Skip to main content
Log in

Wall-climbing robot for non-destructive evaluation using impact-echo and metric learning SVM

  • Regular Paper
  • Published:
International Journal of Intelligent Robotics and Applications Aims and scope Submit manuscript

Abstract

The impact-echo (IE) acoustic inspection method is a non-destructive evaluation technique, which has been widely applied to detect the defects, structural deterioration level, and thickness of plate-like concrete structures. This paper presents a novel climbing robot, namely Rise-Rover, to perform automated IE signal collection from concrete structures with IE signal analyzing based on machine learning techniques. Rise-Rover is our new generation robot, and it has a novel and enhanced absorption system to support heavy load, and crawler-like suction cups to maintain high mobility performance while crossing small grooves. Moreover, the design enables a seamless transition between ground and wall. This paper applies the fast Fourier transform and wavelet transform for feature detection from collected IE signals. A distance metric learning based support vector machine approach is newly proposed to automatically classify the IE signals. With the visual-inertial odometry of the robot, the detected flaws of inspection area on the concrete plates are visualized in 2D/3D. Field tests on a concrete bridge deck demonstrate the efficiency of the proposed robot system in automatic health condition assessment for concrete structures.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

Notes

  1. http://www.impact-echo.com/_resources/Impact-Echo-Manual.pdf

  2. https://www.youtube.com/watch?v=5flaoIwEZFM

  3. https://www.youtube.com/watch?v=Cz8U9M19agA

  4. https://www.youtube.com/watch?v=Cz8U9M19agA#t=0m38s

  5. https://www.youtube.com/watch?v=5flaoIwEZFM#t=0m57s

  6. https://www.youtube.com/watch?v=Cz8U9M19agA#t=1m07s

  7. https://www.youtube.com/watch?v=Cz8U9M19agA#t=1m40s

  8. https://www.youtube.com/watch?v=5flaoIwEZFM#t=0m25s

References

  • Bi, Z., Guan, Y., Chen, S., Zhu, H., Zhang, H.: A miniature biped wall-climbing robot for inspection of magnetic metal surfaces. In: Robotics and Biomimetics (ROBIO), 2012 IEEE International Conference on, IEEE, pp. 324–329. (2012)

  • Carino, N.J., et al.: The impact-echo method: an overview. In: Proceedings of the 2001 Structures Congress & Exposition, pp. 21–23 (2001)

  • Daniels, J.J., et al.: Ground penetrating radar fundamentals, pp. 1–21. Region V, Prepared as an appendix to a Report to the US EPA (2000)

  • Farrar, C.R., Worden, K.: Structural Health Monitoring: A Machine Learning Perspective. Wiley, New York (2012)

    Book  Google Scholar 

  • Galt, S., Luk, B., Cooke, D., Collie, A.: A tele-operated semi-intelligent climbing robot for nuclear applications. In: Mechatronics and Machine Vision in Practice, 1997. Proceedings., Fourth Annual Conference on, IEEE pp. 118–123 (1997)

  • Guan, Y., Zhu, H., Wu, W., Zhou, X., Jiang, L., Cai, C., Zhang, L., Zhang, H.: A modular biped wall-climbing robot with high mobility and manipulating function. IEEE/ASME Trans. Mech. 18(6), 1787–1798 (2013)

    Article  Google Scholar 

  • Gucunski, N., Maher, A.: Evaluation of seismic pavement analyzer for pavement condition monitoring. Technical report (2002)

  • Hao, S.: I-35w bridge collapse. J. Bridge Eng. 15(5), 608–614 (2009)

    Article  Google Scholar 

  • Harley, J.B.: Data-driven, sparsity-based matched field processing for structural health monitoring. (2014)

  • Ito, Y., Uomoto, T.: Nondestructive testing method of concrete using impact acoustics. NDT E Int. 30(4), 217–222 (1997)

    Article  Google Scholar 

  • Jebara, T.: Multi-task feature and kernel selection for svms. In: Proceedings of the twenty-first international conference on Machine learning, ACM, p. 55 (2004)

