Advanced Engineering Informatics最新文献_第8页

A novel user scenario and behavior sequence recognition approach based on vision-context fusion architecture

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

Advanced Engineering Informatics

Pub Date : 2025-02-06 DOI: 10.1016/j.aei.2025.103161

Wenyu Yuan, Danni Chang, Chenlu Mao, Luyao Wang, Ke Ren, Ting Han

Understanding user scenario and behavior is essential for the development of human-centered intelligent service systems. However, the presence of cluttered objects, uncertain human behaviors, and overlapping timelines in daily life scenarios complicates the problem of scenario understanding. This paper aims to address the challenges of identifying and predicting user scenario and behavior sequences through a multimodal data fusion approach, focusing on the integration of visual and environmental data to capture subtle scenario and behavioral features.

For the purpose, a novel Vision-Context Fusion Scenario Recognition (VCFSR) approach was proposed, encompassing three stages. First, four categories of context data related to home scenarios were acquired: physical context, time context, user context, and inferred context. Second, scenarios were represented as multidimensional data relationships through modeling technologies. Third, a scenario recognition model was developed, comprising context feature processing, visual feature handling, and multimodal feature fusion. For illustration, a smart home environment was built, and twenty-six participants were recruited to perform various home activities. Integral sensors were used to collect environmental context data, and video data was captured simultaneously, both of which jointly form a multimodal dataset. Results demonstrated that the VCFSR model achieved an average accuracy of 98.1 %, outperforming traditional machine learning models such as decision trees and support vector machines. This method was then employed for fine-grained human behavior sequence prediction tasks, showing good performance in predicting behavior sequences across all scenarios constructed in this study. Furthermore, the results of ablation experiments revealed that the multimodal feature fusion method increased the average accuracy by at least 1.8 % compared to single-modality data-driven methods.

This novel approach to user behavior modeling simultaneously handles the relationship threads across scenarios and the rich details provided by visual data, paving the way for advanced intelligent services in complex interactive environments such as smart homes and hospitals.

{"title":"A novel user scenario and behavior sequence recognition approach based on vision-context fusion architecture","authors":"Wenyu Yuan, Danni Chang, Chenlu Mao, Luyao Wang, Ke Ren, Ting Han","doi":"10.1016/j.aei.2025.103161","DOIUrl":"10.1016/j.aei.2025.103161","url":null,"abstract":"<div><div>Understanding user scenario and behavior is essential for the development of human-centered intelligent service systems. However, the presence of cluttered objects, uncertain human behaviors, and overlapping timelines in daily life scenarios complicates the problem of scenario understanding. This paper aims to address the challenges of identifying and predicting user scenario and behavior sequences through a multimodal data fusion approach, focusing on the integration of visual and environmental data to capture subtle scenario and behavioral features.</div><div>For the purpose, a novel Vision-Context Fusion Scenario Recognition (VCFSR) approach was proposed, encompassing three stages. First, four categories of context data related to home scenarios were acquired: physical context, time context, user context, and inferred context. Second, scenarios were represented as multidimensional data relationships through modeling technologies. Third, a scenario recognition model was developed, comprising context feature processing, visual feature handling, and multimodal feature fusion. For illustration, a smart home environment was built, and twenty-six participants were recruited to perform various home activities. Integral sensors were used to collect environmental context data, and video data was captured simultaneously, both of which jointly form a multimodal dataset. Results demonstrated that the VCFSR model achieved an average accuracy of 98.1 %, outperforming traditional machine learning models such as decision trees and support vector machines. This method was then employed for fine-grained human behavior sequence prediction tasks, showing good performance in predicting behavior sequences across all scenarios constructed in this study. Furthermore, the results of ablation experiments revealed that the multimodal feature fusion method increased the average accuracy by at least 1.8 % compared to single-modality data-driven methods.</div><div>This novel approach to user behavior modeling simultaneously handles the relationship threads across scenarios and the rich details provided by visual data, paving the way for advanced intelligent services in complex interactive environments such as smart homes and hospitals.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103161"},"PeriodicalIF":8.0,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143368501","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

