Among the near-miss incidents related to the operation of training ship of the JMETS(Japan Agency of Maritime Education and Training for Seafarers),three characteristic cases were analyzed,extracting their circumstanc...Among the near-miss incidents related to the operation of training ship of the JMETS(Japan Agency of Maritime Education and Training for Seafarers),three characteristic cases were analyzed,extracting their circumstances and near-miss factors.Based on the results of these analyses,measures to prevent vessel collisions were studied,from which we proposed collision prevention training.The training entails(1)lookout training,(2)navigation planning training,(3)resource management training,and(4)false assumption prevention training.In future research,we aim to verify the effectiveness of the proposed training,improve the training’s effectiveness,and contribute to the development of effective anti-collision support devices.展开更多
The consequences of ship collisions with an oil rig, offshore installation or platform can be far more expensive in relation to safety, environment and costs of damage. The damage due to a single incident of an Oil Ri...The consequences of ship collisions with an oil rig, offshore installation or platform can be far more expensive in relation to safety, environment and costs of damage. The damage due to a single incident of an Oil Rig Collision can be catastrophic due to the number of people on board and the added risk of explosion. However, the existing rules and regulations of collisions prevention are insufficient. The purpose of this article is to critically evaluate the risk of ships collisions with offshore platforms and installations and therefore propose an international regulation for the preventions of this type of collisions.展开更多
To improve the passive safety of high-speed trains,it is very important to understand the mechanism of head injury in high-speed train collisions.In this study,the head injury mechanisms of occupants in high-speed tra...To improve the passive safety of high-speed trains,it is very important to understand the mechanism of head injury in high-speed train collisions.In this study,the head injury mechanisms of occupants in high-speed train rear-end collisions were investigated based on the occupant-seat coupling model,which included a dummy representing the Chinese 50th percentile adult male.The typical injury responses in terms of skull fractures,brain contusions,and diffuse axonal injury(DAI)were analyzed.Meanwhile,the influences of collision speed and seat parameters on head injury response were examined.The simulation results indicate that the skull fractures primarily occur at the skull base region due to excessive neck extension,while the brain contusions and DAI result from the relative displacement of different brain regions.The increase in collision speed will promote the probability of skull fracture,brain contusion,and DAI.Seat design modifications,such as reduced seat spacing,increased seat backrest angles,and selecting the appropriate cushion angle(76°)and friction coefficient(0.15),can effectively mitigate probably occupant's head injury.展开更多
为解决大数据下船舶会遇识别算法效率不高且存在误判等问题,提出一种融合国际海上避碰规则(International Regulations for Preventing Collisions at Sea,COLREGs)的带噪声的基于密度的空间聚类(density-based spatial clustering of a...为解决大数据下船舶会遇识别算法效率不高且存在误判等问题,提出一种融合国际海上避碰规则(International Regulations for Preventing Collisions at Sea,COLREGs)的带噪声的基于密度的空间聚类(density-based spatial clustering of applications with noise,DBSCAN)算法,建立船舶会遇识别模型。在DBSCAN算法对邻域内的船舶数量进行统计时,计算船舶间的最近会遇距离(distance to closest point of approach,DCPA)和最近会遇时间(time to closest point of approach,TCPA),初步筛选邻域内的噪声点;基于模糊综合评价模型计算船舶会遇风险,对邻域内的船舶进行二次筛选,实现船舶会遇态势的提取。结果表明:改进后的DBSCAN算法过滤掉传统DBSCAN算法识别到的非会遇局面,并且在同一会遇局面下的船舶数量均保持在4艘以内;输出的会遇船舶风险演变趋势对实际水域内高风险船舶的监控适用性较好,能有效辅助船舶避碰。所提识别模型对保障航行安全和提高海事监管效率具有重要意义。展开更多
针对多无人艇编队避障问题,对静态避障的路径消耗问题进行建模分析,在动态避障时提出一种偏置人工势场法使策略符合艇群国际海上避碰规则(swarm International Regulations for Preventing Collisions at Sea,sCOLREGS)。本方法首先对...针对多无人艇编队避障问题,对静态避障的路径消耗问题进行建模分析,在动态避障时提出一种偏置人工势场法使策略符合艇群国际海上避碰规则(swarm International Regulations for Preventing Collisions at Sea,sCOLREGS)。本方法首先对传统人工势场法进行改进,定义符合艇群会遇态势判断需求的sCOLREGS,通过速度障碍法实时判断碰撞风险,然后利用偏置斥力区域的改进人工势场法实现对规则的遵守。仿真实验表明,本文方法在障碍物与编队大小相当时可显著减少避障路程,在确保避障实时性的同时,较好地遵守了国际海上避碰规则相关条例。研究结论可为海面无人艇集群安全航行提供参考。展开更多
Vehicles involved in traffic accidents generally experience divergent vehicle motion,which causes severe damage.This paper presents a self-learning drift-control method for the purpose of stabilizing a vehicle’s yaw ...Vehicles involved in traffic accidents generally experience divergent vehicle motion,which causes severe damage.This paper presents a self-learning drift-control method for the purpose of stabilizing a vehicle’s yaw motions after a high-speed rear-end collision.The struck vehicle generally experiences substantial drifting and/or spinning after the collision,which is beyond the handling limit and difficult to control.Drift control of the struck vehicle along the original lane was investigated.The rear-end collision was treated as a set of impact forces,and the three-dimensional non-linear dynamic responses of the vehicle were considered in the drift control.A multi-layer perception neural network was trained as a deterministic control policy using the actor-critic reinforcement learning framework.The control policy was iteratively updated,initiating from a random parameterized policy.The results show that the self-learning controller gained the ability to eliminate unstable vehicle motion after data-driven training of about 60,000 iterations.The controlled struck vehicle was also able to drift back to its original lane in a variety of rear-end collision scenarios,which could significantly reduce the risk of a second collision in traffic.展开更多
文摘Among the near-miss incidents related to the operation of training ship of the JMETS(Japan Agency of Maritime Education and Training for Seafarers),three characteristic cases were analyzed,extracting their circumstances and near-miss factors.Based on the results of these analyses,measures to prevent vessel collisions were studied,from which we proposed collision prevention training.The training entails(1)lookout training,(2)navigation planning training,(3)resource management training,and(4)false assumption prevention training.In future research,we aim to verify the effectiveness of the proposed training,improve the training’s effectiveness,and contribute to the development of effective anti-collision support devices.
