Digital Chemical Engineering最新文献_第9页

Exploring spatial and temporal importance of input features and the explainability of machine learning-based modelling of water distribution systems 探索输入特征的空间和时间重要性以及基于机器学习的水分配系统建模的可解释性

IF 3 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-03-01 Epub Date: 2024-11-27 DOI: 10.1016/j.dche.2024.100202

Ammar Riyadh, Nicolas M. Peleato

Ensuring safe drinking water necessitates advanced management and monitoring techniques for water quality in distribution systems. This study leverages machine learning (ML) to model chlorine decay in a water distribution system (WDS) in British Columbia, Canada. A four-layer long short term memory (LSTM) network was trained to predict chlorine concentrations at a reservoir >24,000 m from the treatment plant. Explainable AI (XAI) techniques were applied to the trained network to address critical issues, such as enhancing the transparency and reliability of ML models. Several XAI methods were used to investigate the importance of sensor placement, identify the most significant features, understand feature ranges that result in poor performance, and validate model logic. Results demonstrated that for ML-based WDS control, sensor location is not critical, with high prediction accuracy achieved (mean absolute error <0.025 mg/L) even when exclusively using data from nodes spatially distant from the prediction site. XAI techniques showed the capability of identifying essential features and demonstrated that the behaviour of the ML model conformed with the expectations of chlorine behaviour. Superfluous variables were ranked low in importance, and the model learned fundamental aspects of chemical kinetics, such as temperature dependence and decay rate. Most importantly, the XAI methods applied showed the capability to communicate the reasoning for specific predictions, even at a local or sample-specific level. This study underscores the importance of transparency and trust in ML models, especially as the field transitions towards digital twin and Internet of Things (IoT) technologies, to enhance the effective management of water quality systems.

确保安全饮用水需要先进的供水系统水质管理和监测技术。本研究利用机器学习（ML）来模拟加拿大不列颠哥伦比亚省供水系统（WDS）中的氯衰变。一个四层长短期记忆（LSTM）网络被训练来预测距离处理厂24000米的水库的氯浓度。可解释人工智能（XAI）技术被应用于训练后的网络，以解决关键问题，例如提高机器学习模型的透明度和可靠性。使用了几种XAI方法来研究传感器放置的重要性，确定最重要的特征，了解导致性能差的特征范围，并验证模型逻辑。结果表明，对于基于ml的WDS控制，传感器位置并不重要，即使仅使用距离预测地点较远的节点数据，也可以获得较高的预测精度（平均绝对误差<；0.025 mg/L）。XAI技术显示了识别基本特征的能力，并证明ML模型的行为符合氯行为的预期。多余的变量在重要性上排名较低，模型学习化学动力学的基本方面，如温度依赖性和衰变率。最重要的是，所应用的XAI方法显示了沟通特定预测推理的能力，甚至在局部或特定于样本的级别上也是如此。这项研究强调了机器学习模型的透明度和信任的重要性，特别是随着该领域向数字孪生和物联网（IoT）技术的过渡，以加强对水质系统的有效管理。

{"title":"Exploring spatial and temporal importance of input features and the explainability of machine learning-based modelling of water distribution systems","authors":"Ammar Riyadh, Nicolas M. Peleato","doi":"10.1016/j.dche.2024.100202","DOIUrl":"10.1016/j.dche.2024.100202","url":null,"abstract":"<div><div>Ensuring safe drinking water necessitates advanced management and monitoring techniques for water quality in distribution systems. This study leverages machine learning (ML) to model chlorine decay in a water distribution system (WDS) in British Columbia, Canada. A four-layer long short term memory (LSTM) network was trained to predict chlorine concentrations at a reservoir >24,000 m from the treatment plant. Explainable AI (XAI) techniques were applied to the trained network to address critical issues, such as enhancing the transparency and reliability of ML models. Several XAI methods were used to investigate the importance of sensor placement, identify the most significant features, understand feature ranges that result in poor performance, and validate model logic. Results demonstrated that for ML-based WDS control, sensor location is not critical, with high prediction accuracy achieved (mean absolute error <0.025 mg/L) even when exclusively using data from nodes spatially distant from the prediction site. XAI techniques showed the capability of identifying essential features and demonstrated that the behaviour of the ML model conformed with the expectations of chlorine behaviour. Superfluous variables were ranked low in importance, and the model learned fundamental aspects of chemical kinetics, such as temperature dependence and decay rate. Most importantly, the XAI methods applied showed the capability to communicate the reasoning for specific predictions, even at a local or sample-specific level. This study underscores the importance of transparency and trust in ML models, especially as the field transitions towards digital twin and Internet of Things (IoT) technologies, to enhance the effective management of water quality systems.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"14 ","pages":"Article 100202"},"PeriodicalIF":3.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143160283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Machine learning and response surface methodology forecasting comparison for improved spray dry scrubber performance with brine sludge-derived sorbent 机器学习和响应面方法预测与盐水污泥衍生吸附剂改进喷雾干式洗涤器性能的比较

IF 3 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-03-01 Epub Date: 2024-12-20 DOI: 10.1016/j.dche.2024.100214

