Canadian Journal of Chemical Engineering最新文献_第9页

Interpretable symbolic machine learning and optimization framework for reducing arcing time in energy-intensive steelmaking 可解释的符号机器学习和优化框架，以减少能源密集型炼钢电弧时间

IF 1.9 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2026-06-10 Epub Date: 2026-01-15 DOI: 10.1002/cjce.70242

Somashish Saha, Narottam Behera, Sandip Kumar Lahiri

{"title":"Interpretable symbolic machine learning and optimization framework for reducing arcing time in energy-intensive steelmaking","authors":"Somashish Saha, Narottam Behera, Sandip Kumar Lahiri","doi":"10.1002/cjce.70242","DOIUrl":"https://doi.org/10.1002/cjce.70242","url":null,"abstract":"This study presents an interpretable, data-driven framework for predicting and optimizing arcing time in direct reduced iron (DRI)-based electric arc furnace (EAF) steelmaking using genetic programming (GP) and multi-gene genetic programming (MGGP). Unlike traditional machine learning models, GP and MGGP generate explicit symbolic equations that not only deliver high prediction accuracy but also reveal the mathematical relationships between process inputs and arcing time. This transparency enhances operator trust and facilitates practical deployment, as the derived equations can be directly used for manual verification and process control. Real industrial data comprising 22 process variables from over 8692 heats were used for model training and validation. To ensure interpretability and industrial applicability, a novel feature-selection algorithm using iterative MGGP relevance analysis was implemented yielding 12 key inputs. The resulting symbolic models were integrated with genetic algorithms (GA) to identify optimal input conditions for minimizing arcing time, leading to reduced energy consumption. MGGP models trained and validated on an 80/20 split, achieved R2 = 0.89 and RMSE = 0.906 min on training data, and R2 = 0.889 and RMSE = 0.932 min on test data. GA optimization reduced mean arcing time by 1.45 min and energy consumption by 4%, boosting productivity by 3.54% from 211.95 to 219.45 t/h. Sensitivity trends matched established metallurgical principles. The hybrid MGGP–GA framework generates transparent symbolic equations and prescriptive control settings, striking an effective balance between predictive fidelity and interpretability. This approach is well suited for real-time EAF energy optimization and operator acceptance.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"104 7","pages":"3574-3592"},"PeriodicalIF":1.9,"publicationDate":"2026-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148215193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Treatment of commercial industrial wastewater using electrocoagulation: Understanding effect of operating conditions 电絮凝法处理商业工业废水：操作条件的影响

IF 1.9 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2026-06-10 Epub Date: 2025-12-14 DOI: 10.1002/cjce.70204

Jyoti S. Sangle, Parag R. Gogate

{"title":"Treatment of commercial industrial wastewater using electrocoagulation: Understanding effect of operating conditions","authors":"Jyoti S. Sangle, Parag R. Gogate","doi":"10.1002/cjce.70204","DOIUrl":"https://doi.org/10.1002/cjce.70204","url":null,"abstract":"The wastewater generated from various stages in pharmaceutical industries such as production, washing processes, and formulation contains a wide range of hazardous chemicals. The objective of this study is to investigate the application of electrocoagulation (EC) for the treatment of real industrial pharmaceutical wastewater obtained from various processing stages. Aluminium and stainless steel (SS) electrodes were used to conduct the treatment. The effects of important operating conditions for EC such as current density (1.08–3.33A/cm2), electrode spacing (varied from 4 to 7 cm), pH (from 4.0 to 10.0), and poly aluminium chloride (PAC) dose (chemical oxygen demand [COD]: PAC ratio as 1:0.025–1:0.3) on the COD removal efficiency have been studied. TDS and electrical conductivity were also monitored during the treatment. The optimum COD reduction was observed at a current density of 1.33 A/cm2, an electrode spacing of 5 cm, a pH of 7, and a COD: PAC dosage ratio of 1:0.2. The maximum COD reduction recorded for samples A, B, C, and D corresponding to various stages were 62%, 71%, 51%, and 86%, respectively. It was also concluded that the COD reduction was improved after the addition of external coagulant as PAC. The research work has clearly confirmed that the EC process can be considered as an effective method of treatment for COD reduction.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"104 7","pages":"3402-3417"},"PeriodicalIF":1.9,"publicationDate":"2026-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148215064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mathematical modelling and simulation of hemodynamic alterations in atherosclerotic arteries 动脉粥样硬化血流动力学改变的数学建模和模拟

IF 1.9 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2026-06-10 Epub Date: 2026-01-22 DOI: 10.1002/cjce.70272