  • Li, B., Cao, J., Xiao, J., Zhang, X., Wang, H.: Robotic impact-echo non-destructive evaluation based on fft and svm. In: Intelligent Control and Automation (WCICA), 2014 11th World Congress on, IEEE, pp. 2854–2859 (2014)

  • Liu, Y., Caselles, V.: Improved support vector machines with distance metric learning. In: International Conference on Advanced Concepts for Intelligent Vision Systems, pp. 82–91. Springer (2011)

  • Liu, D., Dissanayake, G., Miro, J.V., Waldron, K.: Infrastructure robotics: Research challenges and opportunities. In: ISARC. Proceedings of the International Symposium on Automation and Robotics in Construction, vol. 31, p. 1. Vilnius Gediminas Technical University, Department of Construction Economics and Property (2014)

  • Liu, K.P., Luk, B.L., Yeung, T.W., Tso, S.K., Tong, F.: Wall inspection system for safety maintenance of high-rise buildings. Int. J. Perform. Eng. 3(1), 187 (2007)

    Google Scholar 

  • Liu, P.L., Yeh, P.L.: Imaging Methods of Concrete Structure Based on Impact-Echo Test. INTECH Open Access Publisher, Rijeka (2012)

    Book  Google Scholar 

  • Liu, P.L., Yeh, B.L., Yiu, C.Y.: Imaging of concrete defects using elastic wave tests. Bull Coll Eng, NTU 91, 41–50 (2004)

  • Luk, B.L., Liu, K., Jiang, Z., Tong, F.: Robotic impact-acoustics system for tile-wall bonding integrity inspection. Mechatronics 19(8), 1251–1260 (2009)

    Article  Google Scholar 

  • McCann, D., Forde, M.: Review of ndt methods in the assessment of concrete and masonry structures. NDT E Int. 34(2), 71–84 (2001)

    Article  Google Scholar 

  • Mur-Artal, R., Tardós, J.D.: ORB-SLAM2: an open-source SLAM system for monocular, stereo and RGB-D cameras. IEEE Trans Robot (2017)

  • Nguyen, N., Guo, Y.: Metric learning: A support vector approach. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 125–136. Springer (2008)

  • Olson, L.D.: Innovations in bridge superstructure condition assessment with sonic and radar methods. Struct. Mater. Technol. 2010 (2010)

  • Pratt, D., Sansalone, M.: Impact-echo signal interpretation using artificial intelligence. Mater. J. 89(2), 178–187 (1992)

    Google Scholar 

  • Sansalone, M.J., Streett, W.B.: Impact-echo. nondestructive evaluation of concrete and masonry (1997)

  • Sardy, S., Tseng, P., Bruce, A.: Robust wavelet denoising. IEEE Trans. Signal Process. 49(6), 1146–1152 (2001)

    Article  Google Scholar 

  • Shalev-Shwartz, S., Singer, Y., Srebro, N., Cotter, A.: Pegasos: primal estimated sub-gradient solver for svm. Math. Program. 127(1), 3–30 (2011)

    Article  MathSciNet  MATH  Google Scholar 

  • Short, R., Fukunaga, K.: The optimal distance measure for nearest neighbor classification. IEEE Trans. Info. Theory 27(5), 622–627 (1981)

    Article  MathSciNet  MATH  Google Scholar 

  • Srivastava, A.N., Han, J.:: Machine Learning and Knowledge Discovery for Engineering Systems Health Management. CRC Press, Boca Raton (2011)

    Google Scholar 

  • Strickland, E.: Crawler bot could inspect nuclear power stations. IEEE Spectr. (2013)

  • Tan, K., Chan, K., Wong, B., Guan, L.: Ultrasonic evaluation of cement adhesion in wall tiles. Cem. Concr. Compos. 18(2), 119–124 (1996)

    Article  Google Scholar 

  • Tong, F., Xu, X., Luk, B., Liu, K.: Evaluation of tile-wall bonding integrity based on impact acoustics and support vector machine. Sens. Actuators A Phys. 144(1), 97–104 (2008)