B.J. Chepkonga , L. Koech , R.S. Makomere , H.L. Rutto

In this study, hydrated lime (Ca(OH)₂) sorbent was prepared from industrial brine sludge waste using simple laboratory procedures and utilized in a laboratory-scale spray dry scrubber for desulfurization tests. The effects of key process parameters in spray drying (sorbent particle size, inlet gas phase temperature, and Ca:S ratio) on desulfurization efficiency were investigated using central composite design (CCD). Three machine learning (ML) models, multilayer perceptron (MLP), support vector regressor (SVR), and light gradient boosting machine (LightGBM), were assessed for their output estimation accuracy and compared to the CCD prediction model. The computational framework utilized experimental variables structured by CCD software as input metadata. Model performance was evaluated through generalization and accuracy measurements, including the coefficient of determination (R²), root mean square error (RMSE), mean square error (MSE), and mean squared logarithmic error (MSLE). Analysis of variance revealed that the Ca:S ratio had the most significant influence on SO₂ absorption. A quadratic model correlating the process variables with desulfurization efficiency was developed, yielding an R-squared value of 93.47%. Characterization of the final desulfurization products, particularly using XRD, showed the emergence of new phases such as hannebachite (CaSO₃.0·5H₂O), while FTIR analysis identified unreacted portlandite and calcite. Among the ML models, the MLP demonstrated superior performance over SVR and LightGBM, highlighting its efficacy in extracting and decoding information from the input data. The response surface methodology (RSM) model also proved to be a reliable forecasting tool, indicating its potential as a practical alternative to complex algorithmic computations in scenarios with limited raw data.

在本研究中，利用简单的实验室程序从工业卤水污泥废物中制备了水合石灰（Ca(OH) 2）吸附剂，并在实验室规模的喷雾干燥洗涤器中进行了脱硫试验。采用中心复合设计（CCD）研究了喷雾干燥过程中关键工艺参数（吸附剂粒径、入口气相温度和Ca:S比）对脱硫效率的影响。对多层感知器（MLP）、支持向量回归器（SVR）和光梯度增强机（LightGBM）三种机器学习模型的输出估计精度进行了评估，并与CCD预测模型进行了比较。计算框架采用CCD软件构建的实验变量作为输入元数据。通过决定系数（R²）、均方根误差（RMSE）、均方误差（MSE）和均方对数误差（MSLE）来评估模型的性能。方差分析表明，Ca:S比对so2吸收的影响最为显著。建立了工艺变量与脱硫效率的二次方程，其r平方值为93.47%。最终脱硫产物的表征，特别是XRD，发现了新相的出现，如hannebacite (CaSO3.0·5H2O)，而FTIR分析发现了未反应的波特兰石和方解石。在ML模型中，MLP表现出优于SVR和LightGBM的性能，突出了其从输入数据中提取和解码信息的有效性。响应面方法（RSM）模型也被证明是一种可靠的预测工具，表明它在原始数据有限的情况下作为复杂算法计算的实际替代方案的潜力。

{"title":"Machine learning and response surface methodology forecasting comparison for improved spray dry scrubber performance with brine sludge-derived sorbent","authors":"B.J. Chepkonga , L. Koech , R.S. Makomere , H.L. Rutto","doi":"10.1016/j.dche.2024.100214","DOIUrl":"10.1016/j.dche.2024.100214","url":null,"abstract":"<div><div>In this study, hydrated lime (Ca(OH)₂) sorbent was prepared from industrial brine sludge waste using simple laboratory procedures and utilized in a laboratory-scale spray dry scrubber for desulfurization tests. The effects of key process parameters in spray drying (sorbent particle size, inlet gas phase temperature, and Ca:S ratio) on desulfurization efficiency were investigated using central composite design (CCD). Three machine learning (ML) models, multilayer perceptron (MLP), support vector regressor (SVR), and light gradient boosting machine (LightGBM), were assessed for their output estimation accuracy and compared to the CCD prediction model. The computational framework utilized experimental variables structured by CCD software as input metadata. Model performance was evaluated through generalization and accuracy measurements, including the coefficient of determination (R²), root mean square error (RMSE), mean square error (MSE), and mean squared logarithmic error (MSLE). Analysis of variance revealed that the Ca:S ratio had the most significant influence on SO₂ absorption. A quadratic model correlating the process variables with desulfurization efficiency was developed, yielding an R-squared value of 93.47%. Characterization of the final desulfurization products, particularly using XRD, showed the emergence of new phases such as hannebachite (CaSO<sub>3</sub>.0·5H<sub>2</sub>O), while FTIR analysis identified unreacted portlandite and calcite. Among the ML models, the MLP demonstrated superior performance over SVR and LightGBM, highlighting its efficacy in extracting and decoding information from the input data. The response surface methodology (RSM) model also proved to be a reliable forecasting tool, indicating its potential as a practical alternative to complex algorithmic computations in scenarios with limited raw data.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"14 ","pages":"Article 100214"},"PeriodicalIF":3.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143160284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Conversion of Spirulina platensis into methanol via gasification: Process simulation modeling and economic evaluation 螺旋藻气化制甲醇：过程模拟建模及经济评价

IF 3 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-03-01 Epub Date: 2024-12-04 DOI: 10.1016/j.dche.2024.100204

