Advanced Engineering Informatics最新文献

英文中文

Multi-aircraft attention-based model for perceptive arrival transit time prediction

IF 8 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2024-12-31 DOI: 10.1016/j.aei.2024.103067

Chris H.C. Nguyen , Rhea P. Liem

The states and trajectories of other aircraft are crucial in predicting arrival transit time; yet, current research predominantly concentrates on individual aircraft prediction and inadequately considers other aircraft within the airspace. The oversimplification of existing models raises concerns regarding their relevance and real-time applicability. Indeed, to effectively assist decision-making processes in air traffic management, we need solutions that are accurate, computationally efficient, and consistent with air traffic controller operations. To this end, we leverage the attention mechanism—which has demonstrated success in natural language processing—to appropriately consider all aircraft in the airspace in deriving a perceptive multi-aircraft transit time prediction. To achieve this, we propose a modified attention layer that can realistically mimic aircraft’s paying attention to others in a dynamic environment. The introduced model demonstrates a notable reduction in absolute prediction error by approximately 25% compared to state-of-the-art approaches. The functionality and effectiveness of the proposed attention layer are rigorously validated through extensive evaluation during the model’s learning process. Additionally, we introduce a model detachment technique in the feature importance analysis to determine the features that influence the attention decision of one flight with respect to another. The promising results highlight the potential of employing the customized attention mechanism in multi-agent systems both within and beyond air transportation research.

{"title":"Multi-aircraft attention-based model for perceptive arrival transit time prediction","authors":"Chris H.C. Nguyen , Rhea P. Liem","doi":"10.1016/j.aei.2024.103067","DOIUrl":"10.1016/j.aei.2024.103067","url":null,"abstract":"<div><div>The states and trajectories of other aircraft are crucial in predicting arrival transit time; yet, current research predominantly concentrates on individual aircraft prediction and inadequately considers other aircraft within the airspace. The oversimplification of existing models raises concerns regarding their relevance and real-time applicability. Indeed, to effectively assist decision-making processes in air traffic management, we need solutions that are accurate, computationally efficient, and consistent with air traffic controller operations. To this end, we leverage the attention mechanism—which has demonstrated success in natural language processing—to appropriately consider all aircraft in the airspace in deriving a perceptive multi-aircraft transit time prediction. To achieve this, we propose a modified attention layer that can realistically mimic aircraft’s paying attention to others in a dynamic environment. The introduced model demonstrates a notable reduction in absolute prediction error by approximately 25% compared to state-of-the-art approaches. The functionality and effectiveness of the proposed attention layer are rigorously validated through extensive evaluation during the model’s learning process. Additionally, we introduce a model detachment technique in the feature importance analysis to determine the features that influence the attention decision of one flight with respect to another. The promising results highlight the potential of employing the customized attention mechanism in multi-agent systems both within and beyond air transportation research.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103067"},"PeriodicalIF":8.0,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143129633","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

Forecasting and analyzing technology development trends with self-attention and frequency enhanced LSTM

IF 8 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2024-12-31 DOI: 10.1016/j.aei.2024.103093

Zhi-Xing Chang , Wei Guo , Lei Wang , Hong-Yu Shao , Yuan-Rong Zhang , Zheng-Hong Liu

Analyzing and forecasting technology development trends is of significant importance for formulating research and development (R&D) strategies. Existing research focused on analyzing historical trends of technology development or utilizing link prediction to forecast future technology interactions, thereby providing decision support for formulating R&D strategies. However, these methods rely on expert experience or fail to produce predictive trend insights, thus lacking objectivity and effectiveness. To address these issues, we start with predictions of technology interaction intensity trends to understand future technology interactions, thereby providing decision support for R&D. Specifically, we represent technology interactions using the co-occurrence of classification codes and developed a Self-Attention and Frequency Enhanced Long-Short Term Memory (SAFE-LSTM) model to predict the future connection strengths of classification codes, thereby constructing the landscape for future technology interactions. We trained this model on the American patent dataset and compared it with several typical machine-learning methods. The results indicate that the SAFE-LSTM model achieved significant advantages in single- and multi-step predictions. Building on this foundation, we further analyze technology development trends, yielding valuable insights. This study provides researchers with more comprehensive and predictive insights, supporting the integration with additional analytical methods to offer more robust decision-making support for R&D, thereby contributing to the future competitiveness of enterprises.

