首页 > 最新文献

Engineering最新文献

英文 中文
Promising Results Predict Role for Artificial Intelligence in Weather Forecasting 有希望的结果预示人工智能在天气预报中的作用
IF 10.1 1区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-08-01 DOI: 10.1016/j.eng.2024.07.003
{"title":"Promising Results Predict Role for Artificial Intelligence in Weather Forecasting","authors":"","doi":"10.1016/j.eng.2024.07.003","DOIUrl":"10.1016/j.eng.2024.07.003","url":null,"abstract":"","PeriodicalId":11783,"journal":{"name":"Engineering","volume":null,"pages":null},"PeriodicalIF":10.1,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2095809924003916/pdfft?md5=4f48c46bfc5553e5c413642a973dd516&pid=1-s2.0-S2095809924003916-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141849548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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
Repurposing Loperamide as an Anti-Infection Drug for the Treatment of Intracellular Bacterial Pathogens 将洛哌丁胺重新用作治疗细胞内细菌病原体的抗感染药物
IF 10.1 1区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-08-01 DOI: 10.1016/j.eng.2024.01.011

Infections caused by intracellular bacterial pathogens are difficult to treat since most antibiotics have low cell permeability and undergo rapid degradation within cells. The rapid development and dissemination of antimicrobial–resistant strains have exacerbated this dilemma. With the increasing knowledge of host–pathogen interactions, especially bacterial strategies for survival and proliferation within host cells, host-directed therapy (HDT) has attracted increased interest and has emerged as a promising anti-infection method for treating intracellular infection. Herein, we applied a cell-based screening approach to a US Food and Drug Administration (FDA)-approved drug library to identify compounds that can inhibit the intracellular replication of Salmonella Typhimurium (S. Typhimurium). This screening allowed us to identify the antidiarrheal agent loperamide (LPD) as a potent inhibitor of S. Typhimurium intracellular proliferation. LPD treatment of infected cells markedly promoted the host autophagic response and lysosomal activity. A mechanistic study revealed that the increase in host autophagy and elimination of intracellular bacteria were dependent on the high expression of glycoprotein nonmetastatic melanoma protein B (GPNMB) induced by LPD. In addition, LPD treatment effectively protected against S. Typhimurium infection in Galleria mellonella and mouse models. Thus, our study suggested that LPD may be useful for the treatment of diseases caused by intracellular bacterial pathogens. Moreover, LPD may serve as a promising lead compound for the development of anti-infection drugs based on the HDT strategy.

