|本期目录/Table of Contents|

[1]张光远,李婧,秦诗雨,等.基于脑电信号非线性特征的高铁调度员压力状态识别研究*[J].中国安全生产科学技术,2026,22(2):202-208.[doi:10.11731/j.issn.1673-193x.2026.02.025]
　ZHANG Guangyuan,LI Jing,QIN Shiyu,et al.Research on stress state recognition of high speed railway dispatchers based on nonlinear features of EEG signals[J].Journal of Safety Science and Technology,2026,22(2):202-208.[doi:10.11731/j.issn.1673-193x.2026.02.025]
点击复制

基于脑电信号非线性特征的高铁调度员压力状态识别研究*

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
22
期数:
2026年2期
页码:
202-208
栏目:
职业健康与防护
出版日期:
2026-02-28

文章信息/Info

Title:
Research on stress state recognition of high speed railway dispatchers based on nonlinear features of EEG signals
文章编号:
1673-193X(2026)-02-0202-07
作者:
张光远; 李婧; 秦诗雨; 王敬儒; 朱泊霖; 徐方轩
（1.西南交通大学 交通运输与物流学院，四川 成都 610031；
2.西南交通大学 综合交通运输智能化国家地方联合工程实验室，四川 成都 610031）
Author(s):
ZHANG Guangyuan;  LI Jing;  QIN Shiyu;  WANG Jingru;  ZHU Bolin;  XU Fangxuan
（1.School of Transportation and Logistics,Southwest Jiaotong University,Chengdu Sichuan 610031,China；
2.National United Engineering Laboratory of Integrated and Intelligent TransPortation,Southwest Jiaotong University, Chengdu Sichuan 610031,China）
关键词:
高速铁路行车调度员; 脑电信号; 压力状态识别; 非线性动力学; 学习向量量化神经网络
Keywords:
highspeed railway dispatchers;  EEG signal;  stress state recognition;  nonlinear dynamics;  LVQ neural network
分类号:
X951
DOI:
10.11731/j.issn.1673-193x.2026.02.025
文献标志码:
A
摘要:
为了正确评估高速铁路调度员的工作压力状态，保障铁路系统的有序运行。构建基于多特征融合的脑电信号监督学习的高铁调度员工作压力状态分类识别模型，该模型采集高铁调度员工作时脑电信号，使用非线性动力学的方法提取排列熵（PE）、赫斯特指数（Hurst）、希尔伯特黄谱熵（HHSE）3种非线性特征并通过平均影响值算法（mean impact value，MIV）进行筛选和特征级融合，将融合后的特征集输入至经粒子群算法（particle swarm optimization，PSO）、模拟退火算法(simulated annealing，SA)优化的学习向量量化神经网络中（learning vector quantization，LVQ），实现对高铁调度员压力状态的分类识别。研究结果表明：优化后的学习向量量化神经网络可以较好地识别高铁调度员的压力状态，平均分类准确率达90.7%。研究结果可为高铁调度员压力状态的精准监测与预警提供有效参考。
Abstract:
In order to accurately assess the work stress state of high speed railway dispatchers and ensure the orderly operation of the railway system,this study develops a classification and identification model for dispatcher stress states based on supervised learning of electroencephalography signals with multi feature fusion.Electroencephalography signals are collected from high speed railway dispatchers during work.Using nonlinear dynamics methods,three nonlinear features,namely permutation entropy (PE),the Hurst exponent (Hurst),and Hilbert Huang spectral entropy (HHSE),are extracted and then selected and fused at the feature level using the mean impact value algorithm (MIV).The fused feature set is fed into a learning vector quantization neural network (LVQ) optimized by particle swarm optimization (PSO) and simulated annealing (SA),thereby enabling classification and identification of dispatcher stress states.Results show that the optimized learning vector quantization neural network can effectively recognize the stress states of high speed railway dispatchers,achieving an average classification accuracy of 90.7%.These findings provide a useful reference for accurate monitoring and early warning of dispatcher stress states.

参考文献/References:

［1］PUSPITASARI M D,KUSTANTI E R.Hubungan antara persepsi beban kerja dengan stress kerja pada air traffic controller di perum LPPNPI airnav indonesia cabang madya surabaya［J］.Jurnal Empati,2020,7(1):113-118.
［2］JEBELLI H,HWANG S,LEE S.EEG-based workers’ stress recognition at construction sites［J］.Automation in Construction,2018,93,315-324.
［3］JEBELLI H,HWANG S,LEE S,et al.A Supervised learning-based construction workers’ stress recognition usinga wearable electroencephalography(EEG) device［C］Construction Research Congress,2018:40-50.
［4］张光远,邓龙,王亚伟,等.基于脑电信号特征的高铁调度员疲劳状态识别［J］.中国安全科学学报,2024,34(6):235-246. ZHANG Guangyuan,DENG Long,WANG Yawei,et al.Recognition of fatigue state of high-speed rail dispatchers based on EEG signal characteristics ［J］.China Safety Science Journal,2024,34(6):235-246.
［5］陈龙,王崴,瞿珏,等.EEG功率信息显示特征对认知负荷的影响［J］.中国安全科学学报,2020,30(2):183-189. CHEN Long,WANG Wei,Qu Jue,et al.Influence of display characteristics of EEG power on cognitive load ［J］.China Safety Science Journal,2020,30(2):183-189.
［6］张硕,嵇晓强,杨鸽,等.心电与脑电信号结合方法评估心理压力［J］.长春理工大学学报（自然科学版）,2020,43(2):127-134. ZHANG Shuo,JI Xiaoqiang,YANG Ge,et al.Research on the method of evaluating psychological stressby combination of ECG and EEG［J］.Jour-nal of Changchun University of Science and Technology（Natural Science Edition）,2020,43(2):127-134.
［7］张宏远.基于短时心电信号的压力识别研究［D］.天津:天津理工大学，2020.
［8］ZHOU R,WANG C,ZHANG P,et al.ECG-based biometric under different psychological stress states［J］.Computer Methods and Programs in Bio-medicine,2021,202:106005-106005.
［9］BRUCE M,BRYAN R,JOSEPH F C.Sensitivity of physiological measures for detecting systematic variations in cognitive demand from a working memory task:an On-Road study across three age groups［J］.Human Factors,2012,54(3):396-412.
［10］BOUCSEIN W.Principles of electrodermal phenomena ［M］.Boston,MA:Springer US,2011:1-86.
［11］李红红.脑电数据分析方法及其在压力情感状态评估中的应用［D］.秦皇岛:燕山大学,2014.
［12］PENG H,HU B,ZHENG F,et al.A method of identifying chronic stress by EEG［J］.Personal and Ubiquitous Computing,2013,17(7):1341-1347
［13］LU Y,WANG M,WU W,Dynamic entropy-based pattern learning to identify emotions from EEG signals across individuals［J］.Measurement,2020,150.
［14］WANG H,WU,C,LI T,et al.Driving fatigue classification based on fusion entropy analysis combining EOG and EEG［J］.IEEE Access,2019,7:61975-61986.
［15］孔令明,张理义,张其军,等.中国心理承受力量表的研制及其信效度检验［J］.中国健康心理学杂志,2015,23(4):577-581. KONG Lingming,ZHANG Liyi,ZHANG Qijun,et al.Development of Chinese psychological resilience scale and confirmation for reliability and validity ［J］.China Journal of Health Psychology,2015,23(4):577-581.
［16］李昕,孙小棋,齐晓英,等.面向心理压力评估的脑电信号多重分形去趋势波动分析方法研究［J］.生物医学工程学杂志,2017,34(2):180-187. LI Xin,SUN Xiaoqi,QI Xiaoying,et al.Research on analysis method of multi-fractal detrended fluctuation of electroencephalogram focus on mental stress evaluation［J］.Journal of Biomedical En-gineering,2017,34(2):180-187.
［17］王小川,史峰,郁磊,等.MATLAB神经网络43个案例分析［M］.北京:航空航天大学出版社,2013.
［18］郭中小,宋一凡,廖梓龙,等.基于MIV的遗传神经网络径流预报模型［J］.人民黄河,2014,36(10):33-35. GUO Zhongxiao,SONG Yifan,LIAO Zilong,et al.A GA-BP neural network model based on MIV for annual runoff forecasting［J］.Yellow River,2014,36(10):33-35.
［19］张超,魏三强,胡秀建,等.基于粒子群算法优化LVQ神经网络的应用研究［J］.贵州大学学报（自然科学版）,2013,30(5):95-99. ZHANG Chao,WEI Sanqiang,HU Xiujian,et al.Research and application of LVQ neural network based on particle swarm optimization algorithm［J］.Journal of Guizhou University(Natural Sciences),2013,30(5):95-99.
［20］郑凯,袁丹,刘剑清,等.基于SA-PSO优化自适应PNN网络的变压器故障诊断研究［J］.计算机测量与控制,2014,22(4):1015-1017. ZHENG Kai,YUAN Dan,LIU Jianqing,et al.Fault diagnosis for transformer based on adaptive PNN optimized by SA—PSO algorithm［J］.Computer Measurement ＆ Control,2014,22(4):1015-1017.
［21］张顶学,关治洪,刘新芝.一种动态改变惯性权重的自适应粒子群算法［J］.控制与决策,2008,23(11):1253-1257. ZHANG Dingxue,GUAN Zhihong,LIU Xinzhi.Adaptive particle swarm optimization algorithm with dynamically changing inertia weight［J］.Controland Decision,2008,23(11):1253-1257.

相似文献/References:

[1]张光远,王敬儒,梁心怡,等.基于SVM-KNN算法的高铁行车调度员认知负荷脑电评估方法*[J].中国安全生产科学技术,2025,21(7):166.[doi:10.11731/j.issn.1673-193x.2025.07.022]
　ZHANG Guangyuan,WANG Jingru,LIANG Xinyi,et al.EEG-based assessment method of cognitive load of high-speed railway dispatchers using SVM-KNN algorithm[J].Journal of Safety Science and Technology,2025,21(2):166.[doi:10.11731/j.issn.1673-193x.2025.07.022]

备注/Memo

备注/Memo:
收稿日期： 2025-11-13
* 基金项目： 国家自然科学基金面上项目（52472332）；四川省自然科学基金面上项目（2024NSFSC0178）；四川省高等教育人才培养质量和教学改革项目(JG2024-0291)；西南交通大学本科教改项目(JG2024031)
作者简介： 张光远，博士，正高级实验师，主要研究方向为铁路运输规划与安全行为。
更新日期/Last Update: 2026-03-09