Ultrasonic Weld Quality Inspection Involving Strength Prediction and Defect Detection in Data-Constrained Training Environments
Abstract
:1. Introduction
- First, LSS evaluation is performed to ensure the strength of the joint is within acceptable limits.
- Then, an automated assessment of visual defects in the joint is executed to determine if any defects will lead to premature failure.
- This work proposes a complete two-stage inspection procedure to determine weld joint quality, comprising strength prediction from a multimodal dataset and visual inspection from an augmented image dataset.
- Development of a multimodal dataset containing encoded image data and input parameter settings data to reduce prediction errors in weld quality prediction.
- Demonstrated improvement in USW weld strength prediction using a multimodal dataset. This work illustrates a 34% reduction in prediction errors when using multimodal data.
- Presentation of a novel CAE design that can efficiently extract encoded image data when the dataset available is extremely small.
- A benchmark comparison of weld defect detection methods on the developed USW defect dataset against publicly available surface defect detection dataset methods is provided.
2. Background and Literature Review
2.1. Weld Defect Detection
- Dimensional quality, where the dimensions of the object under inspection are assessed to determine if they are within specific tolerances.
- Surface quality, where the surface is inspected for cracks, wear, scratches, etc.
- Structural quality, where the manufactured component is analyzed for the presence of unnecessary parts, or lack of required components.
- Operational quality, where the quality of the object is inspected to determine if it is fit for the required purpose.
2.2. Autoencoders
3. Methodology
3.1. Experiment: Weld Strength Prediction
3.1.1. Design of Convolutional Autoencoder
3.1.2. Latent Space Representation
3.1.3. Multimodal Dataset
3.2. Experiment: Weld Defect Detection Using Computer Vision
3.2.1. Dataset and Annotation
3.2.2. Deep Learning Models Used
4. Experiment and Results
4.1. Experimental Setup
4.2. Data Augmentation
4.3. Results from Weld Quality Prediction
Discussion of Results
4.4. Results from Weld Defect Detection
Discussion of Results
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
CNN | Convolutional Neural Network |
CAE | Convolutional Autoencoder |
IoT | Internet of Things |
LSS | Lap Shear Strength |
MAE | Mean Absolute Error MAE |
NDT | Non-Destructive Testing |
NDI | Non-Destructive Inspection |
NEU | North Eastern University |
PCA | Principal Component Analysis |
RGB | red-green-blue |
RMSE | Root Mean-Squared Error |
SSIM | Structural Similarity Index Measure |
USW | Ultrasonic Welding |
References
- Xu, H.; Yan, Z.; Ji, B.; Huang, P.; Cheng, J.; Wu, X. Defect detection in welding radiographic images based on semantic segmentation methods. Measurement 2022, 188, 110569. [Google Scholar] [CrossRef]
- Hou, W.; Zhang, D.; Wei, Y.; Guo, J.; Zhang, X. Review on computer-aided weld defect detection from radiography images. Appl. Sci. 2020, 10, 1878. [Google Scholar] [CrossRef]
- Liao, T.W. Improving the accuracy of computer-aided radiographic weld inspection by feature selection. NDT E Int. 2009, 42, 229–239. [Google Scholar] [CrossRef]
- Zuo, F.; Liu, J.; Zhao, X.; Chen, L.; Wang, L. An X-ray-based automatic welding defect detection method for special equipment system. IEEE/ASME Trans. Mechatron. 2023, 29, 2241–2252. [Google Scholar] [CrossRef]
