Pub Date : 2026-01-10DOI: 10.1016/j.aei.2026.104321
Jinjing Li , Xianbo Zhao , Haizhe Yu , Lili Gao , Xiaopeng Deng , Bon-Gang Hwang
Over 85 % of construction data remains unstructured, creating urgent needs for text mining (TM). While considerable attention has been directed toward the evolution of TM, a critical gap persists in the form of diachronic analysis, with limited exploration of its trajectory in the context of large language models (LLMs). Hence, this research aims to: (1) generate the LLM-based TM framework for construction; (2) explore different evolutions of TM methods in construction; and (3) identify the driving factors for the evolution. To achieve these objectives, two LLM-based TM methods were used to review the TM-related literature. The results reveal a dual delay pattern: internally, statistical machine learning maintains dominance over LLMs in the construction industry, while externally, LLM adoption lags 2–3 years behind sectors such as healthcare and biomedicine. The study extends existing taxonomies by introducing novel data sources (elicited discourse corpora and multimodal data) and establishing software-based analysis as a distinct methodological stage. Moreover, it addresses the research paradigm gap for LLM-based TM, offering enhanced strategic guidance for practitioners in selecting TM tools.
{"title":"Evolution of text mining in construction industry: an LLM-driven analysis of statistical machine learning dominance and internal-external delayed LLM adoption","authors":"Jinjing Li , Xianbo Zhao , Haizhe Yu , Lili Gao , Xiaopeng Deng , Bon-Gang Hwang","doi":"10.1016/j.aei.2026.104321","DOIUrl":"10.1016/j.aei.2026.104321","url":null,"abstract":"<div><div>Over 85 % of construction data remains unstructured, creating urgent needs for text mining (TM). While considerable attention has been directed toward the evolution of TM, a critical gap persists in the form of diachronic analysis, with limited exploration of its trajectory in the context of large language models (LLMs). Hence, this research aims to: (1) generate the LLM-based TM framework for construction; (2) explore different evolutions of TM methods in construction; and (3) identify the driving factors for the evolution. To achieve these objectives, two LLM-based TM methods were used to review the TM-related literature. The results reveal a dual delay pattern: internally, statistical machine learning maintains dominance over LLMs in the construction industry, while externally, LLM adoption lags 2–3 years behind sectors such as healthcare and biomedicine. The study extends existing taxonomies by introducing novel data sources (elicited discourse corpora and multimodal data) and establishing software-based analysis as a distinct methodological stage. Moreover, it addresses the research paradigm gap for LLM-based TM, offering enhanced strategic guidance for practitioners in selecting TM tools.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104321"},"PeriodicalIF":9.9,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926969","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}
Pub Date : 2026-01-10DOI: 10.1016/j.aei.2026.104320
Yong Wang , Jiawei Cui , Changhai Zhai , Xigui Tao , Yuhao Li
The rapid assessment of constructed facilities after extreme events is a knowledge-intensive task critical for effective emergency management. However, methodologies for automated, object-level damage assessment at scale remain underdeveloped, often lacking fine-grained interpretability or scalability. This paper introduces a framework that integrates instance segmentation with temporal Vision Language Model (VLM), which is empowered with visual damage reasoning capabilities through fine-tuning on domain-specific knowledge, for the automated and interpretable assessment of structural assets from satellite imagery. Our three-stage approach synergizes: high-precision segmentation via a modified Segment Anything Model (SAM); spatiotemporal data pairing to isolate asset-specific changes; and BDAChat, the first temporal VLM fine-tuned for object-level damage assessment. Unlike traditional black-box models, BDAChat provides both high-accuracy damage classification and causal interpretations, serving as an intelligent damage inference system. The framework’s effectiveness and scalability are validated through the Lahaina wildfire and hurricane Ian case study. This modular framework automates and accelerates the object-level building damage assessment process, demonstrating significant potential for real-time building damage evaluation and resilient infrastructure planning. The code and dataset are available at https://github.com/WangYong921/BDAChat.