    Article  Google Scholar 

  • Ward, P., Liu, D., Waldron, K., Hasan, M.: Optimal design of a magnetic adhesion for climbing robots. In: Proceedings of the 16th international conference CLAWAR-2013 on nature-inspired mobile robotics, Sydney, Australia, pp. 375–382. World Scientific Publishing (2013)

  • Wu, H., Siegel, M.: Correlation of accelerometer and microphone data in the coin tap test. IEEE Trans. Instrum. Meas. 49(3), 493–497 (2000)

    Article  Google Scholar 

  • Xiao, J., Agrawal, A.: Robotic inspection of bridges using impact-echo technology. UTRC-RITA Project Final Report (2015)

  • Xiao, J., Calle, A., Sadegh, A., Elliott, M.: Modular wall climbing robots with transition capability. In: 2005 IEEE International Conference on Robotics and Biomimetics-ROBIO, pp. 246–250. IEEE (2005)

  • Xiao, J., Li, B., Ushiroda, K., Song, Q.: Rise-rover: A wall-climbing robot with high reliability and load-carrying capacity. In: Assistive Robotics: Proceedings of the 18th International Conference on CLAWAR 2015, World Scientific, p. 299 (2015)

  • Xiao, J., Morris, W., Chakravarthy, N., Calle, A.: City climber: a new generation of mobile robot with wall-climbing capability. In: Proceedings of SPIE, vol. 6230, p. 62301d. (2006)

  • Xiao, J., Sadegh, A., Elliot, M., Calle, A., Persad, A., Chiu, H.M.: Design of mobile robots with wall climbing capability. Proceedings of IEEE AIM, pp. 438–443. Monterey, CA (2005)

  • Xiao, J., Wang, H.: Contemporary issues in systems science and engineering (chapter22: Advances in climbing robots) (2015)

  • Xiao, J., Sadegh, A.: City-Climber: A New Generation Wall-Climbing Robots. INTECH Open Access Publisher, Rijeka (2007)

    Google Scholar 

  • Xing, E.P., Ng, A.Y., Jordan, M.I., Russell, S.: Distance metric learning with application to clustering with side-information. Adv. Neural Info. Process. Syst. 15, 505–512 (2003)

    Google Scholar 

  • Yeh, P.L., Liu, P.L.: Application of the wavelet transform and the enhanced fourier spectrum in the impact echo test. NDT E Int. 41(5), 382–394 (2008)

    Article  Google Scholar 

  • Ying, Y., Garrett Jr., J.H., Oppenheim, I.J., Soibelman, L., Harley, J.B., Shi, J., Jin, Y.: Toward data-driven structural health monitoring: application of machine learning and signal processing to damage detection. J. Comput. Civil Eng. 27(6), 667–680 (2012)

    Article  Google Scholar 

  • Zhang, J.K., Yan, W., Cui, D.M.: Concrete condition assessment using impact-echo method and extreme learning machines. Sensors 16(4), 447 (2016)

    Article  Google Scholar 

Download references

Acknowledgements

This research was supported by US National Science Foundation (NSF) I-Corps program and The Small Business Technology Transfer (STTR) Phase-1 grant: Wall-climbing Robots for Nondestructive Inspection to Ensure Sustainable Infrastructure, and US Department. of Transportation (RITA/USDOT) Grant 49997-41-24: Robotic Inspection of Bridges Using impact-echo Technology. The authors would like to thank Dr. Anil Agrawal and Dr. Hongfan Wang at the Department of Civil Engineering, The City College of New York, for providing guidance on empirical analysis for our experiment on impact-generated stress wave on the concrete bridge.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jizhong Xiao.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, B., Ushiroda, K., Yang, L. et al. Wall-climbing robot for non-destructive evaluation using impact-echo and metric learning SVM. Int J Intell Robot Appl 1, 255–270 (2017). https://doi.org/10.1007/s41315-017-0028-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s41315-017-0028-4

Keywords

Navigation