细胞内细菌病原体引起的感染很难治疗,因为大多数抗生素的细胞渗透性较低,在细胞内会迅速降解。抗生素耐药菌株的快速发展和传播加剧了这一困境。随着人们对宿主与病原体之间相互作用的了解不断加深,尤其是细菌在宿主细胞内的生存和增殖策略,宿主导向疗法(HDT)引起了越来越多的关注,并已成为治疗细胞内感染的一种很有前景的抗感染方法。在本文中,我们将基于细胞的筛选方法应用于美国食品药品管理局(FDA)批准的药物库,以确定可抑制鼠伤寒沙门氏菌(S. Typhimurium)细胞内复制的化合物。通过这次筛选,我们发现止泻药洛哌丁胺(LPD)是鼠伤寒沙门氏菌细胞内增殖的有效抑制剂。对感染细胞进行 LPD 处理可显著促进宿主的自噬反应和溶酶体活性。一项机理研究发现,宿主自噬反应的增强和细胞内细菌的清除依赖于LPD诱导的糖蛋白非转移性黑色素瘤蛋白B(GPNMB)的高表达。此外,LPD 还能有效防止鼠伤寒杆菌感染。因此,我们的研究表明,LPD 可用于治疗由细胞内细菌病原体引起的疾病。此外,LPD 可能是基于 HDT 策略开发抗感染药物的一种有前途的先导化合物。
{"title":"Repurposing Loperamide as an Anti-Infection Drug for the Treatment of Intracellular Bacterial Pathogens","authors":"","doi":"10.1016/j.eng.2024.01.011","DOIUrl":"10.1016/j.eng.2024.01.011","url":null,"abstract":"<div><p>Infections caused by intracellular bacterial pathogens are difficult to treat since most antibiotics have low cell permeability and undergo rapid degradation within cells. The rapid development and dissemination of antimicrobial–resistant strains have exacerbated this dilemma. With the increasing knowledge of host–pathogen interactions, especially bacterial strategies for survival and proliferation within host cells, host-directed therapy (HDT) has attracted increased interest and has emerged as a promising anti-infection method for treating intracellular infection. Herein, we applied a cell-based screening approach to a US Food and Drug Administration (FDA)-approved drug library to identify compounds that can inhibit the intracellular replication of <em>Salmonella</em> Typhimurium (<em>S.</em> Typhimurium). This screening allowed us to identify the antidiarrheal agent loperamide (LPD) as a potent inhibitor of <em>S.</em> Typhimurium intracellular proliferation. LPD treatment of infected cells markedly promoted the host autophagic response and lysosomal activity. A mechanistic study revealed that the increase in host autophagy and elimination of intracellular bacteria were dependent on the high expression of glycoprotein nonmetastatic melanoma protein B (GPNMB) induced by LPD. In addition, LPD treatment effectively protected against <em>S.</em> Typhimurium infection in <em>Galleria mellonella</em> and mouse models. Thus, our study suggested that LPD may be useful for the treatment of diseases caused by intracellular bacterial pathogens. Moreover, LPD may serve as a promising lead compound for the development of anti-infection drugs based on the HDT strategy.</p></div>","PeriodicalId":11783,"journal":{"name":"Engineering","volume":null,"pages":null},"PeriodicalIF":10.1,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2095809924000560/pdfft?md5=48c4a988b7dc1a14f7297b53c1717076&pid=1-s2.0-S2095809924000560-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139876826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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
Porous-DeepONet: Learning the Solution Operators of Parametric Reactive Transport Equations in Porous Media Porous-DeepONet:学习多孔介质中参数反应传输方程的求解算子
IF 10.1 1区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-08-01 DOI: 10.1016/j.eng.2024.07.002

Reactive transport equations in porous media are critical in various scientific and engineering disciplines, but solving these equations can be computationally expensive when exploring different scenarios, such as varying porous structures and initial or boundary conditions. The deep operator network (DeepONet) has emerged as a popular deep learning framework for solving parametric partial differential equations. However, applying the DeepONet to porous media presents significant challenges due to its limited capability to extract representative features from intricate structures. To address this issue, we propose the Porous-DeepONet, a simple yet highly effective extension of the DeepONet framework that leverages convolutional neural networks (CNNs) to learn the solution operators of parametric reactive transport equations in porous media. By incorporating CNNs, we can effectively capture the intricate features of porous media, enabling accurate and efficient learning of the solution operators. We demonstrate the effectiveness of the Porous-DeepONet in accurately and rapidly learning the solution operators of parametric reactive transport equations with various boundary conditions, multiple phases, and multi-physical fields through five examples. This approach offers significant computational savings, potentially reducing the computation time by 50–1000 times compared with the finite-element method. Our work may provide a robust alternative for solving parametric reactive transport equations in porous media, paving the way for exploring complex phenomena in porous media.