{"title":"Forecasting and analyzing technology development trends with self-attention and frequency enhanced LSTM","authors":"Zhi-Xing Chang , Wei Guo , Lei Wang , Hong-Yu Shao , Yuan-Rong Zhang , Zheng-Hong Liu","doi":"10.1016/j.aei.2024.103093","DOIUrl":"10.1016/j.aei.2024.103093","url":null,"abstract":"<div><div>Analyzing and forecasting technology development trends is of significant importance for formulating research and development (R&D) strategies. Existing research focused on analyzing historical trends of technology development or utilizing link prediction to forecast future technology interactions, thereby providing decision support for formulating R&D strategies. However, these methods rely on expert experience or fail to produce predictive trend insights, thus lacking objectivity and effectiveness. To address these issues, we start with predictions of technology interaction intensity trends to understand future technology interactions, thereby providing decision support for R&D. Specifically, we represent technology interactions using the co-occurrence of classification codes and developed a Self-Attention and Frequency Enhanced Long-Short Term Memory (SAFE-LSTM) model to predict the future connection strengths of classification codes, thereby constructing the landscape for future technology interactions. We trained this model on the American patent dataset and compared it with several typical machine-learning methods. The results indicate that the SAFE-LSTM model achieved significant advantages in single- and multi-step predictions. Building on this foundation, we further analyze technology development trends, yielding valuable insights. This study provides researchers with more comprehensive and predictive insights, supporting the integration with additional analytical methods to offer more robust decision-making support for R&D, thereby contributing to the future competitiveness of enterprises.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103093"},"PeriodicalIF":8.0,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143129738","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}

引用次数: 0

Knowledge graph-driven decision support for manufacturing process: A graph neural network-based knowledge reasoning approach

IF 8 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2024-12-30 DOI: 10.1016/j.aei.2024.103098

Chang Su, Qi Jiang, Yong Han, Tao Wang, Qingchen He

In modern manufacturing, effectively reusing and sharing knowledge is essential due to the vast amounts of data and resources available. This research introduces a three-layer cognitive manufacturing paradigm that integrates data, knowledge, and decision-making. Our model uses a manufacturing knowledge graph to organize various data sources and applies a dual-driven knowledge reasoning strategy for smooth data-to-knowledge transitions. We developed an automated framework to construct knowledge graphs specifically for machining product knowledge and implemented an RGAT-PRotatE method for regular knowledge updates. The RGAT encoder effectively captures complex relational dynamics using attention mechanisms to focus on key interactions within mechanical processes. Meanwhile, the PRotatE decoder predicts and fills in missing information in the graph. We also introduce a knowledge-centric decision support system that utilizes the knowledge graph’s reasoning capabilities. An empirical study on the fabrication of aero-engine casings demonstrates the practicality and effectiveness of our framework, contributing to advancements in cognitive manufacturing and decision-making.

{"title":"Knowledge graph-driven decision support for manufacturing process: A graph neural network-based knowledge reasoning approach","authors":"Chang Su, Qi Jiang, Yong Han, Tao Wang, Qingchen He","doi":"10.1016/j.aei.2024.103098","DOIUrl":"10.1016/j.aei.2024.103098","url":null,"abstract":"<div><div>In modern manufacturing, effectively reusing and sharing knowledge is essential due to the vast amounts of data and resources available. This research introduces a three-layer cognitive manufacturing paradigm that integrates data, knowledge, and decision-making. Our model uses a manufacturing knowledge graph to organize various data sources and applies a dual-driven knowledge reasoning strategy for smooth data-to-knowledge transitions. We developed an automated framework to construct knowledge graphs specifically for machining product knowledge and implemented an RGAT-PRotatE method for regular knowledge updates. The RGAT encoder effectively captures complex relational dynamics using attention mechanisms to focus on key interactions within mechanical processes. Meanwhile, the PRotatE decoder predicts and fills in missing information in the graph. We also introduce a knowledge-centric decision support system that utilizes the knowledge graph’s reasoning capabilities. An empirical study on the fabrication of aero-engine casings demonstrates the practicality and effectiveness of our framework, contributing to advancements in cognitive manufacturing and decision-making.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103098"},"PeriodicalIF":8.0,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143129733","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}

