检索结果-内蒙古大学图书馆

batch-to-batch optimization Control of Fed-batch Fermentation Process Based on Recursively Updated Extreme Learning Machine Models

引用

ALGORITHMS 2025年第2期18卷 87-87页

作者： Moore, Alex Zhang, Jie Newcastle Univ Sch Engn Merz Court Newcastle Upon Tyne NE1 7RU England

This paper presents a new method of batch-to-batch optimization control for a fed-batch fermentation process. A recursively updated extreme learning machine (ELM) neural network model is used to model a fed-batch fermentation process. ELM models have advantages over other neural networks in that they can be trained very fast and have good generalization performance. However, the ELM model loses its predictive abilities in the presence of batch-to-batch process variations or disturbances, which lead to a process-model mismatch. The recursive least squares (RLS) technique takes the model prediction error from the previous batch and uses it to update the model parameters for the next batch. This improves the performance of the model and helps it to respond to any changes in process conditions or disturbances. The updated model is used in an optimization control procedure, which generates an improved control profile for the next batch. The update of the RLS model enables the optimization control strategy to maintain a high final product quality in the presence of disturbances. The proposed batch-to-batch optimization control method is demonstrated on a simulated fed-batch fermentation process.

关键词： extreme learning machine recursive least squares fed-batch fermentation neural networks batch-to-batch optimization

来源：评论

学校读者我要写书评

暂无评论

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

引用

COMPUTERS & CHEMICAL ENGINEERING 2025年 193卷

作者： Ghodba, Ali Richelle, Anne Mccready, Chris Ricardez-Sandoval, Luis Budman, Hector Univ Waterloo Chem Engn Dept Waterloo ON N2L 3G1 Canada Sartorius Corp Res Brussels Belgium Sartorius Corp Res Toronto ON Canada

The study proposes a robust algorithm for batch-to-batch optimization in the presence of model-mismatch. Robustness is achieved by the implementation of the following features: i - the gradient correction step is modified to consider the gradients of the cost function and constraints at both final and intermediate points, ii - Economic Model Predictive Control is applied to mitigate the impact of unmeasured disturbances on the optimum, and iii - an optimal design of experiments is performed to expedite convergence. Significant improvements of the proposed algorithm in convergence to the process optimum and robustness to noise, unmeasured disturbances, and model error are demonstrated using a fed-batch fermentation for penicillin production.

关键词： Model-based optimization batch-to-batch optimization Model-plant mismatch Model gradient correction Design of experiments Economic model predictive control

来源：评论

学校读者我要写书评

暂无评论

Embedding active learning in batch-to-batch optimization using reinforcement learning

引用

AUTOMATICA 2023年第1期157卷

作者： Byun, Ha-Eun Kim, Boeun Lee, Jay H. Korea Adv Inst Sci & Technol KAIST Dept Chem & Biomol Engn 291 Daehak Ro Daejeon 34141 South Korea Princeton Univ Andlinger Ctr Energy & Environm Princeton NJ 08544 USA Univ Southern Calif Mork Family Dept Chem Engn & Mat Sci 925 Bloom Walk Los Angeles CA 90089 USA Kongju Natl Univ Dept Chem Engn 1223-24 Cheonan Daero Cheonan 31080 South Korea

batch-to-batch (B2B) or run-to-run (R2R) optimization refers to the strategy of updating the operating parameters of a batch run based on the results of previous runs and exploits the repetitive nature of batch process operation. Although B2B optimization uses feedback from previous batch runs to learn about model uncertainty and improve the operation of future runs, the standard techniques have the limitations of passive learning and being myopic in making adjustments. This work proposes a novel way to use the reinforcement learning approach to embed the active learning feature into B2B optimization. For this, the B2B optimization problem is formulated as a maximization of a long-term performance of repeated batch runs, which are modeled as a stochastic process with uncertain parameters. To solve the resulting Bayes-Adaptive Markov decision process (BAMDP) problem in a near-optimal manner, a policy gradient reinforcement learning algorithm is employed. Through case studies, the behavior and effectiveness of the proposed B2B optimization method are examined by comparing it with the traditional certainty equivalence based B2B optimization method with passive learning.& COPY;2023 Elsevier Ltd. All rights reserved.