The human-centric framework integrating knowledge distillation architecture with fine-tuning mechanism for equipment health monitoring

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

Advanced Engineering Informatics

Pub Date : 2025-02-06 DOI: 10.1016/j.aei.2025.103167

Jr-Fong Dang , Tzu-Li Chen , Hung-Yi Huang

Human-centricity serves as the cornerstone of the evolution of manufacturing into Industry 5.0. Accordingly, modern manufacturing prioritizes both the well-being of human workers and their collaboration with production systems. Successful systems would be user-friendly and market-appropriate, effectively identifying and analyzing user needs. This study aims to integrate user requirements into the framework for equipment health monitoring (EHM). The proposed framework addresses issues related to insufficient training samples and variable-length data by combining an encoder-decoder architecture with an attention mechanism and a conditional generative adversarial network (EDA-CGAN). Furthermore, the authors utilize a teacher-student network to reduce model complexity through knowledge distillation (KD). To prevent negative knowledge distillation, this study incorporates user requirements using Kullback-Leibler divergence (KLD) to determine whether the teacher model would be fine-tuned. Consequently, we employ the explainable AI (XAI) to provide a clear and understandable explanation for the prediction results. Thus, the proposed human-centric EHM consisting of four modules: (i) the data augmentation (ii) the fine-tuning mechanism (ii) the equipment health prediction model (iv) the explainable AI (XAI). The authors employ these methods to uncover new research insights that are vital for advancing the methodological innovation within the proposed framework. To evaluate model performance, this study conducts an empirical investigation to illustrate the capability and practicality of the proposed framework. The results indicate that our algorithm outperforms existing machine learning models, enabling the implementation of the proposed framework in the real-world manufacturing environment to maintain equipment health.

以人为本是制造业向工业 5.0 演进的基石。因此，现代制造业既要优先考虑人类工人的福祉，也要考虑他们与生产系统的协作。成功的系统应具有用户友好性和市场适应性，并能有效识别和分析用户需求。本研究旨在将用户需求纳入设备健康监测（EHM）框架。建议的框架通过将编码器-解码器架构与注意力机制和条件生成对抗网络（EDA-CGAN）相结合，解决了与训练样本不足和数据长度可变相关的问题。此外，作者还利用师生网络，通过知识提炼（KD）来降低模型的复杂性。为防止出现消极的知识蒸馏，本研究利用库尔贝-莱布勒发散（KLD）将用户需求纳入其中，以确定是否对教师模型进行微调。因此，我们采用了可解释人工智能（XAI），为预测结果提供清晰易懂的解释。因此，所提出的以人为本的 EHM 由四个模块组成：(i) 数据增强；(ii) 微调机制；(ii) 设备健康预测模型；(iv) 可解释的人工智能（XAI）。作者采用这些方法来揭示新的研究见解，这些见解对于推进拟议框架内的方法创新至关重要。为评估模型性能，本研究开展了一项实证调查，以说明拟议框架的能力和实用性。结果表明，我们的算法优于现有的机器学习模型，从而能够在现实世界的制造环境中实施所提出的框架，以维护设备健康。

{"title":"The human-centric framework integrating knowledge distillation architecture with fine-tuning mechanism for equipment health monitoring","authors":"Jr-Fong Dang , Tzu-Li Chen , Hung-Yi Huang","doi":"10.1016/j.aei.2025.103167","DOIUrl":"10.1016/j.aei.2025.103167","url":null,"abstract":"<div><div>Human-centricity serves as the cornerstone of the evolution of manufacturing into Industry 5.0. Accordingly, modern manufacturing prioritizes both the well-being of human workers and their collaboration with production systems. Successful systems would be user-friendly and market-appropriate, effectively identifying and analyzing user needs. This study aims to integrate user requirements into the framework for equipment health monitoring (EHM). The proposed framework addresses issues related to insufficient training samples and variable-length data by combining an encoder-decoder architecture with an attention mechanism and a conditional generative adversarial network (EDA-CGAN). Furthermore, the authors utilize a teacher-student network to reduce model complexity through knowledge distillation (KD). To prevent negative knowledge distillation, this study incorporates user requirements using Kullback-Leibler divergence (KLD) to determine whether the teacher model would be fine-tuned. Consequently, we employ the explainable AI (XAI) to provide a clear and understandable explanation for the prediction results. Thus, the proposed human-centric EHM consisting of four modules: (i) the data augmentation (ii) the fine-tuning mechanism (ii) the equipment health prediction model (iv) the explainable AI (XAI). The authors employ these methods to uncover new research insights that are vital for advancing the methodological innovation within the proposed framework. To evaluate model performance, this study conducts an empirical investigation to illustrate the capability and practicality of the proposed framework. The results indicate that our algorithm outperforms existing machine learning models, enabling the implementation of the proposed framework in the real-world manufacturing environment to maintain equipment health.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103167"},"PeriodicalIF":8.0,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143368497","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