引用次数: 0

Integrative human and object aware online progress observation for human-centric augmented reality assembly

IF 8 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2024-12-29 DOI: 10.1016/j.aei.2024.103081

Tienong Zhang, Yuqing Cui, Wei Fang

Augmented reality (AR) can provide step-by-step intuitive guidance for workers on the shop floor, enabling time-saving and error-avoid assembly actions. Nevertheless, existing AR-guided assembly methods have primarily paid attention to information on assembly objects and usually ignore the human factor in the assembly process. Further, there are a series of details regarding the AR system design that are frequently neglected, including systematic usability, human intervention, and AR perspective. To alleviate these limitations, this paper proposes a real-time two-branch approach that integrates human action-based human factor evaluation and object-based assembly progress observation. In the online human factor evaluation, a skeleton-based model is applied to predict the operator’s assembly action, providing a quantitative analysis and optimized indicator for the ongoing AR assembly. In the assembly progress observation, the object-based model is deployed to recognize the assembly part, and the AR assembly status is checked automatically based on the prior sequential assembly knowledge without human intervention. Thus, a holistic human-object integrated framework is established for the human-centric AR assembly process inspection, as well as the quantitative analysis and optimized indicator output from the framework are actively feedback in the first-person AR perspective, where the operators can perceive the assembly stage and whether their working posture is appropriate or not intuitively. Finally, extensive experiments are carried out on the human-object integrated performance in the smart AR assembly, and results illustrate that the proposed method can monitor the online assembly observation from a holistic perspective, alleviate the cognitive load, and achieve superior performance for the AR assembly tasks.

{"title":"Integrative human and object aware online progress observation for human-centric augmented reality assembly","authors":"Tienong Zhang, Yuqing Cui, Wei Fang","doi":"10.1016/j.aei.2024.103081","DOIUrl":"10.1016/j.aei.2024.103081","url":null,"abstract":"<div><div>Augmented reality (AR) can provide step-by-step intuitive guidance for workers on the shop floor, enabling time-saving and error-avoid assembly actions. Nevertheless, existing AR-guided assembly methods have primarily paid attention to information on assembly objects and usually ignore the human factor in the assembly process. Further, there are a series of details regarding the AR system design that are frequently neglected, including systematic usability, human intervention, and AR perspective. To alleviate these limitations, this paper proposes a real-time two-branch approach that integrates human action-based human factor evaluation and object-based assembly progress observation. In the online human factor evaluation, a skeleton-based model is applied to predict the operator’s assembly action, providing a quantitative analysis and optimized indicator for the ongoing AR assembly. In the assembly progress observation, the object-based model is deployed to recognize the assembly part, and the AR assembly status is checked automatically based on the prior sequential assembly knowledge without human intervention. Thus, a holistic human-object integrated framework is established for the human-centric AR assembly process inspection, as well as the quantitative analysis and optimized indicator output from the framework are actively feedback in the first-person AR perspective, where the operators can perceive the assembly stage and whether their working posture is appropriate or not intuitively. Finally, extensive experiments are carried out on the human-object integrated performance in the smart AR assembly, and results illustrate that the proposed method can monitor the online assembly observation from a holistic perspective, alleviate the cognitive load, and achieve superior performance for the AR assembly tasks.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103081"},"PeriodicalIF":8.0,"publicationDate":"2024-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143129630","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}

引用次数: 0

Modelling and disrupting counterfeit N95 respirator supply chains

IF 8 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2024-12-28 DOI: 10.1016/j.aei.2024.103084

Edward Huang , Louise Shelley , Layla Hashemi

During the COVID-19 pandemic, millions of counterfeit respirators and fraudulent medical products infiltrated legitimate supply chains, often facilitated by registered businesses, third-party logistics providers, and companies in the technology sector. The trade in counterfeit respirators during the global health crisis threatened public health, safety, and security. The study uses seizure data, as well as analysis of shipping records and investigation reports to understand illicit supply chains of counterfeit N95 respirators. To compare the effectiveness of different types of disruption strategies, the authors propose a multi-period optimization problem and study different types of disruption strategies that would undermine counterfeit respirator supply chains. The authors also share numerical experiments and findings concerning the effectiveness of the proposed model.