Muhammad Shahbaz , Muhammad Ammar , Sukarni Sukarni

The conversion of bioresources like Spirulina platensis (SP) into value-added chemicals, such as methanol, offers a sustainable replacement of fossil fuels and contributes to greenhouse gas mitigation. This study presents an integrated process simulation model, developed using Aspen Plus v10®, for the steam gasification of SP and subsequent methanol production. Process parameters, including temperature range from 650-950 °C, steam/feed ratio from 0.5–2, and recycle ratio from 0–9, were investigated to optimize syngas composition and methanol yield. Results demonstrated that increasing temperature enhances H₂ and CO production while reducing CO₂ and CH₄, significantly increasing methanol production from 6500 to 9500 kg/h. The steam/feed ratio also influences syngas composition and methanol yield, with higher ratios promoting H₂ and CO₂ production and reducing CO and CH₄. The economic evaluation of two scenarios, a base case and an optimum case, shows that the capital expenditure (Capex) and operating expenditure (Opex) are 19.3M$ and 9.07M$ for the base case, and 20.018M$ and 10.21M$ for the optimum case. The analysis also reveals that the optimum case, with higher methanol production (7.2 tonnes/h compared to 6.7 tonnes/h in the base case), generates a higher net income (9.76 M$/y) and reduces CO₂ emissions (4.918 tonnes CO₂-e/y compared to 5.72 tonnes CO₂-e/y). The energy flow indicates the input energy requirement, the energy carried by methanol, and the surplus energy, totalling 26740 kW to meet the major system's energy demands. This study provides valuable insights for researchers, policymakers, and commercial entities seeking to develop sustainable and economically viable biofuel production processes.

将螺旋藻等生物资源转化为甲醇等增值化学品，可以可持续地替代化石燃料，并有助于减少温室气体排放。本研究提出了一个集成的过程模拟模型，使用Aspen Plus v10®开发，用于SP的蒸汽气化和随后的甲醇生产。研究了温度650 ~ 950℃、汽料比0.5 ~ 2、循环比0 ~ 9的工艺参数，以优化合成气组成和甲醇收率。结果表明，温度升高可以提高H2和CO的产量，同时降低CO2和CH4的产量，甲醇产量从6500 kg/h显著提高到9500 kg/h。汽料比也影响合成气组成和甲醇收率，较高的汽料比促进H2和CO2的生成，减少CO和CH4。对基本情况和最优情况两种情况的经济评估表明，基本情况下的资本支出（Capex）和运营支出（Opex）分别为1930万美元和907万美元，而最优情况下的资本支出（Capex）和运营支出（Opex）分别为2011.8万美元和1021万美元。分析还显示，最佳情况下，甲醇产量较高（7.2吨/小时，而基本情况为6.7吨/小时），可产生更高的净收入（976万美元/年），并减少二氧化碳排放（4.918吨二氧化碳-e/年，而5.72吨二氧化碳-e/年）。能量流为输入能量需求、甲醇携带能量和剩余能量，总计26740 kW，可满足主要系统的能量需求。本研究为研究人员、政策制定者和寻求开发可持续和经济上可行的生物燃料生产工艺的商业实体提供了有价值的见解。

{"title":"Conversion of Spirulina platensis into methanol via gasification: Process simulation modeling and economic evaluation","authors":"Muhammad Shahbaz , Muhammad Ammar , Sukarni Sukarni","doi":"10.1016/j.dche.2024.100204","DOIUrl":"10.1016/j.dche.2024.100204","url":null,"abstract":"<div><div>The conversion of bioresources like Spirulina platensis (SP) into value-added chemicals, such as methanol, offers a sustainable replacement of fossil fuels and contributes to greenhouse gas mitigation. This study presents an integrated process simulation model, developed using Aspen Plus v10®, for the steam gasification of SP and subsequent methanol production. Process parameters, including temperature range from 650-950 °C, steam/feed ratio from 0.5–2, and recycle ratio from 0–9, were investigated to optimize syngas composition and methanol yield. Results demonstrated that increasing temperature enhances H<sub>2</sub> and CO production while reducing CO<sub>2</sub> and CH<sub>4</sub>, significantly increasing methanol production from 6500 to 9500 kg/h. The steam/feed ratio also influences syngas composition and methanol yield, with higher ratios promoting H<sub>2</sub> and CO<sub>2</sub> production and reducing CO and CH<sub>4</sub>. The economic evaluation of two scenarios, a base case and an optimum case, shows that the capital expenditure (Capex) and operating expenditure (Opex) are 19.3M$ and 9.07M$ for the base case, and 20.018M$ and 10.21M$ for the optimum case. The analysis also reveals that the optimum case, with higher methanol production (7.2 tonnes/h compared to 6.7 tonnes/h in the base case), generates a higher net income (9.76 M$/y) and reduces CO<sub>2</sub> emissions (4.918 tonnes CO<sub>2</sub>-e/y compared to 5.72 tonnes CO<sub>2</sub>-e/y). The energy flow indicates the input energy requirement, the energy carried by methanol, and the surplus energy, totalling 26740 kW to meet the major system's energy demands. This study provides valuable insights for researchers, policymakers, and commercial entities seeking to develop sustainable and economically viable biofuel production processes.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"14 ","pages":"Article 100204"},"PeriodicalIF":3.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143159035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hyperbox Mixture Regression for process performance prediction in antibody production Hyperbox混合回归用于抗体生产过程性能预测

