Digital Chemical Engineering最新文献_第3页

Integration of sustainability assessment into early-stage carbon capture process design with an explainable AI framework 通过可解释的人工智能框架，将可持续性评估整合到早期碳捕获过程设计中

IF 4.1 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-12-01 Epub Date: 2025-09-02 DOI: 10.1016/j.dche.2025.100265

Xin Yee Tai , Oliver Fisher , Lei Xing , Jin Xuan

This study introduces a novel framework for reducing environmental impacts by optimising operating conditions using a surrogate modelling approach integrated with Explainable AI (XAI). Two surrogate models were developed: a sequential surrogate model (SSM) with a two-step structure, and a direct surrogate model (DSM) with a single-step architecture. Both were trained on data from a validated physics-based simulation of a monoethanolamine (MEA)-based carbon capture process to predict environmental impacts across human health, ecosystem quality, and resource depletion. SHapley Additive exPlanations (SHAP) were used to enhance transparency by identifying key input variables influencing outcomes. Multi-objective optimisation was conducted using Particle Swarm Optimisation (PSO) and NSGA-II to determine optimal operating conditions. DSM achieved high prediction accuracy (R² up to 0.995) and lower errors, while SSM offered better interpretability and broader exploration of Pareto-optimal solutions. This study also shows that our framework identified optimum parameters that reduced environmental impacts by 76–88 % compared with the experiment optimum. This framework supports sustainable process design by combining interpretability, predictive performance, and computational efficiency.

本研究引入了一个新的框架，通过使用与可解释人工智能（XAI）集成的代理建模方法来优化操作条件，从而减少对环境的影响。开发了两个代理模型：具有两步结构的顺序代理模型（SSM）和具有单步结构的直接代理模型（DSM）。两者都是根据基于单乙醇胺（MEA）的碳捕获过程的经过验证的物理模拟数据进行训练的，以预测人类健康、生态系统质量和资源枯竭方面的环境影响。SHapley加性解释（SHAP）通过识别影响结果的关键输入变量来提高透明度。采用粒子群算法（PSO）和NSGA-II进行多目标优化，确定最优操作条件。DSM具有较高的预测精度（R²高达0.995）和较低的误差，而SSM具有更好的可解释性和更广泛的探索帕累托最优解。该研究还表明，我们的框架确定的最优参数与实验最优参数相比，减少了76 - 88%的环境影响。该框架通过结合可解释性、预测性能和计算效率来支持可持续的过程设计。

{"title":"Integration of sustainability assessment into early-stage carbon capture process design with an explainable AI framework","authors":"Xin Yee Tai , Oliver Fisher , Lei Xing , Jin Xuan","doi":"10.1016/j.dche.2025.100265","DOIUrl":"10.1016/j.dche.2025.100265","url":null,"abstract":"<div><div>This study introduces a novel framework for reducing environmental impacts by optimising operating conditions using a surrogate modelling approach integrated with Explainable AI (XAI). Two surrogate models were developed: a sequential surrogate model (SSM) with a two-step structure, and a direct surrogate model (DSM) with a single-step architecture. Both were trained on data from a validated physics-based simulation of a monoethanolamine (MEA)-based carbon capture process to predict environmental impacts across human health, ecosystem quality, and resource depletion. SHapley Additive exPlanations (SHAP) were used to enhance transparency by identifying key input variables influencing outcomes. Multi-objective optimisation was conducted using Particle Swarm Optimisation (PSO) and NSGA-II to determine optimal operating conditions. DSM achieved high prediction accuracy (R² up to 0.995) and lower errors, while SSM offered better interpretability and broader exploration of Pareto-optimal solutions. This study also shows that our framework identified optimum parameters that reduced environmental impacts by 76–88 % compared with the experiment optimum. This framework supports sustainable process design by combining interpretability, predictive performance, and computational efficiency.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"17 ","pages":"Article 100265"},"PeriodicalIF":4.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145007597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CFD and OCT-based optimisation of impeller-induced shear stress on membrane surfaces in a circular test cell 基于CFD和oct的圆形试验池中叶轮引起的膜表面剪切应力优化

IF 4.1 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-12-01 Epub Date: 2025-09-25 DOI: 10.1016/j.dche.2025.100267

Masoud Haghshenasfard , Arthur Leon , Robin Starke , Steffi Drescher , Uli Klümper , Thomas Berendonk , Kristin Kerst , André Lerch