Vehicle spatiotemporal distribution identification in low-light environment based on image enhancement and object detection

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

Advanced Engineering Informatics

Pub Date : 2025-02-06 DOI: 10.1016/j.aei.2025.103165

Jie Zhang , Jiaqiang Peng , Xuan Kong , Shuo Wang , Jiexuan Hu

The spatiotemporal distribution of vehicles on roads and bridges is important for the operation and maintenance of transportation systems. The accuracy of vehicle identification is affected by the lighting conditions, especially low-light environments. This study proposes a vehicle spatiotemporal distribution identification method using image enhancement and object detection. First, the FP-ZeroDCE algorithm is used to enhance low-light images, which improves the brightness and contrast of images. Next, the enhanced images are input into the AFF-YOLO model to identify the spatiotemporal distribution of vehicles. Finally, the proposed method is validated using public datasets and tested in the field. The results indicate that the proposed method can enhance the quality of low-light images, with an increase in the Peak Signal-to-Noise Ratio by 8.257 dB, and improve the accuracy of vehicle detection, with an accuracy of 92.7 %. The proposed method is an effective means for identifying vehicle spatiotemporal distribution under low-light conditions.

{"title":"Vehicle spatiotemporal distribution identification in low-light environment based on image enhancement and object detection","authors":"Jie Zhang , Jiaqiang Peng , Xuan Kong , Shuo Wang , Jiexuan Hu","doi":"10.1016/j.aei.2025.103165","DOIUrl":"10.1016/j.aei.2025.103165","url":null,"abstract":"<div><div>The spatiotemporal distribution of vehicles on roads and bridges is important for the operation and maintenance of transportation systems. The accuracy of vehicle identification is affected by the lighting conditions, especially low-light environments. This study proposes a vehicle spatiotemporal distribution identification method using image enhancement and object detection. First, the FP-ZeroDCE algorithm is used to enhance low-light images, which improves the brightness and contrast of images. Next, the enhanced images are input into the AFF-YOLO model to identify the spatiotemporal distribution of vehicles. Finally, the proposed method is validated using public datasets and tested in the field. The results indicate that the proposed method can enhance the quality of low-light images, with an increase in the Peak Signal-to-Noise Ratio by 8.257 dB, and improve the accuracy of vehicle detection, with an accuracy of 92.7 %. The proposed method is an effective means for identifying vehicle spatiotemporal distribution under low-light conditions.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103165"},"PeriodicalIF":8.0,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143368502","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 augmented generalizer specializer: A framework for early stage design exploration

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

Advanced Engineering Informatics

Pub Date : 2025-02-04 DOI: 10.1016/j.aei.2025.103141

Vijayalaxmi Sahadevan , Rohin Joshi , Kane Borg , Vishal Singh , Abhishek Raj Singh , Bilal Muhammed , Soban Babu Beemaraj , Amol Joshi

