An arrival time picker for microseismic rock fracturing waveforms and its quality control for automatic localization in tunnels

Zhang, Wei; Feng, Xia‐Ting; Bi, Xin; Yao, Zhibin; Xiao, Yuzhou; Hu, Lei; Niu, Wen-jing; Feng, Guang-Liang

doi:10.1016/j.compgeo.2021.104175

Cited by 29 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some algorithms are helpful in improving the quality of the original waveform [19,44], but the processing algorithm is bound to cause some changes in the original waveform, and the processing process is also a certain source of error. A better way is to obtain relatively clear take-off points and other information indicators without waveform processing and then use them for positioning [45]. If the quality of the original waveform is high, there is no need for noise reduction, and the take-off points can be picked up manually for positioning [46].…”

Section: Introductionmentioning

confidence: 99%

Waveform Complexity and Positioning Analysis of Acoustic Emission Events during the Compression Failure Process of a Rock Burst Prone Sample

Zhang,

Yu,

et al. 2024

Buildings

View full text Add to dashboard Cite

The localization results of acoustic emission (AE) events can reflect the location and pattern of burst-prone rock failures. However, event localization heavily depends on the quality of the original waveform of the sensor. Therefore, this study analyzed the AE waveform of a rock sample under compression to evaluate its failure localization and quality. From the research results, it could be seen that the initial failure was relatively calm, with clear take-off points, which can be better used for accurate AE event positioning. However, the later failure was severe, causing the take-off points of most sensors to be very unclear, and positioning methods that rely on take-off points cannot be used for positioning, let alone simply using the positioning results of the built-in software. This research result reminds researchers who use AE signals for event localization to first examine the quality and status of the original waveform, providing a basis for obtaining accurate localization results, in order to further accurately study the subsequent failure patterns. The above facts indicate that the initial failure is small and scattered, while the later failure is large and concentrated, with certain fractal characteristics.

show abstract

Section: Introductionmentioning

confidence: 99%

Waveform Complexity and Positioning Analysis of Acoustic Emission Events during the Compression Failure Process of a Rock Burst Prone Sample

Zhang,

Yu,

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

“…For automatic first-arrival picking, deep learning has emerged as a prominent alternative to conventional approaches, as it can handle large datasets without requiring professional knowledge [ 27 ]. Particularly in recent years, several effective deep learning approaches have been presented for first-arrival picking, such as the combination of a regression convolutional neural network (CNN) and AIC [ 21 ], the parallel dual task network (PDTN) [ 28 ], CNN-based methods [ 29 , 30 ], feature pyramid networks (FPNs) [ 31 ], acoustic emission AEnet [ 32 ], CapsNet [ 33 , 34 ], PhaseNet [ 35 ], PickNet [ 36 ], the pixel-level network [ 37 ], U-net [ 38 ], and improved picking approaches using deep learning [ 39 , 40 ]. These approaches have demonstrated superior performance compared to traditional methods.…”

Section: Introductionmentioning

confidence: 99%

Using Fuzzy C-Means Clustering to Determine First Arrival of Microseismic Recordings

Zhao,

Chen,

et al. 2024

Sensors

View full text Add to dashboard Cite

Accurate and automatic first-arrival picking is one of the most crucial steps in microseismic monitoring. We propose a method based on fuzzy c-means clustering (FCC) to accurately divide microseismic data into useful waveform and noise sections. The microseismic recordings’ polarization linearity, variance, and energy are employed as inputs for the fuzzy clustering algorithm. The FCC produces a membership degree matrix that calculates the membership degree of each feature belonging to each cluster. The data section with the higher membership degree is identified as the useful waveform section, whose first point is determined as the first arrival. The extracted polarization linearity improves the classification performance of the fuzzy clustering algorithm, thereby enhancing the accuracy of first-arrival picking. Comparison tests using synthetic data with different signal-to-noise ratios (SNRs) demonstrate that the proposed method ensures that 94.3% of the first arrivals picked have an error within 2 ms when SNR = −5 dB, surpassing the residual U-Net, Akaike information criterion, and short/long time average ratio approaches. In addition, the proposed method achieves a picking accuracy of over 95% in the real dataset tests without requiring labelled data.

show abstract

“…The results showed that accuracy of seismic phases was promoted but the accuracy of recognition of valid signals was not high enough. Recently, Zhang et al (2021) proposed a residual link nested U-Net network (RLU-Net). This algorithm can be used to obtain P and S phases in low signal-to-noise conditions.…”

Section: Introductionmentioning

confidence: 99%

“…However, the training samples are from the STA/LTA+AIC algorithm and no solution is given for wrong and missed pickup. In short, deep learning is currently the preferable algorithm to achieve automatic P-phase pickup (and Chen, 2021;Zhang et al, 2021). Nevertheless, how to resolve the contradiction between sample training and practical applications needs further consideration.…”

Section: Introductionmentioning

confidence: 99%

Automatic P-phase picking based on machine learning and AIC algorithm and its application in engineering geological hazards warning

Zhang¹,

Li²,

Mu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Accurate P-phase first arrival time is a premise for improving accuracy of seismic source localizations and achieving hazard warning. Traditional algorithms failed to meet the requirements of high precision and accuracy for microseismic (MS) monitoring in deep geological engineering. In this study, a multi-step method: convolutional neural network combined with K-means and AIC (CNN-KA) for picking up arrival time of P-phases is proposed. Firstly, convolutional neural network (CNN) technique is used to recognize waveforms of rock fractures instead of manual. Secondly, maximum overlapping discrete wavelet transform and multi-resolution analysis are combined to denoise. Finally, a new picker was developed by introducing K-means clustering algorithm, which was used to extract the target time window where the P-phase was located. It compensates for inherent shortcomings of AIC when applied to field data itself. Experiments and engineering applications show that the average absolute error of the proposed method (CNN-KA) is 0.0915s at frequency of 200Hz, which is 86.65% lower than STA/LTA algorithm. Automatic location error of rock fracture MS events is reduced from 37.33m to 10.89m. CNN-KA was able to warn a potential geological hazard in a coal mine of Anhui Province, China. The in-situ mine pressure data validated the validity of CNN-KA. The proposed workflow greatly improves accuracy of P-phases and identification of rock fracturing events in geo-engineering. The computed results can be used further for calculating precise parameters of MS sources and early warning of engineering geohazards.

show abstract

An arrival time picker for microseismic rock fracturing waveforms and its quality control for automatic localization in tunnels

Cited by 29 publications

References 37 publications

Waveform Complexity and Positioning Analysis of Acoustic Emission Events during the Compression Failure Process of a Rock Burst Prone Sample

Waveform Complexity and Positioning Analysis of Acoustic Emission Events during the Compression Failure Process of a Rock Burst Prone Sample

Using Fuzzy C-Means Clustering to Determine First Arrival of Microseismic Recordings

Automatic P-phase picking based on machine learning and AIC algorithm and its application in engineering geological hazards warning

Contact Info

Product

Resources

About