论文部分内容阅读
为更有效地实现具有复杂性、时变性及非线性的机场滑行道安全风险预警,降低事故发生率,针对小波神经网络(WNN)训练过程易陷入局部最优以及训练不稳定等影响预测准确性问题,采用蝙蝠算法(BA)优化WNN,设计和实现基于BA-WNN的滑行道安全风险预警方法,并将其与BP神经网络(BPNN)、WNN、遗传算法优化小波网络(GA-WNN)等3种方法进行有效性对比。结果表明:BA-WNN方法的预警准确率最高(约为84%),在所有工况下误警率都较低。
In order to realize the early warning of the safety risk of airport taxiway with complexity, time-varying and non-linearity more effectively, reduce the accident rate, the prediction accuracy of WNN training process is easy to fall into local optimum and training instability (BA) is used to optimize the WNN, and the warning method of taxiway safety risk based on BA-WNN is designed and implemented. The method is combined with BP neural network (BPNN), WNN, GA-WNN Three methods for effectiveness comparison. The results show that the BA-WNN method has the highest early warning accuracy (about 84%) and the false alarm rate is lower under all operating conditions.