Abstract
Automated inspection systems are gaining importance for quick inspection and maintenance purpose for large volume of data in welding fields. Welding is very complex process and during the process defects may arise in weld zone. Identifying those defects requires skill and is impractical for large volume of data. This paper focuses to solve the problem by implementing deep learning model which is part of industrial 4.0 revolution, to classify seven common defects and locate them automatically for ‘v’ butt joint weld of 12 mm plate thickness for 19 angles from 2 groups by using ‘A’ scan signal of non-destructive testing method, phased array ultrasonic testing (PAUT). For feature extraction, discrete wavelet transform (DWT) is used with selection of proper mother wavelet. For supervised training, two architectures namely feed forward neural network (FFNN), convolutional neural network (CNN) are used. FFNN used features from DWT and for CNN we used both features and whole signal for training. Finally we discussed about implementation details for different models. It is observed that due to distribution of training data all the models achieves about 80% accuracy but for simple applications FFNN can give satisfactory results but if output is complex then CNN should be implemented.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Gholizadeha S (2016) A review of non-destructive testing methods of composite materials. Procedia Struct Integr 1:50–57
Suh DM, Kim WW (1995) A new ultrasonic technique for detection and sizing of small cracks in studs and bolts. J Nondestruct Eval 14(4)
Li B, Shen Y, Hu W (2011) The study on defects in aluminum 2219-T6 thick butt friction stir welds with the application of multiple non-destructive testing methods. Mater Des 32(4):2073–2084
Taheri H, Hassen AA (2019) Nondestructive ultrasonic inspection of composite materials: a comparative advantage of phased array ultrasonic. Appl Sci 9(8)
Singh A, Thakur N, Sharma A (2016) A review of supervised machine learning algorithms. In: 2016 3rd international conference on computing for sustainable global development (INDIACom), New Delhi, pp 1310–1315
Shrestha A, Mahmood A (2019) Review of deep learning algorithms and architectures. IEEE Access 7:53040–53065
Rumelhart D, Hinton G, Williams R (1986) Learning representations by back-propagating errors. Nature 323:533–536
Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. In: Proceedings of advances in neural information processing systems, vol 25, no 2, pp 1090–1098
Simonea G, Morabitoa FC, Polikarb R, Ramuhallib P, Udpab L, Udpab S (2002) Feature extraction techniques for ultrasonic signal classification. Int J Appl Electromagnet Mech 15(1–4):291–294.
Mallat S (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Pattern Anal Mach Intell 11:674–693
Akram NA, Isa D, Rajkumar R, Lee LH (2014) Active incremental support vector machine for oil and gas pipeline defects prediction system using long range ultrasonic transducers. Ultrasonics 54(6):1534–1544
Lee LH, Rajkumar R, Lo LH, Wan CH, Isa D (2013) Oil and gas pipeline failure prediction system using long range ultrasonic transducers and Euclidean-support vector machines classification approach. Exp Syst Appl 40(6):1925–1934
Jahankhani P, Kodogiannis V, Revett K (2006) EEG signal classification using wavelet feature extraction and neural networks. In: IEEE John Vincent Atanasoff JVA international symposium on modem computing. IEEE, Sofia, pp 120–124
Kesharaju M, Nagarajah R (2015) Feature selection for neural network based defect classification of ceramic components using high frequency ultrasound. Ultrasonics 62:271–277
Halil Ibrahim Erdal AN, Onur Karakurt B, Namli E (2013) High performance concrete compressive strength forecasting using ensemble models based on discrete wavelet transform. Eng Appl Artif Intell 26(4):1246–1254
Iyer S, Sinha SK, Tittmann BR, Pedrick MK (2012) Ultrasonic signal processing methods for detection of defects in concrete pipes. Autom Constr 22:135–148
Hou W, Wei Y, Jin Y, Zhu C (2019) Deep features based on a DCNN model for classifying imbalanced weld flaw types. Measurement 131
Meng M, Chua YJ, Wouterson E, Ong CPK (2017) Ultrasonic signal classification and imaging system for composite materials via deep convolutional neural networks. Neurocomputing 257:128–135
He H, Tan Y, Wang Y (2015) Optimal base wavelet selection for ECG noise reduction using a comprehensive entropy criterion. Entropy 17(9):6093–6109.
Lazaro JC, San Emeterio JL, Ramos A, Fernandez-Marrona JL (2002) Influence of thresholding procedures in ultrasonic grain noise reduction using wavelets. Ultrasonics 40(1–8):263–267.
Stepinski T, Lingvall F (2000) Automatic defect characterization in ultrasonic NDT. In: 15th WCNDT, conference proceedings, Roma
Ali MGS, Elsayed NZ, Eid AM (2012) Investigation of ultrasonic calibration using steel standard reference blocks. Walailak J Sci Technol (WJST) 9(4):417–424
Safari A, Zhang J, Velichko A, Drinkwater BW (2017) Assessment methodology for defect characterization using ultrasonic arrays. NDT and E Int 94:126–136
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Pawar, P., Buktar, R. (2022). Detection and Classification of Defects in Ultrasonic Testing Using Deep Learning. In: Gunjan, V.K., Zurada, J.M. (eds) Proceedings of the 2nd International Conference on Recent Trends in Machine Learning, IoT, Smart Cities and Applications. Lecture Notes in Networks and Systems, vol 237. Springer, Singapore. https://doi.org/10.1007/978-981-16-6407-6_1
Download citation
DOI: https://doi.org/10.1007/978-981-16-6407-6_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6406-9
Online ISBN: 978-981-16-6407-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)