Engineering最新文献

{"title":"A Mathematical Formulation of AGI in the (C, U, V) Framework","authors":"Di He, Cong Fang, Yisen Wang, Yujia Peng, Yizhou Wang, Song-Chun Zhu","doi":"10.1016/j.eng.2025.08.034","DOIUrl":"https://doi.org/10.1016/j.eng.2025.08.034","url":null,"abstract":"This article seeks to explore a general formulation of artificial general intelligence (AGI) under a unified framework that defines AGI agents as points in a joint (<span><span style=\"\"></span><span data-mathml='&lt;math xmlns=\"http://www.w3.org/1998/Math/MathML\"&gt;&lt;mrow is=\"true\"&gt;&lt;mi is=\"true\"&gt;C&lt;/mi&gt;&lt;mo is=\"true\"&gt;,&lt;/mo&gt;&lt;mi is=\"true\"&gt;U&lt;/mi&gt;&lt;mo is=\"true\"&gt;,&lt;/mo&gt;&lt;mi is=\"true\"&gt;V&lt;/mi&gt;&lt;/mrow&gt;&lt;/math&gt;' role=\"presentation\" style=\"font-size: 90%; display: inline-block; position: relative;\" tabindex=\"0\"><svg aria-hidden=\"true\" focusable=\"false\" height=\"2.432ex\" role=\"img\" style=\"vertical-align: -0.582ex;\" viewbox=\"0 -796.9 3187.8 1047.3\" width=\"7.404ex\" xmlns:xlink=\"http://www.w3.org/1999/xlink\"><g fill=\"currentColor\" stroke=\"currentColor\" stroke-width=\"0\" transform=\"matrix(1 0 0 -1 0 0)\"><g is=\"true\"><g is=\"true\"><use xlink:href=\"#MJMATHI-43\"></use></g><g is=\"true\" transform=\"translate(760,0)\"><use xlink:href=\"#MJMAIN-2C\"></use></g><g is=\"true\" transform=\"translate(1205,0)\"><use xlink:href=\"#MJMATHI-55\"></use></g><g is=\"true\" transform=\"translate(1973,0)\"><use xlink:href=\"#MJMAIN-2C\"></use></g><g is=\"true\" transform=\"translate(2418,0)\"><use xlink:href=\"#MJMATHI-56\"></use></g></g></g></svg><span role=\"presentation\"><math xmlns=\"http://www.w3.org/1998/Math/MathML\"><mrow is=\"true\"><mi is=\"true\">C</mi><mo is=\"true\">,</mo><mi is=\"true\">U</mi><mo is=\"true\">,</mo><mi is=\"true\">V</mi></mrow></math></span></span><script type=\"math/mml\"><math><mrow is=\"true\"><mi is=\"true\">C</mi><mo is=\"true\">,</mo><mi is=\"true\">U</mi><mo is=\"true\">,</mo><mi is=\"true\">V</mi></mrow></math></script></span>) space. An agent is characterized by three components: ① a cognitive architecture <span><span style=\"\"></span><span data-mathml='&lt;math xmlns=\"http://www.w3.org/1998/Math/MathML\"&gt;&lt;mrow is=\"true\"&gt;&lt;mi is=\"true\"&gt;C&lt;/mi&gt;&lt;mo is=\"true\"&gt;,&lt;/mo&gt;&lt;/mrow&gt;&lt;/math&gt;' role=\"presentation\" style=\"font-size: 90%; display: inline-block; position: relative;\" tabindex=\"0\"><svg aria-hidden=\"true\" focusable=\"false\" height=\"2.432ex\" role=\"img\" style=\"vertical-align: -0.582ex;\" viewbox=\"0 -796.9 1039 1047.3\" width=\"2.413ex\" xmlns:xlink=\"http://www.w3.org/1999/xlink\"><g fill=\"currentColor\" stroke=\"currentColor\" stroke-width=\"0\" transform=\"matrix(1 0 0 -1 0 0)\"><g is=\"true\"><g is=\"true\"><use xlink:href=\"#MJMATHI-43\"></use></g><g is=\"true\" transform=\"translate(760,0)\"><use xlink:href=\"#MJMAIN-2C\"></use></g></g></g></svg><span role=\"presentation\"><math xmlns=\"http://www.w3.org/1998/Math/MathML\"><mrow is=\"true\"><mi is=\"true\">C</mi><mo is=\"true\">,</mo></mrow></math></span></span><script type=\"math/mml\"><math><mrow is=\"true\"><mi is=\"true\">C</mi><mo is=\"true\">,</mo></mrow></math></script></span> which represents the modules (mathematical functions) inside the agent’s mind, as well as the connections and communication protocols between these modules, including the theory of mind (ToM); ② a set of","PeriodicalId":11783,"journal":{"name":"Engineering","volume":"19 1","pages":""},"PeriodicalIF":12.8,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144987647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ion Transport Mechanisms in Janus Nanofiltration Membranes with Asymmetric Charge Distribution: Quantitative Analysis of Electromigration Effects Driven by Charge Gradients","authors":"Yu-Xuan Sun, Zhen-Yuan Wang, Liu-Yong Zhao, Rui-Hao Liu, Wu-Cong Wang, Mei-Ling Liu, Shi-Peng Sun, Weihong Xing","doi":"10.1016/j.eng.2025.08.035","DOIUrl":"https://doi.org/10.1016/j.eng.2025.08.035","url":null,"abstract":"Rising freshwater scarcity in arid regions requires advanced desalination and resource recovery technologies to address brackish water threats to agriculture, drinking water, and ecosystems. Charge-asymmetric Janus nanofiltration (NF) membranes demonstrate significant potential for resource recovery in brackish water treatment, particularly enabling efficient ion-selective separation. However, current models remain limited to qualitative speculation regarding the ion transport mechanisms in Janus membranes, as they fail to incorporate quantitative descriptions of axial charge heterogeneity. Herein, we address this gap by integrating axial charge distribution into the Donnan Steric Pore Model with Dielectric Exclusion (DSPM-DE). A charge-asymmetric Janus membrane (R90-AC) was fabricated by coating a positively charged polyelectrolyte layer onto a commercial NF membrane (R90-SC). The axial-charge-distributed