This study investigates the distribution of shear stress in a lab-scale membrane bioreactor consisting of a 56 mm-diameter cylindrical test cell, a 0.25 mm-thick polyethersulfone membrane, and a centrally mounted 35 mm rotating impeller. Computational Fluid Dynamics (CFD) simulations were used to examine how impeller speed and geometry affect wall shear stress across the membrane surface. Higher rotational speeds significantly increased shear stress, with the highest levels observed near the impeller rim and a marked decline beyond a radial distance of 0.0175 m due to wall-induced flow dampening. To validate CFD predictions, Optical Coherence Tomography (OCT) was employed for in-situ, real-time biofilm monitoring. OCT results confirmed that low-shear regions—particularly at the membrane periphery—were more prone to rapid and extensive biofilm accumulation, whereas high-shear areas exhibited delayed or reduced fouling. To improve shear distribution and minimize localized fouling, a multi-objective optimization was performed using response surface methodology. This led to an enhanced impeller design that promoted more uniform and effective shear coverage across the membrane. The integration of CFD modeling, experimental validation, and optimization provides a robust framework for the design of membrane systems with improved anti-fouling performance and operational stability.

本研究研究了实验室规模的膜生物反应器中剪切应力的分布，该反应器由直径56 mm的圆柱形试验池、0.25 mm厚的聚醚砜膜和中央安装的35 mm旋转叶轮组成。利用计算流体动力学（CFD）模拟研究了叶轮转速和几何形状对膜表面壁面剪应力的影响。较高的转速显著增加了剪切应力，在叶轮边缘附近观察到的剪切应力最高，在径向距离为0.0175 m时，由于壁面诱导的流动阻尼，剪切应力显著下降。为了验证CFD预测，光学相干断层扫描（OCT）用于现场实时生物膜监测。OCT结果证实，低剪切区域，特别是在膜周围，更容易快速和广泛地积累生物膜，而高剪切区域则表现出延迟或减少的污染。为了改善剪切分布，减少局部污染，采用响应面法进行多目标优化。这导致了叶轮设计的增强，促进了更均匀和有效的剪切覆盖在膜上。CFD建模、实验验证和优化的集成为膜系统的设计提供了一个强大的框架，提高了膜系统的防污性能和运行稳定性。

{"title":"CFD and OCT-based optimisation of impeller-induced shear stress on membrane surfaces in a circular test cell","authors":"Masoud Haghshenasfard , Arthur Leon , Robin Starke , Steffi Drescher , Uli Klümper , Thomas Berendonk , Kristin Kerst , André Lerch","doi":"10.1016/j.dche.2025.100267","DOIUrl":"10.1016/j.dche.2025.100267","url":null,"abstract":"<div><div>This study investigates the distribution of shear stress in a lab-scale membrane bioreactor consisting of a 56 mm-diameter cylindrical test cell, a 0.25 mm-thick polyethersulfone membrane, and a centrally mounted 35 mm rotating impeller. Computational Fluid Dynamics (CFD) simulations were used to examine how impeller speed and geometry affect wall shear stress across the membrane surface. Higher rotational speeds significantly increased shear stress, with the highest levels observed near the impeller rim and a marked decline beyond a radial distance of 0.0175 m due to wall-induced flow dampening. To validate CFD predictions, Optical Coherence Tomography (OCT) was employed for in-situ, real-time biofilm monitoring. OCT results confirmed that low-shear regions—particularly at the membrane periphery—were more prone to rapid and extensive biofilm accumulation, whereas high-shear areas exhibited delayed or reduced fouling. To improve shear distribution and minimize localized fouling, a multi-objective optimization was performed using response surface methodology. This led to an enhanced impeller design that promoted more uniform and effective shear coverage across the membrane. The integration of CFD modeling, experimental validation, and optimization provides a robust framework for the design of membrane systems with improved anti-fouling performance and operational stability.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"17 ","pages":"Article 100267"},"PeriodicalIF":4.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards robust fault detection for industrial processes with a hybrid feature fusion and ensemble learning framework 基于混合特征融合和集成学习框架的工业过程鲁棒故障检测

IF 4.1 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-12-01 Epub Date: 2025-10-16 DOI: 10.1016/j.dche.2025.100270

Abid Aman, Yiqi Liu, Yan Chen

Early fault identification and evaluation are crucial to ensure the efficiency, safety, and reliability of the industrial process. With the rapid growth of process data in modern industries, machine learning and data-driven methods have become indispensable for effective process monitoring and fault diagnosis. This study proposes a fault detection framework that effectively leverages feature fusion and ensemble learning to boost monitoring performance under intricate industrial conditions. The proposed method combines Slow Feature Analysis (SFA), Kernel SFA (KSFA), and Dynamic SFA (DSFA) to extract distinctive features that accurately reflect linear, nonlinear, and dynamic changes in process data. Furthermore, independent applications of ensemble learning techniques, such as majority and weighted voting, can further increase the reliability of identifying faults with the help of statistical monitoring metrics. The effectiveness of this approach is confirmed using the Tennessee Eastman (TE) benchmark dataset alongside real-world data from a wastewater treatment facility in Beijing. The study spans simulated and real industrial settings to develop a robust framework for fault detection in dynamic and nonlinear processes. The results show that feature fusion and ensemble learning outperform single-model approaches, offering higher sensitivity and reliability. The framework demonstrates strong potential to reduce false alarms, improve anomaly detection, and enhance both efficiency and safety in industrial operations.