{"title":"Integrating segmentation and vision-language model for automated and interpretable building damage assessment from satellite imagery","authors":"Yong Wang , Jiawei Cui , Changhai Zhai , Xigui Tao , Yuhao Li","doi":"10.1016/j.aei.2026.104320","DOIUrl":"10.1016/j.aei.2026.104320","url":null,"abstract":"<div><div>The rapid assessment of constructed facilities after extreme events is a knowledge-intensive task critical for effective emergency management. However, methodologies for automated, object-level damage assessment at scale remain underdeveloped, often lacking fine-grained interpretability or scalability. This paper introduces a framework that integrates instance segmentation with temporal Vision Language Model (VLM), which is empowered with visual damage reasoning capabilities through fine-tuning on domain-specific knowledge, for the automated and interpretable assessment of structural assets from satellite imagery. Our three-stage approach synergizes: high-precision segmentation via a modified Segment Anything Model (SAM); spatiotemporal data pairing to isolate asset-specific changes; and BDAChat, the first temporal VLM fine-tuned for object-level damage assessment. Unlike traditional black-box models, BDAChat provides both high-accuracy damage classification and causal interpretations, serving as an intelligent damage inference system. The framework’s effectiveness and scalability are validated through the Lahaina wildfire and hurricane Ian case study. This modular framework automates and accelerates the object-level building damage assessment process, demonstrating significant potential for real-time building damage evaluation and resilient infrastructure planning. The code and dataset are available at <span><span>https://github.com/WangYong921/BDAChat</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104320"},"PeriodicalIF":9.9,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978254","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}
Pub Date : 2026-01-10DOI: 10.1016/j.aei.2025.104299
Wentong Guo , Wenzhu Xu , Chengcheng Yang , Zhijian Zhao , Xi Gao , WenBin Yao , Sheng Jin
Urban traffic accidents result in significant casualties and property losses. Conducting traffic risk mapping and inference for urban areas provides substantial benefits for accident prevention as well as future planning and governance. However, pixel-level fine-grained inference of urban traffic risk maps remains challenging, primarily due to the complex layout of urban road networks, the temporal variability of traffic dynamics, and the heterogeneity of spatial semantic information. In this study, we propose an end-to-end Context-Aware Risk Feature Perception and Inference Network (CRFPI-Net) based on multimodal data to achieve fine-grained inference of urban traffic risk maps. In CRFPI-Net, three separate branches are designed to capture risk features from satellite remote sensing imagery, spatiotemporal traffic sequences, and area-of-interest (AOI) semantic information. The risk-aware features from each branch are integrated using a gated fusion mechanism to eliminate redundant information, and the fused features are further processed by context-aware multi-scale correlation analysis to reduce the adverse impact of heterogeneous variations in risk regions on risk perception. Finally, CRFPI-Net produces pixel-level inference maps of urban traffic accident risk, enabling effective and low-cost guidance for traffic accident prevention. The proposed model is quantitatively evaluated on real-world datasets and achieves state-of-the-art performance. Ablation experiments further demonstrate the rationality and effectiveness of the designed modules. The code and pretrained models for urban traffic risk mapping are publicly available at https://github.com/gwt-ZJU/CRFPI-Net.
{"title":"CRFPI-Net: context-aware risk feature perception and inference network for pixel-level urban traffic risk mapping","authors":"Wentong Guo , Wenzhu Xu , Chengcheng Yang , Zhijian Zhao , Xi Gao , WenBin Yao , Sheng Jin","doi":"10.1016/j.aei.2025.104299","DOIUrl":"10.1016/j.aei.2025.104299","url":null,"abstract":"<div><div>Urban traffic accidents result in significant casualties and property losses. Conducting traffic risk mapping and inference for urban areas provides substantial benefits for accident prevention as well as future planning and governance. However, pixel-level fine-grained inference of urban traffic risk maps remains challenging, primarily due to the complex layout of urban road networks, the temporal variability of traffic dynamics, and the heterogeneity of spatial semantic information. In this study, we propose an end-to-end Context-Aware Risk Feature Perception and Inference Network (CRFPI-Net) based on multimodal data to achieve fine-grained inference of urban traffic risk maps. In CRFPI-Net, three separate branches are designed to capture risk features from satellite remote sensing imagery, spatiotemporal traffic sequences, and area-of-interest (AOI) semantic information. The risk-aware features from each branch are integrated using a gated fusion mechanism to eliminate redundant information, and the fused features are further processed by context-aware multi-scale correlation analysis to reduce the adverse impact of heterogeneous variations in risk regions on risk perception. Finally, CRFPI-Net produces pixel-level inference maps of urban traffic accident risk, enabling effective and low-cost guidance for traffic accident prevention. The proposed model is quantitatively evaluated on real-world datasets and achieves state-of-the-art performance. Ablation experiments further demonstrate the rationality and effectiveness of the designed modules. The code and pretrained models for urban traffic risk mapping are publicly available at <span><span>https://github.com/gwt-ZJU/CRFPI-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104299"},"PeriodicalIF":9.9,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978253","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}
Pub Date : 2026-01-10DOI: 10.1016/j.aei.2025.104305
Li Zhu , Ching-Lien Liu , Junghui Chen
To address the challenges of zero-shot fault diagnosis in industrial systems, this study proposes a novel approach—Meta-CCVAE, a constrained conditional variational autoencoder (CCVAE) embedded within a meta-learning framework. By leveraging predefined attributes, Meta-CCVAE expands the representation space for unseen faults across three training phases, improving the quality of generated samples and minimizing overlap with known faults. To mitigate the limitations of scarce fault data, the framework incorporates both common and individual models: the common model enables knowledge sharing across fault classes, while the individual model ensures accurate fault characterization. This dual-model strategy reduces the impact of limited data and lowers computational costs. Experimental results on both simulated and real-world datasets validate the effectiveness of Meta-CCVAE, highlighting its potential for reliable zero-shot fault identification in industrial applications.
