Yizhao Wang , Xuejian Kang , Xingju Wang , Yang Yang , Xuewei Li
{"title":"High-dynamic impact mechanism of complex spiral tunnel environments on driving behavior based on multi-source data fusion","authors":"Yizhao Wang , Xuejian Kang , Xingju Wang , Yang Yang , Xuewei Li","doi":"10.1016/j.tust.2025.106584","DOIUrl":null,"url":null,"abstract":"<div><div>The complexity of spiral tunnels exacerbates driving safety risks, making it essential to elucidate the mechanisms of various factors to conduct effective research in this area. This study, based on the “road-driver-vehicle” feedback process, analyzed the impact mechanisms of three dimensions—road alignment, lighting environment, and traffic flow—on driver behavior and vehicle dynamics in spiral tunnels. Environmental variables were controlled in simulated driving experiments to conduct this study. First, the variation characteristics of driver visual and psychological behavior in spiral tunnel environments were analyzed. A driver cognitive load model was constructed to compare and analyze the impact mechanisms of environmental factors across the three dimensions of driver cognitive load and quantify their coupling weights. Second, an ARIMAX model was developed incorporating the exogenous variable of driver cognitive load to analyze its impact on vehicle operating conditions. Finally, an LSTM-SHAP model was employed for multivariate time series prediction of vehicle operating states. The model structure was explained from global and local perspectives to assess the influence of environmental factors on vehicle prediction outcomes. The analysis revealed that traffic flow (0.01) has the greatest impact on driver cognitive load, followed by lighting conditions (0.001), with road alignment having the smallest effect (10-<sup>5</sup>). Driver cognitive load has the greatest impact on vehicle acceleration (0.632), followed by speed (−0.234), with lane deviation having the smallest effect (−0.185). The influence of environmental factors on vehicle operating conditions exhibits a similar trend to their impact on driver cognitive load.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"161 ","pages":"Article 106584"},"PeriodicalIF":6.7000,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tunnelling and Underground Space Technology","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0886779825002226","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
The complexity of spiral tunnels exacerbates driving safety risks, making it essential to elucidate the mechanisms of various factors to conduct effective research in this area. This study, based on the “road-driver-vehicle” feedback process, analyzed the impact mechanisms of three dimensions—road alignment, lighting environment, and traffic flow—on driver behavior and vehicle dynamics in spiral tunnels. Environmental variables were controlled in simulated driving experiments to conduct this study. First, the variation characteristics of driver visual and psychological behavior in spiral tunnel environments were analyzed. A driver cognitive load model was constructed to compare and analyze the impact mechanisms of environmental factors across the three dimensions of driver cognitive load and quantify their coupling weights. Second, an ARIMAX model was developed incorporating the exogenous variable of driver cognitive load to analyze its impact on vehicle operating conditions. Finally, an LSTM-SHAP model was employed for multivariate time series prediction of vehicle operating states. The model structure was explained from global and local perspectives to assess the influence of environmental factors on vehicle prediction outcomes. The analysis revealed that traffic flow (0.01) has the greatest impact on driver cognitive load, followed by lighting conditions (0.001), with road alignment having the smallest effect (10-5). Driver cognitive load has the greatest impact on vehicle acceleration (0.632), followed by speed (−0.234), with lane deviation having the smallest effect (−0.185). The influence of environmental factors on vehicle operating conditions exhibits a similar trend to their impact on driver cognitive load.
期刊介绍:
Tunnelling and Underground Space Technology is an international journal which publishes authoritative articles encompassing the development of innovative uses of underground space and the results of high quality research into improved, more cost-effective techniques for the planning, geo-investigation, design, construction, operation and maintenance of underground and earth-sheltered structures. The journal provides an effective vehicle for the improved worldwide exchange of information on developments in underground technology - and the experience gained from its use - and is strongly committed to publishing papers on the interdisciplinary aspects of creating, planning, and regulating underground space.