早期的故障识别和评估对于保证工业过程的效率、安全性和可靠性至关重要。随着现代工业中过程数据的快速增长，机器学习和数据驱动方法已成为有效的过程监控和故障诊断不可或缺的方法。本研究提出了一个故障检测框架，有效地利用特征融合和集成学习来提高复杂工业条件下的监测性能。该方法结合慢特征分析（Slow Feature Analysis， SFA）、核特征分析（Kernel SFA， KSFA）和动态特征分析（Dynamic SFA， DSFA），提取出准确反映过程数据线性、非线性和动态变化的特征。此外，集成学习技术的独立应用，如多数和加权投票，可以在统计监控指标的帮助下进一步提高故障识别的可靠性。使用田纳西伊士曼（TE）基准数据集以及来自北京污水处理设施的真实数据，证实了该方法的有效性。该研究跨越了模拟和真实工业环境，以开发动态和非线性过程中故障检测的鲁棒框架。结果表明，特征融合和集成学习方法优于单模型方法，具有更高的灵敏度和可靠性。该框架在减少误报、改善异常检测、提高工业操作效率和安全性方面具有强大的潜力。

{"title":"Towards robust fault detection for industrial processes with a hybrid feature fusion and ensemble learning framework","authors":"Abid Aman, Yiqi Liu, Yan Chen","doi":"10.1016/j.dche.2025.100270","DOIUrl":"10.1016/j.dche.2025.100270","url":null,"abstract":"<div><div>Early fault identification and evaluation are crucial to ensure the efficiency, safety, and reliability of the industrial process. With the rapid growth of process data in modern industries, machine learning and data-driven methods have become indispensable for effective process monitoring and fault diagnosis. This study proposes a fault detection framework that effectively leverages feature fusion and ensemble learning to boost monitoring performance under intricate industrial conditions. The proposed method combines Slow Feature Analysis (SFA), Kernel SFA (KSFA), and Dynamic SFA (DSFA) to extract distinctive features that accurately reflect linear, nonlinear, and dynamic changes in process data. Furthermore, independent applications of ensemble learning techniques, such as majority and weighted voting, can further increase the reliability of identifying faults with the help of statistical monitoring metrics. The effectiveness of this approach is confirmed using the Tennessee Eastman (TE) benchmark dataset alongside real-world data from a wastewater treatment facility in Beijing. The study spans simulated and real industrial settings to develop a robust framework for fault detection in dynamic and nonlinear processes. The results show that feature fusion and ensemble learning outperform single-model approaches, offering higher sensitivity and reliability. The framework demonstrates strong potential to reduce false alarms, improve anomaly detection, and enhance both efficiency and safety in industrial operations.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"17 ","pages":"Article 100270"},"PeriodicalIF":4.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145416789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Utilizing reinforcement learning in feedback control of nonlinear processes with stability guarantees 将强化学习应用于具有稳定性保证的非线性过程反馈控制

IF 4.1 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-12-01 Epub Date: 2025-12-03 DOI: 10.1016/j.dche.2025.100277

Arthur Khodaverdian , Xiaodong Cui , Panagiotis D. Christofides

This work explores the implementation of reinforcement learning (RL)-based approaches to replace model predictive control (MPC) in cases where practical implementations of MPC are infeasible due to excessive computation times. Specifically, with the use of externally enforced stability guarantees, an RL-based controller that is trained to optimize the same cost function as the MPC with a long horizon that achieves the desirable closed-loop performance can serve as a potentially more appealing real-time option as opposed to using the same MPC with a shorter horizon. A benchmark nonlinear chemical process model is used to demonstrate the feasibility of this RL-based framework that simultaneously guarantees stability and enables improvements in computational efficiency and potential control quality of the closed-loop system. To explore the influence of the RL training method, two RL algorithms are explored, with one imitation learning method used as a reference.

这项工作探讨了基于强化学习（RL）的方法的实现，以取代模型预测控制（MPC），在MPC的实际实现由于计算时间过多而不可行的情况下。具体来说，通过使用外部强制稳定性保证，基于rl的控制器经过训练，可以优化与MPC相同的成本函数，并具有较长的视界，从而实现理想的闭环性能，与使用相同的MPC具有较短的视界相比，这可能是一种更具吸引力的实时选择。一个基准的非线性化学过程模型被用来证明这个基于rl的框架的可行性，同时保证了稳定性，提高了闭环系统的计算效率和潜在的控制质量。为了探讨强化学习训练方法的影响，本文以一种模仿学习方法为参考，探讨了两种强化学习算法。