IF 3 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-03-01 Epub Date: 2025-02-15 DOI: 10.1016/j.dche.2025.100221

Ali Nik-Khorasani , Thanh Tung Khuat , Bogdan Gabrys

This paper addresses the challenges of predicting bioprocess performance, particularly in monoclonal antibody (mAb) production, where conventional statistical methods often fall short due to time-series data’s complexity and high dimensionality. We propose a novel Hyperbox Mixture Regression (HMR) model that employs hyperbox-based input space partitioning to enhance predictive accuracy while managing uncertainty inherent in bioprocess data. The HMR model is designed to dynamically generate hyperboxes for input samples in a single-pass process, thereby improving learning speed and reducing computational complexity. Our experimental study utilizes a dataset that contains 106 bioreactors. This study evaluates the model’s performance in predicting critical quality attributes in monoclonal antibody manufacturing over a 15-day cultivation period. The results demonstrate that the HMR model outperforms comparable approximators in accuracy and learning speed and maintains interpretability and robustness under uncertain conditions. These findings underscore the potential of HMR as a powerful tool for enhancing predictive analytics in bioprocessing applications.

本文解决了预测生物过程性能的挑战，特别是在单克隆抗体（mAb）生产中，由于时间序列数据的复杂性和高维性，传统的统计方法往往不足。我们提出了一种新的Hyperbox混合回归（HMR）模型，该模型采用基于Hyperbox的输入空间划分来提高预测精度，同时管理生物过程数据中固有的不确定性。HMR模型设计为在单遍过程中动态生成输入样本的超盒，从而提高了学习速度并降低了计算复杂度。我们的实验研究使用了包含106个生物反应器的数据集。本研究评估了该模型在预测单克隆抗体生产中15天培养期关键质量属性方面的性能。结果表明，HMR模型在精度和学习速度上优于同类逼近器，并在不确定条件下保持可解释性和鲁棒性。这些发现强调了HMR作为生物加工应用中增强预测分析的强大工具的潜力。

{"title":"Hyperbox Mixture Regression for process performance prediction in antibody production","authors":"Ali Nik-Khorasani , Thanh Tung Khuat , Bogdan Gabrys","doi":"10.1016/j.dche.2025.100221","DOIUrl":"10.1016/j.dche.2025.100221","url":null,"abstract":"<div><div>This paper addresses the challenges of predicting bioprocess performance, particularly in monoclonal antibody (mAb) production, where conventional statistical methods often fall short due to time-series data’s complexity and high dimensionality. We propose a novel Hyperbox Mixture Regression (HMR) model that employs hyperbox-based input space partitioning to enhance predictive accuracy while managing uncertainty inherent in bioprocess data. The HMR model is designed to dynamically generate hyperboxes for input samples in a single-pass process, thereby improving learning speed and reducing computational complexity. Our experimental study utilizes a dataset that contains 106 bioreactors. This study evaluates the model’s performance in predicting critical quality attributes in monoclonal antibody manufacturing over a 15-day cultivation period. The results demonstrate that the HMR model outperforms comparable approximators in accuracy and learning speed and maintains interpretability and robustness under uncertain conditions. These findings underscore the potential of HMR as a powerful tool for enhancing predictive analytics in bioprocessing applications.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"14 ","pages":"Article 100221"},"PeriodicalIF":3.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143436459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Controlling tangential flow filtration in biomanufacturing processes via machine learning: A literature review 通过机器学习控制生物制造过程中的切向流过滤：文献综述

IF 3 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-03-01 Epub Date: 2025-01-02 DOI: 10.1016/j.dche.2024.100211

Bastian Oetomo , Ling Luo , Yiran Qu , Michele Discepola , Sandra E. Kentish , Sally L. Gras

With the rapid growth of the biopharmaceutical sector in recent years, in conjunction with many recent successful developments in machine learning and artificial intelligence, the demand for the sector to shift to Industry 4.0 has emerged. Process Analytical Technology (PAT) makes it possible to monitor and control the manufacturing processes of monoclonal antibodies (mAbs), both in upstream and downstream processing. Despite downstream processing being responsible for approximately 60% of the cost of biological drug production, most of the recent developments focus on its upstream counterpart. This paper investigates existing literature on the application of machine learning and/or process control in downstream processing, with an emphasis on ultrafiltration/diafiltration (UF/DF) via tangential flow filtration (TFF). Literature on the intersection between control systems and machine learning will also be explored.

