The safe driving and operation of trains is a necessary condition for ensuring the safe operation of trains.In particular,heavy-haul trains are characterized by the difficulty in driving and operation.Considering the ...The safe driving and operation of trains is a necessary condition for ensuring the safe operation of trains.In particular,heavy-haul trains are characterized by the difficulty in driving and operation.Considering the uncertainties in train driving and operation,this paper analyzes the relationship between the safety of heavy-haul electric locomotive hauled trains and driving and operation.It studies the auxiliary intelligent driving safety operation control methods.Through K-means to identify the characteristics of drivers'driving manipulation,the hidden Markov model adaptively adjusts the train driving and operation sequence,and conducts auxiliary driving reconstruction for heavy-haul locomotive driving and operation.Based on the train running curve and the locomotive traction/braking characteristics,it smoothly controls the exertion of the traction/braking force of heavy-haul locomotives,thereby optimizing the driving safety control of heavy-haul trains in the vehicle-environment-track system.Finally,the train operation simulation and optimized driving verification are carried out by simulating some track sections.The results show that the proposed method can correct and pre-optimize driving operations,improving the smoothness of heavy-haul trains by approximately 10%.It verifies the effectiveness of the proposed train assisted driving control reconstruction method,facilitating the smooth and safe operation of heavy-haul trains.展开更多
基金Project(U2034211)supported by the National Natural Science Foundation of ChinaProject(20232ACE01013)supported by the Major Scientific and Technological Research and Development Special Project of Jiangxi Province,China。
文摘The safe driving and operation of trains is a necessary condition for ensuring the safe operation of trains.In particular,heavy-haul trains are characterized by the difficulty in driving and operation.Considering the uncertainties in train driving and operation,this paper analyzes the relationship between the safety of heavy-haul electric locomotive hauled trains and driving and operation.It studies the auxiliary intelligent driving safety operation control methods.Through K-means to identify the characteristics of drivers'driving manipulation,the hidden Markov model adaptively adjusts the train driving and operation sequence,and conducts auxiliary driving reconstruction for heavy-haul locomotive driving and operation.Based on the train running curve and the locomotive traction/braking characteristics,it smoothly controls the exertion of the traction/braking force of heavy-haul locomotives,thereby optimizing the driving safety control of heavy-haul trains in the vehicle-environment-track system.Finally,the train operation simulation and optimized driving verification are carried out by simulating some track sections.The results show that the proposed method can correct and pre-optimize driving operations,improving the smoothness of heavy-haul trains by approximately 10%.It verifies the effectiveness of the proposed train assisted driving control reconstruction method,facilitating the smooth and safe operation of heavy-haul trains.
文摘疲劳驾驶作为交通事故的主要诱因之一,针对其客观准确检测是预防事故发生的重要途径。鉴于信息互补与融合理论,提出一种融合前额单通道脑电(electroencephalogram,EEG)与内嵌眨眼电位(eye blink potential,EBP)特征的列车司机疲劳驾驶检测方法。设计移动标准差(moving standard deviation,MSD)算法从前额EEG中检测EBP,以精确提取其相关特征;在此基础上,采用离散小波变换剔除EEG中的EBP,获得相对纯净的EEG信号,对其进行子带分解,分解后提取各子带的时频特征;为发挥不同类型特征内在潜能,设计基于权重系数的特征融合策略,用于融合内嵌EBP特征和EEG子带特征,将融合特征输入至由CNN和LSTM构成的并行神经网络架构中,以实现多种生理特征信息互补,充分发挥2类神经网络在数据挖掘中的优势互补,进而实现疲劳驾驶检测。实验结果表明:从EBP中提取的3种特征能够有效用于疲劳驾驶检测,通过为不同特征添加权重系数进行融合,充分发挥2类特征内在潜能,相比于未添加权重系数的检测方法,检测准确率从82.12%提升至91.35%,提升了9.23个百分点。同时并行CNN-LSTM网络有效整合2类网络的决策优势,大幅提升了疲劳驾驶检测精度,最终获得了95.48%的检测准确率。该方法有效融合EEG与EBP特征中疲劳驾驶检测潜在的有价值信息,验证了前额单通道EEG在疲劳驾驶检测中良好的实用性,为铁路运输中疲劳驾驶预警和辅助安全驾驶提供一种有效的解决方案。
