CAJ | 학술논문

基于空中交通复杂程度刻画管制工作负荷是当前空中交通管理领域的研究热点。本文采集了厦门空管站的雷达数据，计算得出10个空中交通复杂性评价指标数值，通过共线性诊断发现复杂性指标间存在较强的多重共线性。在利用岭迹图对复杂性评价指标进行筛选的基础上，建立岭回归—BP神经网络组合模型对管制员工作负荷进行预测，并通过实测陆空通话数据进行验证。结果表明，本文提出的岭回归—BP神经网络组合模型收敛速度快、训练时间少；组合模型的均方误差、均方根误差、平均绝对误差、平均绝对相对误差等4项性能指标都相对较小，预测精度较高。
기우공중교통복잡정도각화관제공작부하시당전공중교통관리영역적연구열점。본문채집료하문공관참적뢰체수거，계산득출10개공중교통복잡성평개지표수치，통과공선성진단발현복잡성지표간존재교강적다중공선성。재이용령적도대복잡성평개지표진행사선적기출상，건립령회귀—BP신경망락조합모형대관제원공작부하진행예측，병통과실측륙공통화수거진행험증。결과표명，본문제출적령회귀—BP신경망락조합모형수렴속도쾌、훈련시간소；조합모형적균방오차、균방근오차、평균절대오차、평균절대상대오차등4항성능지표도상대교소，예측정도교고。
It is becoming a new hot topic in the field of air traffic management that evaluating the controller’s workload by the traffic complexity factors. Based on the radar data of Xiamen air traffic control station, 10 typical complexity evaluation factors were calculated. The strong multi-co-linearity among various complexity factors is discovered through co-linearity diagnosis. Using the ridge trace plot of ridge regression, the complexity evaluation factors are selected, and the combined model of ridge regression and neural network are established to predict the controller’s workload. The forecasting results are verified by the pilot/controller voice communication data. It shows that the combination model of ridge regression and BP neural network has fast convergence speed and less training time. The combined forecasting model has high precision because four performance indexes such as mean square error, root mean square error, mean absolute error and mean absolute relative errors are relatively small.