引用次数: 0

Automated flow pattern classification in multiphase systems using artificial intelligence and capacitance sensing techniques 基于人工智能和电容传感技术的多相系统流型自动分类

IF 4.1 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-12-01 Epub Date: 2025-11-10 DOI: 10.1016/j.dche.2025.100274

Nian Ran , Fayez M. Al-Alweet , Richard Allmendinger , Ahmad Almakhlafi

Accurate classification of flow patterns in multiphase systems is pivotal for optimizing fluid transport and enhancing overall system performance. Conventional methods—such as visual inspection, standard video analysis, and high-speed imaging—remain widely used in industrial and laboratory settings. However, these approaches are often constrained by subjective interpretation, limited applicability to non-transparent pipelines, and inconsistent performance under varying operating conditions. To overcome these limitations, this study introduces a novel framework that integrates capacitance sensing with Artificial Intelligence (AI)-driven classification. The proposed methodology employs a one-dimensional Squeeze-and-Excitation Network (1D SENet) to extract and interpret time-series features from raw capacitance signals. Experimental validation demonstrates robust classification accuracies, achieving over 85 % on in-distribution datasets and 71 % on out-of-distribution scenarios—substantially outperforming traditional techniques. These findings underscore the enhanced generalization and reliability of the proposed system. This work establishes a scalable foundation for real-time flow regime monitoring and predictive analytics, offering transformative potential for intelligent fluid management in complex industrial environments.

多相系统中流型的准确分类是优化流体输送和提高系统整体性能的关键。传统的方法，如目视检查、标准视频分析和高速成像，仍然广泛应用于工业和实验室环境。然而，这些方法往往受到主观解释的限制，对非透明管道的适用性有限，并且在不同的操作条件下性能不一致。为了克服这些限制，本研究引入了一种将电容传感与人工智能（AI）驱动的分类相结合的新框架。所提出的方法采用一维挤压激励网络（1D SENet）从原始电容信号中提取和解释时间序列特征。实验验证证明了强大的分类准确性，在分布内数据集上达到85%以上，在分布外场景上达到71% -大大优于传统技术。这些发现强调了所提出的系统的增强泛化和可靠性。这项工作为实时流态监测和预测分析奠定了可扩展的基础，为复杂工业环境中的智能流体管理提供了变革性的潜力。

{"title":"Automated flow pattern classification in multiphase systems using artificial intelligence and capacitance sensing techniques","authors":"Nian Ran , Fayez M. Al-Alweet , Richard Allmendinger , Ahmad Almakhlafi","doi":"10.1016/j.dche.2025.100274","DOIUrl":"10.1016/j.dche.2025.100274","url":null,"abstract":"<div><div>Accurate classification of flow patterns in multiphase systems is pivotal for optimizing fluid transport and enhancing overall system performance. Conventional methods—such as visual inspection, standard video analysis, and high-speed imaging—remain widely used in industrial and laboratory settings. However, these approaches are often constrained by subjective interpretation, limited applicability to non-transparent pipelines, and inconsistent performance under varying operating conditions. To overcome these limitations, this study introduces a novel framework that integrates capacitance sensing with Artificial Intelligence (AI)-driven classification. The proposed methodology employs a one-dimensional Squeeze-and-Excitation Network (1D SENet) to extract and interpret time-series features from raw capacitance signals. Experimental validation demonstrates robust classification accuracies, achieving over 85 % on in-distribution datasets and 71 % on out-of-distribution scenarios—substantially outperforming traditional techniques. These findings underscore the enhanced generalization and reliability of the proposed system. This work establishes a scalable foundation for real-time flow regime monitoring and predictive analytics, offering transformative potential for intelligent fluid management in complex industrial environments.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"17 ","pages":"Article 100274"},"PeriodicalIF":4.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145578596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predicting the viscosity of hydrogen – methane blends at high pressure for hydrogen transportation and geo-storage: Integration of robust white-box machine learning frameworks 预测氢-甲烷混合物在高压下用于氢气运输和地质储存的粘度：强大的白盒机器学习框架的集成

IF 4.1 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-12-01 Epub Date: 2025-10-30 DOI: 10.1016/j.dche.2025.100273

