Simulation Modelling Practice and Theory最新文献_第10页

Evaluating traffic and safety impacts of diverging diamond interchange replacing roundabouts: A microsimulation study 分道菱形立交取代环形交叉路口对交通和安全影响的微观模拟研究

IF 3.5 2区计算机科学

Simulation Modelling Practice and Theory Pub Date : 2025-11-01 Epub Date: 2025-07-17 DOI: 10.1016/j.simpat.2025.103179

Jingshuo Qiu , Léah Camarcat , Paraskevi Koliou , Yuxiang Feng , Nicolette Formosa , Georgios Zacharopoulos , Paraskevi Michalaki , Panagiotis Angeloudis , Mohammed Quddus

{"title":"Evaluating traffic and safety impacts of diverging diamond interchange replacing roundabouts: A microsimulation study","authors":"Jingshuo Qiu , Léah Camarcat , Paraskevi Koliou , Yuxiang Feng , Nicolette Formosa , Georgios Zacharopoulos , Paraskevi Michalaki , Panagiotis Angeloudis , Mohammed Quddus","doi":"10.1016/j.simpat.2025.103179","DOIUrl":"10.1016/j.simpat.2025.103179","url":null,"abstract":"<div><div>With increasing traffic volumes and worsening congestion, conventional interchanges are facing ever-growing challenges. These issues can potentially be mitigated by implementing suitable alternative designs, such as the Diverging Diamond Interchange (DDI). While simulation studies and real-world implementations have validated the DDI’s superiority over conventional interchanges, existing research primarily focuses on right-hand driving and has not considered roundabout layouts prevalent in the UK. This study employs the simulation of the UK Strategic Road Network (SRN) to address this gap. Four hypothetical scenarios are constructed, transitioning conventional junctions between J23 and J26 on the M1 Motorway of SRN to DDIs. By comparing a series of Key Performance Indicators (KPIs), the study quantitatively assesses the impact of DDI implementation on traffic flow, delay and safety. The simulation results reveal that replacing roundabouts to DDIs in a motorway corridor can lead to a 55% reduction in average delay and a 5.96% increase in average speed. However, upon evaluating traffic safety through the Surrogate Safety Assessment Model, a slight decline in the majority of safety performance measures is observed. This study provides evidence to support the adoption of DDIs in the UK, highlighting the trade-offs between improved traffic flow and potential safety concerns.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"144 ","pages":"Article 103179"},"PeriodicalIF":3.5,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144702137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analysis and optimizations of PMI and rank selection algorithms for 5G NR 5G NR的PMI和rank选择算法分析与优化

IF 3.5 2区计算机科学

Simulation Modelling Practice and Theory Pub Date : 2025-11-01 Epub Date: 2025-06-19 DOI: 10.1016/j.simpat.2025.103162

Gabriel Carvalho, Sandra Lagén

{"title":"Analysis and optimizations of PMI and rank selection algorithms for 5G NR","authors":"Gabriel Carvalho, Sandra Lagén","doi":"10.1016/j.simpat.2025.103162","DOIUrl":"10.1016/j.simpat.2025.103162","url":null,"abstract":"<div><div>Multiple-Input Multiple-Output (MIMO) is crucial for enhancing spectral efficiency, channel capacity, coverage, and robustness. However, it requires significant computations to determine a precoding matrix for transmitted data streams. In closed-loop MIMO, as adopted in 3GPP 5G NR, these computations occur on the user side. To avoid transmitting large matrices, 3GPP defined codebooks with pre-defined precoding matrices indexed by the Precoding Matrix Indicator (PMI). The User Equipment (UE) selects a PMI and a Rank Indicator (RI) to report to the Next Generation Node Base (gNB) as part of the Channel State Information (CSI) feedback. PMI/RI selection can be done via exhaustive search or more efficient techniques, which are crucial for real UE implementations due to their impact on computational complexity and energy consumption. This paper analyzes various PMI/RI selection techniques using the open-source ns-3 5G-LENA simulator. We have implemented state-of-the-art techniques in the system-level simulator and carried out extensive simulation campaigns. Also, we propose new PMI/RI selection methods by focusing on performance versus computational complexity trade-offs. Our proposed techniques show a superior simulation speedup (3.71x to 1.119x) with minimal throughput degradation (3% to 3.3%) compared to exhaustive search, depending on sub-band downsampling settings. Other state-of-the-art techniques implemented exhibit greater throughput losses (up to 8.3%) for a lower speedup (up to 3.54x) or similar losses with smaller speedups and potential slowdowns.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"144 ","pages":"Article 103162"},"PeriodicalIF":3.5,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144338635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Peridynamic modeling of rock cutting under a TBM disc cutter using LS-DYNA 基于LS-DYNA的TBM盘式切割机岩石切削动力学模拟

