Aviation accidents are currently one of the leading causes of significant injuries and deaths worldwide. This entices researchers to investigate aircraft safety using data analysis approaches based on an advanced mach...Aviation accidents are currently one of the leading causes of significant injuries and deaths worldwide. This entices researchers to investigate aircraft safety using data analysis approaches based on an advanced machine learning algorithm.To assess aviation safety and identify the causes of incidents, a classification model with light gradient boosting machine (LGBM)based on the aviation safety reporting system (ASRS) has been developed. It is improved by k-fold cross-validation with hybrid sampling model (HSCV), which may boost classification performance and maintain data balance. The results show that employing the LGBM-HSCV model can significantly improve accuracy while alleviating data imbalance. Vertical comparison with other cross-validation (CV) methods and lateral comparison with different fold times comprise the comparative approach. Aside from the comparison, two further CV approaches based on the improved method in this study are discussed:one with a different sampling and folding order, and the other with more CV. According to the assessment indices with different methods, the LGBMHSCV model proposed here is effective at detecting incident causes. The improved model for imbalanced data categorization proposed may serve as a point of reference for similar data processing, and the model’s accurate identification of civil aviation incident causes can assist to improve civil aviation safety.展开更多
利用传感器数据进行预测性维护是航空发动机故障预测与健康管理(prognostic and health management, PHM)的关键问题。针对发动机剩余寿命预测准确性低的问题,提出基于长短期记忆网络(long short-term memory network, LSTM)分类器的预...利用传感器数据进行预测性维护是航空发动机故障预测与健康管理(prognostic and health management, PHM)的关键问题。针对发动机剩余寿命预测准确性低的问题,提出基于长短期记忆网络(long short-term memory network, LSTM)分类器的预测性维护模型。LSTM分类器通过门控单元对长时间序列信息进行充分筛选,并将有效信息用于时间序列预测。首先,采用滑动时间窗口制备训练样本。其次,将预处理后的样本输入LSTM,预测设备在特定时间窗口内的失效概率。然后,通过调整窗口大小,得到最优性能的二分类模型,以更好地适应预测维护需求。最后,利用美国航空航天局C-MAPSS数据集验证了该模型的有效性,相比于已有分类方法,其在剩余使用寿命分类方面更加准确。展开更多
Safety is the foundation of sustainable development in civil aviation.Although catastrophic accidents are rare,indicators of potential incidents and unsafe events frequently materialize.Therefore,a history of unsafe d...Safety is the foundation of sustainable development in civil aviation.Although catastrophic accidents are rare,indicators of potential incidents and unsafe events frequently materialize.Therefore,a history of unsafe data are considered in predicting safety risks.A deep learning method is adopted for extracting reactions in safety risks.The deep neural network(DNN)model for safety risk prediction is shown to extract complex data characteristics better than a shallow network model.Using extended unsafe data and monthly risk indices,hidden layers and iterations are determined.The effectiveness of DNN is also revealed in comparison with the traditional neural network.Through early risk detection using the method in the paper,airlines and the government can mitigate potential risk and take proactive measures to improve civil aviation safety.展开更多
剩余寿命预测对航空发动机的预防性维修有重要指导作用,是保障飞机安全运行,提高维修保障效率的重要手段。一维卷积神经网络(1-dimensional convolutional neural network,1D-CNN)和双向长短时记忆神经网络(Bidirectional long short me...剩余寿命预测对航空发动机的预防性维修有重要指导作用,是保障飞机安全运行,提高维修保障效率的重要手段。一维卷积神经网络(1-dimensional convolutional neural network,1D-CNN)和双向长短时记忆神经网络(Bidirectional long short memory, Bi-LSTM)被应用于航空发动机剩余寿命预测模型。首先,根据工程经验在多状态参数的主成分分析的基础上对退化过程进行随机分布拟合,得到综合性能退化量;然后将多变量时间序列样本和对应的性能退化量代入1D-CNN模型进行回归分析,从而得到性能退化分析模型;再通过Bi-LSTM对性能退化量进行时间序列预测,得到性能退化的未来趋势;最后通过设定性能退化阈值,得到剩余寿命预测结果,从而得到从多状态参数-性能退化分析-性能退化预测-剩余寿命预测的实时动态感知模型。实例分析结果表明,提出的混合模型与其他单一深度学习和传统模型相比,有更低的回归分析误差和退化预测误差,能够得到更准确可靠的剩余寿命预测结果。展开更多
Nowadays aviation accidents have become one of the major causes of severe injuries and fatalities around the world. This attracts the research community to look into aviation safety by applying data analysis technique...Nowadays aviation accidents have become one of the major causes of severe injuries and fatalities around the world. This attracts the research community to look into aviation safety by applying data analysis techniques based on an advanced machine learning algorithm. An ensemble classification model based on Aviation Safety Reporting System(ASRS) has been proposed to analyze aviation safety targeting the people injured in the system.The ensemble classification model shall contain two modules: the data-driven module consisting of data cleaning, feature selection,and imbalanced data division and reorganization, and the modeldriven module stacked by Random Forest(RF), XGBoost(XGB),and Light Gradient Boosting Machine(LGBM) separately. The results indicate that the ensemble model could solve the data imbalance while vastly improving accuracy. LGBM illustrates higher accuracy and faster run in the analysis of a single model of the ASRS-based imbalanced data, while the ensemble model has the best performance in classification at the same time. The ensemble model proposed for imbalanced data classification can provide a certain reference for similar data processing while improving the safety of civil aviation.展开更多
