The anomaly detection of the brake operating unit (BOU) in thebrake systems on metro vehicle is critical for the safety and reliability ofthe trains. On the other hand, current periodic inspection and maintenanceare u...The anomaly detection of the brake operating unit (BOU) in thebrake systems on metro vehicle is critical for the safety and reliability ofthe trains. On the other hand, current periodic inspection and maintenanceare unable to detect anomalies in an early stage. Also, building an accurateand stable system for detecting anomalies is extremely difficult. Therefore,we present an efficient model that use an ensemble of recurrent autoencodersto accurately detect the BOU abnormalities of metro trains. This is the firstproposal to employ an ensemble deep learning technique to detect BOUabnormalities in metro train braking systems. One of the anomalous caseson metro vehicles is the case when the air cylinder (AC) pressures are less thanthe brake cylinder (BC) pressures in certain parts where the brake pressuresincrease before coming to a halt. Hence, in this work, we first extract the dataof BC and AC pressures. Then, the extracted data of BC and AC pressuresare divided into multiple subsequences that are used as an input for bothbi-directional long short-term memory (biLSTM) and bi-directional gatedrecurrent unit (biGRU) autoencoders. The biLSTM and biGRU autoencodersare trained using training dataset that only contains normal subsequences. Fordetecting abnormalities from test dataset which consists of abnormal subsequences, the mean absolute errors (MAEs) between original subsequences andreconstructed subsequences from both biLSTM and biGRU autoencoders arecalculated. As an ensemble step, the total error is calculated by averaging twoMAEs from biLSTM and biGRU autoencoders. The subsequence with totalerror greater than a pre-defined threshold value is considered an abnormality.We carried out the experiments using the BOU dataset on metro vehiclesin South Korea. Experimental results demonstrate that the ensemble modelshows better performance than other autoencoder-based models, which showsthe effectiveness of our ensemble model for detecting BOU anomalies onmetro trains.展开更多
Once operating trains are disabled on the railway lines,an efficient manner is to utilize the train for train rescue.Owning to the different train and coupler types,it is difficult to formulate uniform regulations for...Once operating trains are disabled on the railway lines,an efficient manner is to utilize the train for train rescue.Owning to the different train and coupler types,it is difficult to formulate uniform regulations for train to train rescue.In this paper,the longitudinal train dynamics of electric multiple units under rescue were analyzed by field and laboratory tests.The angling behavior of the brakinginduced coupler under compressed in-train forces was analyzed.A dynamic model for the train and draft gear system was developed considering accurate boundary limitations and braking characteristics.The safety indices and their limits for the coupled rescue train were defined.Thedynamic evaluations of different train to train rescue scenarios were analyzed.It is indicated that the coupler vertical rotation occurs during the emergency braking applied by the assisting train.The vertical force components of intrain forces lead to the carbody pitch behavior and even cause local destructions to the coupler system.The carbody pitch motion can arise the inference of in-train devices.Based on the safety evaluation of train and coupler system,the regulations for typical train to train rescue scenarios were formulated.展开更多
基金This research is supported by the Korea Agency for Infrastructure Technology Advancement(KAIA)grant funded by the Ministry of Land,Infrastructure and Transport(Grant21QPWO-B152223-03).
文摘The anomaly detection of the brake operating unit (BOU) in thebrake systems on metro vehicle is critical for the safety and reliability ofthe trains. On the other hand, current periodic inspection and maintenanceare unable to detect anomalies in an early stage. Also, building an accurateand stable system for detecting anomalies is extremely difficult. Therefore,we present an efficient model that use an ensemble of recurrent autoencodersto accurately detect the BOU abnormalities of metro trains. This is the firstproposal to employ an ensemble deep learning technique to detect BOUabnormalities in metro train braking systems. One of the anomalous caseson metro vehicles is the case when the air cylinder (AC) pressures are less thanthe brake cylinder (BC) pressures in certain parts where the brake pressuresincrease before coming to a halt. Hence, in this work, we first extract the dataof BC and AC pressures. Then, the extracted data of BC and AC pressuresare divided into multiple subsequences that are used as an input for bothbi-directional long short-term memory (biLSTM) and bi-directional gatedrecurrent unit (biGRU) autoencoders. The biLSTM and biGRU autoencodersare trained using training dataset that only contains normal subsequences. Fordetecting abnormalities from test dataset which consists of abnormal subsequences, the mean absolute errors (MAEs) between original subsequences andreconstructed subsequences from both biLSTM and biGRU autoencoders arecalculated. As an ensemble step, the total error is calculated by averaging twoMAEs from biLSTM and biGRU autoencoders. The subsequence with totalerror greater than a pre-defined threshold value is considered an abnormality.We carried out the experiments using the BOU dataset on metro vehiclesin South Korea. Experimental results demonstrate that the ensemble modelshows better performance than other autoencoder-based models, which showsthe effectiveness of our ensemble model for detecting BOU anomalies onmetro trains.
基金supported by the National Natural Science Foundation of China [No.U1334206]the National Key R&D Program of China [No.2016YFB1200500]
文摘Once operating trains are disabled on the railway lines,an efficient manner is to utilize the train for train rescue.Owning to the different train and coupler types,it is difficult to formulate uniform regulations for train to train rescue.In this paper,the longitudinal train dynamics of electric multiple units under rescue were analyzed by field and laboratory tests.The angling behavior of the brakinginduced coupler under compressed in-train forces was analyzed.A dynamic model for the train and draft gear system was developed considering accurate boundary limitations and braking characteristics.The safety indices and their limits for the coupled rescue train were defined.Thedynamic evaluations of different train to train rescue scenarios were analyzed.It is indicated that the coupler vertical rotation occurs during the emergency braking applied by the assisting train.The vertical force components of intrain forces lead to the carbody pitch behavior and even cause local destructions to the coupler system.The carbody pitch motion can arise the inference of in-train devices.Based on the safety evaluation of train and coupler system,the regulations for typical train to train rescue scenarios were formulated.
