Chinese Journal of Chemical Engineering最新文献_第6页

Intelligent prediction of ionic liquids and deep eutectic solvents by machine learning 离子液体和深度共晶溶剂的机器学习智能预测

IF 3.7 3区工程技术

Chinese Journal of Chemical Engineering Pub Date : 2025-08-01 DOI: 10.1016/j.cjche.2025.06.006

Yuan Tian , Honghua Zhang , Yueyang Qiao , Han Yang , Yanrong Liu , Xiaoyan Ji

{"title":"Intelligent prediction of ionic liquids and deep eutectic solvents by machine learning","authors":"Yuan Tian , Honghua Zhang , Yueyang Qiao , Han Yang , Yanrong Liu , Xiaoyan Ji","doi":"10.1016/j.cjche.2025.06.006","DOIUrl":"10.1016/j.cjche.2025.06.006","url":null,"abstract":"<div><div>Ionic liquids (ILs) and deep eutectic solvents (DESs) as green solvents have attracted dramatic attention recently due to their highly tunable properties. However, traditional experimental screening methods are inefficient and resource-intensive. The article provides a comprehensive overview of various ML algorithms, including artificial neural network (ANN), support vector machine (SVM), random forest (RF), and gradient boosting trees (GBT), <em>etc.</em>, which have demonstrated exceptional performance in handling complex and high-dimensional data. Furthermore, the integration of ML with quantum chemical calculations and conductor-like screening model-real solvent (COSMO-RS) has significantly enhanced predictive accuracy, enabling the rapid screening and design of novel solvents. Besides, recent ML applications in the prediction and design of ILs and DESs focused on solubility, melting point, electrical conductivity, and other physicochemical properties become more and more. This paper emphasizes the potential of ML in solvent design, overviewing an efficient approach to accelerate the development of sustainable and high-performance materials, providing guidance for their widespread application in a variety of industrial processes.</div></div>","PeriodicalId":9966,"journal":{"name":"Chinese Journal of Chemical Engineering","volume":"84 ","pages":"Pages 227-243"},"PeriodicalIF":3.7,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144852529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Molecular design of high energy density fuels from coal-to-liquids 煤制油高能量密度燃料的分子设计

IF 3.7 3区工程技术

Chinese Journal of Chemical Engineering Pub Date : 2025-08-01 DOI: 10.1016/j.cjche.2025.06.005

Haowei Li , Bingzhu Min , Yaling Gong , Linsheng Li , Xingbao Wang , Yimeng Zhu , Wenying Li

{"title":"Molecular design of high energy density fuels from coal-to-liquids","authors":"Haowei Li , Bingzhu Min , Yaling Gong , Linsheng Li , Xingbao Wang , Yimeng Zhu , Wenying Li","doi":"10.1016/j.cjche.2025.06.005","DOIUrl":"10.1016/j.cjche.2025.06.005","url":null,"abstract":"<div><div>Direct coal liquefaction products offer a considerable quantity of cycloalkanes, which are the valuable candidates for making the high energy density fuels. The creation of such fuels depends on designing molecular structures and calculating their properties, which can be expedited with computer-aided techniques. In this study, a dataset containing 367 fuel molecules was constructed based on the analysis of direct coal liquefied oil. Three convolutional neural network property prediction models have been created based on molecular structure-physical and chemical property data from the library. All the models have good fitting ability with <em>R</em><sup>2</sup> values above 0.97. Then, a variational autoencoder generation model has been established using the molecular structures from the library, focusing on the structure of saturated cycloalkanes. The structure-property prediction model was then applied to the newly generated molecules, assessing their density, volumetric calorific value, and melting point. As a result, 70000 novel molecular structures were generated, and 25 molecular structures meeting the criteria for high energy density fuels were identified. The established variational autoencoder model in this study effectively assimilates the structural information from the sample set and autonomously generates novel high energy density fuels, which is difficult to achieve in traditional experimental methods.</div></div>","PeriodicalId":9966,"journal":{"name":"Chinese Journal of Chemical Engineering","volume":"84 ","pages":"Pages 266-273"},"PeriodicalIF":3.7,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144852456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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-assisted high-throughput computational screening of the n-hexane cracking initiator 机器学习辅助下正己烷裂化引发剂的高通量计算筛选