Saad Alatefi , Mohamed Riad Youcefi , Menad Nait Amar , Hakim Djema

The integration of hydrogen into underground storage systems is pivotal for large-scale energy management, often involving blends with methane to leverage existing infrastructure. Accurate viscosity prediction of hydrogen – methane blends under subsurface conditions is essential for optimizing flow assurance and operational safety. Accordingly, this study employs three data-driven models, namely Genetic Expression Programming (GEP), Group Method of Data Handling (GMDH), and Multi-Gene Genetic Programming (MGGP), to predict the viscosity of hydrogen – methane mixtures for transportation and underground storage applications. A comprehensive dataset of 313 experimentally measured values from the literature were utilized to develop and validate the established correlations. The MGGP paradigm emerged as the top performer, achieving a root mean square error (RMSE) of 0.4054 and an R² value of 0.9940, outperforming both GEP and GMDH, as well as prior predictive models. The consistency of the dataset was confirmed using the Leverage approach, ensuring robust predictions. In addition, the Shapley Additive Explanations technique revealed key factors influencing the viscosity predictions, enhancing the interpretability of the best-performing correlation. Furthermore, comparative trend analysis demonstrated the MGGP correlation's superior accuracy and robustness across varying blend compositions and operational conditions. These findings offer a reliable and simple-to-use predictive correlation for engineers and researchers designing hydrogen transport and storage systems, supporting efficient energy storage and the transition to a low-carbon economy.

将氢气整合到地下储存系统中是大规模能源管理的关键，通常涉及与甲烷的混合物，以利用现有的基础设施。准确预测地下条件下氢-甲烷混合物的粘度对优化流动保障和操作安全至关重要。因此，本研究采用遗传表达式规划（GEP）、数据处理分组方法（GMDH）和多基因遗传规划（MGGP）三种数据驱动模型，对运输和地下储存应用的氢-甲烷混合物粘度进行预测。利用文献中313个实验测量值的综合数据集来开发和验证已建立的相关性。MGGP范式表现最佳，其均方根误差（RMSE）为0.4054，R2值为0.9940，优于GEP和GMDH以及先前的预测模型。使用杠杆方法确认了数据集的一致性，确保了稳健的预测。此外，Shapley加性解释技术揭示了影响粘度预测的关键因素，提高了最佳相关性的可解释性。此外，对比趋势分析表明，MGGP相关性在不同混合成分和操作条件下具有较好的准确性和鲁棒性。这些发现为设计氢运输和储存系统的工程师和研究人员提供了可靠且易于使用的预测相关性，支持高效的能源储存和向低碳经济的过渡。

{"title":"Predicting the viscosity of hydrogen – methane blends at high pressure for hydrogen transportation and geo-storage: Integration of robust white-box machine learning frameworks","authors":"Saad Alatefi , Mohamed Riad Youcefi , Menad Nait Amar , Hakim Djema","doi":"10.1016/j.dche.2025.100273","DOIUrl":"10.1016/j.dche.2025.100273","url":null,"abstract":"<div><div>The integration of hydrogen into underground storage systems is pivotal for large-scale energy management, often involving blends with methane to leverage existing infrastructure. Accurate viscosity prediction of hydrogen – methane blends under subsurface conditions is essential for optimizing flow assurance and operational safety. Accordingly, this study employs three data-driven models, namely Genetic Expression Programming (GEP), Group Method of Data Handling (GMDH), and Multi-Gene Genetic Programming (MGGP), to predict the viscosity of hydrogen – methane mixtures for transportation and underground storage applications. A comprehensive dataset of 313 experimentally measured values from the literature were utilized to develop and validate the established correlations. The MGGP paradigm emerged as the top performer, achieving a root mean square error (RMSE) of 0.4054 and an R<sup>2</sup> value of 0.9940, outperforming both GEP and GMDH, as well as prior predictive models. The consistency of the dataset was confirmed using the Leverage approach, ensuring robust predictions. In addition, the Shapley Additive Explanations technique revealed key factors influencing the viscosity predictions, enhancing the interpretability of the best-performing correlation. Furthermore, comparative trend analysis demonstrated the MGGP correlation's superior accuracy and robustness across varying blend compositions and operational conditions. These findings offer a reliable and simple-to-use predictive correlation for engineers and researchers designing hydrogen transport and storage systems, supporting efficient energy storage and the transition to a low-carbon economy.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"17 ","pages":"Article 100273"},"PeriodicalIF":4.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145473898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimization-based framework for kernel parameter identification in multi-material population balance models 基于优化的多物质种群平衡模型核参数辨识框架

IF 4.1 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-12-01 Epub Date: 2025-10-27 DOI: 10.1016/j.dche.2025.100272

Haoran Ji, Lena Fuhrmann, Juan Fernando Meza Gonzalez, Frank Rhein

This study presents a robust, parallelized optimization framework for kernel parameter identification that is adaptable to any population balance equation (PBE) formulation and process type. The framework addresses the challenge of incomplete 2D particle size distribution (PSD) measurements in multi-material systems by combining a reduced 2D PSD with complementary 1D datasets. The framework was validated by using noisy synthetic PSD data and evaluating both the error in PSD and kernel values across eight kernel parameters. Hyperparameter and sensitivity analyses provided configuration recommendations and insights into the influence of individual parameters, thus guiding kernel model selection. Incorporating prior knowledge of one kernel parameter (e.g., through multi-scale simulations) mitigated non-unique solutions and enhanced noise tolerance, ultimately improving the framework’s robustness and reliability. A case study based on experimental data from a dispersion process demonstrated the framework’s flexibility and practical relevance.