In non-routine engineering design projects, the design outcome is determined by how the problem is formulated and represented in the early conceptual stage. The problem representation comprises schemas, ontologies, variables, and parameters relevant to the given problem class. Despite the critical role of early conceptual decisions in shaping the eventual design outcome, most of the computational support and automation are focused on the latter stages of parametric modelling, problem-solving, and optimization. There is inadequate support for aiding and automating problem formulation, variable and parameter identification and representation, and early-stage conceptual decisions. Therefore, this paper presents an innovative, transparent, and explainable method employing semantic reasoning to automate the step-by-step conceptual design generation process, including problem formulation, identification and representation of the variables and parameters and their dependencies. The method is realized through a novel framework called Knowledge Augmented Generalizer Specializer (KAGS). KAGS employs the Function-Behavior-Structure (FBS) ontology and the Graph-of-Thought (GoT) mechanism to enable automated reasoning with a Large Language Model (LLM). The workflow comprises various stages: problem breakdown, design prototype creation, assessment, and prototype merging. The framework is implemented and tested on a Subsea Layout (SSL) planning problem, a special class of infrastructure planning projects in deep-sea oil and gas production systems. The experimentations with KAGS demonstrate its capacity to support problem formulation, hierarchical decomposition, and solution generation. The research also provides new insights into the FBS framework and meta-level reasoning in early design stages.

{"title":"Knowledge augmented generalizer specializer: A framework for early stage design exploration","authors":"Vijayalaxmi Sahadevan , Rohin Joshi , Kane Borg , Vishal Singh , Abhishek Raj Singh , Bilal Muhammed , Soban Babu Beemaraj , Amol Joshi","doi":"10.1016/j.aei.2025.103141","DOIUrl":"10.1016/j.aei.2025.103141","url":null,"abstract":"<div><div>In non-routine engineering design projects, the design outcome is determined by how the problem is formulated and represented in the early conceptual stage. The problem representation comprises schemas, ontologies, variables, and parameters relevant to the given problem class. Despite the critical role of early conceptual decisions in shaping the eventual design outcome, most of the computational support and automation are focused on the latter stages of parametric modelling, problem-solving, and optimization. There is inadequate support for aiding and automating problem formulation, variable and parameter identification and representation, and early-stage conceptual decisions. Therefore, this paper presents an innovative, transparent, and explainable method employing semantic reasoning to automate the step-by-step conceptual design generation process, including problem formulation, identification and representation of the variables and parameters and their dependencies. The method is realized through a novel framework called Knowledge Augmented Generalizer Specializer (KAGS). KAGS employs the Function-Behavior-Structure (FBS) ontology and the Graph-of-Thought (GoT) mechanism to enable automated reasoning with a Large Language Model (LLM). The workflow comprises various stages: problem breakdown, design prototype creation, assessment, and prototype merging. The framework is implemented and tested on a Subsea Layout (SSL) planning problem, a special class of infrastructure planning projects in deep-sea oil and gas production systems. The experimentations with KAGS demonstrate its capacity to support problem formulation, hierarchical decomposition, and solution generation. The research also provides new insights into the FBS framework and <em>meta</em>-level reasoning in early design stages.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103141"},"PeriodicalIF":8.0,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136971","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

Dual adversarial and contrastive network for single-source domain generalization in fault diagnosis

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

Advanced Engineering Informatics

Pub Date : 2025-02-03 DOI: 10.1016/j.aei.2025.103140

Guangqiang Li , M. Amine Atoui , Xiangshun Li

Domain generalization achieves fault diagnosis on unseen modes. In process industrial systems, fault samples are limited, and it is quite common that the available fault data are from a single mode. Extracting domain-invariant features from single-mode data for unseen mode fault diagnosis poses challenges. Existing methods utilize a generator module to simulate samples of unseen modes. However, multi-mode samples contain complex spatiotemporal information, which brings significant difficulties to accurate sample generation. To solve this problem, this paper proposed a dual adversarial and contrastive network (DACN) for single-source domain generalization in fault diagnosis. The main idea of DACN is to generate diverse sample features and extract domain-invariant feature representations. An adversarial pseudo-sample feature generation strategy is developed to create fake unseen mode sample features with sufficient semantic information and diversity, leveraging adversarial learning between the feature transformer and domain-invariant feature extractor. An enhanced domain-invariant feature extraction strategy is designed to capture common feature representations across multi-modes, utilizing contrastive learning and adversarial learning between the domain-invariant feature extractor and the discriminator. Experiments on the Tennessee Eastman process and continuous stirred-tank reactor demonstrate that DACN achieves high classification accuracy on unseen modes while maintaining a small model size.