IF 3.5 2区计算机科学

Simulation Modelling Practice and Theory Pub Date : 2025-09-01 Epub Date: 2025-05-20 DOI: 10.1016/j.simpat.2025.103146

Rashid Hajivand Dastgerdi , Mohammad Salimi , Torsten Wichtmann , Agnieszka Malinowska

{"title":"Peridynamic modeling of rock cutting under a TBM disc cutter using LS-DYNA","authors":"Rashid Hajivand Dastgerdi , Mohammad Salimi , Torsten Wichtmann , Agnieszka Malinowska","doi":"10.1016/j.simpat.2025.103146","DOIUrl":"10.1016/j.simpat.2025.103146","url":null,"abstract":"<div><div>Rock cutting force prediction and damage assessment are crucial elements in optimizing tunneling and excavation equipment performance. This study presents a numerical investigation of rock-tool interaction using a Linear Cutting Machine (LCM) test on Colorado Red Granite, implemented through the bond-based Peridynamic framework in LS-DYNA. The numerical model evaluates both normal and rolling forces at three distinct penetration depths (3.2 mm, 5.1 mm, and 6.4 mm). Results demonstrate exceptional correlation with experimental data, achieving accuracy within 0.5–4 % for normal forces and 8–14 % for rolling forces. Furthermore, the model successfully captures the morphology and extent of the induced damage zone during the cutting process. The computational efficiency is particularly noteworthy, with a runtime of only 1 hour and 33 min on a standard engineering workstation. This study establishes the bond-based Peridynamic approach in LS-DYNA as a robust and practical methodology for simulating rock-tool interactions, providing valuable insights for the optimization of cutting tool design in rock excavation applications.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"143 ","pages":"Article 103146"},"PeriodicalIF":3.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144115818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modeling and simulation of L-shaped merging behavior incorporating behavioral characteristic lines 结合行为特征线的l型合并行为建模与仿真

IF 3.5 2区计算机科学

Simulation Modelling Practice and Theory Pub Date : 2025-09-01 Epub Date: 2025-05-30 DOI: 10.1016/j.simpat.2025.103150

Wenhang Li , Yi Li , Ping Yu , Jianhua Gong , Haonan Ma

{"title":"Modeling and simulation of L-shaped merging behavior incorporating behavioral characteristic lines","authors":"Wenhang Li , Yi Li , Ping Yu , Jianhua Gong , Haonan Ma","doi":"10.1016/j.simpat.2025.103150","DOIUrl":"10.1016/j.simpat.2025.103150","url":null,"abstract":"<div><div>Merging behavior is a common phenomenon in real-life environments that may lead to congestion and even stampedes. In this study, we examined merging behavior in <span>l</span>-shaped corridors and identified phenomena such as behavioral characteristic lines and turning urgency. These findings were incorporated to develop a model for <span>l</span>-shaped merging behavior. Comparisons between real and simulated behaviors show that the model successfully replicates both the spatial and temporal characteristics of the turning and merging processes, validating its applicability. Further analysis of various pedestrian and spatial factors affecting <span>l</span>-shaped merging behavior and traffic efficiency via the model reveals that (1) moderate yielding by pedestrians in the main corridor increases traffic efficiency, while no yielding or excessive yielding reduces efficiency; (2) increasing the desired velocity increases efficiency; however, the benefits diminish beyond velocities of 2.0 m/s; (3) interpersonal distances in both corridors influence the overall traffic efficiency, and maintaining pedestrian spacing at or below 2.0 m is recommended; and (4) larger turning areas increase merging efficiency, indicating that small-scale optimization of key local spaces can significantly increase efficiency. These insights are valuable for managing pedestrian behavior and designing <span>l</span>-shaped corridors.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"143 ","pages":"Article 103150"},"PeriodicalIF":3.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144169095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An Intelligent Pedestrian Model with perception distance and speed to better reproduce traffic dynamics in the single-file movement 具有感知距离和速度的智能行人模型，以更好地再现单队列运动中的交通动态