关键词： batch process optimization batch-to-batch optimization Reinforcement learning Active learning Hyper-state optimization under uncertainty Model-plant mismatch Bayes-Adaptive Markov decision process

来源：评论

学校读者我要写书评

暂无评论

Multi-step lookahead Bayesian optimization with active learning using reinforcement learning and its application to data-driven batch-to-batch optimization

引用

COMPUTERS & CHEMICAL ENGINEERING 2022年 167卷

This study presents a novel multi-step lookahead Bayesian optimization method which strives for optimal active learning by balancing exploration and exploitation over multiple future sampling-evaluation trials. The approach adopts a Gaussian process (GP) model to represent the underlying function, which is updated after each sampling and evaluation. Then, a reinforcement learning method of Proximal Policy optimization (PPO) is used to locate the next optimal point to sample while considering multiple future such trials using the current GP model as the fictitious environment. The approach is applied to batch-to-batch (B2B) optimization where an optimal batch recipe is searched for without any process knowledge. The B2B optimization is formulated as a partially observable Markov decision process (POMDP) problem, and GP model learning and policy learning through PPO are iteratively performed to suggest the next batch recipe. The effectiveness of the approach in the B2B optimization problem is demonstrated through two case studies.

关键词： Data-driven optimization Multi-step lookahead Bayesian optimization Reinforcement learning Active learning batch-to-batch optimization

来源：评论

学校读者我要写书评

暂无评论

Combining just-in-time modelling and batch-wise unfolded PLS model for the derivative-free batch-to-batch optimization

引用

CANADIAN JOURNAL OF CHEMICAL ENGINEERING 2018年第5期96卷 1156-1167页

作者： Jia, Runda Mao, Zhizhong Wang, Fuli Northeastern Univ Sch Informat Sci Engn Shenyang 110004 Liaoning Peoples R China Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110004 Liaoning Peoples R China

In this work, a derivative-free batch-to-batch optimization method is proposed. In order to conquer the difficulties in building a first principal model, a local batch-wise unfolded PLS (BW-PLS) model is used to accurately describe the concerned region, and the first principal model based dynamic optimization problem is transformed into a static one. The just-in-time (JIT) modelling method is employed to dynamically update the local BW-PLS model upon request, and the nonlinearity and abrupt changes from one batch run to another can be effectively resolved. Then the proposed local BW-PLS model with JIT modelling method is integrated into the trust-region framework. Not only can the issue of plant-model mismatch be dealt with, but also the computation of the experimental gradients can be avoided. In addition, taking the advantages of PLS regression, the Hotelling's T-2 statistic is utilized as a hard constraint to ensure the reliability of the optimal solution. Extension to handle soft inequality constraints is also included in this work. Finally, the efficacy of the proposed batch-to-batch optimization method is illustrated via a toy example and a simulated cobalt oxalate synthesis process under different operating conditions, and satisfied optimization performances were obtained.

关键词： batch process batch-to-batch optimization just-in-time modelling trust-region framework

来源：评论

学校读者我要写书评

暂无评论

SELF-CORRECTING MODIFIER-ADAPTATION STRATEGY FOR batch-to-batch optimization BASED ON batch-WISE UNFOLDED PLS MODEL

引用

CANADIAN JOURNAL OF CHEMICAL ENGINEERING 2016年第9期94卷 1770-1782页

作者： Jia, Runda Mao, Zhizhong Wang, Fuli Northeastern Univ Sch Informat Sci & Engn Shenyang 110004 Peoples R China Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110004 Peoples R China

The problem of optimizing a batch process under model uncertainty using a batch-wise unfolded PLS (BW-PLS) model-based modifier-adaptation (MA) strategy lis described. The main idea behind the strategy is to use measurements and iteratively modify the model to compensate for the mismatch of the necessary condition of optimality (NCO) between the plant and the model-based optimization problem. It is proven that the popular data data-driven-model-based iterative learning control (ILC) strategy is equivalent to the proposed MA strategy using only zero order modifier. Inspired by the effectiveness of the ILC being enhanced by rebuilding the data-driven model, a more elaborate model updating scheme is proposed in this paper to improve the optimization performances. The heuristic rules for choosing filtering gain matrix are also presented to further accelerate the convergence rate and reduce the variation of the cost during the period of evolution. Finally, the efficacy of the proposed MA strategy is illustrated via a simulated typical batch reaction and a simulated cobalt oxalate synthesis process.

关键词： batch-to-batch optimization modifier-adaptation self-correcting batch-wise unfolded PLS model iterative learning control

来源：评论

学校读者我要写书评

暂无评论

batch-to-batch optimization of cobalt oxalate synthesis process using modifier-adaptation strategy with latent variable model

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2015年 140卷 73-85页

作者： Jia, Runda Mao, Zhizhong Wang, Fuli He, Dakuo Northeastern Univ Sch Informat Sci & Engn Shenyang 110004 Peoples R China Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110004 Peoples R China

A batch-to-batch optimization strategy is proposed to cope with the presence of data-driven model uncertainty, and applied to a cobalt oxalate synthesis process. In order to overcome the difficulties in developing the first principle model of a fed-batch synthesis process, latent variable model incorporated with batch-wise unfolding approach is used to describe the causal relationship between the manipulated variables and the final product quality. Based on modifier-adaptation methodology, the idea of using final quality measurements in response to handling data-driven model uncertainty is formalized. And the batch-to-batch update criterion is presented to compensate for the mismatch of the necessary condition of optimality (NCO) between the plant and the data-driven model based optimization problem. The extensions to avoid using the latent variable model for extrapolation and to model the variability in initial conditions are also presented. Simulation studies demonstrate that the proposed strategy can result in better optimization performances compared to traditional modeladaptation strategy from batch to batch. (C) 2014 Elsevier B.V. All rights reserved.