{"title":"Dual adversarial and contrastive network for single-source domain generalization in fault diagnosis","authors":"Guangqiang Li , M. Amine Atoui , Xiangshun Li","doi":"10.1016/j.aei.2025.103140","DOIUrl":"10.1016/j.aei.2025.103140","url":null,"abstract":"<div><div>Domain generalization achieves fault diagnosis on unseen modes. In process industrial systems, fault samples are limited, and it is quite common that the available fault data are from a single mode. Extracting domain-invariant features from single-mode data for unseen mode fault diagnosis poses challenges. Existing methods utilize a generator module to simulate samples of unseen modes. However, multi-mode samples contain complex spatiotemporal information, which brings significant difficulties to accurate sample generation. To solve this problem, this paper proposed a dual adversarial and contrastive network (DACN) for single-source domain generalization in fault diagnosis. The main idea of DACN is to generate diverse sample features and extract domain-invariant feature representations. An adversarial pseudo-sample feature generation strategy is developed to create fake unseen mode sample features with sufficient semantic information and diversity, leveraging adversarial learning between the feature transformer and domain-invariant feature extractor. An enhanced domain-invariant feature extraction strategy is designed to capture common feature representations across multi-modes, utilizing contrastive learning and adversarial learning between the domain-invariant feature extractor and the discriminator. Experiments on the Tennessee Eastman process and continuous stirred-tank reactor demonstrate that DACN achieves high classification accuracy on unseen modes while maintaining a small model size.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103140"},"PeriodicalIF":8.0,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137038","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

Collaborative scheduling of handling equipment in automated container terminals with limited AGV-mates considering energy consumption

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

Advanced Engineering Informatics

Pub Date : 2025-02-03 DOI: 10.1016/j.aei.2025.103133

Xurui Yang , Hongtao Hu , Chen Cheng

AGV-mates (automated guided vehicle, AGV) are a type of buffering equipment installed in the seaside area of the yard block, which can decouple AGV and yard crane operations. In recent years, an AGV charging function has been integrated in AGV-mates, providing AGVs with an alternative charging method besides battery recovery at the battery swapping station. This has resulted in time constraints and additional energy replenishment decisions in collaborative scheduling optimization, complicating the terminal equipment scheduling problem. Therefore, this paper investigates the collaborative scheduling problem of yard equipment in each operation stage of an automated container terminal, proposes charging-swapping mode for AGV energy replenishment, and develops a mixed integer programming model to minimize equipment no-load energy consumption and operational delay costs. In order to address the difficulty of solving large-scale cases, a solution method based on the variable neighborhood search algorithm is developed. Considering the decoupling and charging characteristics of AGV-mates, local search operators for the AGVs’ task sequence, the yard crane’s task sequence, and the AGV battery swapping task nodes are designed. Finally, the efficiency and effectiveness of proposed solution and operators are verified through a series of numerical experiments. This paper presents practical equipment scheduling solutions and management strategies, compared to a single charging or swapping mode, the charging-swapping mode proposed in this paper has a significant improvement in the no-load cost and the delay cost.

{"title":"Collaborative scheduling of handling equipment in automated container terminals with limited AGV-mates considering energy consumption","authors":"Xurui Yang , Hongtao Hu , Chen Cheng","doi":"10.1016/j.aei.2025.103133","DOIUrl":"10.1016/j.aei.2025.103133","url":null,"abstract":"<div><div>AGV-mates (automated guided vehicle, AGV) are a type of buffering equipment installed in the seaside area of the yard block, which can decouple AGV and yard crane operations. In recent years, an AGV charging function has been integrated in AGV-mates, providing AGVs with an alternative charging method besides battery recovery at the battery swapping station. This has resulted in time constraints and additional energy replenishment decisions in collaborative scheduling optimization, complicating the terminal equipment scheduling problem. Therefore, this paper investigates the collaborative scheduling problem of yard equipment in each operation stage of an automated container terminal, proposes charging-swapping mode for AGV energy replenishment, and develops a mixed integer programming model to minimize equipment no-load energy consumption and operational delay costs. In order to address the difficulty of solving large-scale cases, a solution method based on the variable neighborhood search algorithm is developed. Considering the decoupling and charging characteristics of AGV-mates, local search operators for the AGVs’ task sequence, the yard crane’s task sequence, and the AGV battery swapping task nodes are designed. Finally, the efficiency and effectiveness of proposed solution and operators are verified through a series of numerical experiments. This paper presents practical equipment scheduling solutions and management strategies, compared to a single charging or swapping mode, the charging-swapping mode proposed in this paper has a significant improvement in the no-load cost and the delay cost.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103133"},"PeriodicalIF":8.0,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137074","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

