Transportation Research Part C-Emerging Technologies最新文献

{"title":"Coordinating ride-pooling with public transit using Reward-Guided Conservative Q-Learning: An offline training and online fine-tuning reinforcement learning framework","authors":"Yulong Hu ,&nbsp;Tingting Dong ,&nbsp;Sen Li","doi":"10.1016/j.trc.2025.105051","DOIUrl":"10.1016/j.trc.2025.105051","url":null,"abstract":"<div><div>This paper introduces a novel reinforcement learning (RL) framework, termed Reward-Guided Conservative Q-learning (RG-CQL), to enhance coordination between ride-pooling and public transit within a multimodal transportation network. We model each ride-pooling vehicle as an agent governed by a Markov Decision Process (MDP), which includes a state for each agent encompassing the vehicle’s location, the number of vacant seats, and all pertinent information regarding the passengers on board. We propose an offline training and online fine-tuning RL framework to learn the optimal operational decisions of the multimodal transportation systems, including rider-vehicle matching, selection of drop-off locations for passengers, and vehicle routing decisions, with improved data efficiency. During the offline training phase, we develop a Conservative Double Deep Q Network (CDDQN) as the action executor and a supervised learning-based reward estimator, termed the Guider Network, to extract valuable insights into action-reward relationships from data batches. In the online fine-tuning phase, the Guider Network serves as an exploration guide, aiding CDDQN in effectively and conservatively exploring unknown state–action pairs to bridge the gap between the conservative offline training and optimistic online fine-tuning. The efficacy of our algorithm is demonstrated through a realistic case study using real-world data from Manhattan. We show that integrating ride-pooling with public transit outperforms two benchmark cases—solo rides coordinated with transit and ride-pooling without transit coordination—by 17% and 22% in the achieved system rewards, respectively. Furthermore, our innovative offline training and online fine-tuning framework offers a remarkable 81.3% improvement in data efficiency compared to traditional online RL methods with adequate exploration budgets, with a 4.3% increase in total rewards and a 5.6% reduction in overestimation errors. Experimental results further demonstrate that RG-CQL effectively addresses the challenges of transitioning from offline to online RL in large-scale ride-pooling systems integrated with transit.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105051"},"PeriodicalIF":7.6,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143610246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Variational inference for high-dimensional integrated choice and latent variable (ICLV) models within a Bayesian framework","authors":"Gyeongjun Kim ,&nbsp;Yeseul Kang ,&nbsp;Keemin Sohn","doi":"10.1016/j.trc.2025.105023","DOIUrl":"10.1016/j.trc.2025.105023","url":null,"abstract":"<div><div>The variational Bayes is widely used to deal with high-dimensional models. The present study attempts to apply variational inference (VI) to estimate high-dimensional integrated choice and latent variable (ICLV) models. When utilizing the Maximum Simulated Likelihood (MSL) technique to calibrate an ICLV model with the Gaussian kernel, the log-likelihood function cannot be evaluated if the dimension of latent variables and choice options grows. Addressing this, the present study proposes a conditional variational inference (CVI) method that consistently estimate an ICLV model regardless of the dimensions of choice options and latent variables within a Bayesian framework. Variational models are supplanted by neural embedding, and the mean and variance of the Gaussian probability density are parameterized by a neural network, which is called the reparameterization trick. Furthermore, the Gumbel softmax function approximates the ’argmax’ operation for selecting a choice option of the maximum utility, which bypasses the computationally intensive task of calculating choice probabilities. Collectively, these strategies ensure the scalable ICLV model estimation, as increasing the number of latent variables and choice options. The calibration method succeeded in reproducing parameters of a large-scale ICLV model with 30 latent variables and 30 choice options.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105023"},"PeriodicalIF":7.6,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143610242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Stochastic game-based cross-layer defense scheme for jamming-resistant virtual coupled train sets","authors":"Shuomei Ma ,&nbsp;Xiaozhi Qi ,&nbsp;Zhijiang Lou ,&nbsp;Hongwei Wang ,&nbsp;Li Zhu ,&nbsp;Taiyuan Gong ,&nbsp;Yang Li ,&nbsp;Hairong Dong","doi":"10.1016/j.trc.2025.105028","DOIUrl":"10.1016/j.trc.2025.105028","url":null,"abstract":"<div><div>The railway operation concept of Virtually Coupled Train Sets (VCTS) allows for shorter headways between units in a train convoy, enhancing the current capacity limit imposed by existing Communication-Based Train Control (CBTC) systems by enabling units to operate safely at shorter distances. However, due to the use of open Train-to-Train (T2T) wireless communication through Long-Terms Evolution for Metro (LTE-M), VCTS is vulnerable to various cyber-attacks, including jamming attacks, which have largely been overlooked. To address this issue, this paper proposes a Stochastic Game-Based Cross-Layer Defense (SGCD) scheme. This scheme aims to enhance the safety and stability of VCTS in both the physical and cyber layers, in the presence of uncertain communication failures caused by jamming attacks. This proposed scheme formulates the defense approach and the particularly jamming actions as a stochastic game. A cross-layer control approach is employed to mitigate the impact of jamming attacks on the train convoy. The performance of this cross-layer control is mapped to the frequency domain and quantified using the <span><math><msup><mrow><mi>H</mi></mrow><mrow><mi>∞</mi></mrow></msup></math></span> norm to ensure the stability and safety of the VCTS system. Extensive simulation results demonstrate that the SGCD scheme can effectively ensure the running stability and safety of a train convoy under random jamming attacks in the VCTS. The proposed defense mechanism can enhance the security and reliability of the VCTS system, thereby enabling safer and more efficient train operations with shorter headways.