Ultrasonic Testing of Corrosion in Aircraft Rivet Using Spiking Neural Network
Tóm tắt
This paper proposes a nondestructive testing (NDT) method for the inspection of corrosion in rivets used in an aircraft. The NDT system uses an ultrasonic sensor coupling with a membrane that allows the ultrasonic wave propagates through to the inspecting rivet. The measured signal is then analyzed by a spiking neural network (SNN), a neural network that mimics the biological neurons for efficient detection of the corrosion in rivet. Compared to the conventional deep neural network, SNN is low energy consumption and can be implemented on a compact SNN accelerator chip, making them better run on a compact NDT system and general edge computing applications. We have tested the proposed SNN model on different sizes of corrosion in rivets (i.e., 30–70% of cross-section area) and at different depths from the surface (i.e., 1.0–2.0 mm). The proposed SNN model achieves about 95.4% accuracy with a small number of rivet samples (i.e., four rivet with corrosion) for training.
Tài liệu tham khảo
Job, M.: Air Disaster, vol 2. Aerospace Publications Pty Ltd, ACT, Australia (1996). ISBN 1-875671-19-6
Hendricks, W.R.: The Aloha-airlines accident-a new era for aging aircraft. In: Atluri, S.N., Sampath, S.G., Tong, P. (eds.) Structural Integrity of Aging Airplanes, pp. 153–165. Springer, New York (1991)
Pitt, S., Jones, R.: Multiple-site and widespread fatigue damage in ageing aircraft. Engg. Fail. Anal. 4(4), 237–257 (1997)
Fitzpatrick, G., Thome, D., Skaugset, R., Shih, E., Shih, W.: Magneto-optical/ Eddy current imaging of aging aircraft—a new NDI technique. Mater. Eval. 51, 1402–1407 (1993)
Thome, D.K., Fitzpatrick, G.L., Skaugset, R.L., Shih, W.C.L.: Aircraft corrosion and defect inspection using advanced magneto-optic imaging technology. Proc. SPIE 2945, 365–373 (1996)
Karpenko, O., Efremov, A., Ye, C., Udpa, L.: Multi-frequency fusion algorithm for detection of defects under fasteners with EC-GMR probe data. NDT&E Int. 110, 102227 (2020)
Chady, T., Okarma, K., Mikołajczyk, R., Dziendzikowski, M., Synaszko, P., Dragan, K.: Extended damage detection and identification in aircraft structure based on multifrequency Eddy current method and mutual image similarity assessment. Materials 14, 4452 (2021). https://doi.org/10.3390/ma14164452
Horan, P., Lowerhill, P.R., Krause, T.W.: Pulsed eddy current detection of defects in F/A-18 inner wing spar without wing skin removal using modified principal component analysis. NDT&E Int. 44, 21–27 (2013)
Stott, C.A., Underhill, P.R., Babbar, V.K., Krause, T.W.: Pulsed Eddy current detection of cracks in multilayer aluminum lap joints. Sens. J. IEEE 15, 956–962 (2015). https://doi.org/10.1109/JSEN.2014.2354404
Postolacheab, O., Ribeiroac, A.L., Ramos, H.G.: GMR array uniform eddy current probe for defect detection in conductive specimens. Measurement 46, 4369–4378 (2013)
Le, M., Kim, J., Kim, S., Wang, D., Hwang, Y., Lee, J.: Nondestructive evaluation algorithm of fatigue cracks and far-side corrosion around a rivet fastener in multi-layered structures. J. Mech. Sci. Technol. 30, 4205–4215 (2016)
Kim, J., Le, M., Lee, J., Kim, S., Hwang, Y.: Nondestructive evaluation of far-side corrosion around a rivet in a multilayer structure. RNDE 29, 1–20 (2016)
Le, M., Luong, V.S., Nguyen, D.K., Lee, J.: Electromagnetic testing of corrosion at river sites via principal component analysis. J. Nondestruct. Eval. (2021). https://doi.org/10.1007/s10921-021-00768-8
Le, M., Kim, J., Kim, S., Lee, J.: B-scan ultrasonic testing of rivets in multilayer structures based on short-time fourier transform analysis. J. Meas. 128, 495–503 (2018)
Cobb, A.C., Micheals, J.E., Micheals, T.E.: An automated time-frequency approach for ultrasonic monitoring of fastener hole cracks. NDT&E Int. 40, 525–536 (2007)
Senyurek, V.Y.: Detection of cuts and impact damage at the aircraft wing slat by using Lamb wave method. Measurement 67, 10–23 (2015)
Hoseini, M.R., Zuo, M.J., Wang, X.: Using ultrasonic pulse-echo B-scan signal for estimation of time of flight. Measurement 46, 3593–3599 (2013)
Ushakov, V.M., Mikhalev, V.V., Davydov, D.M., Davydova, V.I.: Detection of cracks under threads of studs of power equipment and drill pipes during ultrasonic testing. Russ. J. Nondestruct. Test. 45(9), 627–630 (2009)
