Page 26 - Kỷ yếu hội thảo khoa học lần thứ 12 - Công nghệ thông tin và Ứng dụng trong các lĩnh vực (CITA 2023)
P. 26

10


                      Table 3. The comparison between the proposed method (AECWT-3DR-Net) and other methods
                                         Single CWT Image
                                                                ToA method [6]      AECWT-3DR-Net
                                            as Input [11]
                            Axis          x      y      z      x      y       z      x       y      z
                        RMSE (mm)       475.7  161.4  478.0  118.5  203.1  215.5    9.6     7.9    9.3

                      Avg. RMSE (mm)           371.7                 179.0                 8.9


                     4     Conclusion and Future Works


                     The  AECWT-3DR-Net  for  3D  test  regression  produced  impressive  results,  with
                     RMSE measurements of less than 9.6 mm. The study applied a heterogeneous materi-
                     al,  specifically  concrete,  for  the  experiment.  The  proposed  method  overcomes  the
                     limitations of traditional methods and produces high accuracy by utilizing the rela-
                     tionships between signals collected from sensors in multiple locations. In future work,
                     we will continue to improve the accuracy of detecting cracks.



                     Acknowledgements


                     This work was supported by the National Research Foundation of Korea (NRF) grant
                     funded  by  the  Korea  government  (MSIT)  (NRF-2021R1A4A3033128  and  NRF-
                     2022R1C1C1003012).


                     References


                      1.  C.C.  Yang,  S.Y.Chen,  Y.J.  Hsieh,  F.C.  Cheng,  Y.C.  Huang,  J.J.  Chue,  C.T.  Kuo, C.M.
                         Wu,  C.M  .  Huang,  "A  rugged  sensor  system  for  real-time  bridge  safety  monitoring  in
                         Taiwan," in IEEE Sensors Applications Symposium (SAS), Catania, Italy, 2016.
                      2.  Z. Ahmad, T. Nguyen, A. Rai, J. Kim, "Industrial fluid pipeline leak detection and locali-
                         zation  based  on  a  multiscale  mann-whitney  test  and  acoustic  emission  event  tracking,"
                         Mechanical Systems and Signal Processing, vol. 189, 2023.
                      3.  W.  Suwansin,  P.  Phasukkit,  "Deep  Learning-Based  Acoustic  Emission  Scheme  for
                         Nondestructive  Localization  of  Cracks  in  Train  Rails  under  a  Load,"  Sensors,  vol.  21,
                         no. 1, 2020.
                      4.  L. Cheng, H. Xin, R.M. Groves, M. Veljkovic, "Acoustic emission source location using
                         Lamb wave propagation simulation and artificial neural network for I-shaped steel girder,"
                         Construction and Building Materials, 2021.
                      5.  K.  Ohno,  M.  Ohtsu,  "Crack  classification  in  concrete  based  on  acoustic  emission,"
                         Construction and Building Materials, vol. 24 (12), 2010.
                      6.  S. Ravindra, S. N. Jagadeesha, "Time Of Arrival Based Localization In Wireless Sensor
                         Networks: A Linear Approach," Signal & Image Processing (SIPIJ), vol. 4, 2013.
                      7.  P.  Wu,  S.  Su,  Z.  Zuo,  X.  Guo,  B.  Sun,  X.  Wen,  "Time  Difference  of  Arrival  (TDoA)
                         Localization Combining Weighted Least Squares and Firefly Algorithm," Sensors, vol. 19,
                         no. 11, 2019.




                     CITA 2023                                                   ISBN: 978-604-80-8083-9
   21   22   23   24   25   26   27   28   29   30   31