多孔介质中的反应输运方程在各种科学和工程学科中都至关重要,但在探索不同场景(如改变多孔结构和初始或边界条件)时,求解这些方程的计算成本可能会很高。深度算子网络(DeepONet)已成为解决参数偏微分方程的流行深度学习框架。然而,由于 DeepONet 从错综复杂的结构中提取代表性特征的能力有限,因此将其应用于多孔介质面临巨大挑战。为了解决这个问题,我们提出了多孔-深度网络(Porous-DeepONet),它是 DeepONet 框架的一个简单而高效的扩展,利用卷积神经网络(CNN)来学习多孔介质中参数反应传输方程的解算子。通过结合 CNN,我们可以有效捕捉多孔介质的复杂特征,从而准确、高效地学习解算子。我们通过五个例子展示了 Porous-DeepONet 在准确、快速地学习具有各种边界条件、多相和多物理场的参数反应传输方程的解算子方面的有效性。与有限元方法相比,这种方法大大节省了计算时间,有可能将计算时间缩短 50-1000 倍。我们的工作为解决多孔介质中的参数反应输运方程提供了一种稳健的替代方法,为探索多孔介质中的复杂现象铺平了道路。
{"title":"Porous-DeepONet: Learning the Solution Operators of Parametric Reactive Transport Equations in Porous Media","authors":"","doi":"10.1016/j.eng.2024.07.002","DOIUrl":"10.1016/j.eng.2024.07.002","url":null,"abstract":"<div><p>Reactive transport equations in porous media are critical in various scientific and engineering disciplines, but solving these equations can be computationally expensive when exploring different scenarios, such as varying porous structures and initial or boundary conditions. The deep operator network (DeepONet) has emerged as a popular deep learning framework for solving parametric partial differential equations. However, applying the DeepONet to porous media presents significant challenges due to its limited capability to extract representative features from intricate structures. To address this issue, we propose the Porous-DeepONet, a simple yet highly effective extension of the DeepONet framework that leverages convolutional neural networks (CNNs) to learn the solution operators of parametric reactive transport equations in porous media. By incorporating CNNs, we can effectively capture the intricate features of porous media, enabling accurate and efficient learning of the solution operators. We demonstrate the effectiveness of the Porous-DeepONet in accurately and rapidly learning the solution operators of parametric reactive transport equations with various boundary conditions, multiple phases, and multi-physical fields through five examples. This approach offers significant computational savings, potentially reducing the computation time by 50–1000 times compared with the finite-element method. Our work may provide a robust alternative for solving parametric reactive transport equations in porous media, paving the way for exploring complex phenomena in porous media.</p></div>","PeriodicalId":11783,"journal":{"name":"Engineering","volume":null,"pages":null},"PeriodicalIF":10.1,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2095809924003904/pdfft?md5=87f14902089ff32a74087b166ecdf4be&pid=1-s2.0-S2095809924003904-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141841628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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
Generative AI for Materials Discovery: Design Without Understanding 用于材料发现的生成式人工智能:无需理解的设计
IF 10.1 1区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-08-01 DOI: 10.1016/j.eng.2024.07.008
{"title":"Generative AI for Materials Discovery: Design Without Understanding","authors":"","doi":"10.1016/j.eng.2024.07.008","DOIUrl":"10.1016/j.eng.2024.07.008","url":null,"abstract":"","PeriodicalId":11783,"journal":{"name":"Engineering","volume":null,"pages":null},"PeriodicalIF":10.1,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2095809924003977/pdfft?md5=0fdf24fb9b2d54ffd13f62c3e30d792d&pid=1-s2.0-S2095809924003977-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141776936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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
Unprecedented Collaboration Plots Largest, Most Detailed Maps of the Brain 史无前例的合作绘制出最大、最详细的大脑地图
IF 10.1 1区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-08-01 DOI: 10.1016/j.eng.2024.07.004
{"title":"Unprecedented Collaboration Plots Largest, Most Detailed Maps of the Brain","authors":"","doi":"10.1016/j.eng.2024.07.004","DOIUrl":"10.1016/j.eng.2024.07.004","url":null,"abstract":"","PeriodicalId":11783,"journal":{"name":"Engineering","volume":null,"pages":null},"PeriodicalIF":10.1,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2095809924003928/pdfft?md5=be589efd905b42e4ed52c698aa918ee3&pid=1-s2.0-S2095809924003928-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141841478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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
An Improved Machine Learning Model for Pure Component Property Estimation 用于纯组件特性估计的改进型机器学习模型
IF 10.1 1区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-08-01 DOI: 10.1016/j.eng.2023.08.024

Information on the physicochemical properties of chemical species is an important prerequisite when performing tasks such as process design and product design. However, the lack of extensive data and high experimental costs hinder the development of prediction techniques for these properties. Moreover, accuracy and predictive capabilities still limit the scope and applicability of most property estimation methods. This paper proposes a new Gaussian process-based modeling framework that aims to manage a discrete and high-dimensional input space related to molecular structure representation with the group-contribution approach. A warping function is used to map discrete input into a continuous domain in order to adjust the correlation between different compounds. Prior selection techniques, including prior elicitation and prior predictive checking, are also applied during the building procedure to provide the model with more information from previous research findings. The framework is assessed using datasets of varying sizes for 20 pure component properties. For 18 out of the 20 pure component properties, the new models are found to give improved accuracy and predictive power in comparison with other published models, with and without machine learning.