{"title":"Enhancing industrial fault diagnosis via A Meta-learning: Zero-shot identification with constraint conditional variational autoencoder","authors":"Li Zhu , Ching-Lien Liu , Junghui Chen","doi":"10.1016/j.aei.2025.104305","DOIUrl":"10.1016/j.aei.2025.104305","url":null,"abstract":"<div><div>To address the challenges of zero-shot fault diagnosis in industrial systems, this study proposes a novel approach—Meta-CCVAE, a constrained conditional variational autoencoder (CCVAE) embedded within a <em>meta</em>-learning framework. By leveraging predefined attributes, Meta-CCVAE expands the representation space for unseen faults across three training phases, improving the quality of generated samples and minimizing overlap with known faults. To mitigate the limitations of scarce fault data, the framework incorporates both common and individual models: the common model enables knowledge sharing across fault classes, while the individual model ensures accurate fault characterization. This dual-model strategy reduces the impact of limited data and lowers computational costs. Experimental results on both simulated and real-world datasets validate the effectiveness of Meta-CCVAE, highlighting its potential for reliable zero-shot fault identification in industrial applications.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104305"},"PeriodicalIF":9.9,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978249","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}
Pub Date : 2026-01-09DOI: 10.1016/j.aei.2026.104311
Emmanuel A. Bamidele
Plasmonic devices, fundamental to modern nanophotonics, exploit resonant interactions between light and free electrons in metals to achieve enhanced light trapping and electromagnetic field confinement. However, modeling their complex, nonlinear optical responses remain computationally intensive. In this work, we combine finite-difference time-domain (FDTD) simulations with machine learning (ML) to simulate and predict absorbed power behavior in multilayer plasmonic stacks composed of SiO2, gold (Au), silver (Ag), and indium tin oxide (ITO). By varying Au and Ag thicknesses (10–50 nm) across a spectral range of 300–1500 nm, we generate spatial absorption maps and integrated power metrics from full-wave solutions to Maxwell’s equations. A multilayer perceptron models global absorption behavior with a mean absolute error (MAE) of 0.0953, while a convolutional neural network predicts spatial absorption distributions with an MAE of 0.0101. SHapley Additive exPlanations identify plasmonic layer thickness and excitation wavelength as dominant contributors to absorption, which peaks between 450 and 850 nm. Gold demonstrates broader and more sustained absorption compared to silver, although both metals exhibit reduced efficiency outside the resonance window. The integrated FDTD–ML framework accelerates plasmonic design while maintaining physical interpretability and predictive accuracy, enabling efficient exploration of tunable optical responses in multilayer nanophotonic systems for applications in optical sensing, photovoltaics, and device engineering.