DSPM-DE model reduced prediction deviations for six ions in brackish water systems to &lt; 8%, outperforming conventional models (deviations &gt; 16%). Theoretical simulations revealed an intrinsic electric field (18.87 mV·μm⁻¹) within Janus structures, driving anomalous electromigration contributions exceeding 100% for cations and −50% to −20% for anions. This “electrostatic diode” effect was experimentally validated, with Mg²⁺ forward flux (2.69 × 10⁻² mol·m⁻²·h⁻¹) surpassing reverse flux (2.98 × 10⁻³ mol·m⁻²·h⁻¹) by nearly an order of magnitude. The study bridges theoretical modeling and practical structure design, offering a robust framework for tailoring charge-asymmetric structures in ion-selective separations.","PeriodicalId":11783,"journal":{"name":"Engineering","volume":"21 1","pages":""},"PeriodicalIF":12.8,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144987645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial Intelligence in Energy Pipelines: Opportunities and Risks","authors":"Hongfang Lu, Y. Frank Cheng","doi":"10.1016/j.eng.2025.08.032","DOIUrl":"https://doi.org/10.1016/j.eng.2025.08.032","url":null,"abstract":"Artificial intelligence (AI) is reshaping the operation and management of energy pipelines that transport oil, natural gas, hydrogen, and carbon dioxide. This review provides a critical synthesis of current developments, highlighting how AI is being applied across pipeline life cycle stages—from route design and construction quality assurance to operation, maintenance, and eventual decommissioning. Recent advances in deep learning, transformer architectures, graph neural networks, and physics-informed models demonstrate the ability to detect anomalies, optimize multiphase flows, and support predictive maintenance with greater adaptability and robustness than conventional methods. Case studies illustrate how industrial operators are deploying AI platforms to improve efficiency, reduce environmental impact, and enhance system resilience. Alongside these opportunities, the review identifies systemic risks, including data bias, algorithmic opacity, cybersecurity vulnerabilities, and overreliance on automation, and discusses emerging mitigation strategies such as synthetic data generation, explainable AI, defense-in-depth frameworks, and mixed-initiative human–machine collaboration. Looking ahead, the field is moving toward multi-source heterogeneous data fusion, few-shot and transfer learning for data-scarce environments, and causal inference for decision support. AI applications in hydrogen and CO₂ pipelines, though nascent, offer promising directions for building safer and more sustainable infrastructures. This review underscores the need for continued interdisciplinary efforts to balance innovation with reliability, ensuring that AI becomes a trusted enabler of next-generation pipeline systems in the global energy transition.","PeriodicalId":11783,"journal":{"name":"Engineering","volume":"15 1","pages":""},"PeriodicalIF":12.8,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144928402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"More Data Centers May Boast Their Own Power Plants","authors":"","doi":"10.1016/j.eng.2025.06.021","DOIUrl":"10.1016/j.eng.2025.06.021","url":null,"abstract":"","PeriodicalId":11783,"journal":{"name":"Engineering","volume":"52 ","pages":"Pages 3-5"},"PeriodicalIF":11.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144337584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Foundation Models for the Process Industry: Challenges and Opportunities","authors":"Lei Ren ,&nbsp;Haiteng Wang ,&nbsp;Yuqing Wang ,&nbsp;Keke Huang ,&nbsp;Lihui Wang ,&nbsp;Bohu Li","doi":"10.1016/j.eng.2025.03.023","DOIUrl":"10.1016/j.eng.2025.03.023","url":null,"abstract":"<div><div>With the emergence of general foundational models, such as Chat Generative Pre-trained Transformer (ChatGPT), researchers have shown considerable interest in the potential applications of foundation models in the process industry. This paper provides a comprehensive overview of the challenges and opportunities presented by the use of foundation models in the process industry, including the frameworks, core applications, and future prospects. First, this paper proposes a framework for foundation models for the process industry. Second, it summarizes the key capabilities of industrial foundation models and their practical applications. Finally, it highlights future research directions and identifies unresolved open issues related to the use of foundation models in the process industry.</div></div>","PeriodicalId":11783,"journal":{"name":"Engineering","volume":"52 ","pages":"Pages 53-59"},"PeriodicalIF":11.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data Security and Privacy for AI-Enabled Smart Manufacturing","authors":"Xin Wang ,&nbsp;Daniel E. Quevedo ,&nbsp;Dongrun Li ,&nbsp;Peng Cheng ,&nbsp;Jiming Chen ,&nbsp;Youxian Sun","doi":"10.1016/j.eng.2025.08.008","DOIUrl":"10.1016/j.eng.2025.08.008","url":null,"abstract":"","PeriodicalId":11783,"journal":{"name":"Engineering","volume":"52 ","pages":"Pages 34-39"},"PeriodicalIF":11.