Distributed Acoustic Sensing(DAS) is an emerging technique for ultra-dense seismic observation, which provides a new method for high-resolution sub-surface seismic imaging. Recently a large number of linear DAS arrays...Distributed Acoustic Sensing(DAS) is an emerging technique for ultra-dense seismic observation, which provides a new method for high-resolution sub-surface seismic imaging. Recently a large number of linear DAS arrays have been used for two-dimensional S-wave near-surface imaging in urban areas. In order to explore the feasibility of three-dimensional(3D) structure imaging using a DAS array, we carried out an active source experiment at the Beijing National Earth Observatory. We deployed a 1 km optical cable in a rectangular shape, and the optical cable was recast into 250 sensors with a channel spacing of 4 m. The DAS array clearly recorded the P, S and surface waves generated by a hammer source. The first-arrival P wave travel times were first picked with a ShortTerm Average/Long-Term Average(STA/LTA) method and further manually checked. The P-wave signals recorded by the DAS are consistent with those recorded by the horizontal components of short-period seismometers. At shorter source-receiver distances, the picked P-wave arrivals from the DAS recording are consistent with vertical component recordings of seismometers, but they clearly lag behind the latter at greater distances.This is likely due to a combination of the signal-to-noise ratio and the polarization of the incoming wave. Then,we used the Tomo DD software to invert the 3D P-wave velocity structure for the uppermost 50 m with a resolution of 10 m. The inverted P-wave velocity structures agree well with the S-wave velocity structure previously obtained through ambient noise tomography. Our study indicates the feasibility of 3D near-surface imaging with the active source and DAS array. However, the inverted absolute velocity values at large depths may be biased due to potential time shifts between the DAS recording and seismometer at large source-receiver distances.展开更多
Railroad condition monitoring is paramount due to frequent passage through densely populated regions.This significance arises from the potential consequences of accidents such as train derailments,hazardous materials ...Railroad condition monitoring is paramount due to frequent passage through densely populated regions.This significance arises from the potential consequences of accidents such as train derailments,hazardous materials leaks,or collisions which may have far-reaching impacts on communities and the surrounding areas.As a solution to this issue,the use of distributed acoustic sensing(DAS)-fiber optic cables along railroads provides a feasible tool for monitoring the health of these extended infrastructures.Nevertheless,analyzing DAS data to assess railroad health or detect potential damage is a challenging task.Due to the large amount of data generated by DAS,as well as the unstructured patterns and substantial noise present,traditional analysis methods are ineffective in interpreting this data.This paper introduces a novel approach that harnesses the power of deep learning through a combination of CNNs and LSTMs,augmented by sliding window techniques(CNN-LSTM-SW),to advance the state-of-the-art in the railroad condition monitoring system.As well as it presents the potential for DAS and fiber optic sensing technologies to revolutionize the proposed CNN-LSTM-SW model to detect conditions along the rail track networks.Extracting insights from the data of High tonnage load(HTL)-a 4.16 km fiber optic and DAS setup,we were able to distinguish train position,normal condition,and abnormal conditions along the railroad.Notably,our investigation demonstrated that the proposed approaches could serve as efficient techniques for processing DAS signals and detecting the condition of railroad infrastructures at any remote distance with DAS-Fiber optic cable setup.Moreover,in terms of pinpointing the train's position,the CNN-LSTM architecture showcased an impressive 97%detection rate.Applying a sliding window,the CNN-LSTM labeled data,the remaining 3%of misclassified labels have been improved dramatically by predicting the exact locations of each type of condition.Altogether,these proposed models exhibit promising potential for accurately identifying various railroad conditions,including anomalies and discrepancies that warrant thorough exploration.展开更多
基金supported by the National Key R&D Program of China(2022YFC3102202)the Chinese Academy of Sciences (CAS) Project for Young Scientists in Basic Research (YSBR-020)。
文摘Distributed Acoustic Sensing(DAS) is an emerging technique for ultra-dense seismic observation, which provides a new method for high-resolution sub-surface seismic imaging. Recently a large number of linear DAS arrays have been used for two-dimensional S-wave near-surface imaging in urban areas. In order to explore the feasibility of three-dimensional(3D) structure imaging using a DAS array, we carried out an active source experiment at the Beijing National Earth Observatory. We deployed a 1 km optical cable in a rectangular shape, and the optical cable was recast into 250 sensors with a channel spacing of 4 m. The DAS array clearly recorded the P, S and surface waves generated by a hammer source. The first-arrival P wave travel times were first picked with a ShortTerm Average/Long-Term Average(STA/LTA) method and further manually checked. The P-wave signals recorded by the DAS are consistent with those recorded by the horizontal components of short-period seismometers. At shorter source-receiver distances, the picked P-wave arrivals from the DAS recording are consistent with vertical component recordings of seismometers, but they clearly lag behind the latter at greater distances.This is likely due to a combination of the signal-to-noise ratio and the polarization of the incoming wave. Then,we used the Tomo DD software to invert the 3D P-wave velocity structure for the uppermost 50 m with a resolution of 10 m. The inverted P-wave velocity structures agree well with the S-wave velocity structure previously obtained through ambient noise tomography. Our study indicates the feasibility of 3D near-surface imaging with the active source and DAS array. However, the inverted absolute velocity values at large depths may be biased due to potential time shifts between the DAS recording and seismometer at large source-receiver distances.
基金supported by funding from The Association of American Railroads(AAR)-MxV Rail(Award number:21-0825-007538)Impact Area Accelerator Award Grant 2023 from Georgia Southern University's Office of Research.
文摘Railroad condition monitoring is paramount due to frequent passage through densely populated regions.This significance arises from the potential consequences of accidents such as train derailments,hazardous materials leaks,or collisions which may have far-reaching impacts on communities and the surrounding areas.As a solution to this issue,the use of distributed acoustic sensing(DAS)-fiber optic cables along railroads provides a feasible tool for monitoring the health of these extended infrastructures.Nevertheless,analyzing DAS data to assess railroad health or detect potential damage is a challenging task.Due to the large amount of data generated by DAS,as well as the unstructured patterns and substantial noise present,traditional analysis methods are ineffective in interpreting this data.This paper introduces a novel approach that harnesses the power of deep learning through a combination of CNNs and LSTMs,augmented by sliding window techniques(CNN-LSTM-SW),to advance the state-of-the-art in the railroad condition monitoring system.As well as it presents the potential for DAS and fiber optic sensing technologies to revolutionize the proposed CNN-LSTM-SW model to detect conditions along the rail track networks.Extracting insights from the data of High tonnage load(HTL)-a 4.16 km fiber optic and DAS setup,we were able to distinguish train position,normal condition,and abnormal conditions along the railroad.Notably,our investigation demonstrated that the proposed approaches could serve as efficient techniques for processing DAS signals and detecting the condition of railroad infrastructures at any remote distance with DAS-Fiber optic cable setup.Moreover,in terms of pinpointing the train's position,the CNN-LSTM architecture showcased an impressive 97%detection rate.Applying a sliding window,the CNN-LSTM labeled data,the remaining 3%of misclassified labels have been improved dramatically by predicting the exact locations of each type of condition.Altogether,these proposed models exhibit promising potential for accurately identifying various railroad conditions,including anomalies and discrepancies that warrant thorough exploration.
