly. A case study using a sizable CCU superstructure demonstrates that LOA can reduce the computational time from hours to minutes while identifying any sustainable pathway from a superstructure with highly nonlinear surrogate models.</span></span></p></div>","PeriodicalId":286,"journal":{"name":"Computers & Chemical Engineering","volume":"178 ","pages":"Article 108408"},"PeriodicalIF":4.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84933259","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