IF 3.5 2区计算机科学

Simulation Modelling Practice and Theory Pub Date : 2025-09-01 Epub Date: 2025-05-22 DOI: 10.1016/j.simpat.2025.103145

Ning Guo , Changqing Zhang , Xiang Ling , Jiajia Chen , Chaoyun Wu , Qingyi Hao , Kongjin Zhu

{"title":"An Intelligent Pedestrian Model with perception distance and speed to better reproduce traffic dynamics in the single-file movement","authors":"Ning Guo , Changqing Zhang , Xiang Ling , Jiajia Chen , Chaoyun Wu , Qingyi Hao , Kongjin Zhu","doi":"10.1016/j.simpat.2025.103145","DOIUrl":"10.1016/j.simpat.2025.103145","url":null,"abstract":"<div><div>In the pedestrian traffic flow, individuals should continuously adjust the movement speed and direction based on the distance to and speed of the surrounding ones. However, during the interaction process, the pedestrian can hardly obtain the real distance and speed instantly, and he/she has to instead rely on perceptual estimates. Current pedestrian flow models typically overlook this crucial relationship between the real and perceived variables. In this paper, we propose an Intelligent Pedestrian model (IPM) incorporating perception headway and speed in the single-file movement scenarios. Experiments to estimate distance and speed are conducted respectively to establish quantitative functions for perception. Individuals tend to overestimate these two variables on average, with perception deviations exhibiting significant variability. Furthermore, it can effectively capture the headway fluctuation characteristics in the stop-and-go flow. Sensitivity analysis reveals that systematic overestimation or underestimation influences the average speed in the flow, while perception heterogeneity predominantly affects the headway fluctuation patterns.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"143 ","pages":"Article 103145"},"PeriodicalIF":3.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144169093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A credibility evaluation method for digital twin based on improved evidence theory 基于改进证据理论的数字孪生可信度评估方法

IF 3.5 2区计算机科学

Simulation Modelling Practice and Theory Pub Date : 2025-09-01 Epub Date: 2025-05-26 DOI: 10.1016/j.simpat.2025.103152

Jianfeng Shi , Qian Zhou , Chengsheng Pan

{"title":"A credibility evaluation method for digital twin based on improved evidence theory","authors":"Jianfeng Shi , Qian Zhou , Chengsheng Pan","doi":"10.1016/j.simpat.2025.103152","DOIUrl":"10.1016/j.simpat.2025.103152","url":null,"abstract":"<div><div>With the rapid development of digital twin technology, the evaluation of its credibility has become a critical issue that needs to be addressed. Existing evaluation methods struggle to effectively cope with the complex and highly dynamic characteristics of digital twins. Therefore, an improved credibility evaluation method based on evidence theory is proposed to enhance the accuracy and reliability of the evaluation results. Firstly, to address the challenge of inconsistent data types across different evaluation metrics in twin models, a cloud model is utilized to generate a unified basic probability assignment, providing a consistent data foundation for the credibility evaluation method. Secondly, to overcome the limitations of traditional evidence theory in handling evidence conflict and uncertainty, an improved evidence theory-based credibility evaluation method is proposed. This method can address conflict resolution and uncertainty expression by incorporating evidence sufficiency and indicator importance. Finally, by effectively integrating multi-source heterogeneous data, this evaluation method enables an accurate evaluation of the credibility of digital twin. Experimental results demonstrate that the proposed method outperforms traditional approaches in handling evidence conflict, providing a more precise evaluation of digital twin credibility, and offering a more reliable basis and evaluation standard for digital twin system design.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"143 ","pages":"Article 103152"},"PeriodicalIF":3.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144177714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing IoMT network performance using gateway placement 使用网关布局优化IoMT网络性能

IF 3.5 2区计算机科学

Simulation Modelling Practice and Theory Pub Date : 2025-09-01 Epub Date: 2025-06-07 DOI: 10.1016/j.simpat.2025.103164