{"title":"Tunable plasmonic absorption in metal–dielectric multilayers via FDTD simulations and an explainable machine learning approach","authors":"Emmanuel A. Bamidele","doi":"10.1016/j.aei.2026.104311","DOIUrl":"10.1016/j.aei.2026.104311","url":null,"abstract":"<div><div>Plasmonic devices, fundamental to modern nanophotonics, exploit resonant interactions between light and free electrons in metals to achieve enhanced light trapping and electromagnetic field confinement. However, modeling their complex, nonlinear optical responses remain computationally intensive. In this work, we combine finite-difference time-domain (FDTD) simulations with machine learning (ML) to simulate and predict absorbed power behavior in multilayer plasmonic stacks composed of SiO<sub>2</sub>, gold (Au), silver (Ag), and indium tin oxide (ITO). By varying Au and Ag thicknesses (10–50 nm) across a spectral range of 300–1500 nm, we generate spatial absorption maps and integrated power metrics from full-wave solutions to Maxwell’s equations. A multilayer perceptron models global absorption behavior with a mean absolute error (MAE) of 0.0953, while a convolutional neural network predicts spatial absorption distributions with an MAE of 0.0101. SHapley Additive exPlanations identify plasmonic layer thickness and excitation wavelength as dominant contributors to absorption, which peaks between 450 and 850 nm. Gold demonstrates broader and more sustained absorption compared to silver, although both metals exhibit reduced efficiency outside the resonance window. The integrated FDTD–ML framework accelerates plasmonic design while maintaining physical interpretability and predictive accuracy, enabling efficient exploration of tunable optical responses in multilayer nanophotonic systems for applications in optical sensing, photovoltaics, and device engineering.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104311"},"PeriodicalIF":9.9,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926900","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}
Pub Date : 2026-01-09DOI: 10.1016/j.aei.2025.104308
Shouqi Wang , Xuejin Gao , Huayun Han , Huihui Gao , Yongsheng Qi , Huazheng Han , Huimin Cheng
The Universal Domain Adaptation (UniDA) method can realize cross-device transfer diagnosis of ground source heat pump (GSHP) units when the class space of the target domain is unknown. However, existing methods generally design models on the premise that unknown faults exist in the target domain. When there are actually no unknown faults, the models often misclassify a large number of samples as unknown fault classes, thereby significantly reducing the diagnostic accuracy. Therefore, this paper proposes a UniDA method with Unknown Fault Awareness Capability (UFAC), which addresses the transfer challenge of inconsistent class spaces in GSHP units from a new perspective. First, the network trained on the source domain is used to perform feature extraction on the source domain and the target domain data, compute intra-class compactness and inter-class distance, and determine whether unknown fault classes exist in the target domain by combining One-sided T-test (OST) and Kernel Density Estimation (KDE). Subsequently, corresponding diagnostic models are constructed according to the judgment results, and the Balanced Adversarial Alignment (BAA) mechanism is introduced during training to achieve balanced cross-domain category distribution, unifying the model into the closed-set and open-set frameworks and improving cross-domain diagnostic efficiency. Experimental results show that this method achieves an average accuracy of 86.67 % in cross-device diagnosis of GSHP units, with performance significantly superior to existing methods, verifying its practicality and engineering application prospects under complex transfer environments.
{"title":"A universal domain adaptive fault diagnosis method for ground source heat pump units with unknown fault awareness capability","authors":"Shouqi Wang , Xuejin Gao , Huayun Han , Huihui Gao , Yongsheng Qi , Huazheng Han , Huimin Cheng","doi":"10.1016/j.aei.2025.104308","DOIUrl":"10.1016/j.aei.2025.104308","url":null,"abstract":"<div><div>The Universal Domain Adaptation (UniDA) method can realize cross-device transfer diagnosis of ground source heat pump (GSHP) units when the class space of the target domain is unknown. However, existing methods generally design models on the premise that unknown faults exist in the target domain. When there are actually no unknown faults, the models often misclassify a large number of samples as unknown fault classes, thereby significantly reducing the diagnostic accuracy. Therefore, this paper proposes a UniDA method with Unknown Fault Awareness Capability (UFAC), which addresses the transfer challenge of inconsistent class spaces in GSHP units from a new perspective. First, the network trained on the source domain is used to perform feature extraction on the source domain and the target domain data, compute intra-class compactness and inter-class distance, and determine whether unknown fault classes exist in the target domain by combining One-sided T-test (OST) and Kernel Density Estimation (KDE). Subsequently, corresponding diagnostic models are constructed according to the judgment results, and the Balanced Adversarial Alignment (BAA) mechanism is introduced during training to achieve balanced cross-domain category distribution, unifying the model into the closed-set and open-set frameworks and improving cross-domain diagnostic efficiency. Experimental results show that this method achieves an average accuracy of 86.67 % in cross-device diagnosis of GSHP units, with performance significantly superior to existing methods, verifying its practicality and engineering application prospects under complex transfer environments.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104308"},"PeriodicalIF":9.9,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926901","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}