在进行工艺设计和产品设计等工作时,有关化学物质理化性质的信息是一个重要的先决条件。然而,大量数据的缺乏和高昂的实验成本阻碍了这些性质预测技术的发展。此外,准确性和预测能力仍然限制了大多数性质估计方法的范围和适用性。本文提出了一种新的基于高斯过程的建模框架,旨在利用组贡献方法管理与分子结构表征相关的离散高维输入空间。使用扭曲函数将离散输入映射到连续域,以调整不同化合物之间的相关性。在构建过程中,还应用了先验选择技术,包括先验激发和先验预测检查,以便从先前的研究成果中为模型提供更多信息。该框架使用不同规模的数据集对 20 种纯成分特性进行了评估。在 20 个纯组件属性中的 18 个属性中,与其他已发布的模型相比,无论是否使用机器学习,新模型的准确性和预测能力都有所提高。
{"title":"An Improved Machine Learning Model for Pure Component Property Estimation","authors":"","doi":"10.1016/j.eng.2023.08.024","DOIUrl":"10.1016/j.eng.2023.08.024","url":null,"abstract":"<div><p>Information on the physicochemical properties of chemical species is an important prerequisite when performing tasks such as process design and product design. However, the lack of extensive data and high experimental costs hinder the development of prediction techniques for these properties. Moreover, accuracy and predictive capabilities still limit the scope and applicability of most property estimation methods. This paper proposes a new Gaussian process-based modeling framework that aims to manage a discrete and high-dimensional input space related to molecular structure representation with the group-contribution approach. A warping function is used to map discrete input into a continuous domain in order to adjust the correlation between different compounds. Prior selection techniques, including prior elicitation and prior predictive checking, are also applied during the building procedure to provide the model with more information from previous research findings. The framework is assessed using datasets of varying sizes for 20 pure component properties. For 18 out of the 20 pure component properties, the new models are found to give improved accuracy and predictive power in comparison with other published models, with and without machine learning.</p></div>","PeriodicalId":11783,"journal":{"name":"Engineering","volume":null,"pages":null},"PeriodicalIF":10.1,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2095809924001590/pdfft?md5=1467de2f6cb3888be2501c5f8217cd9b&pid=1-s2.0-S2095809924001590-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141948978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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
AI in Chemical Engineering: A New Chapter of Innovation 化学工程中的人工智能:创新的新篇章
IF 10.1 1区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-08-01 DOI: 10.1016/j.eng.2024.07.006
{"title":"AI in Chemical Engineering: A New Chapter of Innovation","authors":"","doi":"10.1016/j.eng.2024.07.006","DOIUrl":"10.1016/j.eng.2024.07.006","url":null,"abstract":"","PeriodicalId":11783,"journal":{"name":"Engineering","volume":null,"pages":null},"PeriodicalIF":10.1,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2095809924003941/pdfft?md5=6021d4c6ed6be7e338d3df21bc4cbe5b&pid=1-s2.0-S2095809924003941-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141841706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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
Multi-Pollutant Formation and Control in Pressurized Oxy-Combustion: SOx, NOx, Particulate Matter, and Mercury 加压富氧燃烧中多种污染物的形成与控制:二氧化硫、氮氧化物、颗粒物和汞
IF 10.1 1区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-08-01 DOI: 10.1016/j.eng.2024.03.005