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105028"},"PeriodicalIF":7.6,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143610243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Driving towards stability and efficiency: A variable time gap strategy for Adaptive Cruise Control","authors":"Shaimaa K. El-Baklish,&nbsp;Anastasios Kouvelas,&nbsp;Michail A. Makridis","doi":"10.1016/j.trc.2025.105074","DOIUrl":"10.1016/j.trc.2025.105074","url":null,"abstract":"<div><div>Automated vehicle technologies offer a promising avenue for enhancing traffic efficiency, safety, and energy consumption. Among these, Adaptive Cruise Control (ACC) systems stand out as a prevalent form of automation on today’s roads, with their time gap settings holding paramount importance. While decreasing the average time headway tends to enhance traffic capacity, it simultaneously raises concerns regarding safety and string stability. This study introduces a novel variable time gap feedback control policy aimed at striking a balance between maintaining a minimum time gap setting under equilibrium car-following conditions, thereby improving traffic capacity, while ensuring string stability to mitigate disturbances away from the equilibrium flow. Leveraging nonlinear <span><math><msub><mrow><mi>H</mi></mrow><mrow><mi>∞</mi></mrow></msub></math></span> control technique, the strategy employs a variable time gap component as the manipulated control signal, complemented by a constant time gap component that predominates during car-following equilibrium. The effectiveness of the proposed scheme is evaluated against its constant time-gap counterpart calibrated using field platoon data from the OpenACC dataset. Through numerical and traffic simulations, our findings illustrate that the proposed algorithm effectively dampens perturbations within vehicle platoons, leading to a more efficient and safer mixed traffic flow.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105074"},"PeriodicalIF":7.6,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143619227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MoGERNN: An inductive traffic predictor for unobserved locations","authors":"Qishen Zhou ,&nbsp;Yifan Zhang ,&nbsp;Michail A. Makridis ,&nbsp;Anastasios Kouvelas ,&nbsp;Yibing Wang ,&nbsp;Simon Hu","doi":"10.1016/j.trc.2025.105080","DOIUrl":"10.1016/j.trc.2025.105080","url":null,"abstract":"<div><div>Given a partially observed road network, how can we predict the traffic state of interested unobserved locations? Traffic prediction is crucial for advanced traffic management systems, with deep learning approaches showing exceptional performance. However, most existing approaches assume sensors are deployed at all locations of interest, which is impractical due to financial constraints. Furthermore, these methods are typically fragile to structural changes in sensing networks, which require costly retraining even for minor changes in sensor configuration. To address these challenges, we propose MoGERNN, an inductive spatio-temporal graph model with two key components: (i) a Mixture of Graph Experts (MoGE) with sparse gating mechanisms that dynamically route nodes to specialized graph aggregators, capturing heterogeneous spatial dependencies efficiently; (ii) a graph encoder-decoder architecture that leverages these embeddings to capture both spatial and temporal dependencies for comprehensive traffic state prediction. Experiments on two real-world datasets show MoGERNN consistently outperforms baseline methods for both observed and unobserved locations. MoGERNN can accurately predict congestion evolution even in areas without sensors, offering valuable information for traffic management. Moreover, MoGERNN is adaptable to the changes of sensor network, maintaining competitive performance even compared to its retrained counterpart. Tests performed with different numbers of available sensors confirm its consistent superiority, and ablation studies validate the effectiveness of its key modules. The code of this work is publicly available at: <span><span>https://github.com/ZJU-TSELab/MoGERNN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105080"},"PeriodicalIF":7.6,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated optimization of demand-oriented timetabling and rolling stock circulation planning with flexible train compositions and multiple service routes on urban rail lines","authors":"Xinyu Bao ,&nbsp;Qi Zhang ,&nbsp;Haodong Yin ,&nbsp;Entai Wang ,&nbsp;Yaling Xiao","doi":"10.1016/j.trc.2025.105071","DOIUrl":"10.1016/j.trc.2025.105071","url":null,"abstract":"<div><div>This study investigates an integrated train operation plan problem with flexible train compositions and multiple service routes, which allows trains to couple, decouple and turn around at intermediate turnaround stations based on virtual coupling technology. An integrated optimization model for demand-oriented