Fractional-order PID-based search algorithms: A math-inspired meta-heuristic technique with historical information consideration

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

Advanced Engineering Informatics

Pub Date : 2025-02-03 DOI: 10.1016/j.aei.2024.103088

Guangyao Chen , Yangze Liang , Ziyang Jiang , Sihao Li , Heng Li , Zhao Xu

The PID-based Search Algorithm (PSA) is a novel math-inspired metaheuristic algorithm. However, the traditional PSA, based on PID principles, only considers the current population information. To investigate the influence of Population Historical Information (PHI) on the convergence performance of PSA and design a more effective population evolution mechanism, we drew inspiration from the fractional-order PID and introduced the fractional-order Nabla operator, which is well-suited for modeling discrete systems characterized by memory and heredity, to improve PSA. We proposed three fractional-order variants of PSA, named FoPSA-I, FoPSA-II, and FoPSA-III, based on three types of historical information in the population update process: error, input, and position. Through fractional-order sensitivity analysis on CEC benchmark test functions and numerical experiments in relevant engineering applications, we found that among the three FoPSA variants, FoPSA-III, which considers historical position information, showed significant differences in convergence performance compared to PSA, whereas FoPSA-I and FoPSA-II showed minimal differences from PSA. Additionally, the p-values obtained from the Wilcoxon test further validated the differences among the three FoPSAs and PSA, with p-values for FoPSA-I, FoPSA-II, and FoPSA-III being 0.1446, 0.0475, and 0.0019, respectively. Finally, through mathematical analysis, we qualitatively explored the reasons for the differing convergence performance of the three FoPSA variants. The results indicate that considering historical position information in the PSA population update process can enhance population diversity and the algorithm’s convergence performance. This provides new insights into the design of population update mechanisms in metaheuristic algorithms.

{"title":"Fractional-order PID-based search algorithms: A math-inspired meta-heuristic technique with historical information consideration","authors":"Guangyao Chen , Yangze Liang , Ziyang Jiang , Sihao Li , Heng Li , Zhao Xu","doi":"10.1016/j.aei.2024.103088","DOIUrl":"10.1016/j.aei.2024.103088","url":null,"abstract":"<div><div>The PID-based Search Algorithm (PSA) is a novel math-inspired metaheuristic algorithm. However, the traditional PSA, based on PID principles, only considers the current population information. To investigate the influence of Population Historical Information (PHI) on the convergence performance of PSA and design a more effective population evolution mechanism, we drew inspiration from the fractional-order PID and introduced the fractional-order Nabla operator, which is well-suited for modeling discrete systems characterized by memory and heredity, to improve PSA. We proposed three fractional-order variants of PSA, named FoPSA-I, FoPSA-II, and FoPSA-III, based on three types of historical information in the population update process: error, input, and position. Through fractional-order sensitivity analysis on CEC benchmark test functions and numerical experiments in relevant engineering applications, we found that among the three FoPSA variants, FoPSA-III, which considers historical position information, showed significant differences in convergence performance compared to PSA, whereas FoPSA-I and FoPSA-II showed minimal differences from PSA. Additionally, the <em>p</em>-values obtained from the Wilcoxon test further validated the differences among the three FoPSAs and PSA, with <em>p</em>-values for FoPSA-I, FoPSA-II, and FoPSA-III being 0.1446, 0.0475, and 0.0019, respectively. Finally, through mathematical analysis, we qualitatively explored the reasons for the differing convergence performance of the three FoPSA variants. The results indicate that considering historical position information in the PSA population update process can enhance population diversity and the algorithm’s convergence performance. This provides new insights into the design of population update mechanisms in metaheuristic algorithms.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103088"},"PeriodicalIF":8.0,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137076","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 collaborative adversarial framework: Distribution characteristics-guided alignment mechanism for fault diagnosis of machines considering domain shift