本研究提出了一个鲁棒的、并行化的核参数识别优化框架，该框架适用于任何种群平衡方程（PBE）公式和过程类型。该框架通过将简化的2D粒径分布与互补的1D数据集相结合，解决了多材料系统中不完整的2D粒径分布（PSD）测量的挑战。利用有噪声的合成PSD数据，对该框架进行了验证，并评估了8个核参数的PSD误差和核值。超参数和敏感性分析提供了配置建议，并深入了解了单个参数的影响，从而指导了核模型的选择。结合一个核参数的先验知识（例如，通过多尺度模拟）减轻了非唯一解并增强了噪声容忍度，最终提高了框架的鲁棒性和可靠性。一个基于分散过程实验数据的案例研究证明了该框架的灵活性和实际相关性。

引用次数: 0

Root cause identification of fault in hot-rolling process by causal plot 用因果图识别热轧过程故障的根本原因

IF 4.1 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-12-01 Epub Date: 2025-08-25 DOI: 10.1016/j.dche.2025.100263

Koichi Fujiwara , Yoshiaki Uchida , Taketsugu Osaka

In the steel manufacturing industry, a hot-rolling process produces a thick steel plate from a slab as a batch operation; however, off-spec steel plates are sometimes produced when abnormalities occur during rolling operations. To improve the product yield, it is necessary to appropriately ascertain the root cause of a fault. Because the physicochemical behaviors of the slab during hot-rolling are complicated and yet to be fully understood, we adopted a data-driven approach to identify the cause of the fault in the hot-rolling process. We previously proposed a data-driven fault diagnosis method, referred to as a causal plot, that considers the causal relationships between process variables and monitoring indexes for process monitoring. In the causal plot, monitoring indexes were calculated using existing process monitoring methods, and the causal relationships between the process variables and the calculated monitoring indices were estimated. A linear non-Gaussian acyclic model (LiNGAM) can be adopted for causal inferences between the process variables and calculated monitoring indexes. In this study, we propose a new fault diagnosis method for a batch process, referred to as a b-causal plot, utilizing the causal plot and dynamic time warping (DTW). We analyzed real operation data when defective coils were produced in the hot-rolling process with the proposed b-causal plot and confirmed that the identified root cause was consistent with process engineers’ knowledge, which is typically a low-importance variable that operators do not constantly monitor in daily operation. Because the root cause identification of faults is crucial for maintaining product quality and efficiency in batch processes, the proposed b-causal plot contributes to improving productivity across industries, as demonstrated in this work.

在钢铁制造行业中，热轧工艺将板坯批量生产成厚钢板；然而，当轧制过程中出现异常时，有时会产生不符合规格的钢板。为了提高产品成品率，有必要适当地确定故障的根本原因。由于板坯在热轧过程中的物理化学行为复杂且尚未完全了解，我们采用数据驱动的方法来识别热轧过程中的故障原因。我们之前提出了一种数据驱动的故障诊断方法，称为因果图，该方法考虑过程变量与监控指标之间的因果关系，进行过程监控。在因果图中，利用现有的过程监测方法计算监测指标，并估计过程变量与计算出的监测指标之间的因果关系。采用线性非高斯无循环模型（LiNGAM）对过程变量与计算出的监测指标进行因果推理。在这项研究中，我们提出了一种新的故障诊断方法，称为b-因果图，利用因果图和动态时间规整（DTW）。我们利用提出的b因果图分析了热轧过程中产生缺陷线圈的实际操作数据，并确认确定的根本原因与工艺工程师的知识一致，这通常是操作员在日常操作中不经常监控的低重要性变量。由于故障的根本原因识别对于维持批处理过程中的产品质量和效率至关重要，因此所提出的b-因果图有助于提高各行业的生产率，正如本工作所示。