IF 3.7 3区工程技术

Chinese Journal of Chemical Engineering Pub Date : 2025-08-01 DOI: 10.1016/j.cjche.2025.07.002

Xiaodong Hong , Yudong Shen , Zuwei Liao , Yongrong Yang

引用次数: 0

Prediction of mass transfer performance in gas-liquid stirred bioreactor using machine learning 用机器学习预测气液搅拌生物反应器的传质性能

IF 3.7 3区工程技术

Chinese Journal of Chemical Engineering Pub Date : 2025-08-01 DOI: 10.1016/j.cjche.2025.06.010

Feifei Chen , Zhenyuan Xiao , Zhongfan Luo , Peng Jiang , Jingjing Chen , Yuanhui Ji , Jiahua Zhu , Xiaohua Lu , Liwen Mu

{"title":"Prediction of mass transfer performance in gas-liquid stirred bioreactor using machine learning","authors":"Feifei Chen , Zhenyuan Xiao , Zhongfan Luo , Peng Jiang , Jingjing Chen , Yuanhui Ji , Jiahua Zhu , Xiaohua Lu , Liwen Mu","doi":"10.1016/j.cjche.2025.06.010","DOIUrl":"10.1016/j.cjche.2025.06.010","url":null,"abstract":"<div><div>The structural and operational optimization of gas-liquid stirred bioreactors presents both complexity and critical importance for enhancing mass transfer performance. This study proposes a machine learning (ML)-driven approach to identify key features and predict the volumetric mass transfer coefficient (<em>k</em><sub><em>L</em></sub><em>a</em>). Four ML models were adopted and compared for <em>k</em><sub><em>L</em></sub><em>a</em> prediction in Newtonian and non-Newtonian fluids by evaluative indices, with CatBoost and XGBoost emerging as the optimal models, respectively. Specifically, it is demonstrated that Catboost has higher prediction accuracy (AARD = 18.84%) than empirical equations by effectively incorporating multidimensional features (structural, impeller, and operational), while simultaneously extending applicability to diverse Newtonian fluids. For non-Newtonian fluids, XGBoost outperforms empirical equations by effectively incorporating fluid rheological parameters (consistency coefficient, power-law index), thereby better capturing shear-thinning behavior. Feature importance analysis further identified rotational speed (for Newtonian fluids) and liquid height (for non-Newtonian fluids) as the key features, while 2D partial dependence analysis establishes quantitative optimization ranges. This ML approach provides an efficient predictive tool for gas-liquid stirred bioreactor design and optimization.</div></div>","PeriodicalId":9966,"journal":{"name":"Chinese Journal of Chemical Engineering","volume":"84 ","pages":"Pages 211-226"},"PeriodicalIF":3.7,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144852601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Knowledge graphs in heterogeneous catalysis: Recent advances and future opportunities 多相催化的知识图谱：最近的进展和未来的机会

IF 3.7 3区工程技术

Chinese Journal of Chemical Engineering Pub Date : 2025-08-01 DOI: 10.1016/j.cjche.2025.06.008

