An acoustic emission onset time determination method based on Transformer

Abstract

Acoustic emission (AE) technology, as the main method of non-destructive testing technology, has been widely used in structural health monitoring (known as SHM) in the fields of machinery and civil engineering. Locating the failure source is an important application of SHM, and accurately identifying the moment when the AE signal first reaches the sensor (which is called onset time) is of vital importance. Deep learning model has been widely used in onset time determination of AE signals in recent years due to its powerful feature extraction ability. However, as one of the most popular models, Transformer has not been further studied in such field and its effectiveness remains to be proven. In this paper, a novel AE onset time determination method based on Transformer is proposed. Firstly, a preprocessing method based on segmentation-concatenation is applied to divide original data into several connected small segments, while the integrating labeling method is applied on small label segments. Secondly, the preprocessed data and labels are substituted into the Transformer model for training. Finally, for the sequence processed by the Transformer model, the first-time index that reaches the maximum value is obtained as the determination result. Based on the Hsu-Nielson source AE data, the feasibility and performance of this method are analyzed and compared with several commonly used methods: Akaike information criterion (AIC), short/long term average combined with AIC (STA/LTA-AIC), floating threshold (FT) and 1D-CNN-AIC method. The results show that the proposed method is significantly better than AIC, STA/LTA-AIC and FT. Moreover, the determination efficiency is greatly improved while the performance of the proposed method is close to that of 1D-CNN-AIC. Meanwhile, the method has robust performance especially in low signal-to-noise ratio scenario. In practical applications with small-scale data, the proposed method is of relatively high reference as well as application value.

Keywords

Onset time acoustic emission Transformer low SNR

Get full access to this article

View all access options for this article.

References

Kendall

Maxwell

Foulger

, et al. Microseismicity: beyond dots in a box – introduction. Geophysics 2011; 76(6): WC1–WC3.

Piotrowski

Sertucha

. An adaptive approach to non-destructive evaluation (NDE) of cast irons containing precipitated graphite particles with the help of magnetoacoustic emission. NDT & E Int 2023; 133: 102739.

Calabrese

Galeano

Proverbio

, et al. Topological neural network of combined AE and EN signals for assessment of SCC damage. Nondestr Testing Eval 2019; 35(1): 1–22.

Maleki

Abazadeh

Arao

, et al. Selection of an appropriate non-destructive testing method for evaluating drilling-induced delamination in natural fiber composites. NDT & E Int 2022; 126: 102567.

Koester

Taheri

Bigelow

, et al. In-situ acoustic signature monitoring in additive manufacturing processes. AIP Conf Proc 1949; 2018: 020006.

Chethan

Ravindra

Krishnegowda

. Optimization of machining parameters in turning Nimonic-75 using machine vision and acoustic emission signals by Taguchi technique. Measurement 2019; 144: 144–154.

De Santis

Tomor

. Laboratory and field studies on the use of acoustic emission for masonry bridges. NDT & E Int 2013; 55: 64–74.

Madarshahian

Ziehl

Caisedo

. Acoustic emission Bayesian source location: onset time challenge. Mech Syst Signal Process 2019; 123(23): 483–495.

Sleeman

van Eck

. Robust automatic p-phase picking: an on-line implementation in the analysis of broadband seismogram recordings. Phys Earth Planet Inter 1999; 113(1–4): 265–275.

10.

Allen

. Automatic earthquake recognition and timing from single traces. Bull Seismol Soc Am 1978; 68(5): 1521–1532.

11.

Allen

. Automatic phase pickers: their present use and future prospects. Bull Seismol Soc Am 1982; 72(6B): S225–S242.

12.

Kim

Han

Kim

, et al. An integrated approach to real-time acoustic emission damage source localization in piled raft foundations. Appl Sci 2020; 10(23): 8727.

13.

Zhou

Cheng

Rui

, et al. An improved onset time picking method for low SNR acoustic emission signals. IEEE Access 2020; 8: 47756–47767.

14.

Earle

Shearer

. Characterization of global seismograms using an automatic picking algorithm. Bull Seismol Soc Am 1994; 84(2): 366–376.

15.

Chai

Zhang

Duan

. A new qualitative acoustic emission parameter based on Shannon’s entropy for damage monitoring. Mech Syst Signal Process 2018; 100: 617–629.

16.

Van

Nasser

Verstrynge

, et al. Acoustic emission source characterisation of chloride-induced corrosion damage in reinforced concrete. Struct Health Monit 2022; 21(3): 1266–1286.

17.

Ross

Meier

Hauksson

. P-wave arrival picking and first-motion polarity determination with deep learning. J Geophys Res Solid Earth 2018; 123(6): 5120–5129.