- Stavridis, J.; Papacharalampopoulos, A.; Stavropoulos, P. Quality assessment in laser welding: A critical review. Int. J. Adv. Manuf. Technol. 2018, 94, 1825–1847. [Google Scholar] [CrossRef]
- Reddy, K.A. Non-destructive testing, evaluation of stainless steel materials. Mater. Today Proc. 2017, 4, 7302–7312. [Google Scholar] [CrossRef]
- Block, S.B.; Da Silva, R.D.; Lazzaretti, A.E.; Minetto, R. LoHi-WELD: A novel industrial dataset for weld defect detection and classification, a deep learning study, and future perspectives. IEEE Access 2024, 12, 77442–77453. [Google Scholar] [CrossRef]
- Nadzri, N.A.; Ishak, M.; Saari, M.M.; Halil, A.M. Development of eddy current testing system for welding inspection. In Proceedings of the 2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC), Shah Alam, Malaysia, 3–4 August 2018; pp. 94–98. [Google Scholar]
- LeTessier, R.; Coade, R.; Geneve, B. Sizing of cracks using the alternating current field measurement technique. Int. J. Press. Vessel. Pip. 2002, 79, 549–554. [Google Scholar] [CrossRef]
- Madhvacharyula, A.S.; Pavan, A.V.S.; Gorthi, S.; Chitral, S.; Venkaiah, N.; Kiran, D.V. In situ detection of welding defects: A review. Weld. World 2022, 66, 611–628. [Google Scholar] [CrossRef]
- Handoko, D. Weld Defect Detection and Classification based on Deep Learning Method: A Review. J. Ilmu Komput. Dan Inf. J. Comput. Sci. Inf. 2023, 16, 77–87. [Google Scholar]
- Li, P.; Pei, Y.; Li, J. A comprehensive survey on design and application of autoencoder in deep learning. Appl. Soft Comput. 2023, 138, 110176. [Google Scholar] [CrossRef]
- Xu, M.; Yoon, S.; Fuentes, A.; Park, D.S. A comprehensive survey of image augmentation techniques for deep learning. Pattern Recognit. 2023, 137, 109347. [Google Scholar] [CrossRef]
- Mongan, P.G.; Hinchy, E.P.; O’Dowd, N.P.; McCarthy, C.T. Quality prediction of ultrasonically welded joints using a hybrid machine learning model. J. Manuf. Process. 2021, 71, 571–579. [Google Scholar] [CrossRef]
- Mongan, P.G.; Modi, V.; McLaughlin, J.W.; Hinchy, E.P.; O’Higgins, R.M.; O’Dowd, N.P.; McCarthy, C.T. Multi-objective optimisation of ultrasonically welded dissimilar joints through machine learning. J. Intell. Manuf. 2022, 33, 1125–1138. [Google Scholar] [CrossRef]
- Rizvi, S.A.; Alib, W. Welding defects, Causes and their Remedies: A Review: Welding defects. Teknomekanik 2019, 2, 39–47. [Google Scholar] [CrossRef]
- Benatar, A.; Marcus, M. Ultrasonic welding of plastics and polymeric composites. In Power Ultrasonics; Elsevier: Amsterdam, The Netherlands, 2023; pp. 205–225. [Google Scholar]
- Rajakumar, S.; Kavitha, S.; Sonar, T. Optimization of ultrasonic welding parameters to maximize the tensile shear fracture load bearing capability of lap welded ABS plastic sheets. Int. J. Interact. Des. Manuf. IJIDeM 2023, 18, 1–10. [Google Scholar] [CrossRef]
- Jones, I. Laser welding of plastics. In Handbook of Laser Welding Technologies; Elsevier: Amsterdam, The Netherlands, 2013; pp. 280–301e. [Google Scholar]
- Bindal, T.; Saxena, R.K.; Pandey, S. Investigating friction spin welding of thermoplastics in shear joint configuration. SN Appl. Sci. 2021, 3, 1–17. [Google Scholar]
- Stokes, V.; Hobbs, S. Vibration welding of ABS to itself and to polycarbonate, poly (butylene terephthalate), poly (ether imide) and modified poly (phenylene oxide). Polymer 1993, 34, 1222–1231. [Google Scholar] [CrossRef]
- Bucknall, C.; Drinkwater, I.; Smith, G. Hot plate welding of plastics: Factors affecting weld strength. Polym. Eng. Sci. 1980, 20, 432–440. [Google Scholar] [CrossRef]
- Trofimov, N.; Yulenets, Y.P.; Markov, A. High-frequency welding of plastic components of complicated shape. Weld. Int. 2011, 25, 196–199. [Google Scholar] [CrossRef]