R. Mahalakshmi, N. Lalithamani

{"title":"Optimizing IoMT network performance using gateway placement","authors":"R. Mahalakshmi, N. Lalithamani","doi":"10.1016/j.simpat.2025.103164","DOIUrl":"10.1016/j.simpat.2025.103164","url":null,"abstract":"<div><div>Gateway Device placement for processing patient data, plays a pivotal role in providing accurate and critical care for patient monitoring and assistance in a connected healthcare system. Long Range Wide Area Network (LoRaWAN) is a wide area network protocol used in providing low-power, seamless communication between the patient health sensors, monitors and the health assistance services in a healthcare network using gateway devices. Objective of the research work is to achieve optimization in the gateway by an adaptive device placement strategy using LoRaWAN thereby improving the network performance. The strategy is a multi-objective optimization, which includes Coverage Maximization, connectivity Optimization, and Energy Minimization for improving the network performance. The gateway placement strategy is verified with the simulation results obtained from Omnet++ Framework for LoRa (FLoRa). The network performance improvement is verified with key metric results observed based on the gateway placement strategy, resulted in Average Energy Consumption being 4.44 mJ, Packet Delivery Ratio (PDR) at 69 %, and Throughput reaching to 481 bps.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"143 ","pages":"Article 103164"},"PeriodicalIF":3.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144262387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A multi-objective deep reinforcement learning algorithm for spatio-temporal latency optimization in mobile IoT-enabled edge computing networks 移动物联网边缘计算网络时空延迟优化的多目标深度强化学习算法

IF 3.5 2区计算机科学

Simulation Modelling Practice and Theory Pub Date : 2025-09-01 Epub Date: 2025-05-27 DOI: 10.1016/j.simpat.2025.103161

Parisa Khoshvaght , Amir Haider , Amir Masoud Rahmani , Farhad Soleimanian Gharehchopogh , Ferzat Anka , Jan Lansky , Mehdi Hosseinzadeh

{"title":"A multi-objective deep reinforcement learning algorithm for spatio-temporal latency optimization in mobile IoT-enabled edge computing networks","authors":"Parisa Khoshvaght , Amir Haider , Amir Masoud Rahmani , Farhad Soleimanian Gharehchopogh , Ferzat Anka , Jan Lansky , Mehdi Hosseinzadeh","doi":"10.1016/j.simpat.2025.103161","DOIUrl":"10.1016/j.simpat.2025.103161","url":null,"abstract":"<div><div>The rapid increase in Mobile Internet of Things (IoT) devices requires novel computational frameworks. These frameworks must meet strict latency and energy efficiency requirements in Edge and Mobile Edge Computing (MEC) systems. Spatio-temporal dynamics, which include the position of edge servers and the timing of task schedules, pose a complex optimization problem. These challenges are further exacerbated by the heterogeneity of IoT workloads and the constraints imposed by device mobility. The balance between computational overhead and communication challenges is also a problem. To solve these issues, advanced methods are needed for resource management and dynamic task scheduling in mobile IoT and edge computing environments. In this paper, we propose a Deep Reinforcement Learning (DRL) multi-objective algorithm, called a Double Deep Q-Learning (DDQN) framework enhanced with Spatio-temporal mobility prediction, latency-aware task offloading, and energy-constrained IoT device trajectory optimization for federated edge computing networks. DDQN was chosen for its optimize stability and reduced overestimation in Q-values. The framework employs a reward-driven optimization model that dynamically prioritizes latency-sensitive tasks, minimizes task migration overhead, and balances energy efficiency across devices and edge servers. It integrates dynamic resource allocation algorithms to address random task arrival patterns and real-time computational demands. Simulations demonstrate up to a 35 % reduction in end-to-end latency, a 28 % improvement in energy efficiency, and a 20 % decrease in the deadline-miss ratio compared to benchmark algorithms.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"143 ","pages":"Article 103161"},"PeriodicalIF":3.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144190215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An improved CA model for evacuation simulation in super high-rise buildings: Considering evacuees’ rest on refuge floors and preference for taking evacuation elevators 超高层建筑疏散仿真的改进CA模型：考虑疏散人员在避难层休息和乘坐疏散电梯的偏好