Oxy-combustion is a promising carbon-capture technology, but atmospheric-pressure oxy-combustion has a relatively low net efficiency, limiting its application in power plants. In pressurized oxy-combustion (POC), the boiler, air separation unit, flue gas recirculation unit, and CO2 purification and compression unit are all operated at elevated pressure; this makes the process more efficient, with many advantages over atmospheric pressure, such as low NOx emissions, a smaller boiler size, and more. POC is also more promising for industrial application and has attracted widespread research interest in recent years. It can produce high-pressure CO2 with a purity of approximately 95%, which can be used directly for enhanced oil recovery or geo-sequestration. However, the pollutant emissions must meet the standards for carbon capture, storage, and utilization. Because of the high oxygen and moisture concentrations in POC, the formation of acids via the oxidation and solution of SOx and NOx can be increased, causing the corrosion of pipelines and equipment. Furthermore, particulate matter (PM) and mercury emissions can harm the environment and human health. The main distinction between pressurized and atmospheric-pressure oxy-combustion is the former’s elevated pressure; thus, the effect of this pressure on the pollutants emitted from POC—including SOx, NOx, PM, and mercury—must be understood, and effective control methodologies must be incorporated to control the formation of these pollutants. This paper reviews recent advances in research on SOx, NOx, PM, and mercury formation and control in POC systems that can aid in pollutant control in such systems.

全氧燃烧是一种前景广阔的碳捕集技术,但常压全氧燃烧的净效率相对较低,限制了其在发电厂中的应用。在加压全氧燃烧(POC)中,锅炉、空气分离装置、烟气再循环装置以及二氧化碳净化和压缩装置均在高压下运行;这使得该过程更加高效,与常压相比具有许多优势,如氮氧化物排放量低、锅炉体积小等。POC 在工业应用方面也更有前景,近年来引起了广泛的研究兴趣。它可以产生纯度约为 95% 的高压二氧化碳,可直接用于提高石油采收率或地质封存。但是,污染物排放必须符合碳捕获、封存和利用的标准。由于 POC 中的氧气和水分浓度较高,通过 SOx 和 NOx 的氧化和溶解形成的酸会增加,导致管道和设备腐蚀。此外,颗粒物质(PM)和汞排放也会危害环境和人类健康。加压全氧燃烧与常压全氧燃烧的主要区别在于前者的压力较高;因此,必须了解这种压力对 POC 排放的污染物(包括 SOx、NOx、PM 和汞)的影响,并采用有效的控制方法来控制这些污染物的形成。本文回顾了有关 POC 系统中硫氧化物、氮氧化物、可吸入颗粒物和汞的形成与控制的最新研究进展,这些研究进展有助于此类系统中的污染物控制。
{"title":"Multi-Pollutant Formation and Control in Pressurized Oxy-Combustion: SOx, NOx, Particulate Matter, and Mercury","authors":"","doi":"10.1016/j.eng.2024.03.005","DOIUrl":"10.1016/j.eng.2024.03.005","url":null,"abstract":"<div><p>Oxy-combustion is a promising carbon-capture technology, but atmospheric-pressure oxy-combustion has a relatively low net efficiency, limiting its application in power plants. In pressurized oxy-combustion (POC), the boiler, air separation unit, flue gas recirculation unit, and CO<sub>2</sub> purification and compression unit are all operated at elevated pressure; this makes the process more efficient, with many advantages over atmospheric pressure, such as low NO<em><sub>x</sub></em> emissions, a smaller boiler size, and more. POC is also more promising for industrial application and has attracted widespread research interest in recent years. It can produce high-pressure CO<sub>2</sub> with a purity of approximately 95%, which can be used directly for enhanced oil recovery or geo-sequestration. However, the pollutant emissions must meet the standards for carbon capture, storage, and utilization. Because of the high oxygen and moisture concentrations in POC, the formation of acids via the oxidation and solution of SO<em><sub>x</sub></em> and NO<em><sub>x</sub></em> can be increased, causing the corrosion of pipelines and equipment. Furthermore, particulate matter (PM) and mercury emissions can harm the environment and human health. The main distinction between pressurized and atmospheric-pressure oxy-combustion is the former’s elevated pressure; thus, the effect of this pressure on the pollutants emitted from POC—including SO<em><sub>x</sub></em>, NO<em><sub>x</sub></em>, PM, and mercury—must be understood, and effective control methodologies must be incorporated to control the formation of these pollutants. This paper reviews recent advances in research on SO<em><sub>x</sub></em>, NO<em><sub>x</sub></em>, PM, and mercury formation and control in POC systems that can aid in pollutant control in such systems.</p></div>","PeriodicalId":11783,"journal":{"name":"Engineering","volume":null,"pages":null},"PeriodicalIF":10.1,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2095809924001462/pdfft?md5=871940dc290f2f67d26d0a3b1ddbb10e&pid=1-s2.0-S2095809924001462-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140401392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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
An Interpretable Light Attention–Convolution–Gate Recurrent Unit Architecture for the Highly Accurate Modeling of Actual Chemical Dynamic Processes 用于高精度模拟实际化学动态过程的可解释光注意-卷积-门递归单元结构
IF 10.1 1区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-08-01 DOI: 10.1016/j.eng.2024.07.009