关键词： batch-to-batch optimization Modifier adaptation Latent variable model Model uncertainty Cobalt oxalate synthesis process

来源：评论

学校读者我要写书评

暂无评论

A study of model adaptation in iterative real-time optimization of processes with uncertainties

引用

COMPUTERS & CHEMICAL ENGINEERING 2019年 122卷 218-227页

作者： Ahmad, Afaq Gao, Weihua Engell, Sebastian TU Dortmund Univ Dept Biochem & Chem Engn Proc Dynam & Operat Grp Emil Figge Str 70 D-44227 Dortmund Germany Fangyuan Grp Germany GmbH Martin Schmeisser Weg 12a D-44227 Dortmund Germany

In real-time optimization, plant-model mismatch can be handled by adding bias and gradient correction terms to the model-based optimization problem in order to meet the first-order necessary conditions of optimality. However, since these correction terms do not ensure the satisfaction of the second-order condition of optimality upon convergence, the model that is used in the optimization can be inadequate. In the framework of iterative modifier-adaptation, this paper proposes to only use effective model parameter updates to ensure and to speed up the convergence to the process optimum. Additionally, this paper shows that model adequacy can and should be enforced explicitly in model parameter adaptation. By means of a simulation study of maximizing the product yield in a fed-batch reactor, we demonstrate that the proposed model adaptation procedure computes model parameters which make the iterative real-time optimization with modifier-adaptation converge faster and more reliably to the plant optimum. (C) 2018 The Authors. Published by Elsevier Ltd.

关键词： Real-time optimization Modifier adaptation Effective model adaptation Convex model approximations Plant-model mismatch Model adequacy batch-to-batch optimization

来源：评论

学校读者我要写书评

暂无评论

Model Adaptation with Quadratic Approximation in Iterative Real-Time optimization 22

Model Adaptation with Quadratic Approximation in Iterative R...

引用

22nd International Conference on Process Control (PC19)

作者： Ahmad, Afaq Mukkula, Anwesh Reddy Gottu Engell, Sebastian TU Dortmund Univ Dept Biochem & Chem Engn Dortmund Germany

ISBN: (纸本)9781728137582

This paper deals with the iterative real-time optimization (RTO) of chemical processes under plant-model mismatch. Modifier-adaptation can cope with the plant-model mismatch by adding bias- and gradient-correction terms to the underlying model based optimization problem. These correction terms ensure the convergence to the true plant optimum via enforcing the first-order necessary-conditions of optimality of the plant despite plant-model mismatch. However, the estimation of the empirical gradients from noisy measurement data is a limiting factor and also the added correction terms do not guarantee that the second-order conditions of the optimality are satisfied upon convergence. Modifier adaptation can be combined with the quadratic approximation approach used in derivative-free optimization to ensure the convergence to the process optimum. In the framework of modifier-adaptation with quadratic approximation, this contribution proposes to add a model adaptation step such that the second-order optimality conditions are met at the plant optimum. Also to improve the estimates of the model parameters may speed up convergence. The performance of the proposed scheme is demonstrated by using a fed-batch reactor case-study.

关键词： Model adequacy Quadratic approximation Real-time optimization Gradient estimation batch-to-batch optimization Effective model adaptation Plant-model mismatch Modifier adaptation

来源：评论

学校读者我要写书评

暂无评论

Modeling and Optimizing Control of Particle Quality for Drug Fluidized Bed Granulation Process

Modeling and Optimizing Control of Particle Quality for Drug...

引用

2nd International Conference on Industrial Informatics - Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII)

作者： Wang, Zhengsong Yang, Le He, Dakuo Ding, Shuai Du, Bo Northeastern Univ Coll Informat Sci & Engn Shenyang 110004 Liaoning Peoples R China

ISBN: (纸本)9781509035755

This paper presents an optimization control strategy of particle quality for drug fluidized bed granulation process. Firstly, a predictive model of average particle size is established to construct the optimization model. However, this quality optimization will be hampered by model uncertainty. The batch-to-batch optimization based on ILC method is utilized to overcome model uncertainty and the integrated optimization method that combines batch-to-batch optimization and optimization in the batch is proposed to increase the convergence rate and eliminate or reduce the adverse effect of process disturbance. The effectiveness of proposed method is validated by simulations.

关键词： optimization control drug fluidized bed granulation process batch-to-batch optimization integrated optimization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：