IF 3.5 2区计算机科学

Simulation Modelling Practice and Theory Pub Date : 2025-09-01 Epub Date: 2025-05-21 DOI: 10.1016/j.simpat.2025.103148

Jianfei Huang , Xinnan Liu , Yingbo Ji , Feifan Song , Tengteng Jiang , Tiantian Du , Xin Fan

{"title":"An improved CA model for evacuation simulation in super high-rise buildings: Considering evacuees’ rest on refuge floors and preference for taking evacuation elevators","authors":"Jianfei Huang , Xinnan Liu , Yingbo Ji , Feifan Song , Tengteng Jiang , Tiantian Du , Xin Fan","doi":"10.1016/j.simpat.2025.103148","DOIUrl":"10.1016/j.simpat.2025.103148","url":null,"abstract":"<div><div>Most of the previous studies on emergency evacuation simulation in super high-rise buildings have overlooked the role of refuge floors, which are vital for recovery of fatigued evacuees. Additionally, advancements in elevator safety have made evacuation elevators a feasible option as supplementary evacuation facilities to staircases in super high-rise buildings. While some evacuees prefer to take evacuation elevators during emergencies, others still tend to use staircases only. This study proposes an improved cellular automata (CA) model that accounts for the effects of evacuees’ rest on refuge floors and preference for taking evacuation elevators. To build the foundation for setting model parameters of speed recovery after resting on refuge floors, two evacuation experiments are conducted in a super high-rise office building. The improved CA model is developed by incorporating space configurations, updating rules of evacuees and evacuation elevators. Effects of thresholds for taking rest on refuge floors, rest time on refuge floors, ratio of evacuees with different evacuation facility preferences, as well as gender ratio of evacuees on the evacuation efficiency are simulated by the improved CA model. The findings demonstrate that the proposed model can effectively simulate complex evacuation scenarios, including the effects of speed recovery after fatigued evacuees rest on refuge floors and evacuees’ preference for taking evacuation elevators. This study offers valuable insights for optimizing evacuation plans in super high-rise buildings.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"143 ","pages":"Article 103148"},"PeriodicalIF":3.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144169091","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhanced flame detection in virtual tunnels using DEV-YOLOv8 and digital twin systems 使用DEV-YOLOv8和数字孪生系统增强虚拟隧道中的火焰探测

IF 3.5 2区计算机科学

Simulation Modelling Practice and Theory Pub Date : 2025-09-01 Epub Date: 2025-06-02 DOI: 10.1016/j.simpat.2025.103143

Yongjiang Li , Xingguo Song , Faming Lin , Xu Fang

{"title":"Enhanced flame detection in virtual tunnels using DEV-YOLOv8 and digital twin systems","authors":"Yongjiang Li , Xingguo Song , Faming Lin , Xu Fang","doi":"10.1016/j.simpat.2025.103143","DOIUrl":"10.1016/j.simpat.2025.103143","url":null,"abstract":"<div><div>Highway tunnel fires pose significant safety challenges requiring reliable detection and response strategies. Traditional testing methods face limitations due to insufficient sample diversity and high costs, thus making virtual environments a promising alternative for algorithm development. This study proposes DEV-YOLOv8, an enhanced YOLOv8 model integrated with digital twin technology for flame detection in simulated tunnel environments. The model incorporates three key enhancements: deformable convolutions for adaptive feature extraction, an efficient multi-scale attention mechanism for stable parameter updates, and a cross-stage partial connections module for efficient multi-scale fusion. A Unity-ROS2-based digital twin system enables cost-effective simulation and dataset generation. Experiments demonstrate DEV-YOLOv8’s superiority with 2.2%/1.5%/1.2% improvements in accuracy/recall/[email protected] respectively, while reducing computational cost by 0.8 GFLOPs. The integrated system achieves 98.21% simulation accuracy and 96.19% physical deployment accuracy, with latency differences <span><math><mo><</mo></math></span> 3.15 ms and RRT delays below 9.91 ms. This work establishes an efficient framework combining deep learning and digital twins for adaptive fire detection in tunnel environments.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"143 ","pages":"Article 103143"},"PeriodicalIF":3.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144204999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0