基金supported by the National Natural Science Foundation of China Civil Aviation Joint Fund (U1833110)Research on the Dual Prevention Mechanism and Intelligent Management Technology f or Civil Aviation Safety Risks (YK23-03-05)。
文摘Aviation accidents are currently one of the leading causes of significant injuries and deaths worldwide. This entices researchers to investigate aircraft safety using data analysis approaches based on an advanced machine learning algorithm.To assess aviation safety and identify the causes of incidents, a classification model with light gradient boosting machine (LGBM)based on the aviation safety reporting system (ASRS) has been developed. It is improved by k-fold cross-validation with hybrid sampling model (HSCV), which may boost classification performance and maintain data balance. The results show that employing the LGBM-HSCV model can significantly improve accuracy while alleviating data imbalance. Vertical comparison with other cross-validation (CV) methods and lateral comparison with different fold times comprise the comparative approach. Aside from the comparison, two further CV approaches based on the improved method in this study are discussed:one with a different sampling and folding order, and the other with more CV. According to the assessment indices with different methods, the LGBMHSCV model proposed here is effective at detecting incident causes. The improved model for imbalanced data categorization proposed may serve as a point of reference for similar data processing, and the model’s accurate identification of civil aviation incident causes can assist to improve civil aviation safety.
文摘利用传感器数据进行预测性维护是航空发动机故障预测与健康管理(prognostic and health management, PHM)的关键问题。针对发动机剩余寿命预测准确性低的问题,提出基于长短期记忆网络(long short-term memory network, LSTM)分类器的预测性维护模型。LSTM分类器通过门控单元对长时间序列信息进行充分筛选,并将有效信息用于时间序列预测。首先,采用滑动时间窗口制备训练样本。其次,将预处理后的样本输入LSTM,预测设备在特定时间窗口内的失效概率。然后,通过调整窗口大小,得到最优性能的二分类模型,以更好地适应预测维护需求。最后,利用美国航空航天局C-MAPSS数据集验证了该模型的有效性,相比于已有分类方法,其在剩余使用寿命分类方面更加准确。
基金supported by the Joint Funds of the National Natural Science Foundation of China (No. U1833110)
文摘Safety is the foundation of sustainable development in civil aviation.Although catastrophic accidents are rare,indicators of potential incidents and unsafe events frequently materialize.Therefore,a history of unsafe data are considered in predicting safety risks.A deep learning method is adopted for extracting reactions in safety risks.The deep neural network(DNN)model for safety risk prediction is shown to extract complex data characteristics better than a shallow network model.Using extended unsafe data and monthly risk indices,hidden layers and iterations are determined.The effectiveness of DNN is also revealed in comparison with the traditional neural network.Through early risk detection using the method in the paper,airlines and the government can mitigate potential risk and take proactive measures to improve civil aviation safety.
文摘剩余寿命预测对航空发动机的预防性维修有重要指导作用,是保障飞机安全运行,提高维修保障效率的重要手段。一维卷积神经网络(1-dimensional convolutional neural network,1D-CNN)和双向长短时记忆神经网络(Bidirectional long short memory, Bi-LSTM)被应用于航空发动机剩余寿命预测模型。首先,根据工程经验在多状态参数的主成分分析的基础上对退化过程进行随机分布拟合,得到综合性能退化量;然后将多变量时间序列样本和对应的性能退化量代入1D-CNN模型进行回归分析,从而得到性能退化分析模型;再通过Bi-LSTM对性能退化量进行时间序列预测,得到性能退化的未来趋势;最后通过设定性能退化阈值,得到剩余寿命预测结果,从而得到从多状态参数-性能退化分析-性能退化预测-剩余寿命预测的实时动态感知模型。实例分析结果表明,提出的混合模型与其他单一深度学习和传统模型相比,有更低的回归分析误差和退化预测误差,能够得到更准确可靠的剩余寿命预测结果。
基金Supported by the Joint Fund of National Natural Science Foundation of China and Civil Aviation Administration of China (U1833110)。
文摘Nowadays aviation accidents have become one of the major causes of severe injuries and fatalities around the world. This attracts the research community to look into aviation safety by applying data analysis techniques based on an advanced machine learning algorithm. An ensemble classification model based on Aviation Safety Reporting System(ASRS) has been proposed to analyze aviation safety targeting the people injured in the system.The ensemble classification model shall contain two modules: the data-driven module consisting of data cleaning, feature selection,and imbalanced data division and reorganization, and the modeldriven module stacked by Random Forest(RF), XGBoost(XGB),and Light Gradient Boosting Machine(LGBM) separately. The results indicate that the ensemble model could solve the data imbalance while vastly improving accuracy. LGBM illustrates higher accuracy and faster run in the analysis of a single model of the ASRS-based imbalanced data, while the ensemble model has the best performance in classification at the same time. The ensemble model proposed for imbalanced data classification can provide a certain reference for similar data processing while improving the safety of civil aviation.