Pub Date : 2026-01-09DOI: 10.1016/j.aei.2026.104313
Zhao Yongxing, Ta Yuntian, Bi Ran, Tang Bo, Lu Zhengjie, Yan Yihong, Xie Jingsong, Guo Zhibin
This paper tackles the critical challenges in bearing Remaining Useful Life (RUL) prediction, including insecure health indicator construction, ambiguous degradation damage processes, and inadequate cross-working-condition generalizability. It presents a multi-feature HI relying on joint feature distribution modeling and a RUL prediction architecture based on temporal −self-attention (TSA) based Dual-branch Transfer Adversarial Network (TSADTAN). Firstly, a self-supervised probabilistic whitened support vector data description (SPW-SVDD) method is put forward to construct multi-feature health indicators with strong robustness. Secondly, a TSA mechanism is devised to boost the model’s capability to detect early minor faults and cumulative degradation features. Finally, a dual-branch adversarial transfer learning framework is built. By combining maximum mean discrepancy (MMD) and adversarial training through the domain comment feature (CF) branch and domain specific feature (SF) branch, stable feature alignment and knowledge transfer under cross-working conditions are achieved. Four cross-working-condition transfer prediction tasks are designed on two public bearing datasets. Experimental results show that the proposed method outperforms existing mainstream methods in three evaluation metrics, verifying its feasibility and effectiveness in practical cross-working-condition tasks.
{"title":"A cross-working-condition prediction method for bearing remaining useful life based on SPW-SVDD health indicators and temporal-self -attention mechanism","authors":"Zhao Yongxing, Ta Yuntian, Bi Ran, Tang Bo, Lu Zhengjie, Yan Yihong, Xie Jingsong, Guo Zhibin","doi":"10.1016/j.aei.2026.104313","DOIUrl":"10.1016/j.aei.2026.104313","url":null,"abstract":"<div><div>This paper tackles the critical challenges in bearing Remaining Useful Life (RUL) prediction, including insecure health indicator construction, ambiguous degradation damage processes, and inadequate cross-working-condition generalizability. It presents a multi-feature HI relying on joint feature distribution modeling and a RUL prediction architecture based on temporal −self-attention (TSA) based Dual-branch Transfer Adversarial Network (TSADTAN). Firstly, a self-supervised probabilistic whitened support vector data description (SPW-SVDD) method is put forward to construct multi-feature health indicators with strong robustness. Secondly, a TSA mechanism is devised to boost the model’s capability to detect early minor faults and cumulative degradation features. Finally, a dual-branch adversarial transfer learning framework is built. By combining maximum mean discrepancy (MMD) and adversarial training through the domain comment feature (CF) branch and domain specific feature (SF) branch, stable feature alignment and knowledge transfer under cross-working conditions are achieved. Four cross-working-condition transfer prediction tasks are designed on two public bearing datasets. Experimental results show that the proposed method outperforms existing mainstream methods in three evaluation metrics, verifying its feasibility and effectiveness in practical cross-working-condition tasks.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104313"},"PeriodicalIF":9.9,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926902","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}
Pub Date : 2026-01-08DOI: 10.1016/j.aei.2025.104298
Eda Özkul
This study proposes an improved tuna swarm optimization algorithm (I-TSO) for solving global optimization and engineering design problems. However, despite its strong global search ability, tuna swarm optimization (TSO) suffers from trapping in local optima, having premature convergence, and the loss of diversity in the early stage. To eliminate these disadvantages and improve the original TSO, the proposed I-TSO algorithm uses a dimension learning-based hunting (DLH) strategy. DLH constructs a neighborhood for each tuna in the population and uses that information in the optimization process. Thus, it improves population diversity, provides a proper balance between exploration and exploitation, and prevents trapping into local optima. The performance of the proposed algorithm is evaluated on 23 classical benchmark functions, CEC-2017, CEC-2020, and CEC-2022 test suites, and compared it with eight other optimization algorithms. Comparative results demonstrate that I-TSO exhibits stable and effective optimization capabilities. Further, the Friedman test and Wilcoxon signed-rank test are conducted to statistically evaluate the performance of the proposed algorithm, and thus its superiority is statistically confirmed. Moreover, the applicability of the I-TSO in real-world problems is validated on eight engineering design problems. Consequently, the I-TSO algorithm is capable of solving both numerical and engineering design problems with its efficient and superior performance.