Raúl Díaz, Hongliang Xin

{"title":"Knowledge graphs in heterogeneous catalysis: Recent advances and future opportunities","authors":"Raúl Díaz, Hongliang Xin","doi":"10.1016/j.cjche.2025.06.008","DOIUrl":"10.1016/j.cjche.2025.06.008","url":null,"abstract":"<div><div>Knowledge graphs (KGs) offer a structured, machine-readable format for organizing complex information. In heterogeneous catalysis, where data on catalytic materials, reaction conditions, mechanisms, and synthesis routes are dispersed across diverse sources, KGs provide a semantic framework that supports data integration under the FAIR (Findable, Accessible, Interoperable, and Reusable) principles. This review aims to survey recent developments in catalysis KGs, describe the main techniques for graph construction, and highlight how artificial intelligence, particularly large language models (LLMs), enhances graph generation and query. We conducted a systematic analysis of the literature, focusing on ontology-guided text mining pipelines, graph population methods, and maintenance strategies. Our review identifies key trends: ontology-based approaches enable the automated extraction of domain knowledge, LLM-driven retrieval-augmented generation supports natural-language queries, and scalable graph architectures range from a few thousand to over a million triples. We discuss state-of-the-art applications, such as catalyst recommendation systems and reaction mechanism discovery tools, and examine the major challenges, including data heterogeneity, ontology alignment, and long-term graph curation. We conclude that KGs, when combined with AI methods, hold significant promise for accelerating catalyst discovery and knowledge management, but progress depends on establishing community standards for ontology development and maintenance. This review provides a roadmap for researchers seeking to leverage KGs to advance heterogeneous catalysis research.</div></div>","PeriodicalId":9966,"journal":{"name":"Chinese Journal of Chemical Engineering","volume":"84 ","pages":"Pages 179-189"},"PeriodicalIF":3.7,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144814073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Randomized autoregressive dynamic slow feature analysis method for industrial process fault monitoring 工业过程故障监测的随机自回归动态慢特征分析方法

IF 3.7 3区工程技术

Chinese Journal of Chemical Engineering Pub Date : 2025-07-01 DOI: 10.1016/j.cjche.2025.03.006

Qingmin Xu , Peng Li , Aimin Miao , Xun Lang , Hancheng Wang , Chuangyan Yang

{"title":"Randomized autoregressive dynamic slow feature analysis method for industrial process fault monitoring","authors":"Qingmin Xu , Peng Li , Aimin Miao , Xun Lang , Hancheng Wang , Chuangyan Yang","doi":"10.1016/j.cjche.2025.03.006","DOIUrl":"10.1016/j.cjche.2025.03.006","url":null,"abstract":"<div><div>Kernel-based slow feature analysis (SFA) methods have been successfully applied in the industrial process fault detection field. However, kernel-based SFA methods have high computational complexity as dealing with nonlinearity, leading to delays in detecting time-varying data features. Additionally, the uncertain kernel function and kernel parameters limit the ability of the extracted features to express process characteristics, resulting in poor fault detection performance. To alleviate the above problems, a novel randomized auto-regressive dynamic slow feature analysis (RRDSFA) method is proposed to simultaneously monitor the operating point deviations and process dynamic faults, enabling real-time monitoring of data features in industrial processes. Firstly, the proposed Random Fourier mapping-based method achieves more effective nonlinear transformation, contrasting with the current kernel-based RDSFA algorithm that may lead to significant computational complexity. Secondly, a randomized RDSFA model is developed to extract nonlinear dynamic slow features. Furthermore, a Bayesian inference-based overall fault monitoring model including all RRDSFA sub-models is developed to overcome the randomness of random Fourier mapping. Finally, the superiority and effectiveness of the proposed monitoring method are demonstrated through a numerical case and a simulation of continuous stirred tank reactor.</div></div>","PeriodicalId":9966,"journal":{"name":"Chinese Journal of Chemical Engineering","volume":"83 ","pages":"Pages 298-314"},"PeriodicalIF":3.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144665874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Electrochemically reconstructed copper-polypyrrole modified graphite felt electrodes for efficiently electrocatalytic reduction of nitrate 电化学重建铜-聚吡咯改性石墨毡电极的高效电催化还原硝酸盐

IF 3.7 3区工程技术

Chinese Journal of Chemical Engineering Pub Date : 2025-07-01 DOI: 10.1016/j.cjche.2025.04.005