随着近年来生物制药行业的快速增长，加上最近机器学习和人工智能的许多成功发展，该行业向工业4.0转变的需求已经出现。过程分析技术（PAT）使得监测和控制单克隆抗体（mab）的生产过程成为可能，无论是在上游还是下游加工。尽管下游加工约占生物药品生产成本的60%，但最近的大多数发展都集中在上游加工上。本文研究了机器学习和/或过程控制在下游处理中的应用的现有文献，重点研究了通过切向流过滤（TFF）的超滤/滤（UF/DF）。还将探讨控制系统和机器学习之间交叉的文献。

引用次数: 0

Catalytic pyrolysis of HDPE for enhanced hydrocarbon yield: A boosted regression tree assisted kinetics study for effective recycling of waste plastic HDPE催化热解提高碳氢化合物产量：促进回归树辅助动力学研究有效回收废塑料

IF 3 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-03-01 Epub Date: 2024-12-16 DOI: 10.1016/j.dche.2024.100213

Shahina Riaz , Nabeel Ahmad , Wasif Farooq , Imtiaz Ali , Mohd Sajid , Muhammad Naseem Akhtar

Kinetic study is crucial in digital chemical engineering as a foundation for understanding and optimizing chemical processes. By analyzing reaction rates and mechanisms, kinetic models provide essential data for designing reactors, scaling processes, and predicting performance under various conditions. This study is part of a broader research series focused on efficiently converting waste plastics into hydrocarbons through catalytic pyrolysis. As the first study from the series, it investigates the thermal degradation of pristine high-density polyethylene (HDPE), aiming to understand its reaction kinetics under catalytic and non-catalytic conditions. The research employs iso-conventional methods to estimate the activation of energy HDPE and leverages a machine learning algorithm, specifically the BRT model, to effectively predict activation energy and optimize pyrolysis parameters. The activation energy (323 kJ/mol) of non-catalytic pyrolysis of HDPE was reduced to 164 kJ/mol during catalytic pyrolysis. Thermodynamic parameters such as change in activation enthalpy (

Δ H^{‡}

), activation Gibbs free energy (

Δ G^{‡}

) and, activation entropy (

Δ S^{‡}

) were also significantly reduced during catalytic reaction. The statistical and machine-learning approaches were used in the kinetic analyses. Boosted regression trees (BRT) were used to predict the

E_{a}

during conversion at different heating rates for non-catalytic and catalytic processes. The liquid and gas fractions obtained from HDPE at different temperatures were characterized. The increase in yield of hydrocarbons at elevated temperatures indicated the reuse potential of plastic waste. The comprehensive analysis of HDPE exhibited 86 % of carbon and 14 % of hydrogen contributing to high heating value (HHV) of 44.41 MJ/kg.

动力学研究作为理解和优化化学过程的基础，在数字化学工程中是至关重要的。通过分析反应速率和机理，动力学模型为设计反应器、标度过程和预测各种条件下的性能提供了必要的数据。这项研究是一个更广泛的研究系列的一部分，重点是通过催化热解有效地将废塑料转化为碳氢化合物。作为该系列的第一项研究，它研究了原始高密度聚乙烯（HDPE）的热降解，旨在了解其在催化和非催化条件下的反应动力学。该研究采用等常规方法估计HDPE的活化能，并利用机器学习算法，特别是BRT模型，有效预测活化能并优化热解参数。HDPE非催化热解的活化能（323 kJ/mol）在催化热解过程中降至164 kJ/mol。热力学参数如活化焓（ΔH‡）、活化吉布斯自由能（ΔG‡）和活化熵（ΔS‡）的变化也在催化反应过程中显著降低。在动力学分析中使用了统计和机器学习方法。利用增强回归树（boosting regression trees， BRT）预测了非催化和催化过程在不同加热速率下转化过程中的ea。对HDPE在不同温度下的液、气组分进行了表征。高温下碳氢化合物产量的增加表明塑料废物的再利用潜力。HDPE的综合分析显示，86%的碳和14%的氢导致了44.41 MJ/kg的高热值（HHV）。

{"title":"Catalytic pyrolysis of HDPE for enhanced hydrocarbon yield: A boosted regression tree assisted kinetics study for effective recycling of waste plastic","authors":"Shahina Riaz , Nabeel Ahmad , Wasif Farooq , Imtiaz Ali , Mohd Sajid , Muhammad Naseem Akhtar","doi":"10.1016/j.dche.2024.100213","DOIUrl":"10.1016/j.dche.2024.100213","url":null,"abstract":"<div><div>Kinetic study is crucial in digital chemical engineering as a foundation for understanding and optimizing chemical processes. By analyzing reaction rates and mechanisms, kinetic models provide essential data for designing reactors, scaling processes, and predicting performance under various conditions. This study is part of a broader research series focused on efficiently converting waste plastics into hydrocarbons through catalytic pyrolysis. As the first study from the series, it investigates the thermal degradation of pristine high-density polyethylene (HDPE), aiming to understand its reaction kinetics under catalytic and non-catalytic conditions. The research employs iso-conventional methods to estimate the activation of energy HDPE and leverages a machine learning algorithm, specifically the BRT model, to effectively predict activation energy and optimize pyrolysis parameters. The activation energy (323 kJ/mol) of non-catalytic pyrolysis of HDPE was reduced to 164 kJ/mol during catalytic pyrolysis. Thermodynamic parameters such as change in activation enthalpy (<span><math><mrow><mstyle><mi>Δ</mi></mstyle><msup><mrow><mi>H</mi></mrow><mo>‡</mo></msup></mrow></math></span>), activation Gibbs free energy (<span><math><mrow><mstyle><mi>Δ</mi></mstyle><msup><mrow><mi>G</mi></mrow><mo>‡</mo></msup></mrow></math></span>) and, activation entropy (<span><math><mrow><mstyle><mi>Δ</mi></mstyle><msup><mrow><mi>S</mi></mrow><mo>‡</mo></msup></mrow></math></span>) were also significantly reduced during catalytic reaction. The statistical and machine-learning approaches were used in the kinetic analyses. Boosted regression trees (BRT) were used to predict the<span><math><mrow><mspace></mspace><msub><mi>E</mi><mi>a</mi></msub></mrow></math></span> during conversion at different heating rates for non-catalytic and catalytic processes. The liquid and gas fractions obtained from HDPE at different temperatures were characterized. The increase in yield of hydrocarbons at elevated temperatures indicated the reuse potential of plastic waste. The comprehensive analysis of HDPE exhibited 86 % of carbon and 14 % of hydrogen contributing to high heating value (HHV) of 44.41 MJ/kg.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"14 ","pages":"Article 100213"},"PeriodicalIF":3.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143159063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Applications of machine learning for modeling and advanced control of crystallization processes: Developments and perspectives 机器学习在结晶过程建模和高级控制中的应用：发展和前景