Shazmani Sheikh, Anju Saini, Deepika Saini

{"title":"Mathematical modelling and simulation of hemodynamic alterations in atherosclerotic arteries","authors":"Shazmani Sheikh, Anju Saini, Deepika Saini","doi":"10.1002/cjce.70272","DOIUrl":"https://doi.org/10.1002/cjce.70272","url":null,"abstract":"Atherosclerosis-induced arterial stenosis significantly alters hemodynamic conditions, increasing the risk of vascular complications such as rupture and thrombosis. In this study, we develop and analyze a comprehensive mathematical model to investigate steady-state blood flow in arteries with asymmetric stenosis using MATLAB's bvp4c boundary value solver. The model incorporates elastic arterial wall behaviour, variable blood density effects (to simulate anaemia and polycythemia), and multiple stenotic regions to simulate complex atherosclerotic conditions. By comparing healthy and diseased arteries, we compute critical hemodynamic parameters such as pressure drop, wall shear stress (WSS), hoop stress, Reynolds number, and rupture risk index. The results indicate a higher pressure gradient, elevated rupture probability, and localized peaks in WSS and Reynolds number near plaque regions. A 3D visualization of WSS versus hoop stress versus position reveals stress concentration zones, potentially correlating with plaque vulnerability. Additionally, the effect of varying blood density demonstrates how systemic conditions can exacerbate flow disturbances and increase risk. These findings provide a quantitative framework for assessing the biomechanical environment under atherosclerotic conditions and may contribute to improved diagnostics and predictive tools for cardiovascular disease progression.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"104 7","pages":"3390-3401"},"PeriodicalIF":1.9,"publicationDate":"2026-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148215098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Machine learning framework for sulphur content prediction in crude oil using physicochemical properties 利用物化性质预测原油含硫量的机器学习框架

IF 1.9 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2026-06-10 Epub Date: 2026-01-16 DOI: 10.1002/cjce.70240

Suhailam Pullanikkattil, Chandra Shekar Besta

{"title":"Machine learning framework for sulphur content prediction in crude oil using physicochemical properties","authors":"Suhailam Pullanikkattil, Chandra Shekar Besta","doi":"10.1002/cjce.70240","DOIUrl":"https://doi.org/10.1002/cjce.70240","url":null,"abstract":"Accurate prediction of sulphur content in crude oil is essential for optimizing refining efficiency, ensuring environmental compliance, and improving fuel quality. This study introduces an explainable machine-learning framework to predict sulphur weight percentage (wt.%) using a comprehensive dataset of 664 crude oil samples characterized by 73 physicochemical properties. Five regression algorithms including support vector regression, k-nearest neighbours, decision tree, random forest, and extreme gradient boosting (XGBoost) were trained and validated under identical preprocessing and cross-validation protocols. XGBoost achieved the highest test-set accuracy (R2 = 0.89), significantly outperforming random forest (R2 = 0.74) and decision tree regression (R2 = 0.72) and other models. Cross-validation confirmed the robustness of XGBoost (mean R2 = 0.92), while Shapley additive explanations (SHAP) analysis identified Watson K, asphaltene content, and nitrogen by weight (%) as the most influential features. The novelty of this study lies in integrating a high-dimensional dataset with explainable AI (SHAP) to uncover physicochemical drivers of sulphur content, thereby achieving both improved accuracy and interpretability over existing models. This data-driven approach provides a scalable and precise sulphur estimation tool that enables refiners to optimize blending strategies, reduce desulphurization costs, and comply with stringent environmental regulations.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"104 7","pages":"3495-3511"},"PeriodicalIF":1.9,"publicationDate":"2026-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148215139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Micro-explosions caused by the reaction of nano-sized aluminium and polyvinylidene fluoride to promote the micron-sized aluminium combustion and inhibit its agglomeration 纳米级铝与聚偏氟乙烯反应引起微爆炸，促进微米级铝的燃烧，抑制其团聚

IF 1.9 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2026-06-10 Epub Date: 2025-12-26 DOI: 10.1002/cjce.70227