- Tiwary, V.K.; Padmakumar, A.; Malik, V. Adhesive bonding of similar/dissimilar three-dimensional printed parts (ABS/PLA) considering joint design, surface treatments, and adhesive types. Proc. Inst. Mech. Eng. Part C J. Mech. Eng. Sci. 2022, 236, 8991–9002. [Google Scholar] [CrossRef]
- Tripicchio, P.; Camacho-Gonzalez, G.; D’Avella, S. Welding defect detection: Coping with artifacts in the production line. Int. J. Adv. Manuf. Technol. 2020, 111, 1659–1669. [Google Scholar] [CrossRef]
- Hosseinabad, E.R.; Zaman, M.A.U. A brief review on cellular manufacturing and group technology. Res. J. Manag. Rev. 2020, 5, 1–20. [Google Scholar]
- Chen, Y.; Ding, Y.; Zhao, F.; Zhang, E.; Wu, Z.; Shao, L. Surface defect detection methods for industrial products: A review. Appl. Sci. 2021, 11, 7657. [Google Scholar] [CrossRef]
- Ördek, B.; Borgianni, Y.; Coatanea, E. Machine learning-supported manufacturing: A review and directions for future research. Prod. Manuf. Res. 2024, 12, 2326526. [Google Scholar] [CrossRef]
- Wang, J.; Ma, Y.; Zhang, L.; Gao, R.X.; Wu, D. Deep learning for smart manufacturing: Methods and applications. J. Manuf. Syst. 2018, 48, 144–156. [Google Scholar] [CrossRef]
- Ahmad, H.M.; Rahimi, A. Deep learning methods for object detection in smart manufacturing: A survey. J. Manuf. Syst. 2022, 64, 181–196. [Google Scholar] [CrossRef]
- Cumbajin, E.; Rodrigues, N.; Costa, P.; Miragaia, R.; Frazão, L.; Costa, N.; Fernández-Caballero, A.; Carneiro, J.; Buruberri, L.H.; Pereira, A. A systematic review on deep learning with CNNs applied to surface defect detection. J. Imaging 2023, 9, 193. [Google Scholar] [CrossRef]
- Givnan, S.; Chalmers, C.; Fergus, P.; Ortega-Martorell, S.; Whalley, T. Anomaly detection using autoencoder reconstruction upon industrial motors. Sensors 2022, 22, 3166. [Google Scholar] [CrossRef]
- Liang, H.; Fu, W.; Yi, F. A survey of recent advances in transfer learning. In Proceedings of the 2019 IEEE 19th International Conference on Communication Technology (ICCT), Xi’an, China, 16–19 October 2019; pp. 1516–1523. [Google Scholar]
- Guo, W.; Qu, H.; Liang, L. WDXI: The dataset of X-ray image for weld defects. In Proceedings of the 2018 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), Huangshan, China, 28–30 July 2018; pp. 1051–1055. [Google Scholar]
- Papageorgiou, E.I.; Theodosiou, T.; Margetis, G.; Dimitriou, N.; Charalampous, P.; Tzovaras, D.; Samakovlis, I. Short survey of artificial intelligent technologies for defect detection in manufacturing. In Proceedings of the 2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA), Chania Crete, Greece, 12–14 July 2021; pp. 1–7. [Google Scholar]
- Jeffers, J.; Reinders, J. Intel Xeon Phi Coprocessor High Performance Programming; Newnes: Waltham, MC, USA, 2013. [Google Scholar]
- Sassi, P.; Tripicchio, P.; Avizzano, C.A. A smart monitoring system for automatic welding defect detection. IEEE Trans. Ind. Electron. 2019, 66, 9641–9650. [Google Scholar] [CrossRef]
- Huang, G.; Liu, Z.; Van Der Maaten, L.; Weinberger, K.Q. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 4700–4708. [Google Scholar]
- Le, X.; Mei, J.; Zhang, H.; Zhou, B.; Xi, J. A learning-based approach for surface defect detection using small image datasets. Neurocomputing 2020, 408, 112–120. [Google Scholar] [CrossRef]
- Martin, A.; Soumith, C.; Leon, B. Wasserstein generative adversarial networks. In Proceedings of the International Conference on Machine Learning, Sydney, Australia, 6–11 August 2017; pp. 214–223. [Google Scholar]
- Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; Wojna, Z. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 2818–2826. [Google Scholar]
- Howard, A.G.; Zhu, M.; Chen, B.; Kalenichenko, D.; Wang, W.; Weyand, T.; Andreetto, M.; Adam, H. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv 2017, arXiv:1704.04861. [Google Scholar]
- Gao, Y.; Lin, J.; Xie, J.; Ning, Z. A real-time defect detection method for digital signal processing of industrial inspection applications. IEEE Trans. Ind. Inform. 2020, 17, 3450–3459. [Google Scholar] [CrossRef]
- He, Y.; Song, K.; Meng, Q.; Yan, Y. An end-to-end steel surface defect detection approach via fusing multiple hierarchical features. IEEE Trans. Instrum. Meas. 2019, 69, 1493–1504. [Google Scholar] [CrossRef]
- Tang, S.; He, F.; Huang, X.; Yang, J. Online PCB defect detector on a new PCB defect dataset. arXiv 2019, arXiv:1902.06197. [Google Scholar]
- Yang, L.; Fan, J.; Huo, B.; Liu, Y. Inspection of welding defect based on multi-feature fusion and a convolutional network. J. Nondestruct. Eval. 2021, 40, 90. [Google Scholar] [CrossRef]
- Tao, X.; Wang, Z.; Zhang, Z.; Zhang, D.; Xu, D.; Gong, X.; Zhang, L. Wire defect recognition of spring-wire socket using multitask convolutional neural networks. IEEE Trans. Compon. Packag. Manuf. Technol. 2018, 8, 689–698. [Google Scholar] [CrossRef]
- Alfaro, S.C.; Franco, F.D. Exploring infrared sensoring for real time welding defects monitoring in GTAW. Sensors 2010, 10, 5962–5974. [Google Scholar] [CrossRef]
- Duan, F.; Yin, S.; Song, P.; Zhang, W.; Zhu, C.; Yokoi, H. Automatic welding defect detection of x-ray images by using cascade adaboost with penalty term. IEEE Access 2019, 7, 125929–125938. [Google Scholar] [CrossRef]
- Roy, R.B.; Ghosh, A.; Bhattacharyya, S.; Mahto, R.P.; Kumari, K.; Pal, S.K.; Pal, S. Weld defect identification in friction stir welding through optimized wavelet transformation of signals and validation through X-ray micro-CT scan. Int. J. Adv. Manuf. Technol. 2018, 99, 623–633. [Google Scholar] [CrossRef]
- Li, Y.; Li, Y.F.; Wang, Q.L.; Xu, D.; Tan, M. Measurement and defect detection of the weld bead based on online vision inspection. IEEE Trans. Instrum. Meas. 2009, 59, 1841–1849. [Google Scholar]
- Chen, B.; Fang, Z.; Xia, Y.; Zhang, L.; Huang, Y.; Wang, L. Accurate defect detection via sparsity reconstruction for weld radiographs. NDT E Int. 2018, 94, 62–69. [Google Scholar] [CrossRef]
- Du, D.; Cai, G.R.; Tian, Y.; Hou, R.S.; Wang, L. Automatic inspection of weld defects with x-ray real-time imaging. In Robotic Welding, Intelligence and Automation; Springer: Berlin/Heidelberg, Germany, 2007; pp. 359–366. [Google Scholar]
- Günther, J.; Pilarski, P.M.; Helfrich, G.; Shen, H.; Diepold, K. Intelligent laser welding through representation, prediction, and control learning: An architecture with deep neural networks and reinforcement learning. Mechatronics 2016, 34, 1–11. [Google Scholar] [CrossRef]
- Yang, L.; Liu, Y.; Peng, J. An automatic detection and identification method of welded joints based on deep neural network. IEEE Access 2019, 7, 164952–164961. [Google Scholar] [CrossRef]
- Yang, J.; Fu, G.; Zhu, W.; Cao, Y.; Cao, Y.; Yang, M.Y. A deep learning-based surface defect inspection system using multiscale and channel-compressed features. IEEE Trans. Instrum. Meas. 2020, 69, 8032–8042. [Google Scholar]
- Iandola, F.N.; Han, S.; Moskewicz, M.W.; Ashraf, K.; Dally, W.J.; Keutzer, K. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv 2016, arXiv:1602.07360. [Google Scholar]
