基于鸟击事故征候预测的通用航空安全研究

作为民航运输的两翼之一,通用航空安全水平直接影响民机系统的安全。目前，对通航以及鸟击事故征候进行预测的研究较少,本文根据收集到的美国从事通用航空活动发生鸟击事故征候安全状况数据,采用长短期记忆(long short-term memory, LSTM)神经网络模型对鸟击事故征候数据进行训练和预测。实验结果显示，与传统模型相比, LSTM模型具有更好的预测效果,精确度更高。基于此,提出了预测稳定性更好的LSMT-均方根误差(LSTM-root mean square error, LSTM-R)模型，为通用航空鸟击事故征候预测提供了手段和方法,加强了通用航空安全管理。

General aviation safety research based on prediction of bird strike symptom

As one of the two wings of civil aviation transportation, the general aviation safety directly affects the safety of the civil aircraft systems. There are very few research on bird strike symptom prediction. According to the general aviation safety situation of the bird strike symptom in the United States, the long short-term memory (LSTM) neural network model is used to train and predict the bird strike symptom data. The experimental results show that compared with the traditional models, the LSTM model has a better fitting effect and a higher accuracy. Based on this station, an LSTM-root mean square error (LSTM-R) model with a better prediction stability is proposed, which provides a means and method for the general aviation bird strike symptom prediction, and strengthens the safety management of the general aviation.