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

Advanced Engineering Informatics

Pub Date : 2025-02-03 DOI: 10.1016/j.aei.2025.103159

Xiaoxuan Fan , Lixiang Duan , Na Zhang , Mingyu Shen

Fault diagnosis of mechanical systems is essential to minimize damage and downtime in industrial fields. These systems frequently operate under varying and harsh conditions, leading to substantial changes in data distributions, commonly referred to as domain shift problem. This phenomenon presents a significant challenge for reliable fault diagnosis. Although many unsupervised domain adaptation methods effectively align data distributions, they often depend on target-domain pseudo labels. This dependency may lead to inaccurate diagnoses, particularly in the presence of abnormal samples. To address this limitation, a collaborative adversarial framework is proposed to exploit the intrinsic distribution characteristics of mechanical vibration signals to achieve distribution alignment. This framework introduces a two-level adversarial strategy to reduce distribution discrepancies. At the domain level, a novel Domain Alignment Loss (DAL) is designed to guide the adversarial game between the feature generator and the domain discriminator, thereby reducing marginal distribution discrepancies by considering both the amplitude and variability of vibration signals. At the class level, a new Class Alignment Loss (CAL) is proposed to steer the adversarial game between the feature generator and the two classifiers, using Gaussian Mixture Models (GMM) and Reproducing Kernel Hilbert Space (RKHS) to provide a more accurate measurement of conditional distribution discrepancies. Results on two datasets show that the proposed method achieves superior alignment capability and higher diagnostic accuracy compared to other state-of-the-art methods.

{"title":"A collaborative adversarial framework: Distribution characteristics-guided alignment mechanism for fault diagnosis of machines considering domain shift","authors":"Xiaoxuan Fan , Lixiang Duan , Na Zhang , Mingyu Shen","doi":"10.1016/j.aei.2025.103159","DOIUrl":"10.1016/j.aei.2025.103159","url":null,"abstract":"<div><div>Fault diagnosis of mechanical systems is essential to minimize damage and downtime in industrial fields. These systems frequently operate under varying and harsh conditions, leading to substantial changes in data distributions, commonly referred to as domain shift problem. This phenomenon presents a significant challenge for reliable fault diagnosis. Although many unsupervised domain adaptation methods effectively align data distributions, they often depend on target-domain pseudo labels. This dependency may lead to inaccurate diagnoses, particularly in the presence of abnormal samples. To address this limitation, a collaborative adversarial framework is proposed to exploit the intrinsic distribution characteristics of mechanical vibration signals to achieve distribution alignment. This framework introduces a two-level adversarial strategy to reduce distribution discrepancies. At the domain level, a novel Domain Alignment Loss (DAL) is designed to guide the adversarial game between the feature generator and the domain discriminator, thereby reducing marginal distribution discrepancies by considering both the amplitude and variability of vibration signals. At the class level, a new Class Alignment Loss (CAL) is proposed to steer the adversarial game between the feature generator and the two classifiers, using Gaussian Mixture Models (GMM) and Reproducing Kernel Hilbert Space (RKHS) to provide a more accurate measurement of conditional distribution discrepancies. Results on two datasets show that the proposed method achieves superior alignment capability and higher diagnostic accuracy compared to other state-of-the-art methods.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103159"},"PeriodicalIF":8.0,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137073","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

Rainflow evolution model: A holistic method of complex product functional design

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

Advanced Engineering Informatics

Pub Date : 2025-02-03 DOI: 10.1016/j.aei.2025.103162

Chuan He , Mingyan Zhao , Runhua Tan

Product complexity increases along with the increase of product functions. Effective methods are required in complex product development. Axiomatic design can reduce product complexity, but there are deficiencies in innovation improvement. A rainflow evolution model is proposed based on the technological evolution law and scientific effect: it can realize the innovative improvement of complex product functional design processes. Firstly, the functional design direction and the corresponding substitutability technical knowledge are mined for complex products. Then, the technological evolution law and su-field models are introduced to construct the field-combination selection matrix, which defines the design path of the new structure. The scientific effects are retrieved based on the conversion of energy forms, and a new scheme is designed using the analogy method. The introduction of cross-domain knowledge for complex product improves the innovation of functional design. The proposed method is applied to develop a powder dryer machine, to prove its feasibility and effectiveness.

