摘要
为研究地铁驾驶员在应急作业下的工作负荷状态,通过采集驾驶员应急作业状态下的心电信号并分析心电信号与工作负荷之间的关系。首先对心电信号进行去噪处理和对R波波峰提取,计算得到SDNN、RMSSD、pNN50、NN50和MEAN共5个心率变异性时域指标,作为工作负荷状态判别的输入变量。以各指标构成的数据集为样本,应用K-means聚类分析法,对地铁驾驶员应急作业下的工作负荷状态进行划分和判别。结果表明:分类数为2时的Silhouette指标值最佳;基于Silhouette指标将地铁驾驶员工作负荷状态划分为低负荷和高负荷;基于K-means聚类分析法得到两组判别工作负荷状态的心率变异性指标的聚类中心。最后,以驾驶员的低负荷状态样本和高负荷状态样本验证了本文方法的有效性,为监测地铁驾驶员的工作负荷状态提供依据。
In order to study the workload state of subway drivers under emergency operation,the ECG signal of drivers under emergency operation state is collected and the relationship between ECG signal and workload is analyzed.Firstly,the ECG signal is denoised and the R-wave peak is extracted.Five time-domain indexes of heart rate variability,SDNN,RMSSD,pNN50,NN50 and MEAN,are calculated as input variables for workload state discrimination.Taking the data set composed of each index as the sample,the workload state of subway drivers under emergency operation is divided and distinguished by using K-means cluster analysis method.The results show that the Silhouette index value is the best when the classification number is 2;based on the Silhouette index,the workload state of subway drivers is divided into low load and high load;based on K-means cluster analysis,the cluster centers of two groups of heart rate variability indexes that distinguish workload status are obtained.Finally,the effectiveness of this method is verified by the driver's low load state samples and high load state samples,which provides a basis for monitoring the subway driver's workload state.
作者
顾传扬
杨聚芬
刘志钢
GU Chuanyang;YANG Jufen;LIU Zhigang(College of Urban Rail Transportation,Shanghai University of Engineering Science,Shanghai 201620,China)
出处
《物流科技》
2022年第17期52-55,61,共5页
Logistics Sci-Tech
基金
国家自然科学基金资助项目“基于任务分析与多资源理论的轨道交通行车调度工作负荷与人因绩效研究”(71701124)。