引用次数: 0

A multi-stage active learning framework with an instance-based sample selection algorithm for steel surface defect

IF 8 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2024-12-28 DOI: 10.1016/j.aei.2024.103080

Shuo Gao , Yimin Jiang , Tangbin Xia , Yaping Li , Ying Zhu , Lifeng Xi

The application of deep learning (DL) for high-precision inspection to identify and locate the positions of each type of steel surface defect has demonstrated considerable potential for the quality control of steel products. However, the time-consuming and labor-intensive nature of manually labeling large amounts of data has limited DL’s broader deployment in this field. While traditional active learning methods can select the most valuable labels based on the amount of information, they fail to consider the positional and categorical information during the information computation process, thereby preventing the extraction of spatial information with multiple defects simultaneously. To address this challenge, this paper proposes a multi-stage active learning framework with an instance-based sample selection algorithm (MALF) for steel surface defects. Firstly, a soft weighted label assignment with prior information is constructed with the objective of achieving stable training and high-precision instance detection with a minimal amount of label annotation. Furthermore, when provided with high-precision instances, an independent evidence branch utilizing a reweighted Dirichlet distribution is capable of generating epistemic uncertainty with remarkable efficiency. Besides, a methodology based on diversity has been devised to ascertain the similarity with instance data as a diversity criterion, thereby obtaining detailed spatial information in multi-defect images. The results of experiments conducted on a variety of benchmark methods indicate that MALF is capable of filtering out more informative images for annotation while achieving higher accuracy with the same sample size.

{"title":"A multi-stage active learning framework with an instance-based sample selection algorithm for steel surface defect","authors":"Shuo Gao , Yimin Jiang , Tangbin Xia , Yaping Li , Ying Zhu , Lifeng Xi","doi":"10.1016/j.aei.2024.103080","DOIUrl":"10.1016/j.aei.2024.103080","url":null,"abstract":"<div><div>The application of deep learning (DL) for high-precision inspection to identify and locate the positions of each type of steel surface defect has demonstrated considerable potential for the quality control of steel products. However, the time-consuming and labor-intensive nature of manually labeling large amounts of data has limited DL’s broader deployment in this field. While traditional active learning methods can select the most valuable labels based on the amount of information, they fail to consider the positional and categorical information during the information computation process, thereby preventing the extraction of spatial information with multiple defects simultaneously. To address this challenge, this paper proposes a multi-stage active learning framework with an instance-based sample selection algorithm (MALF) for steel surface defects. Firstly, a soft weighted label assignment with prior information is constructed with the objective of achieving stable training and high-precision instance detection with a minimal amount of label annotation. Furthermore, when provided with high-precision instances, an independent evidence branch utilizing a reweighted Dirichlet distribution is capable of generating epistemic uncertainty with remarkable efficiency. Besides, a methodology based on diversity has been devised to ascertain the similarity with instance data as a diversity criterion, thereby obtaining detailed spatial information in multi-defect images. The results of experiments conducted on a variety of benchmark methods indicate that MALF is capable of filtering out more informative images for annotation while achieving higher accuracy with the same sample size.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103080"},"PeriodicalIF":8.0,"publicationDate":"2024-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143129732","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}

引用次数: 0

McGAN: Generating manufacturable designs by embedding manufacturing rules into conditional generative adversarial network

IF 8 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2024-12-28 DOI: 10.1016/j.aei.2024.103074