IF 3 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-03-01 Epub Date: 2024-12-18 DOI: 10.1016/j.dche.2024.100208

Fernando Arrais R.D. Lima , Marcellus G.F. de Moraes , Amaro G. Barreto Jr , Argimiro R. Secchi , Martha A. Grover , Maurício B. de Souza Jr

Crystallization is a separation method relevant to the production of medicines, food and many other products. An efficient crystallization process must obtain a product with the desired size, length, and purity. Therefore, models and control schemes are applied to achieve this goal. Artificial intelligence techniques, such as machine learning (ML), are applied for modeling and controlling these processes. The current review aims to present the use of ML for modeling and advanced control of crystallization processes. Considering modeling crystallization processes, this paper presents the advances and different uses of ML, such as neural networks, symbolic regression, and transformer algorithms. This review also presents the development of hybrid models combining ML with physical laws for crystallization processes. For the advanced control of crystallization processes, this review presents the development of advanced control strategies based on ML approaches, such as applying neural networks in a nonlinear model predictive controller and based on reinforcement learning. This work can be a relevant reference for the progress of the application of ML in the process systems engineering (PSE) to crystallization processes. It is also expected to encourage industry and academy to use these approaches for different crystallization processes.

结晶是一种与药品、食品和许多其他产品生产有关的分离方法。一个有效的结晶过程必须获得具有所需尺寸、长度和纯度的产品。因此，采用模型和控制方案来实现这一目标。人工智能技术，如机器学习（ML），被用于建模和控制这些过程。本综述旨在介绍机器学习在结晶过程建模和高级控制中的应用。考虑到结晶过程的建模，本文介绍了ML的进步和不同用途，如神经网络、符号回归和变压器算法。本文还介绍了结合ML和结晶过程物理规律的混合模型的发展。对于结晶过程的高级控制，本文综述了基于ML方法的高级控制策略的发展，例如在非线性模型预测控制器中应用神经网络和基于强化学习的高级控制策略。本工作可为机器学习在过程系统工程（PSE）结晶过程中的应用提供相关参考。它也有望鼓励工业界和学术界将这些方法用于不同的结晶过程。

{"title":"Applications of machine learning for modeling and advanced control of crystallization processes: Developments and perspectives","authors":"Fernando Arrais R.D. Lima , Marcellus G.F. de Moraes , Amaro G. Barreto Jr , Argimiro R. Secchi , Martha A. Grover , Maurício B. de Souza Jr","doi":"10.1016/j.dche.2024.100208","DOIUrl":"10.1016/j.dche.2024.100208","url":null,"abstract":"<div><div>Crystallization is a separation method relevant to the production of medicines, food and many other products. An efficient crystallization process must obtain a product with the desired size, length, and purity. Therefore, models and control schemes are applied to achieve this goal. Artificial intelligence techniques, such as machine learning (ML), are applied for modeling and controlling these processes. The current review aims to present the use of ML for modeling and advanced control of crystallization processes. Considering modeling crystallization processes, this paper presents the advances and different uses of ML, such as neural networks, symbolic regression, and transformer algorithms. This review also presents the development of hybrid models combining ML with physical laws for crystallization processes. For the advanced control of crystallization processes, this review presents the development of advanced control strategies based on ML approaches, such as applying neural networks in a nonlinear model predictive controller and based on reinforcement learning. This work can be a relevant reference for the progress of the application of ML in the process systems engineering (PSE) to crystallization processes. It is also expected to encourage industry and academy to use these approaches for different crystallization processes.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"14 ","pages":"Article 100208"},"PeriodicalIF":3.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143159059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Implementation of real-time incremental learning for ensemble hybrid model prediction in pilot scale bubble column aeration 中试规模气泡塔曝气集成混合模型预测的实时增量学习实现

IF 3 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-03-01 Epub Date: 2024-12-23 DOI: 10.1016/j.dche.2024.100212