18.

Ince

Kiranyaz

Eren

, et al. Real-time motor fault detection by 1D convolutional neural networks. IEEE Trans Ind Electron 2016; 63(11): 7067–7075.

19.

Ding

. Energy-fluctuated multiscale feature learning with deep ConvNet for intelligent spindle bearing fault diagnosis. IEEE Trans Instrumen Meas 2017; 66(8): 1926–1935.

20.

Yuan

Liu

Wang

, et al. Seismic waveform classification and first-break picking using convolution neural networks. IEEE Geosci Remote Sens Lett 2018; 15(2): 272–276.

21.

Zheng

Peng

, et al. An automatic microseismic or acoustic emission arrival identification scheme with deep recurrent neural networks. Geophys J Int 2017; 212(2): 1389–1397.

22.

Guo

Zhu

Gao

, et al. AEnet: automatic picking of P-wave first arrivals using deep learning. IEEE Trans Geosci Remote Sens 2020; 59(6): 5293–5303.

23.

Zhu

Beroza

. PhaseNet: a deep-neural-network-based seismic arrival-time picking method. Geophys J Int 2019; 12(216): 261–273.

24.

Yang

Yan

. An improved AIC onset-time picking method based on regression convolutional neural network. Mech Syst Signal Process 2022; 171: 108867.

25.

Saad

Inoue

Shalaby

, et al. Automatic arrival time detection for earthquakes based on stacked denoising autoencoder. IEEE Geosci Remote Sens Lett 2018; 15(11): 1687–1691.

26.

Vaswani

Shazeer

Parmar

, et al. Attention is All You Need. In: NIPS'17: Proceedings of the 31st international conference on neural information processing systems, Long Beach, CA, USA, 2017, vol. 12, pp. 6000–6010.

27.

Bahdanau

Cho

Bengio

. Neural machine translation by jointly learning to align and translate. Banff, Canada: International Conference on Learning Representations, 2014.

28.

Kim

Denton

Hoang

, et al. Structured attention networks. In: ICLR 2017 conference, Toulon, France, 2017.

29.

Devlin

Chang

Lee

, et al. BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, Minneapolis, Minnesota, USA, 2019, pp. 4171–4186.

30.

Lim

Arık

SÖ

Loeff

, et al. Temporal fusion transformers for interpretable multi-horizon time series forecasting. Int J Forecasting 2021; 37: 1748–1764.

31.

Zhou

Zhang

Peng

, et al. Informer: beyond efficient transformer for long sequence time-series forecasting. In: The 35th AAAI conference on artificial intelligence (AAAI-21), Vancouver, Canada, 2021, pp. 11106–11115.

32.

Madarshahian

Soltangharaei

Anay

, et al. Hsu-Nielsen source acoustic emission data on a concrete block. Data Brief 2019; 23: 103813.

33.

Nielsen

Breckenridge

. Characterization and calibration of acoustic emission sensors. Mater Eval 1981; 39: 60–68.

34.

Yang

Yan

, et al. Evaluating onset times of acoustic emission signals using histogram distances. IEEE Trans Ind Electron 2021; 68(6): 5237–5247.

35.

Chen

Yang

. Arrival picking of acoustic emission signals using a hybrid algorithm based on AIC and histogram distance. IEEE Trans Instrumen Meas 2021; 70: 3505808.

36.

Madarshahian

Ziehl

Todd

. Bayesian estimation of acoustic emission arrival times for source localization. Model Validation Uncertainty Quantif 2019; 3: 127–133.

37.

Srivastava

Hinton

Krizhevsky

, et al. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 2014; 15(1): 1929–1958.

38.

Akaike

. Autoregressive model fitting for control. Ann Inst Stat Math 1971; 23(1): 163–180.

39.

Bayer

Neto

. Model selection criteria in beta regression with varying dispersion. Commun Stat Simul Comput 2015; 46(1): 729–746.

40.

Akaike

. Markovian representation of stochastic processes and its application to the analysis of autoregressive moving average process. Ann Inst Stat Math 1974; 26: 363–387.

41.

Maeda

. A method for reading and checking phase time in auto-processing system of seismic wave data. J Seismological Soc Japan 2nd Ser 1985; 38(3): 365–379.

42.

Shang

Wang

, et al. Identifying P-phase arrivals with noise: an improved kurtosis method based on DWT and STA/LTA. J Appl Geophys 2016; 133: 50–61.

43.

Zhang

Pahlavan

Yang

. Evaluation of acoustic emission source localization accuracy in concrete structures. Struct Health Monit 2020; 19(6): 2063–2074.