train timetables and rolling stock circulation plans is developed with the consideration of train service routes and the number of train services, by minimizing both passenger waiting time and operation costs. Specifically, with the path-based space–time network representation, we formulate a novel rolling stock circulation model, which accounts for coupling and decoupling operations and stabling track capacity constraints with lower complexity than the assignment model. In addition, we improve the linear dynamic passenger flow loading model, which extends the operational application with multiple service routes and characterizes various passenger waiting behaviors. To solve the proposed model, an adaptive simulated annealing (ASA) algorithm is designed to obtain high-quality solutions using flow-oriented and random operators. Lastly, the performance of the proposed models and algorithms is verified by small-scale numerical experiments. Then, the efficiency of the proposed approaches is further demonstrated through a real-world case study based on Beijing Subway Changping Line, showing a 42% reduction in total passenger waiting time, a decrease of 16 rolling stock, and a 10% reduction in variable operation costs compared to the current operation mode.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105071"},"PeriodicalIF":7.6,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TSGDiff: Traffic state generative diffusion model using multi-source information fusion","authors":"Huipeng Zhang,&nbsp;Honghui Dong,&nbsp;Zhiqiang Yang","doi":"10.1016/j.trc.2025.105081","DOIUrl":"10.1016/j.trc.2025.105081","url":null,"abstract":"<div><div>Accurate analysis and prediction of traffic states are fundamental and crucial for intelligent transportation systems, playing a significant role in enhancing the efficiency and safety of traffic systems. Advances in deep learning have promoted the development of traffic prediction. However, some traditional prediction methods primarily rely on historical traffic data to sequentially predict future traffic trends. While some also incorporate one or more influencing factors, such as weather and day of the week, as covariates, they often lack a unified fusion approach to model the impact of these covariates on future traffic states, and they are prone to error accumulation in long-term predictions. To address these challenges, we propose TSGDiff, a novel traffic state generative diffusion model using multi-source information fusion. The proposed method leverages an innovative diffusion model framework and integrates various sources of information, such as traffic data, weather, and weekdays, to enhance the accuracy of traffic state prediction. TSGDiff transforms historical spatiotemporal information and future environment information into feature representations using an attention-based spatiotemporal extraction module and a traffic semantic encoding module, respectively. These feature representations serve as guiding conditions for the diffusion model to generate traffic states. By incorporating the prediction horizon as an input parameter, TSGDiff directly generates future traffic states point-to-point, thereby avoiding error accumulation inherent in iterative prediction methods. To adapt the diffusion model to graph structure road network data, we introduce a Graph Attention U-Net (GAUNet) to capture the spatial correlations in traffic data. Experiments on real-world Beijing traffic datasets demonstrate that TSGDiff significantly outperforms baseline models for long-term predictions and performs comparably for short-term predictions.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105081"},"PeriodicalIF":7.6,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Manage morning commute problem of household travels under single-step toll: A comparison study","authors":"Yuan Zhang,&nbsp;Hui Zhao,&nbsp;Rui Jiang,&nbsp;Ying Shang","doi":"10.1016/j.trc.2025.105075","DOIUrl":"10.1016/j.trc.2025.105075","url":null,"abstract":"<div><div>In general, road tolls could alleviate travel congestion for commuters during rush hour and improve the efficiency of individual transport trips. But for the household commuters, whether the road toll management framework can achieve the same effect is still unclear. From this perspective, it is meaningful to understand the difference between the impacts of road toll pricing on individual trips and on household trips. Based on this consideration, this paper investigates the influence of single-step toll strategy on household trips using the ADL model and the braking model. The optimal school-work time gap, optimal toll value and optimal toll interval are obtained for optimizing the total system travel cost. To have a deeper insight into the difference between the three types of models, the ADL, braking and Laih (<span><span>Jia et al., 2016</span></span>) models are studied extensively, leading to the following conclusions: (i) Under the optimal strategies in the three single-step household toll models, the optimal school-work time gap ranges and the toll intervals differ, but the optimal toll values are the same; (ii) The ADL model performs optimally in optimizing the total system travel cost, followed by the Laih model; (iii) the total congestion cost decreases with school-work time gap under the optimal strategy of the single-step toll models, and the ADL model performs optimally in this regard. Therefore, management insights can be derived, in which traffic authorities should set proper staggering hours, toll price and interval, as well as cultivate proper travel habits of household travelers, thereby helping to reduce road congestion and improve social welfare. Finally, a comparison of the three toll models through numerical experiments validates our findings.