Zhichao Wang, Xiaoliang Yan, Shreyes Melkote, David Rosen

Generative design (GD) methods aim to automatically generate a wide variety of designs that satisfy functional or aesthetic design requirements. However, research to date generally lacks considerations of manufacturability of the generated designs. To this end, we propose a novel GD approach by using deep neural networks to encode design for manufacturing (DFM) rules, thereby modifying part designs to make them manufacturable by a given manufacturing process. Specifically, a three-step approach is proposed: first, an instance segmentation method, Mask R-CNN, is used to decompose a part design into subregions. Second, a conditional generative adversarial neural network (cGAN), Pix2Pix, transforms unmanufacturable decomposed subregions into manufacturable subregions. The transformed subregions of designs are subsequently reintegrated into a unified manufacturable design. These three steps, Mask-RCNN, Pix2Pix, and reintegration, form the basis of the proposed Manufacturable conditional GAN (McGAN) framework. Experimental results show that McGAN can transform existing unmanufacturable designs to generate their corresponding manufacturable counterparts automatically that realize the specified manufacturing rules in an efficient and robust manner. The effectiveness of McGAN is demonstrated through two-dimensional design case studies focused on the injection molding process, with the potential to generalize across different manufacturing processes for both 2D and 3D input data.

{"title":"McGAN: Generating manufacturable designs by embedding manufacturing rules into conditional generative adversarial network","authors":"Zhichao Wang, Xiaoliang Yan, Shreyes Melkote, David Rosen","doi":"10.1016/j.aei.2024.103074","DOIUrl":"10.1016/j.aei.2024.103074","url":null,"abstract":"<div><div>Generative design (GD) methods aim to automatically generate a wide variety of designs that satisfy functional or aesthetic design requirements. However, research to date generally lacks considerations of manufacturability of the generated designs. To this end, we propose a novel GD approach by using deep neural networks to encode design for manufacturing (DFM) rules, thereby modifying part designs to make them manufacturable by a given manufacturing process. Specifically, a three-step approach is proposed: first, an instance segmentation method, Mask R-CNN, is used to decompose a part design into subregions. Second, a conditional generative adversarial neural network (cGAN), Pix2Pix, transforms unmanufacturable decomposed subregions into manufacturable subregions. The transformed subregions of designs are subsequently reintegrated into a unified manufacturable design. These three steps, Mask-RCNN, Pix2Pix, and reintegration, form the basis of the proposed Manufacturable conditional GAN (McGAN) framework. Experimental results show that McGAN can transform existing unmanufacturable designs to generate their corresponding manufacturable counterparts automatically that realize the specified manufacturing rules in an efficient and robust manner. The effectiveness of McGAN is demonstrated through two-dimensional design case studies focused on the injection molding process, with the potential to generalize across different manufacturing processes for both 2D and 3D input data.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103074"},"PeriodicalIF":8.0,"publicationDate":"2024-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143129731","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}

引用次数: 0

A survey of emerging applications of large language models for problems in mechanics, product design, and manufacturing

IF 8 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2024-12-27 DOI: 10.1016/j.aei.2024.103066

K.B. Mustapha

In the span of three years, the application of large language models (LLMs) has accelerated across a multitude of professional sectors. Amid this development, a new collection of studies has manifested around leveraging LLMs for segments of the mechanical engineering (ME) field. Concurrently, it has become clear that general-purpose LLMs faced hurdles when deployed in this domain, partly due to their training on discipline-agnostic data. Accordingly, there is a recent uptick of derivative ME-specific LLMs being reported. As the research community shifts towards these new LLM-centric solutions for ME-related problems, the shift compels a deeper look at the diffusion of LLMs in this emerging landscape. Consequently, this review consolidates the diversity of ME-tailored LLMs use cases and identifies the supportive technical stacks associated with these implementations. Broadly, the review demonstrates how various categories of LLMs are re-shaping concrete aspects of engineering design, manufacturing and applied mechanics. At a more specific level, it uncovered emerging LLMs’ role in boosting the intelligence of digital twins, enriching bidirectional communication within the human-cyber-physical infrastructure, advancing the development of intelligent process planning in manufacturing and facilitating inverse mechanics. It further spotlights the coupling of LLMs with other generative models for promoting efficient computer-aided conceptual design, prototyping, knowledge discovery and creativity. Finally, it revealed training modalities/infrastructures necessary for developing ME-specific language models, discussed LLMs' features that are incongruent with typical engineering workflows, and concluded with prescriptive approaches to mitigate impediments to the progressive adoption of LLMs as part of advanced intelligent solutions.