Xufei, G., Yan, H.: Ultrasonic total focusing imaging method of multilayer composite structures using the root-mean-square (RMS) velocity. Adv. Mater. Sci. Eng. 2021, 2745732 (2021)
Cantero-Chinchilla, S., Wilcox, P.D., Croxford, A.J.: Deep learning in automated ultrasonic NDE–developments, axioms and opportunities. NDT&E Int. 102703 (2022)
Virupakshappa, K., Marino, M., Oruklu, E.: A multi-resolution convolutional neural network architecture for ultrasonic flaw detection. In: 2018 IEEE International Ultrasonics Symposium (IUS), pp. 1–4. IEEE (2018)
Schlemper, J., Oktay, O., Chen, L., Matthew, J., Knight, C., Kainz, B., Glocker, B., Rueckert, D.: Attention-gated networks for improving ultrasound scan plane detection. arXiv preprint arXiv:1804.05338 (2018)
Słoński, M., Schabowicz, K., Krawczyk, E.: Detection of flaws in concrete using ultrasonic tomography and convolutional neural networks. Materials 13(7), 1557 (2020)
Gao, F., Li, B., Chen, L., Wei, X., Shang, Z., He, C.: Ultrasonic signal denoising based on autoencoder. Rev. Sci. Instrum. 91(4), 045104 (2020)
Munir, N., Park, J., Kim, H.J., Song, S.J., Kang, S.S.: Performance enhancement of convolutional neural network for ultrasonic flaw classification by adopting autoencoder. NDT&E Int. 111, 102218 (2020)
Sun, Y., Fei, T., Li, X., Warnecke, A., Warsitz, E., Pohl, N.: Real-time radar-based gesture detection and recognition built in an edge-computing platform. IEEE Sens. J. 20(18), 10706–10716 (2020)
Davies, M., Srinivasa, N., Lin, T.H., Chinya, G., Cao, Y., Choday, S.H., Dimou, G., Joshi, P., Imam, N., Jain, S., Liao, Y.: Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro 38(1), 82–99 (2018)
Cordone, L., Miramond, B., Ferrante, S.: Learning from event cameras with sparse spiking convolutional neural networks. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2021)
Tsang, I.J., Corradi, F., Sifalakis, M., Van Leekwijck, W., Latré, S.: Radar-based hand gesture recognition using spiking neural networks. Electronics 10(12), 1405 (2021)
Arsalan, M., Chmurski, M., Santra, A., El-Masry, M., Weigel, R., Issakov, V.: Resource efficient gesture sensing based on fmcw radar using spiking neural networks. In: 2021 IEEE MTT-S International Microwave Symposium (2021)
Zahra, O., Navarro-Alarcon, D., Tolu, S.: A neurorobotic embodiment for exploring the dynamical interactions of a spiking cerebellar model and a robot arm during vision-based manipulation tasks. Int. J. Neural Syst. 32(08), 2150028 (2022)
Tieck, J.C., Weber, S., Stewart, T.C., Kaiser, J., Roennau, A., Dillmann, R.: A spiking network classifies human sEMG signals and triggers finger reflexes on a robotic hand. Robot. Auton. Syst. 131, 103566 (2020)
Pang, L., Liu, J., Harkin, J., Martin, G., McElholm, M., Javed, A., McDaid, L.: Case study—spiking neural network hardware system for structural health monitoring. Sensors 20(18), 5126 (2020)
Le, M., Kim, J., Kim, S., Lee, J.: Nondestructive testing of pitting corrosion cracks in rivet of multilayer structures. Int. J. Precis. Eng. Manuf. 17, 1433–1442 (2016)
Dutta, S., Kumar, V., Shukla, A., Mohapatra, N.R., Ganguly, U.: Leaky integrate and fire neuron by charge-discharge dynamics in floating-body MOSFET. Sci. Rep. 7(1), 8257 (2017)
Hunsberger, E., Eliasmith, C.: Training spiking deep networks for neuromorphic hardware. arXiv preprint arXiv:1611.05141 (2016)
Rasmussen, D.: NengoDL: combining deep learning and neuromorphic modelling methods, pp. 1–22. arXiv:1805.11144 (2018)
Le, M., Le, D.V., Le, T.D., Lee, J.: Ultrasonic testing of rivet in multilayer structure using a convolutional neural network on edge device. Sci. Prog. 106(2), 00368504231177551 (2023)
Stuijt, J., Sifalakis, M., Yousefzadeh, A., Corradi, F.: μBrain: an event-driven and fully synthesizable architecture for spiking neural networks. Front. Neurosci. 15, 664208 (2021)
Safa, A., Bourdoux, A., Ocket, I., Catthoor, F., Gielen, G.G.: A 2-J, 12-class, 91% Accuracy spiking neural network approach for radar gesture recognition. arXiv preprint arXiv:2108.02669 (2021)
Annis, C.R.: Package mh1823, Version 4.0.1. https://statistical-engineering.com/mh1823/. Accessed 3 March 2022