{"title":"An improved tuna swarm optimization with dimension learning-based hunting for global optimization and real-world engineering applications","authors":"Eda Özkul","doi":"10.1016/j.aei.2025.104298","DOIUrl":"10.1016/j.aei.2025.104298","url":null,"abstract":"<div><div>This study proposes an improved tuna swarm optimization algorithm (I-TSO) for solving global optimization and engineering design problems. However, despite its strong global search ability, tuna swarm optimization (TSO) suffers from trapping in local optima, having premature convergence, and the loss of diversity in the early stage. To eliminate these disadvantages and improve the original TSO, the proposed I-TSO algorithm uses a dimension learning-based hunting (DLH) strategy. DLH constructs a neighborhood for each tuna in the population and uses that information in the optimization process. Thus, it improves population diversity, provides a proper balance between exploration and exploitation, and prevents trapping into local optima. The performance of the proposed algorithm is evaluated on 23 classical benchmark functions, CEC-2017, CEC-2020, and CEC-2022 test suites, and compared it with eight other optimization algorithms. Comparative results demonstrate that I-TSO exhibits stable and effective optimization capabilities. Further, the Friedman test and Wilcoxon signed-rank test are conducted to statistically evaluate the performance of the proposed algorithm, and thus its superiority is statistically confirmed. Moreover, the applicability of the I-TSO in real-world problems is validated on eight engineering design problems. Consequently, the I-TSO algorithm is capable of solving both numerical and engineering design problems with its efficient and superior performance.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104298"},"PeriodicalIF":9.9,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926970","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}
Pub Date : 2026-01-08DOI: 10.1016/j.aei.2026.104312
Yuntao Zou , Zihui Lin , Qianqi Zhang , Zhichun Liu , Zeling Xu
The battery energy consumption system of lunar exploration rovers, as mission-critical equipment, confronts severe challenges under extreme environmental constraints. However, existing modeling methods face fundamental dilemmas: dynamic uncertainty leads to highly ambiguous constraint boundaries, making it difficult for traditional mathematical languages to describe complex coupling relationships; even when mathematical representations are constructed, high-dimensional nonlinear optimization problems become computationally intractable, with existing algorithms unable to address complexity barriers and lacking interpretability. In response to these challenges, this paper innovatively proposes a hierarchical Stackelberg game optimization framework based on semantic embedding. This framework transcends traditional optimization paradigms by deeply integrating the cognitive intelligence of large language models with the mathematical precision of game theory: large language models acknowledge that overall behavior cannot be predicted from simple combinations of parts, processing fuzzy constraints and cross-domain knowledge integration through semantic understanding; the hierarchical structure of Stackelberg games naturally adapts to the hierarchical decision-making requirements of battery allocation, with multi-agent game frameworks effectively handling coordination and competition relationships between batteries. Through semantic embedding technology, natural language constraints are automatically transformed into mathematical objects comprehensible to game participants, with cognitive intelligence handling the “incomputable” complexity components while game theory ensures “provable” mathematical convergence, synergistically achieving the important paradigm transition from “perfect rationality” to “bounded rationality,” thereby providing a theoretically rigorous and practically viable unified solution for intelligent decision-making in mission-critical systems.