{"title":"Root cause identification of fault in hot-rolling process by causal plot","authors":"Koichi Fujiwara , Yoshiaki Uchida , Taketsugu Osaka","doi":"10.1016/j.dche.2025.100263","DOIUrl":"10.1016/j.dche.2025.100263","url":null,"abstract":"<div><div>In the steel manufacturing industry, a hot-rolling process produces a thick steel plate from a slab as a batch operation; however, off-spec steel plates are sometimes produced when abnormalities occur during rolling operations. To improve the product yield, it is necessary to appropriately ascertain the root cause of a fault. Because the physicochemical behaviors of the slab during hot-rolling are complicated and yet to be fully understood, we adopted a data-driven approach to identify the cause of the fault in the hot-rolling process. We previously proposed a data-driven fault diagnosis method, referred to as a causal plot, that considers the causal relationships between process variables and monitoring indexes for process monitoring. In the causal plot, monitoring indexes were calculated using existing process monitoring methods, and the causal relationships between the process variables and the calculated monitoring indices were estimated. A linear non-Gaussian acyclic model (LiNGAM) can be adopted for causal inferences between the process variables and calculated monitoring indexes. In this study, we propose a new fault diagnosis method for a batch process, referred to as a b-causal plot, utilizing the causal plot and dynamic time warping (DTW). We analyzed real operation data when defective coils were produced in the hot-rolling process with the proposed b-causal plot and confirmed that the identified root cause was consistent with process engineers’ knowledge, which is typically a low-importance variable that operators do not constantly monitor in daily operation. Because the root cause identification of faults is crucial for maintaining product quality and efficiency in batch processes, the proposed b-causal plot contributes to improving productivity across industries, as demonstrated in this work.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"17 ","pages":"Article 100263"},"PeriodicalIF":4.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Data fusion of spectroscopic data for enhancing machine learning model performance 用于增强机器学习模型性能的光谱数据融合

IF 4.1 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-12-01 Epub Date: 2025-10-24 DOI: 10.1016/j.dche.2025.100271

Pál Péter Hanzelik , Szilveszter Gergely , János Abonyi , Alex Kummer

Developing accurate industrial prediction models for complex industrial and geological applications remains a significant challenge, particularly when relying on limited and disparate spectroscopic data. Traditional data fusion methods often fall short in effectively integrating complementary information across different spectral sources, limiting predictive performance. Complex-level ensemble fusion (CLF) is presented as a two-layer chemometric algorithm that jointly selects variables from concatenated mid-infrared (MIR) and Raman spectra with a genetic algorithm, projects them with partial least squares and stacks the latent variables into an XGBoost regressor, thereby capturing feature- and model-level complementarities in a single workflow. When benchmarked against single-source models and classical low-, mid-, and high-level data-fusion schemes, the CLF technique consistently demonstrated significantly improved predictive accuracy. Evaluated on paired Mid-Infrared (MIR) and Raman datasets from industrial lubricant additives and RRUFF minerals, CLF robustly outperformed established methodologies by effectively leveraging complementary spectral information. Mid-level fusion yielded no improvement, underscoring the need for supervised integration. These results constitute the first evidence that a stacked, complex-level scheme can surpass all established fusion levels on real-world spectroscopic regressions comprising fewer than one hundred samples and provide a transferable recipe for building more accurate and resilient soft sensors in quality-control and geochemical applications.

为复杂的工业和地质应用开发准确的工业预测模型仍然是一个重大挑战，特别是当依赖于有限和不同的光谱数据时。传统的数据融合方法往往无法有效地整合不同光谱源的互补信息，从而限制了预测性能。复杂级集成融合（CLF）是一种两层化学测量算法，该算法通过遗传算法从连接的中红外（MIR）和拉曼光谱中选择变量，用偏最小二乘法对其进行投影，并将潜在变量叠加到XGBoost回归量中，从而在单个工作流程中捕获特征级和模型级的互补。当针对单源模型和经典的低、中、高级数据融合方案进行基准测试时，CLF技术始终显示出显著提高的预测准确性。通过对来自工业润滑油添加剂和RRUFF矿物的配对中红外（MIR）和拉曼数据集进行评估，CLF通过有效利用互补光谱信息，大大优于现有方法。中等程度的融合没有改善，强调了监督整合的必要性。这些结果首次证明，在包含少于100个样品的真实光谱回归中，堆叠的复杂水平方案可以超越所有已建立的融合水平，并为在质量控制和地球化学应用中构建更精确、更有弹性的软传感器提供了可转移的配方。

{"title":"Data fusion of spectroscopic data for enhancing machine learning model performance","authors":"Pál Péter Hanzelik , Szilveszter Gergely , János Abonyi , Alex Kummer","doi":"10.1016/j.dche.2025.100271","DOIUrl":"10.1016/j.dche.2025.100271","url":null,"abstract":"<div><div>Developing accurate industrial prediction models for complex industrial and geological applications remains a significant challenge, particularly when relying on limited and disparate spectroscopic data. Traditional data fusion methods often fall short in effectively integrating complementary information across different spectral sources, limiting predictive performance. Complex-level ensemble fusion (CLF) is presented as a two-layer chemometric algorithm that jointly selects variables from concatenated mid-infrared (MIR) and Raman spectra with a genetic algorithm, projects them with partial least squares and stacks the latent variables into an XGBoost regressor, thereby capturing feature- and model-level complementarities in a single workflow. When benchmarked against single-source models and classical low-, mid-, and high-level data-fusion schemes, the CLF technique consistently demonstrated significantly improved predictive accuracy. Evaluated on paired Mid-Infrared (MIR) and Raman datasets from industrial lubricant additives and RRUFF minerals, CLF robustly outperformed established methodologies by effectively leveraging complementary spectral information. Mid-level fusion yielded no improvement, underscoring the need for supervised integration. These results constitute the first evidence that a stacked, complex-level scheme can surpass all established fusion levels on real-world spectroscopic regressions comprising fewer than one hundred samples and provide a transferable recipe for building more accurate and resilient soft sensors in quality-control and geochemical applications.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"17 ","pages":"Article 100271"},"PeriodicalIF":4.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145416790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MIDDoE: An MBDoE Python package for model identification, discrimination, and calibration MIDDoE：用于模型识别、鉴别和校准的MBDoE Python包