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105075"},"PeriodicalIF":7.6,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143549594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved multi-agent deep reinforcement learning-based integrated control for mixed traffic flow in a freeway corridor with multiple bottlenecks","authors":"Lei Han ,&nbsp;Lun Zhang ,&nbsp;Haixiao Pan","doi":"10.1016/j.trc.2025.105077","DOIUrl":"10.1016/j.trc.2025.105077","url":null,"abstract":"<div><div>A major challenging issue related to the emerging mixed traffic flow system, composed of Connected and Automated Vehicles (CAVs) and Human-Driven Vehicles (HDVs), is the lack of adequate traffic control measures, especially in a large freeway corridor with multiple bottlenecks. Multi-agent deep reinforcement learning exhibits significant advantages, such as fast response, high flexibility, strong adaptability, low computational burden, and collaborative optimization. These features enable it to achieve superior efficiency and robustness in handling dynamically changing traffic environments and large-scale traffic control problems. Inspired by this, we propose a novel Integrated Traffic Control (ITC) strategy based on an Improved Multi-Agent Twin Delayed Deep Deterministic Policy Gradient (IPMATD3) algorithm in the mixed traffic environment (abbreviated as IPMATD3-based ITC). Specifically, the proposed IPMATD3-based ITC approach seeks to coordinate multiple Ramp Metering (RM) and Variable Speed Limit (VSL) controllers along a freeway corridor, with the objectives of improving traffic mobility and efficiency, enhancing safety, and reducing emissions. The proposed method utilized a centralized training with decentralized execution paradigm to learn the joint actions of all traffic controllers in a high-dimensional state and action spaces. A hybrid reward function is developed by synchronously considering the above objectives to optimize traffic control performance. Then, the rank-based prioritized experience replay mechanism is incorporated into the conventional MATD3 algorithm to improve learning efficiency. A real-world freeway corridor is selected to test the proposed control method. Moreover, its performance is compared with the several state-of-the-art methods. The simulation results demonstrate that the proposed method achieves remarkable control performance at a 10% CAV Penetration Rate (PR), effectively reducing the spatiotemporal extent of freeway traffic congestion. The proposed method outperforms other approaches in improving freeway traffic efficiency, mobility, safety, and environmental sustainability. Increasing the PR can improve the performance of various methods and benefit traffic operations. However, when the PR reaches higher levels, the marginal benefits of further increases become less pronounced.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105077"},"PeriodicalIF":7.6,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143549666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A real-time synthesized driving risk quantification model based on driver risk perception-response mechanism","authors":"Leipeng Zhu ,&nbsp;Zhiqing Zhang ,&nbsp;Jingyang Yu ,&nbsp;Yongnan Zhang ,&nbsp;Jinxiu Fu","doi":"10.1016/j.trc.2025.105073","DOIUrl":"10.1016/j.trc.2025.105073","url":null,"abstract":"<div><div>Risk factors within the driver-vehicle–road system are dynamically coupled, with the driver being the most critical factor contributing to system destabilization. However, current traffic risk assessment models struggle to accurately measure the dynamic risk caused by the driver, limiting their applicability in increasingly complex driving environments. Based on the artificial potential field theory, the paper begins its investigation with the driver’s risk perception-response mechanism, and incorporates the effects of risk gain and attenuation to develop a driving behavior dynamic risk quantification model (behavior field). This model is then superimposed with enhanced kinetic and potential fields to construct a real-time synthesized driving risk quantification model under the dynamic coupling of the driver-vehicle–road system, which is validated in various traffic scenarios. The results suggest that: (a) The driving behavior dynamic risk quantification model accurately represents the underlying risks during the driver’s perception, judgment, and decision-making phases. It effectively captures the risk differences between different traffic scenarios and drivers, demonstrating high applicability and sensitivity. (b) The kinetic and potential fields that account for the risk diffusion effect are more consistent with the actual risk distribution characteristics. They can also efficiently represent the risk evolution patterns of influencing factors across diverse scenarios. (c) Compared with the conventional driving safety field and risk evaluation metrics (e.g., steering entropy, jerk, and time to collision), the synthesized driving risk real-time quantification model effectively captures the dynamic coupling of objective traffic environment risks and subjective driving behavior risks on a multidimensional spatiotemporal scale. It provides more robust risk prediction results (R² = 0.988, root mean square error = 0.007). This research can provide a theoretical reference for the automatic analysis of comprehensive traffic risk and the development of more intelligent advanced driver assistance systems.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105073"},"PeriodicalIF":7.6,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143549667","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}