Jiahui Wu, Tianyu Yang, Lingqi Zhu, Yunlan Sun, Baozhong Zhu

{"title":"Micro-explosions caused by the reaction of nano-sized aluminium and polyvinylidene fluoride to promote the micron-sized aluminium combustion and inhibit its agglomeration","authors":"Jiahui Wu, Tianyu Yang, Lingqi Zhu, Yunlan Sun, Baozhong Zhu","doi":"10.1002/cjce.70227","DOIUrl":"10.1002/cjce.70227","url":null,"abstract":"Micron-aluminium (μAl) powder is difficult to ignition and prone to agglomeration during combustion, leading to the reduced combustion efficiency. To solve the issues, Al powders with different particle sizes were modified by polyvinylidene fluoride (PVDF) and studied using thermogravimetry–differential scanning calorimetry (TG-DSC), laser ignition experiments, and advanced characterization techniques. These methods revealed that violent micro-explosions caused by the interaction of PVDF and nano-Al (nAl) can effectively promote the combustion of μAl and inhibit its agglomeration. The mixing of nAlPVDF and μAlPVDF accelerates the oxidation reaction, increases heat release, and improves combustion performance, particularly for the nAlPVDF/μAlPVDF (1:4) sample, which exhibits the largest flame area, the highest flame expansion speed and flame temperature, and the shortest ignition delay and combustion time. The synergistic effect of PVDF and nAl enhances the fragmentation of μAl during combustion, resulting in smaller condensed combustion products. These results provide insights from both thermal analysis and combustion experiments, laying a foundation for improving the ignition and combustion efficiency of μAl.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"104 7","pages":"3644-3659"},"PeriodicalIF":1.9,"publicationDate":"2026-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147333656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimization of a reactor for biostimulant production with emphasis on the economic aspects of hydrolysis 生物刺激素生产反应器的优化，着重于水解的经济方面

IF 1.9 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2026-06-10 Epub Date: 2026-01-14 DOI: 10.1002/cjce.70243

Karel Kolomazník, Lubomír Šánek, Petr Dostálek, Clara Desroches

{"title":"Optimization of a reactor for biostimulant production with emphasis on the economic aspects of hydrolysis","authors":"Karel Kolomazník, Lubomír Šánek, Petr Dostálek, Clara Desroches","doi":"10.1002/cjce.70243","DOIUrl":"https://doi.org/10.1002/cjce.70243","url":null,"abstract":"Biostimulants are increasingly used in agriculture to promote plant growth, improve stress tolerance, and support sustainable farming practices. One common method of production is chemical hydrolysis of protein-rich waste, such as tannery by-products, offering an economical and eco-friendly alternative to conventional raw materials. This approach aligns with the principles of the circular economy by transforming industrial waste into valuable agricultural inputs. This study investigates the first stage of biostimulant production, alkaline hydrolysis at elevated temperatures, by analyzing the interplay between reaction kinetics, conversion efficiency, and operational costs. Through experimental data and kinetic modelling using a first-order reaction and the Arrhenius equation, key parameters such as activation energy and frequency factor were established. A techno-economic evaluation was conducted to determine optimal operating conditions, emphasizing the importance of the cost ratio between the reactor and evaporator. The results show that higher conversion rates and shorter reaction times are achievable with optimized temperature and cost parameters. Pilot-scale validation (100 L) confirmed process scalability, and preliminary field trials on maize demonstrated effects comparable to those of commercial products. These insights contribute to the advancement of scalable and cost-effective hydrolysis methods for producing biostimulants from waste protein sources.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"104 7","pages":"3484-3494"},"PeriodicalIF":1.9,"publicationDate":"2026-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cjce.70243","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148215075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Model predictive control of coal-fired power plant desulphurization system based on GJO-TCN-BiGRU-attention 基于GJO-TCN-BiGRU-attention的燃煤电厂脱硫系统模型预测控制

IF 1.9 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2026-06-10 Epub Date: 2026-01-02 DOI: 10.1002/cjce.70231

Minan Tang, Zhongcheng Bai, Jiandong Qiu, Chuntao Rao, Yude Jiang, Wenxin Sheng

{"title":"Model predictive control of coal-fired power plant desulphurization system based on GJO-TCN-BiGRU-attention","authors":"Minan Tang, Zhongcheng Bai, Jiandong Qiu, Chuntao Rao, Yude Jiang, Wenxin Sheng","doi":"10.1002/cjce.70231","DOIUrl":"https://doi.org/10.1002/cjce.70231","url":null,"abstract":"The wet flue gas desulphurization (WFGD) system is characterized by nonlinearity, strong coupling, time-varying, and input–output delays, which make it difficult for traditional control methods to accurately control the WFGD system. In this paper, a combination of neural network (NN) predictive model and model predictive control (MPC) is proposed to be used for the optimal control of the WFGD system. Firstly, the prediction model of the WFGD system is established by temporal convolutional network (TCN)-bidirectional gated recurrent unit (BiGRU)-attention. Secondly, the hyperparameters of the prediction model are optimized using the golden jackal optimization (GJO). Then, the WFGD system is controlled by MPC. Meanwhile, in this paper, the original dataset of the WFGD system is screened to remove outliers using a local outlier factor (LOF) detection algorithm. Finally, based on the Matlab R2023a platform, this method is compared with the PID algorithm, and the actual effect is improved by about 28%. The experimental results show that the GJO-TCN-BiGRU-attention model can predict the desulphurization system well, and the control effect of the MPC method on the desulphurization system is better than PID algorithm.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"104 7","pages":"3527-3545"},"PeriodicalIF":1.9,"publicationDate":"2026-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148215111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Computational intelligence approaches for hydrogen storage material design 储氢材料设计的计算智能方法