To equip data-driven dynamic chemical process models with strong interpretability, we develop a light attention–convolution–gate recurrent unit (LACG) architecture with three sub-modules—a basic module, a brand-new light attention module, and a residue module—that are specially designed to learn the general dynamic behavior, transient disturbances, and other input factors of chemical processes, respectively. Combined with a hyperparameter optimization framework, Optuna, the effectiveness of the proposed LACG is tested by distributed control system data-driven modeling experiments on the discharge flowrate of an actual deethanization process. The LACG model provides significant advantages in prediction accuracy and model generalization compared with other models, including the feedforward neural network, convolution neural network, long short-term memory (LSTM), and attention-LSTM. Moreover, compared with the simulation results of a deethanization model built using Aspen Plus Dynamics V12.1, the LACG parameters are demonstrated to be interpretable, and more details on the variable interactions can be observed from the model parameters in comparison with the traditional interpretable model attention-LSTM. This contribution enriches interpretable machine learning knowledge and provides a reliable method with high accuracy for actual chemical process modeling, paving a route to intelligent manufacturing.

为了使数据驱动的动态化学过程模型具有较强的可解释性,我们开发了一种轻注意力-卷积-门递归单元(LACG)架构,其中包含三个子模块--基本模块、全新的轻注意力模块和残差模块--它们是专门为学习化学过程的一般动态行为、瞬态干扰和其他输入因素而设计的。结合超参数优化框架 Optuna,通过对实际脱乙烷过程的排放流量进行分布式控制系统数据驱动建模实验,检验了所提出的 LACG 的有效性。与其他模型(包括前馈神经网络、卷积神经网络、长短期记忆(LSTM)和注意力-LSTM)相比,LACG 模型在预测精度和模型泛化方面具有显著优势。此外,与使用 Aspen Plus Dynamics V12.1 建立的去乙烷化模型的仿真结果相比,LACG 参数被证明是可解释的,与传统的可解释模型 attention-LSTM 相比,从模型参数中可以观察到更多变量交互的细节。这一贡献丰富了可解释机器学习知识,为实际化学过程建模提供了一种高精度的可靠方法,为智能制造铺平了道路。
{"title":"An Interpretable Light Attention–Convolution–Gate Recurrent Unit Architecture for the Highly Accurate Modeling of Actual Chemical Dynamic Processes","authors":"","doi":"10.1016/j.eng.2024.07.009","DOIUrl":"10.1016/j.eng.2024.07.009","url":null,"abstract":"<div><p>To equip data-driven dynamic chemical process models with strong interpretability, we develop a light attention–convolution–gate recurrent unit (LACG) architecture with three sub-modules—a basic module, a brand-new light attention module, and a residue module—that are specially designed to learn the general dynamic behavior, transient disturbances, and other input factors of chemical processes, respectively. Combined with a hyperparameter optimization framework, Optuna, the effectiveness of the proposed LACG is tested by distributed control system data-driven modeling experiments on the discharge flowrate of an actual deethanization process. The LACG model provides significant advantages in prediction accuracy and model generalization compared with other models, including the feedforward neural network, convolution neural network, long short-term memory (LSTM), and attention-LSTM. Moreover, compared with the simulation results of a deethanization model built using Aspen Plus Dynamics V12.1, the LACG parameters are demonstrated to be interpretable, and more details on the variable interactions can be observed from the model parameters in comparison with the traditional interpretable model attention-LSTM. This contribution enriches interpretable machine learning knowledge and provides a reliable method with high accuracy for actual chemical process modeling, paving a route to intelligent manufacturing.</p></div>","PeriodicalId":11783,"journal":{"name":"Engineering","volume":null,"pages":null},"PeriodicalIF":10.1,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2095809924003989/pdfft?md5=8a3c739a3b730516d835f58e0c61ebce&pid=1-s2.0-S2095809924003989-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141776937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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
Toward Next-Generation Heterogeneous Catalysts: Empowering Surface Reactivity Prediction with Machine Learning 迈向下一代异质催化剂:利用机器学习增强表面反应预测能力
IF 10.1 1区 工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY Pub Date : 2024-08-01 DOI: 10.1016/j.eng.2023.07.021