引用次数: 0

A multi-aircraft co-operative trajectory planning model under dynamic thunderstorm cells using decentralized deep reinforcement learning

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

Advanced Engineering Informatics

Pub Date : 2025-02-03 DOI: 10.1016/j.aei.2025.103157

Bizhao Pang , Xinting Hu , Mingcheng Zhang , Sameer Alam , Guglielmo Lulli

Climate change induces an increased frequency of adverse weather, particularly thunderstorms, posing significant safety and efficiency challenges in en route airspace, especially in oceanic regions with limited air traffic control services. These conditions require multi-aircraft cooperative trajectory planning to avoid both dynamic thunderstorms and other aircraft. Existing literature has typically relied on centralized approaches and single-agent principles, which lack coordination and robustness when surrounding aircraft or thunderstorms change paths, leading to scalability issues due to heavy trajectory regeneration needs. To address these gaps, this paper introduces a multi-agent cooperative method for autonomous trajectory planning. The problem is modeled as a Decentralized Markov Decision Process (DEC-MDP) and solved using an Independent Deep Deterministic Policy Gradient (IDDPG) learning framework. A shared actor-critic network is trained using combined experiences from all aircraft to optimize joint behavior. During execution, each aircraft acts independently based on its own observations, with coordination ensured through the shared policy. The model is validated through extensive simulations, including uncertainty analysis, baseline comparisons, and ablation studies. Under known thunderstorm paths, the model achieved a 2 % loss of separation rate, increasing to 4 % with random storm paths. ETA uncertainty analysis demonstrated the model’s robustness, while baseline comparisons with the Fast Marching Tree and centralized DDPG highlighted its scalability and efficiency. These findings contribute to advancing autonomous aircraft operations.

{"title":"A multi-aircraft co-operative trajectory planning model under dynamic thunderstorm cells using decentralized deep reinforcement learning","authors":"Bizhao Pang , Xinting Hu , Mingcheng Zhang , Sameer Alam , Guglielmo Lulli","doi":"10.1016/j.aei.2025.103157","DOIUrl":"10.1016/j.aei.2025.103157","url":null,"abstract":"<div><div>Climate change induces an increased frequency of adverse weather, particularly thunderstorms, posing significant safety and efficiency challenges in en route airspace, especially in oceanic regions with limited air traffic control services. These conditions require multi-aircraft cooperative trajectory planning to avoid both dynamic thunderstorms and other aircraft. Existing literature has typically relied on centralized approaches and single-agent principles, which lack coordination and robustness when surrounding aircraft or thunderstorms change paths, leading to scalability issues due to heavy trajectory regeneration needs. To address these gaps, this paper introduces a multi-agent cooperative method for autonomous trajectory planning. The problem is modeled as a Decentralized Markov Decision Process (DEC-MDP) and solved using an Independent Deep Deterministic Policy Gradient (IDDPG) learning framework. A shared actor-critic network is trained using combined experiences from all aircraft to optimize joint behavior. During execution, each aircraft acts independently based on its own observations, with coordination ensured through the shared policy. The model is validated through extensive simulations, including uncertainty analysis, baseline comparisons, and ablation studies. Under known thunderstorm paths, the model achieved a 2 % loss of separation rate, increasing to 4 % with random storm paths. ETA uncertainty analysis demonstrated the model’s robustness, while baseline comparisons with the Fast Marching Tree and centralized DDPG highlighted its scalability and efficiency. These findings contribute to advancing autonomous aircraft operations.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103157"},"PeriodicalIF":8.0,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137037","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