Peter Jul-Rasmussen , Mads Stevnsborg , Xiaodong Liang , Jakob Kjøbsted Huusom

Digital twins are frequently discussed in a bio-manufacturing context, but actual realisations of digital twins are rare. To use digital twin instances, significant investments in digital infrastructure and high-fidelity mathematical models are required. This work presents a real-time implementation of an ensemble hybrid model with incremental learning for predicting dissolved oxygen concentration in a pilot-scale bubble column. A bootstrap-aggregated hybrid modelling framework is applied for constructing an ensemble of 1000 hybrid models using different partitions of the training/validation data, providing a measure of the parameter distributions and prediction uncertainty. Each model in the ensemble hybrid model has the same model structure relying on first-principles material balances and an Artificial Neural Network for prediction of the liquid phase volumetric mass transfer coefficient. Incremental learning is applied, efficiently enabling the model to adapt to new data acquired during runtime. The software implementation follows recent ISO issues using a modular structure allowing for flexible allocation of server resources and an intuitive User-Interface is developed for controlling the application. From a real-time prediction study, the models using incremental learning are found to have superior performance both at normal operating conditions, when interpolating, and when extrapolating compared to using only the pre-trained model.

数字双胞胎经常在生物制造环境中被讨论，但数字双胞胎的实际实现很少。要使用数字孪生实例，需要对数字基础设施和高保真数学模型进行大量投资。这项工作提出了一个集成混合模型与增量学习的实时实现，用于预测中试规模气泡柱中的溶解氧浓度。利用训练/验证数据的不同分区，构建了一个由1000个混合模型组成的集合，提供了参数分布和预测不确定性的度量。集合混合模型中的每个模型都具有相同的模型结构，依赖第一性原理物质平衡和人工神经网络来预测液相体积传质系数。采用增量学习，有效地使模型适应运行时获取的新数据。软件实现遵循最近的ISO问题，使用模块化结构允许灵活分配服务器资源，并开发了一个直观的用户界面来控制应用程序。从一项实时预测研究中发现，与仅使用预训练模型相比，使用增量学习的模型在正常操作条件下、内插和外推时都具有优越的性能。

{"title":"Implementation of real-time incremental learning for ensemble hybrid model prediction in pilot scale bubble column aeration","authors":"Peter Jul-Rasmussen , Mads Stevnsborg , Xiaodong Liang , Jakob Kjøbsted Huusom","doi":"10.1016/j.dche.2024.100212","DOIUrl":"10.1016/j.dche.2024.100212","url":null,"abstract":"<div><div>Digital twins are frequently discussed in a bio-manufacturing context, but actual realisations of digital twins are rare. To use digital twin instances, significant investments in digital infrastructure and high-fidelity mathematical models are required. This work presents a real-time implementation of an ensemble hybrid model with incremental learning for predicting dissolved oxygen concentration in a pilot-scale bubble column. A bootstrap-aggregated hybrid modelling framework is applied for constructing an ensemble of 1000 hybrid models using different partitions of the training/validation data, providing a measure of the parameter distributions and prediction uncertainty. Each model in the ensemble hybrid model has the same model structure relying on first-principles material balances and an Artificial Neural Network for prediction of the liquid phase volumetric mass transfer coefficient. Incremental learning is applied, efficiently enabling the model to adapt to new data acquired during runtime. The software implementation follows recent ISO issues using a modular structure allowing for flexible allocation of server resources and an intuitive User-Interface is developed for controlling the application. From a real-time prediction study, the models using incremental learning are found to have superior performance both at normal operating conditions, when interpolating, and when extrapolating compared to using only the pre-trained model.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"14 ","pages":"Article 100212"},"PeriodicalIF":3.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143160286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

APAH: An autonomous IoT driven real-time monitoring system for Industrial wastewater APAH：一个自主的物联网驱动的工业废水实时监控系统

IF 3 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-03-01 Epub Date: 2025-01-04 DOI: 10.1016/j.dche.2025.100217

Nishant Chavhan , Resham Bhattad , Suyash Khot , Shubham Patil , Aditya Pawar , Tejasvi Pawar , Palomi Gawli

Water pollution, worsened by rapid industrialization, poses severe challenges to global water management, particularly in developing countries like India. Conventional water quality monitoring methods, which rely on manual sampling and laboratory analysis are, inadequate for handling the dynamic and real-time nature of industrial wastewater contamination. To address this issue, this research article presents the state-of-the-art IoT-based autonomous real-time monitoring system (APAH), a scalable and frugal solution for industrial wastewater management. APAH integrates multi-parameter sensors to continuously monitor critical water quality parameters such as pH, dissolved oxygen (DO), electrical conductivity (EC), total dissolved solids (TDS), turbidity, and temperature. The system's layered architecture, comprising a sensing layer, edge layer, and application layer, enables data acquisition, processing, and remote access via APAH i.e. developed Android mobile application, respectively. APAH utilizes advanced technologies including, the Internet of Things (IoT) and Machine learning (ML) to provide real-time monitoring and control of wastewater treatment processes. Automated valve controls and real-time alerts enable timely intervention, preventing contamination and ensuring compliance with environmental standards. The system's performance was validated through field tests at four industrial wastewater treatment plants in Maharashtra, India particularly directed towards textile, dairy, and greywater effluents, demonstrating significant improvements in water quality post-treatment. The APAH system offers a promising solution for enhancing industrial wastewater treatment efficiency and ensuring sustainable water resource management. By integrating IoT technologies, real-time monitoring, and predictive analytics, APAH can contribute to addressing the urgent need for effective water quality management in industrial environments, particularly in regions facing acute water scarcity and pollution challenges.