Heterogeneous catalysis remains at the core of various bulk chemical manufacturing and energy conversion processes, and its revolution necessitates the hunt for new materials with ideal catalytic activities and economic feasibility. Computational high-throughput screening presents a viable solution to this challenge, as machine learning (ML) has demonstrated its great potential in accelerating such processes by providing satisfactory estimations of surface reactivity with relatively low-cost information. This review focuses on recent progress in applying ML in adsorption energy prediction, which predominantly quantifies the catalytic potential of a solid catalyst. ML models that leverage inputs from different categories and exhibit various levels of complexity are classified and discussed. At the end of the review, an outlook on the current challenges and future opportunities of ML-assisted catalyst screening is supplied. We believe that this review summarizes major achievements in accelerating catalyst discovery through ML and can inspire researchers to further devise novel strategies to accelerate materials design and, ultimately, reshape the chemical industry and energy landscape.

异相催化仍然是各种大宗化学品生产和能源转换过程的核心,其变革要求我们寻找具有理想催化活性和经济可行性的新材料。计算高通量筛选为这一挑战提供了可行的解决方案,因为机器学习(ML)通过相对低成本的信息提供令人满意的表面反应性估计,在加速此类过程方面展现出巨大的潜力。本综述将重点介绍将 ML 应用于吸附能预测的最新进展,吸附能预测主要量化固体催化剂的催化潜力。本文对利用不同类别输入并表现出不同复杂程度的 ML 模型进行了分类和讨论。在综述的最后,还对 ML 辅助催化剂筛选当前面临的挑战和未来的机遇进行了展望。我们相信,这篇综述总结了通过 ML 加速催化剂发现的主要成就,并能激励研究人员进一步设计新颖的战略,以加速材料设计,最终重塑化学工业和能源格局。
{"title":"Toward Next-Generation Heterogeneous Catalysts: Empowering Surface Reactivity Prediction with Machine Learning","authors":"","doi":"10.1016/j.eng.2023.07.021","DOIUrl":"10.1016/j.eng.2023.07.021","url":null,"abstract":"<div><p>Heterogeneous catalysis remains at the core of various bulk chemical manufacturing and energy conversion processes, and its revolution necessitates the hunt for new materials with ideal catalytic activities and economic feasibility. Computational high-throughput screening presents a viable solution to this challenge, as machine learning (ML) has demonstrated its great potential in accelerating such processes by providing satisfactory estimations of surface reactivity with relatively low-cost information. This review focuses on recent progress in applying ML in adsorption energy prediction, which predominantly quantifies the catalytic potential of a solid catalyst. ML models that leverage inputs from different categories and exhibit various levels of complexity are classified and discussed. At the end of the review, an outlook on the current challenges and future opportunities of ML-assisted catalyst screening is supplied. We believe that this review summarizes major achievements in accelerating catalyst discovery through ML and can inspire researchers to further devise novel strategies to accelerate materials design and, ultimately, reshape the chemical industry and energy landscape.</p></div>","PeriodicalId":11783,"journal":{"name":"Engineering","volume":null,"pages":null},"PeriodicalIF":10.1,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2095809924000225/pdfft?md5=9722d6140698f5ace718ab1ce8657ad7&pid=1-s2.0-S2095809924000225-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139112230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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
期刊
Engineering
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1