基于k-means聚类的管制员注意品质特征研究

On characteristics of attention quality of controller based on k-means clustering

为保障飞行安全,基于作业测验原理,设计20 min连续划消试验,探究管制员注意品质类型及其特征,并进行聚类分析。选取作业错误率、反应时均值、反应时方差作为注意广度、注意稳定性、注意转换与分配的测量参数,运用k-means聚类法将管制员注意品质分类,并描述其特征,对比分析管制员与管制学员的差异。结果表明:181名管制(学)员根据注意品质可分为4类;优秀管制员具有注意广度大、注意稳定性强、注意分配合理、注意转换速度快等特点;管制学员注意品质与管制员有明显差异。

To reveal the type and characteristics of attention quality of controllers,a 20 min continuous cancellation test was designed and carried out. The test data were analyzed by using the clustering analysis method. The error rate of reaction,the mean value of reaction times,and the variance of reaction times were chosen as the measurement parameters of attention span,attention stability,attention switching and distribution. The types of attention quality of controllers were classified by using the k-means clustering analysis method. The characteristics of attention quality of controllers were described and the differences between controllers and controller students were revealed according to the types of attention quality. The results show that 181 testees（ controllers and controller students） could be classified into four types according to attention quality,that these outstanding controllers show large attention span,strong attention stability,rational attention switching and improper attention distribution,and that there is a significant difference between controllers and controller students in attention quality.