IF 1.9 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2026-06-10 Epub Date: 2026-01-14 DOI: 10.1002/cjce.70232

Abdulhalim Musa Abubakar, Mahlon Kida Marvin

{"title":"Computational intelligence approaches for hydrogen storage material design","authors":"Abdulhalim Musa Abubakar, Mahlon Kida Marvin","doi":"10.1002/cjce.70232","DOIUrl":"https://doi.org/10.1002/cjce.70232","url":null,"abstract":"Hydrogen is increasingly recognized as a clean energy carrier in the transition toward low-carbon and sustainable energy systems. However, the development of safe, efficient, and cost-effective hydrogen storage technologies remains a major barrier to its large-scale deployment. This paper presents a review of how advanced computational intelligence encompassing machine learning (ML), deep learning (DL), high-throughput screening, and multi-scale modelling is transforming the discovery, design, and optimization of hydrogen storage materials. The integration of graph neural networks (GNNs), inverse material design, and Bayesian optimization is enabling accelerated screening and performance prediction across diverse material classes such as metal hydrides, complex hydrides, porous frameworks, and carbon nanostructures. Materials informatics platforms and autonomous discovery pipelines, including self-driving laboratories and active learning workflows, are further streamlining the experimental validation of computationally designed materials. In addition, the application of quantum ML and multi-fidelity modelling is improving accuracy while reducing simulation costs. Through a series of case study reviews, this paper demonstrates the critical role of these tools in enhancing thermodynamic tuning, adsorption capacity, and kinetic response in next-generation hydrogen storage systems. This review study highlight that computational intelligence is central to the hydrogen materials innovation cycle.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"104 7","pages":"3618-3643"},"PeriodicalIF":1.9,"publicationDate":"2026-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148215074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Issue Highlights 问题突出

IF 1.9 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2026-06-10 DOI: 10.1002/cjce.70262

引用次数: 0

Reparameterization of the Monod equation for optimum experimental design and enhanced estimation of model parameters: Application to the nitrification kinetics 用于优化实验设计的Monod方程的重新参数化和模型参数的增强估计：在硝化动力学中的应用

IF 1.9 4区工程技术

Canadian Journal of Chemical Engineering Pub Date : 2026-06-10 Epub Date: 2026-01-07 DOI: 10.1002/cjce.70217

Claudia Santiviago, Nahuel Maidana, Elena Castelló, José Carlos Pinto

{"title":"Reparameterization of the Monod equation for optimum experimental design and enhanced estimation of model parameters: Application to the nitrification kinetics","authors":"Claudia Santiviago, Nahuel Maidana, Elena Castelló, José Carlos Pinto","doi":"10.1002/cjce.70217","DOIUrl":"https://doi.org/10.1002/cjce.70217","url":null,"abstract":"The Monod equation is frequently used for modelling of the microbial growth kinetics. Traditionally, the estimation of the Monod parameters is conducted through sampling at arbitrary times, which can lead to unnecessary experimental workload and high parameter uncertainties. In this context, the present manuscript originally applies a nonlinear reparameterized form of the Monod equation that allows the optimal experimental design for the Monod reparameterized equation (OED-R) and improve the statistical quality of parameter estimation, which can lead to estimation of more precise and uncorrelated transformed model parameters with smaller number of experiments. Using nitrification as a case study, it is shown that OED-R can be used to strategically select sampling times during critical phases of the kinetic trajectory, where the system sensitivity to parameter changes is at its peak. This approach can simultaneously enhance the precision and efficiency of experiments by reducing the number of required samples and minimizing parameter uncertainties and correlation during estimation.","PeriodicalId":9400,"journal":{"name":"Canadian Journal of Chemical Engineering","volume":"104 7","pages":"3369-3389"},"PeriodicalIF":1.9,"publicationDate":"2026-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148215159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0