IF 4.1 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-12-01 Epub Date: 2025-11-22 DOI: 10.1016/j.dche.2025.100276

Z. Tabrizi , E. Barbera , W.R. Leal da Silva , F. Bezzo

Mathematical modelling plays a critical role in the design, optimisation, and control of dynamic systems in the process industry. While mechanistic models offer strong explanatory and predictive power, their effectiveness depends on informed model selection and precise parameter calibration. Model-based design of experiments (MBDoE) provides a framework for addressing these challenges by designing experiments that accelerate model discrimination and parameter precision tasks. However, its practical application is frequently constrained by fragmented digital tools that lack integration and make MBDoE implementation a task for expert users. To address that – thus supporting the widespread use of MBDoE – MIDDoE, a modular and user-friendly Python-based framework centred on MBDoE is introduced. MIDDoE supports both model discrimination and parameter precision design strategies, incorporating physical constraints and non-convex design spaces. To provide a comprehensive MBDoE digital tool, the framework integrates numerical techniques such as Global Sensitivity Analysis, Estimability Analysis, parameter estimation, uncertainty analysis, and model validation. Its architecture decouples simulation from analysis, enabling compatibility with both built-in and external simulators, which allows MIDDoE to be applied across different systems. MIDDoE practical application is demonstrated through two case studies in bioprocess and pharmaceutical systems for model discrimination and parameter precision tasks.

数学建模在过程工业中动态系统的设计、优化和控制中起着至关重要的作用。虽然机制模型提供了强大的解释和预测能力，但其有效性取决于知情的模型选择和精确的参数校准。基于模型的实验设计（MBDoE）通过设计加速模型识别和参数精确任务的实验，为解决这些挑战提供了一个框架。然而，它的实际应用经常受到碎片化的数字工具的限制，这些工具缺乏集成，使得MBDoE的实施成为专家用户的任务。为了解决这个问题——从而支持MBDoE的广泛使用——MIDDoE，介绍了一个以MBDoE为中心的模块化和用户友好的基于python的框架。MIDDoE支持模型判别和参数精度设计策略，结合了物理约束和非凸设计空间。为了提供一个全面的MBDoE数字工具，该框架集成了数值技术，如全局敏感性分析、可估计性分析、参数估计、不确定性分析和模型验证。它的体系结构将仿真与分析分离，支持与内置和外部模拟器的兼容性，这使得MIDDoE可以跨不同的系统应用。MIDDoE的实际应用是通过两个案例研究在生物过程和制药系统的模型判别和参数精确任务演示。

{"title":"MIDDoE: An MBDoE Python package for model identification, discrimination, and calibration","authors":"Z. Tabrizi , E. Barbera , W.R. Leal da Silva , F. Bezzo","doi":"10.1016/j.dche.2025.100276","DOIUrl":"10.1016/j.dche.2025.100276","url":null,"abstract":"<div><div>Mathematical modelling plays a critical role in the design, optimisation, and control of dynamic systems in the process industry. While mechanistic models offer strong explanatory and predictive power, their effectiveness depends on informed model selection and precise parameter calibration. Model-based design of experiments (MBDoE) provides a framework for addressing these challenges by designing experiments that accelerate model discrimination and parameter precision tasks. However, its practical application is frequently constrained by fragmented digital tools that lack integration and make MBDoE implementation a task for expert users. To address that – thus supporting the widespread use of MBDoE – <em>MIDDoE</em>, a modular and user-friendly <em>Python</em>-based framework centred on MBDoE is introduced. <em>MIDDoE</em> supports both model discrimination and parameter precision design strategies, incorporating physical constraints and non-convex design spaces. To provide a comprehensive MBDoE digital tool, the framework integrates numerical techniques such as Global Sensitivity Analysis, Estimability Analysis, parameter estimation, uncertainty analysis, and model validation. Its architecture decouples simulation from analysis, enabling compatibility with both built-in and external simulators, which allows <em>MIDDoE</em> to be applied across different systems. <em>MIDDoE</em> practical application is demonstrated through two case studies in bioprocess and pharmaceutical systems for model discrimination and parameter precision tasks.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"17 ","pages":"Article 100276"},"PeriodicalIF":4.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145623996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0