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144851657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design of a Multi-Valent SARS-CoV-2 Peptide Vaccine for Broad Immune Protection via Deep Learning","authors":"Ziyan Feng ,&nbsp;Xuelian Pang ,&nbsp;Qian Xu ,&nbsp;Zijie Gu ,&nbsp;Shiliang Li ,&nbsp;Lili Zhu ,&nbsp;Honglin Li","doi":"10.1016/j.eng.2025.04.025","DOIUrl":"10.1016/j.eng.2025.04.025","url":null,"abstract":"<div><div>The emergence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants capable of evading both convalescent and vaccine-triggered antibody responses has underscored the pivotal role of T-cell immunity in antiviral defense. Here, we develop the ConFormer network for epitope prediction, which couples convolutional neural network (CNN) local features with Transformer global representations to enhance binding prediction performance, and employ the deep learning algorithm and bioinformatics workflows to identify conserved T-cell epitopes within the SARS-CoV-2 proteome. Five epitopes are identified as potential inducers of T-cell immune responses. Notably, the multi-valent vaccine composed of these five peptides significantly activates cluster of differentiation (CD)8⁺ and CD4⁺ T cells both <em>in vitro</em> and <em>in vivo</em>. The serum of mice immunized with this vaccine is able to neutralize the five major SARS-CoV-2 variants of concern. This study provides a candidate peptide vaccine with the potential to trigger antiviral T-cell responses, thereby offering the prospect of immune protection against SARS-CoV-2 variants.</div></div>","PeriodicalId":11783,"journal":{"name":"Engineering","volume":"52 ","pages":"Pages 142-159"},"PeriodicalIF":11.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144183798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Battery Swapping Emerges as Major Alternative to Charging Electric Vehicles","authors":"","doi":"10.1016/j.eng.2025.06.022","DOIUrl":"10.1016/j.eng.2025.06.022","url":null,"abstract":"","PeriodicalId":11783,"journal":{"name":"Engineering","volume":"52 ","pages":"Pages 6-9"},"PeriodicalIF":11.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144337585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AGU Posts Principles to Guide—and Foster—Geoengineering Research","authors":"","doi":"10.1016/j.eng.2025.06.023","DOIUrl":"10.1016/j.eng.2025.06.023","url":null,"abstract":"","PeriodicalId":11783,"journal":{"name":"Engineering","volume":"52 ","pages":"Pages 10-13"},"PeriodicalIF":11.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144337606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Theoretical High-Throughput Screening of Single-Atom CO2 Electroreduction Catalysts to Methanol Using Active Learning","authors":"Honghao Chen ,&nbsp;Jun Yin ,&nbsp;Jiali Li ,&nbsp;Xiaonan Wang","doi":"10.1016/j.eng.2025.03.039","DOIUrl":"10.1016/j.eng.2025.03.039","url":null,"abstract":"<div><div>Industrial decarbonization is critical for achieving net-zero goals. The carbon dioxide electrochemical reduction reaction (CO₂RR) is a promising approach for converting CO₂ into high-value chemicals, offering the potential for decarbonizing industrial processes toward a sustainable, carbon-neutral future. However, developing CO₂RR catalysts with high selectivity and activity remains a challenge due to the complexity of finding such catalysts and the inefficiency of traditional computational or experimental approaches. Here, we present a methodology integrating density functional theory (DFT) calculations, deep learning models, and an active learning strategy to rapidly screen high-performance catalysts. The proposed methodology is then demonstrated on graphene-based single-atom catalysts for selective CO₂ electroreduction to methanol. First, we conduct systematic binding energy calculations for 3045 single-atom catalysts to identify thermodynamically stable catalysts as the design space. We then use a graph neural network, fine-tuned with a specialized adsorption energy database, to predict the relative activity and selectivity of the candidate catalysts. An autonomous active learning framework is used to facilitate the exploration of designs. After six learning cycles and 2180 adsorption calculations across 15 intermediates, we develop a surrogate model that identifies four novel catalysts on the Pareto front of activity and selectivity. Our work demonstrates the effectiveness of leveraging a domain foundation model with an active learning framework and holds potential to significantly accelerate the discovery of high-performance CO₂RR catalysts.</div></div>","PeriodicalId":11783,"journal":{"name":"Engineering","volume":"52 ","pages":"Pages 172-182"},"PeriodicalIF":11.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144787466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}