Ge Liu , Jiahong Wang , Zhi Hu , Tianjiao Lu , Hao Zhang , Jie Zhu

{"title":"Electrochemically reconstructed copper-polypyrrole modified graphite felt electrodes for efficiently electrocatalytic reduction of nitrate","authors":"Ge Liu , Jiahong Wang , Zhi Hu , Tianjiao Lu , Hao Zhang , Jie Zhu","doi":"10.1016/j.cjche.2025.04.005","DOIUrl":"10.1016/j.cjche.2025.04.005","url":null,"abstract":"<div><div>In this work, a simple two-step electrodeposition was employed to prepare PPy-Cu/GF (PPy, polypyrrole; GF, graphite felt) composite cathodes for the nitrate reduction. Characterized results revealed that the introduction of PPy as an intermediate layer resulted in the transformation of both granular and dendritic Cu in form of Cu<sup>+</sup>/Cu<sup>0</sup>, Cu<sup>2+</sup> on the electrode surface. The <span><math><mrow><msup><msub><mtext>NO</mtext><mn>3</mn></msub><mo>−</mo></msup></mrow></math></span>-N of 50 mg·L<sup>−1</sup> was almost completely removed (99.01%) using the PPy-Cu/GF cathode under the optimum condition, which is obviously higher than the GF, PPy/GF and Cu/GF electrodes. <span><math><mrow><msup><msub><mtext>NO</mtext><mn>3</mn></msub><mo>−</mo></msup></mrow></math></span>-N removal was slightly affected over the pH scale of 3.0–11.0, whereas increasing the current density from 10 to 25 mA·cm<sup>−2</sup> boosted the reduction of <span><math><mrow><msup><msub><mtext>NO</mtext><mn>3</mn></msub><mo>−</mo></msup></mrow></math></span>-N. At a Cl<sup>−</sup> concentration of 2000 mg·L<sup>−1</sup>, the removal of <span><math><mrow><msup><msub><mtext>NO</mtext><mn>3</mn></msub><mo>−</mo></msup></mrow></math></span>-N was slightly reduced, while the selectivity for N<sub>2</sub> increased dramatically due to the active chlorine could oxidize <span><math><mrow><msup><msub><mtext>NH</mtext><mn>4</mn></msub><mo>+</mo></msup></mrow></math></span>-N to N<sub>2</sub>. Meanwhile, PPy-Cu/GF cathode exhibits an average removal rate of 97.83% within 12 cycles, highlighting its potential for application in actual water bodies. The EPR analysis and the active species trapping experiment confirmed that the nitrate reduction on the PPy-Cu/GF cathode mainly relies on direct reduction mediated by electron transfer, while <sup>∗</sup>H influences the reduction of nitrite to ammonia.</div></div>","PeriodicalId":9966,"journal":{"name":"Chinese Journal of Chemical Engineering","volume":"83 ","pages":"Pages 51-61"},"PeriodicalIF":3.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144571432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Eulerian-Lagrangian simulation of dispersed liquid flow in turbulent stirred tanks 湍流搅拌槽中分散液体流动的欧拉-拉格朗日模拟

IF 3.7 3区工程技术

Chinese Journal of Chemical Engineering Pub Date : 2025-07-01 DOI: 10.1016/j.cjche.2025.03.004