{"title":"A survey of emerging applications of large language models for problems in mechanics, product design, and manufacturing","authors":"K.B. Mustapha","doi":"10.1016/j.aei.2024.103066","DOIUrl":"10.1016/j.aei.2024.103066","url":null,"abstract":"<div><div>In the span of three years, the application of large language models (LLMs) has accelerated across a multitude of professional sectors. Amid this development, a new collection of studies has manifested around leveraging LLMs for segments of the mechanical engineering (ME) field. Concurrently, it has become clear that general-purpose LLMs faced hurdles when deployed in this domain, partly due to their training on discipline-agnostic data. Accordingly, there is a recent uptick of derivative ME-specific LLMs being reported. As the research community shifts towards these new LLM-centric solutions for ME-related problems, the shift compels a deeper look at the diffusion of LLMs in this emerging landscape. Consequently, this review consolidates the diversity of ME-tailored LLMs use cases and identifies the supportive technical stacks associated with these implementations. Broadly, the review demonstrates how various categories of LLMs are re-shaping concrete aspects of engineering design, manufacturing and applied mechanics. At a more specific level, it uncovered emerging LLMs’ role in boosting the intelligence of digital twins, enriching bidirectional communication within the human-cyber-physical infrastructure, advancing the development of intelligent process planning in manufacturing and facilitating inverse mechanics. It further spotlights the coupling of LLMs with other generative models for promoting efficient computer-aided conceptual design, prototyping, knowledge discovery and creativity. Finally, it revealed training modalities/infrastructures necessary for developing ME-specific language models, discussed LLMs' features that are incongruent with typical engineering workflows, and concluded with prescriptive approaches to mitigate impediments to the progressive adoption of LLMs as part of advanced intelligent solutions.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103066"},"PeriodicalIF":8.0,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143130280","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}

引用次数: 0

A semantics-driven framework to enable demand flexibility control applications in real buildings

IF 8 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2024-12-27 DOI: 10.1016/j.aei.2024.103049

Flavia de Andrade Pereira , Kyriakos Katsigarakis , Dimitrios Rovas , Marco Pritoni , Conor Shaw , Lazlo Paul , Anand Prakash , Susana Martin-Toral , Donal Finn , James O’Donnell

Decarbonising and digitalising the energy sector requires scalable and interoperable Demand Flexibility (DF) applications. Semantic models are promising technologies for achieving these goals, but existing studies focused on DF applications exhibit limitations. These include dependence on bespoke ontologies, lack of computational methods to generate semantic models, ineffective temporal data management and absence of platforms that use these models to easily develop, configure and deploy controls in real buildings. This paper introduces a semantics-driven framework to enable DF control applications in real buildings. The framework supports the generation of semantic models that adhere to Brick and SAREF while using metadata from Building Information Models (BIM) and Building Automation Systems (BAS). The work also introduces a web platform that leverages these models and an actor and microservices architecture to streamline the development, configuration and deployment of DF controls. The paper demonstrates the framework through a case study, illustrating its ability to integrate diverse data sources, execute DF actuation in a real building, and promote modularity for easy reuse, extension, and customisation of applications. The paper also discusses the alignment between Brick and SAREF, the value of leveraging BIM data sources, and the framework’s benefits over existing approaches, demonstrating a 75% reduction in effort for developing, configuring, and deploying building controls.