- Yi, L.; Li, G.; Jiang, M. An end-to-end steel strip surface defects recognition system based on convolutional neural networks. Steel Res. Int. 2017, 88, 1600068. [Google Scholar] [CrossRef]
- Fu, G.; Sun, P.; Zhu, W.; Yang, J.; Cao, Y.; Yang, M.Y.; Cao, Y. A deep-learning-based approach for fast and robust steel surface defects classification. Opt. Lasers Eng. 2019, 121, 397–405. [Google Scholar] [CrossRef]
- Shorten, C.; Khoshgoftaar, T.M. A survey on image data augmentation for deep learning. J. Big Data 2019, 6, 60. [Google Scholar] [CrossRef]
- Yang, J.; Bai, Y.; Li, G.; Liu, M.; Liu, X. A novel method of diagnosing premature ventricular contraction based on sparse auto-encoder and softmax regression. Bio-Med Mater. Eng. 2015, 26, S1549–S1558. [Google Scholar] [CrossRef]
- Goodfellow, I.; Bengio, Y.; Courville, A. Deep Learning; MIT Press: Cambridge, MA, USA, 2016. [Google Scholar]
- Maggipinto, M.; Masiero, C.; Beghi, A.; Susto, G.A. A convolutional autoencoder approach for feature extraction in virtual metrology. Procedia Manuf. 2018, 17, 126–133. [Google Scholar] [CrossRef]
- Gong, D.; Liu, L.; Le, V.; Saha, B.; Mansour, M.R.; Venkatesh, S.; Hengel, A.v.d. Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea, 27 October–2 November 2019; pp. 1705–1714. [Google Scholar]
- Intro to Autoencoders. Available online: https://www.tensorflow.org/tutorials/generative/autoencoder (accessed on 4 October 2022).
- Toğaçar, M.; Ergen, B.; Cömert, Z. Application of breast cancer diagnosis based on a combination of convolutional neural networks, ridge regression and linear discriminant analysis using invasive breast cancer images processed with autoencoders. Med. Hypotheses 2020, 135, 109503. [Google Scholar] [CrossRef] [PubMed]
- Cui, X.; Liu, S.; Lin, Z.; Ma, J.; Wen, F.; Ding, Y.; Yang, L.; Guo, W.; Feng, X. Two-step electricity theft detection strategy considering economic return based on convolutional autoencoder and improved regression algorithm. IEEE Trans. Power Syst. 2021, 37, 2346–2359. [Google Scholar] [CrossRef]
- Steck, H. Autoencoders that don’t overfit towards the identity. Adv. Neural Inf. Process. Syst. 2020, 33, 19598–19608. [Google Scholar]
- Lončarević, Z.; Gams, A.; Ude, A. Robot skill learning in latent space of a deep autoencoder neural network. Robot. Auton. Syst. 2021, 135, 103690. [Google Scholar]
- Dillon, B.M.; Plehn, T.; Sauer, C.; Sorrenson, P. Better latent spaces for better autoencoders. SciPost Phys. 2021, 11, 061. [Google Scholar] [CrossRef]
- Yu, S.; Principe, J.C. Understanding autoencoders with information theoretic concepts. Neural Netw. 2019, 117, 104–123. [Google Scholar] [CrossRef] [PubMed]
- Tapia, N.I.; Estévez, P.A. On the information plane of autoencoders. In Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK, 19–24 July 2020; pp. 1–8. [Google Scholar]
- Hore, A.; Ziou, D. Image quality metrics: PSNR vs. SSIM. In Proceedings of the 2010 20th International Conference on Pattern Recognition, Istanbul, Turkey, 23–26 August 2010; pp. 2366–2369. [Google Scholar]
- Ndajah, P.; Kikuchi, H.; Yukawa, M.; Watanabe, H.; Muramatsu, S. SSIM image quality metric for denoised images. In Proceedings of the 3rd WSEAS International Conference on Visualization, Imaging and Simulation, Faro, Portugal, 3–5 November 2010; pp. 53–57. [Google Scholar]
- Pawłowski, M.; Wróblewska, A.; Sysko-Romańczuk, S. Effective techniques for multimodal data fusion: A comparative analysis. Sensors 2023, 23, 2381. [Google Scholar] [CrossRef]
- Jocher, G.; Chaurasia, A.; Qiu, J. Ultralytics YOLOv8. 2023. Available online: https://docs.ultralytics.com/ (accessed on 15 June 2024).