由于快速工业化而恶化的水污染对全球水资源管理构成严峻挑战，特别是在印度等发展中国家。传统的水质监测方法依赖于人工采样和实验室分析，不足以处理工业废水污染的动态性和实时性。为了解决这一问题，本文介绍了基于物联网的自主实时监控系统（APAH），这是一种可扩展且节约的工业废水管理解决方案。APAH集成了多参数传感器，可连续监测关键水质参数，如pH值、溶解氧（DO）、电导率（EC）、总溶解固体（TDS）、浊度和温度。该系统采用分层架构，包括传感层、边缘层和应用层，分别通过APAH（即开发的Android移动应用程序）实现数据采集、处理和远程访问。APAH利用包括物联网（IoT）和机器学习（ML）在内的先进技术，对废水处理过程进行实时监测和控制。自动化阀门控制和实时警报能够及时干预，防止污染并确保符合环境标准。该系统的性能在印度马哈拉施特拉邦的四家工业废水处理厂进行了现场测试，特别是针对纺织、乳制品和灰水的废水，显示出在水质后处理方面的显着改善。APAH系统为提高工业废水处理效率和确保水资源的可持续管理提供了一个有前途的解决方案。通过整合物联网技术、实时监测和预测分析，APAH可以帮助解决工业环境中对有效水质管理的迫切需求，特别是在面临严重缺水和污染挑战的地区。

{"title":"APAH: An autonomous IoT driven real-time monitoring system for Industrial wastewater","authors":"Nishant Chavhan , Resham Bhattad , Suyash Khot , Shubham Patil , Aditya Pawar , Tejasvi Pawar , Palomi Gawli","doi":"10.1016/j.dche.2025.100217","DOIUrl":"10.1016/j.dche.2025.100217","url":null,"abstract":"<div><div>Water pollution, worsened by rapid industrialization, poses severe challenges to global water management, particularly in developing countries like India. Conventional water quality monitoring methods, which rely on manual sampling and laboratory analysis are, inadequate for handling the dynamic and real-time nature of industrial wastewater contamination. To address this issue, this research article presents the state-of-the-art IoT-based autonomous real-time monitoring system (APAH), a scalable and frugal solution for industrial wastewater management. APAH integrates multi-parameter sensors to continuously monitor critical water quality parameters such as pH, dissolved oxygen (DO), electrical conductivity (EC), total dissolved solids (TDS), turbidity, and temperature. The system's layered architecture, comprising a sensing layer, edge layer, and application layer, enables data acquisition, processing, and remote access via APAH i.e. developed Android mobile application, respectively. APAH utilizes advanced technologies including, the Internet of Things (IoT) and Machine learning (ML) to provide real-time monitoring and control of wastewater treatment processes. Automated valve controls and real-time alerts enable timely intervention, preventing contamination and ensuring compliance with environmental standards. The system's performance was validated through field tests at four industrial wastewater treatment plants in Maharashtra, India particularly directed towards textile, dairy, and greywater effluents, demonstrating significant improvements in water quality post-treatment. The APAH system offers a promising solution for enhancing industrial wastewater treatment efficiency and ensuring sustainable water resource management. By integrating IoT technologies, real-time monitoring, and predictive analytics, APAH can contribute to addressing the urgent need for effective water quality management in industrial environments, particularly in regions facing acute water scarcity and pollution challenges.</div></div>","PeriodicalId":72815,"journal":{"name":"Digital Chemical Engineering","volume":"14 ","pages":"Article 100217"},"PeriodicalIF":3.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143159062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Development of a software architecture for bioprocess modeling 生物过程建模软件体系结构的开发

IF 3 Q2 ENGINEERING, CHEMICAL

Digital Chemical Engineering

Pub Date : 2025-03-01 Epub Date: 2024-12-26 DOI: 10.1016/j.dche.2024.100210

Priscila Marques da Paz , Caroline Satye Martins Nakama , Galo Antonio Carrillo Le Roux

Increasing the productivity of a biotechnological process becomes feasible through the development of Process Systems Engineering tools, which integrate experimental data with mathematical modeling. This work aims to develop a software architecture for modeling bioprocesses that is accessible to a multidisciplinary group. To achieve this aim, the software must be thoroughly designed based on an ontology that describes bioprocesses that can be apprehended by researchers from different fields. The ontological representation is carried out using Unified Modeling Language diagrams, whose use is demonstrated by a parameter estimation case study. It is concluded that good software development practices can be provided through the proposed architecture, since it guides simulations and parameter estimations of biotechnological processes in a structured way.

通过将实验数据与数学建模相结合的过程系统工程工具的开发，提高生物技术过程的生产率变得可行。这项工作的目的是开发一个软件架构建模的生物过程，是可访问的多学科组。为了实现这一目标，软件必须完全基于描述生物过程的本体进行设计，这些过程可以被来自不同领域的研究人员所理解。本体表示使用统一建模语言图进行，其使用通过参数估计案例研究进行了演示。结论是，通过提出的体系结构可以提供良好的软件开发实践，因为它以结构化的方式指导生物技术过程的模拟和参数估计。

引用次数: 0