{"title":"Large language models enable semantic-guided hierarchical games for intelligent battery coordination","authors":"Yuntao Zou , Zihui Lin , Qianqi Zhang , Zhichun Liu , Zeling Xu","doi":"10.1016/j.aei.2026.104312","DOIUrl":"10.1016/j.aei.2026.104312","url":null,"abstract":"<div><div>The battery energy consumption system of lunar exploration rovers, as mission-critical equipment, confronts severe challenges under extreme environmental constraints. However, existing modeling methods face fundamental dilemmas: dynamic uncertainty leads to highly ambiguous constraint boundaries, making it difficult for traditional mathematical languages to describe complex coupling relationships; even when mathematical representations are constructed, high-dimensional nonlinear optimization problems become computationally intractable, with existing algorithms unable to address complexity barriers and lacking interpretability. In response to these challenges, this paper innovatively proposes a hierarchical Stackelberg game optimization framework based on semantic embedding. This framework transcends traditional optimization paradigms by deeply integrating the cognitive intelligence of large language models with the mathematical precision of game theory: large language models acknowledge that overall behavior cannot be predicted from simple combinations of parts, processing fuzzy constraints and cross-domain knowledge integration through semantic understanding; the hierarchical structure of Stackelberg games naturally adapts to the hierarchical decision-making requirements of battery allocation, with multi-agent game frameworks effectively handling coordination and competition relationships between batteries. Through semantic embedding technology, natural language constraints are automatically transformed into mathematical objects comprehensible to game participants, with cognitive intelligence handling the “incomputable” complexity components while game theory ensures “provable” mathematical convergence, synergistically achieving the important paradigm transition from “perfect rationality” to “bounded rationality,” thereby providing a theoretically rigorous and practically viable unified solution for intelligent decision-making in mission-critical systems.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104312"},"PeriodicalIF":9.9,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926893","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}
During the mode transition phase of hypersonic vehicles, stable electrical power supply is essential, while improper multisource power allocation tends to significantly increase fuel consumption or trigger engine safety-limit violations, further exacerbating the complexity of the power allocation problem. This paper aims to develop a deep reinforcement learning (DRL)-based energy management strategy to address these challenges and improve energy efficiency in advanced hypersonic propulsion systems. The strategy models the joint decision-making process of multisource power and engine fuel-flow rates distribution as a Markov decision process, and specifies a reward function that integrates cumulative additional fuel consumption, system demand constraints, and engine safety constraints. The double Q-learning with multi-replay buffer and adaptive soft update for deep deterministic policy gradient algorithm is introduced. First, it employs a state-partitioned multistage experience replay mechanism that organizes the experience buffer according to the sub-stages of the mode transition process. Second, an uncertainty-weighted double Q-network independently evaluates state-action pairs through two critic networks, fusing their outputs due to estimation uncertainty caused by engine state nonlinearities. Finally, a gradient-guided adaptive soft update adjusts the target network update rate, enabling smoother parameter updates amidst rapid engine and power generation transitions. The proposed energy management strategy effectively reduces fuel consumption, demonstrating strong policy adaptability, value estimation accuracy, and convergence stability. It achieved a fuel saving of 18.80% compared to the traditional demand-driven scheme. Relative to the basic DRL-based strategy, it improved the average reward growth by 17.9%, cumulative reward curve area by 23.5%, confidence interval convergence rate by 28.6%, and achieved a fuel saving of 4.6%.
{"title":"Energy management strategy for multisource power generation during hypersonic vehicle mode transition based on improved deep deterministic policy gradient","authors":"Xingjian Jin, Fengying Zheng, Jingyang Zhang, Jiecheng Fu, Mengmeng Lv, Jian Lu, Si Gao","doi":"10.1016/j.aei.2025.104293","DOIUrl":"10.1016/j.aei.2025.104293","url":null,"abstract":"<div><div>During the mode transition phase of hypersonic vehicles, stable electrical power supply is essential, while improper multisource power allocation tends to significantly increase fuel consumption or trigger engine safety-limit violations, further exacerbating the complexity of the power allocation problem. This paper aims to develop a deep reinforcement learning (DRL)-based energy management strategy to address these challenges and improve energy efficiency in advanced hypersonic propulsion systems. The strategy models the joint decision-making process of multisource power and engine fuel-flow rates distribution as a Markov decision process, and specifies a reward function that integrates cumulative additional fuel consumption, system demand constraints, and engine safety constraints. The double Q-learning with multi-replay buffer and adaptive soft update for deep deterministic policy gradient algorithm is introduced. First, it employs a state-partitioned multistage experience replay mechanism that organizes the experience buffer according to the sub-stages of the mode transition process. Second, an uncertainty-weighted double Q-network independently evaluates state-action pairs through two critic networks, fusing their outputs due to estimation uncertainty caused by engine state nonlinearities. Finally, a gradient-guided adaptive soft update adjusts the target network update rate, enabling smoother parameter updates amidst rapid engine and power generation transitions. The proposed energy management strategy effectively reduces fuel consumption, demonstrating strong policy adaptability, value estimation accuracy, and convergence stability. It achieved a fuel saving of 18.80% compared to the traditional demand-driven scheme. Relative to the basic DRL-based strategy, it improved the average reward growth by 17.9%, cumulative reward curve area by 23.5%, confidence interval convergence rate by 28.6%, and achieved a fuel saving of 4.6%.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104293"},"PeriodicalIF":9.9,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926892","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号