文摘The consequences of ship collisions with an oil rig, offshore installation or platform can be far more expensive in relation to safety, environment and costs of damage. The damage due to a single incident of an Oil Rig Collision can be catastrophic due to the number of people on board and the added risk of explosion. However, the existing rules and regulations of collisions prevention are insufficient. The purpose of this article is to critically evaluate the risk of ships collisions with offshore platforms and installations and therefore propose an international regulation for the preventions of this type of collisions.
基金supported by the National Natural Science Foundation of China(Grant No.12122211)the Natural Science Foundation of Sichuan Province(Grant No.2022NSFSC0035)。
文摘To improve the passive safety of high-speed trains,it is very important to understand the mechanism of head injury in high-speed train collisions.In this study,the head injury mechanisms of occupants in high-speed train rear-end collisions were investigated based on the occupant-seat coupling model,which included a dummy representing the Chinese 50th percentile adult male.The typical injury responses in terms of skull fractures,brain contusions,and diffuse axonal injury(DAI)were analyzed.Meanwhile,the influences of collision speed and seat parameters on head injury response were examined.The simulation results indicate that the skull fractures primarily occur at the skull base region due to excessive neck extension,while the brain contusions and DAI result from the relative displacement of different brain regions.The increase in collision speed will promote the probability of skull fracture,brain contusion,and DAI.Seat design modifications,such as reduced seat spacing,increased seat backrest angles,and selecting the appropriate cushion angle(76°)and friction coefficient(0.15),can effectively mitigate probably occupant's head injury.
文摘为解决大数据下船舶会遇识别算法效率不高且存在误判等问题,提出一种融合国际海上避碰规则(International Regulations for Preventing Collisions at Sea,COLREGs)的带噪声的基于密度的空间聚类(density-based spatial clustering of applications with noise,DBSCAN)算法,建立船舶会遇识别模型。在DBSCAN算法对邻域内的船舶数量进行统计时,计算船舶间的最近会遇距离(distance to closest point of approach,DCPA)和最近会遇时间(time to closest point of approach,TCPA),初步筛选邻域内的噪声点;基于模糊综合评价模型计算船舶会遇风险,对邻域内的船舶进行二次筛选,实现船舶会遇态势的提取。结果表明:改进后的DBSCAN算法过滤掉传统DBSCAN算法识别到的非会遇局面,并且在同一会遇局面下的船舶数量均保持在4艘以内;输出的会遇船舶风险演变趋势对实际水域内高风险船舶的监控适用性较好,能有效辅助船舶避碰。所提识别模型对保障航行安全和提高海事监管效率具有重要意义。
文摘针对多无人艇编队避障问题,对静态避障的路径消耗问题进行建模分析,在动态避障时提出一种偏置人工势场法使策略符合艇群国际海上避碰规则(swarm International Regulations for Preventing Collisions at Sea,sCOLREGS)。本方法首先对传统人工势场法进行改进,定义符合艇群会遇态势判断需求的sCOLREGS,通过速度障碍法实时判断碰撞风险,然后利用偏置斥力区域的改进人工势场法实现对规则的遵守。仿真实验表明,本文方法在障碍物与编队大小相当时可显著减少避障路程,在确保避障实时性的同时,较好地遵守了国际海上避碰规则相关条例。研究结论可为海面无人艇集群安全航行提供参考。
基金supported by International Science&Technology Cooperation Program of China(Grant No.2019YFE0100200)the National Natural Science Foundation of China(Grant No.51905483).This paper is also partially supported by Toyota.
文摘Vehicles involved in traffic accidents generally experience divergent vehicle motion,which causes severe damage.This paper presents a self-learning drift-control method for the purpose of stabilizing a vehicle’s yaw motions after a high-speed rear-end collision.The struck vehicle generally experiences substantial drifting and/or spinning after the collision,which is beyond the handling limit and difficult to control.Drift control of the struck vehicle along the original lane was investigated.The rear-end collision was treated as a set of impact forces,and the three-dimensional non-linear dynamic responses of the vehicle were considered in the drift control.A multi-layer perception neural network was trained as a deterministic control policy using the actor-critic reinforcement learning framework.The control policy was iteratively updated,initiating from a random parameterized policy.The results show that the self-learning controller gained the ability to eliminate unstable vehicle motion after data-driven training of about 60,000 iterations.The controlled struck vehicle was also able to drift back to its original lane in a variety of rear-end collision scenarios,which could significantly reduce the risk of a second collision in traffic.