Jingchang Zhang , Xiaoping Guan , Ning Yang , Maximilian Lackner

{"title":"Eulerian-Lagrangian simulation of dispersed liquid flow in turbulent stirred tanks","authors":"Jingchang Zhang , Xiaoping Guan , Ning Yang , Maximilian Lackner","doi":"10.1016/j.cjche.2025.03.004","DOIUrl":"10.1016/j.cjche.2025.03.004","url":null,"abstract":"<div><div>Liquid-liquid dispersion is often performed in stirred tanks, which are valued for their ease of operation, high droplet generation rate and effective droplet dispersion. Many relevant simulations use the Eulerian-Eulerian method, combining population balance equations with statistical models to forecast droplet breakage. Conversely, the Eulerian-Lagrangian (E-L) method provides precise tracking of individual droplets, which is crucial for simulating dispersion processes. However, E-L simulation faces challenges in integrating droplet breakage effectively. To address this issue, our research introduces a probabilistic approach for droplet breakages. It assumes that a longer time increases the likelihood of breakup; a droplet breaks if the calculated probability exceeds a random value from 0 to 1. Consequently, the simulated breakage frequency becomes independent of the Lagrangian time step. The Sauter mean diameter and droplet size distribution can be accurately predicted by this probabilistic approach. By closely monitoring droplet motion, we reveal the complexity of droplet trajectories and the detailed patterns of circulation in stirred tanks. These insights contribute to a deeper understanding of liquid-liquid dispersion dynamics.</div></div>","PeriodicalId":9966,"journal":{"name":"Chinese Journal of Chemical Engineering","volume":"83 ","pages":"Pages 182-190"},"PeriodicalIF":3.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144605239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Combined micromixing and coalescence separation for improved oil desulfurization 微混合与聚结分离相结合改善石油脱硫

IF 3.7 3区工程技术

Chinese Journal of Chemical Engineering Pub Date : 2025-07-01 DOI: 10.1016/j.cjche.2025.02.019

Yaohua Huang, Huatong Zhu, Heping Wu, Lele Zhang, Hao Lu, Qiang Yang

引用次数: 0

Synergetic mechanism between corn stalk biochar and coal pulping in coal-water slurry 玉米秸秆生物炭与水煤浆制浆的协同作用机理

IF 3.7 3区工程技术

Chinese Journal of Chemical Engineering Pub Date : 2025-07-01 DOI: 10.1016/j.cjche.2025.03.011

Gaohan Li , Lirui Mao , Ling Zhang, Qiaoli Wu, Hanxu Li

{"title":"Synergetic mechanism between corn stalk biochar and coal pulping in coal-water slurry","authors":"Gaohan Li , Lirui Mao , Ling Zhang, Qiaoli Wu, Hanxu Li","doi":"10.1016/j.cjche.2025.03.011","DOIUrl":"10.1016/j.cjche.2025.03.011","url":null,"abstract":"<div><div>The multipath application of green resources needs to be realised under the carbon neutrality goal. Worldwide, biomass is a resource in urgent need of treatment. In this paper, corn stover biomass (YM) or biochar with different particle sizes (YMF or YMX) was added during the preparation of coal-water slurry to investigate its effect on the performance of coal-water slurry and the micro-mechanism. The results showed that the fixed viscosity concentration of coal-water slurry (CYWS) with YM was only 47.42%, and the flowability was 49.9 mm, which made the slurry performance poor. The fixed viscosity concentration of coal-water slurry (CFWS) blended with YMF and coal-water slurry (CXWS) blended with YMX increased by 10.41% and 14.24%, respectively, compared with CYWS. Meanwhile, CXWS had the lowest thixotropy and yield stress, with a yield stress of only 16.13 Pa, which was 77.31 Pa lower than that of CYWS. This indicates that YMX treated by charring and milling is more favorable to be blended with coal to prepare coal-water slurry. This is due to the enhanced hydrophilicity and electronegativity of YMX. The enhanced hydrophilicity reduces the tendency to form three-dimensional networks in coal-water slurry, while the enhanced electronegativity improves the electrostatic repulsion between particles, which is beneficial to the dispersion of particles. In the subsequent EDLVO analyses, the same idea was proved.</div></div>","PeriodicalId":9966,"journal":{"name":"Chinese Journal of Chemical Engineering","volume":"83 ","pages":"Pages 1-14"},"PeriodicalIF":3.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144514423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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