{"title":"A semantics-driven framework to enable demand flexibility control applications in real buildings","authors":"Flavia de Andrade Pereira , Kyriakos Katsigarakis , Dimitrios Rovas , Marco Pritoni , Conor Shaw , Lazlo Paul , Anand Prakash , Susana Martin-Toral , Donal Finn , James O’Donnell","doi":"10.1016/j.aei.2024.103049","DOIUrl":"10.1016/j.aei.2024.103049","url":null,"abstract":"<div><div>Decarbonising and digitalising the energy sector requires scalable and interoperable Demand Flexibility (DF) applications. Semantic models are promising technologies for achieving these goals, but existing studies focused on DF applications exhibit limitations. These include dependence on bespoke ontologies, lack of computational methods to generate semantic models, ineffective temporal data management and absence of platforms that use these models to easily develop, configure and deploy controls in real buildings. This paper introduces a semantics-driven framework to enable DF control applications in real buildings. The framework supports the generation of semantic models that adhere to Brick and SAREF while using metadata from Building Information Models (BIM) and Building Automation Systems (BAS). The work also introduces a web platform that leverages these models and an actor and microservices architecture to streamline the development, configuration and deployment of DF controls. The paper demonstrates the framework through a case study, illustrating its ability to integrate diverse data sources, execute DF actuation in a real building, and promote modularity for easy reuse, extension, and customisation of applications. The paper also discusses the alignment between Brick and SAREF, the value of leveraging BIM data sources, and the framework’s benefits over existing approaches, demonstrating a 75% reduction in effort for developing, configuring, and deploying building controls.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103049"},"PeriodicalIF":8.0,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143129727","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

A novel remaining useful life prediction method under multiple operating conditions based on attention mechanism and deep learning

IF 8 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2024-12-27 DOI: 10.1016/j.aei.2024.103083

Jie Wang , Zhong Lu , Jia Zhou , Kai-Uwe Schröder , Xihui Liang

Remaining useful life (RUL) prediction is a key technique for supporting predictive maintenance. Accurate RUL prediction plays an important role in maintenance decisions. However, RUL prediction has two challenges: first, it is difficult to capture long-term dependencies effectively; second, the accuracy and efficiency are not satisfied under multiple operating conditions. A novel RUL prediction model that integrates bidirectional temporal convolution and improved Informer (ABiTCI) is proposed with consideration of multiple operating conditions. First, the bidirectional temporal convolution network (BiTCN) is designed with efficient channel attention (ECA). The degradation features from different channels can be extracted by weighting feature contributions. Second, the Informer with sparse pyramid temporal self-attention is designed to capture degradation information from different time steps. Finally, the effectiveness of the proposed method is verified by different datasets of aircraft engines. Compared with the present methods, the results show that the root mean square errors (RMSEs) have been reduced by 20.84 %–50.38 %, 16.29 %–41.49 %, and 36.96 %–59.53 % on the CMAPSS-FD002, CMAPSS-FD004, and NCMAPSS datasets, respectively. It demonstrates that the ABiTCI model performs well for RUL prediction under multiple operating conditions.

{"title":"A novel remaining useful life prediction method under multiple operating conditions based on attention mechanism and deep learning","authors":"Jie Wang , Zhong Lu , Jia Zhou , Kai-Uwe Schröder , Xihui Liang","doi":"10.1016/j.aei.2024.103083","DOIUrl":"10.1016/j.aei.2024.103083","url":null,"abstract":"<div><div>Remaining useful life (RUL) prediction is a key technique for supporting predictive maintenance. Accurate RUL prediction plays an important role in maintenance decisions. However, RUL prediction has two challenges: first, it is difficult to capture long-term dependencies effectively; second, the accuracy and efficiency are not satisfied under multiple operating conditions. A novel RUL prediction model that integrates bidirectional temporal convolution and improved Informer (ABiTCI) is proposed with consideration of multiple operating conditions. First, the bidirectional temporal convolution network (BiTCN) is designed with efficient channel attention (ECA). The degradation features from different channels can be extracted by weighting feature contributions. Second, the Informer with sparse pyramid temporal self-attention is designed to capture degradation information from different time steps. Finally, the effectiveness of the proposed method is verified by different datasets of aircraft engines. Compared with the present methods, the results show that the root mean square errors (RMSEs) have been reduced by 20.84 %–50.38 %, 16.29 %–41.49 %, and 36.96 %–59.53 % on the CMAPSS-FD002, CMAPSS-FD004, and NCMAPSS datasets, respectively. It demonstrates that the ABiTCI model performs well for RUL prediction under multiple operating conditions.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103083"},"PeriodicalIF":8.0,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143129729","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}

引用次数: 0

首页上一页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Advanced Engineering Informatics

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.

﹀