- Hendrycks, D.; Lee, K.; Mazeika, M. Using pre-training can improve model robustness and uncertainty. In Proceedings of the International Conference on Machine Learning, PMLR, Long Beach, CA, USA, 9–15 June 2019; pp. 2712–2721. [Google Scholar]
- Li, H.; Singh, B.; Najibi, M.; Wu, Z.; Davis, L.S. An analysis of pre-training on object detection. arXiv 2019, arXiv:1904.05871. [Google Scholar]
- Sun, W.; Zhao, H.; Jin, Z. An efficient unconstrained facial expression recognition algorithm based on stack binarized auto-encoders and binarized neural networks. Neurocomputing 2017, 267, 385–395. [Google Scholar] [CrossRef]
- Akbiyik, M.E. Data Augmentation in Training CNNs: Injecting Noise to Images. arXiv 2023, arXiv:2307.06855. [Google Scholar]
- Hao, W.; Zhili, S. Improved Mosaic: Algorithms for more Complex Images. J. Physics Conf. Ser. 2020, 1684, 012094. [Google Scholar] [CrossRef]
- Yu, H.; Chen, C.; Du, X.; Li, Y.; Rashwan, A.; Hou, L.; Jin, P.; Yang, F.; Liu, F.; Kim, J.; et al. TensorFlow Model Garden. 2020. Available online: https://github.com/tensorflow/models (accessed on 17 October 2020).
No. of Epochs | Dimension of Bottleneck Layer | MAE | RMSE |
---|---|---|---|
60 | 7 × 7 × 1 | 6.83 | 8.67 |
80 | 7 × 7 × 1 | 6.89 | 7.82 |
100 | 7 × 7 × 1 | 6.93 | 8.70 |
Decision Tree Regression-Parameter Tuning | MAE | MSE | RMSE |
---|---|---|---|
Max_depth = 10 | 7.7960 | 92.8485 | 9.6357 |
Max_depth = 10, Random_state = 0 | 8.6480 | 84.9982 | 9.2194 |
Max_depth = 10, Random_state = None | 7.688 | 75.4092 | 8.6838 |
Max_depth = 5, Random_state = None | 7.956 | 96.3131 | 9.8139 |
Max_depth = 3, Random_state = None | 7.2493 | 61.2585 | 7.8267 |
Data Used for Final Prediction | MAE (Final) | RSME (Final) | |
---|---|---|---|
1 | Image features extracted (CAE) | 10.98 | 11.98 |
2 | Image features data + input param, data | 7.24 | 7.82 |
Dataset | Model | Precision | Recall | mAP50 | mAP50-95 |
---|---|---|---|---|---|
USW-defect dataset | YOLOv8n | 0.61 | 0.84 | 0.61 | 0.43 |
USW-defect dataset (Aug:noise:0.1) | YOLOv8n | 0.66 | 0.80 | 0.68 | 0.43 |
USW-defect dataset (Aug:noise:0.3) | YOLOv8n | 0.55 | 0.82 | 0.746 | 0.50 |
USW-defect dataset | YOLOv8x | 0.65 | 0.82 | 0.79 | 0.58 |
USW-defect dataset (Aug:noise:0.3) | YOLOv8x | 0.64 | 0.83 | 0.72 | 0.52 |
NEU-DET | YOLOv8x | 0.54 | 0.61 | 0.58 | 0.28 |
NEU-DET | YOLOv8n | 0.55 | 0.61 | 0.59 | 0.29 |
NEU-DET (Aug:noise:0.3) | YOLOv8n | 0.52 | 0.60 | 0.57 | 0.29 |
Data Used for Final Prediction | Original Sample Size | Accuracy | Recall |
---|---|---|---|
USW defect dataset | 28 | 0.74 (mAP) | 0.82 |
Radiographic images of welding defects (RIWD) | 95 | 0.73 (mIoU) | 0.86 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Mohandas, R.; Mongan, P.; Hayes, M. Ultrasonic Weld Quality Inspection Involving Strength Prediction and Defect Detection in Data-Constrained Training Environments. Sensors 2024, 24, 6553. https://doi.org/10.3390/s24206553
Mohandas R, Mongan P, Hayes M. Ultrasonic Weld Quality Inspection Involving Strength Prediction and Defect Detection in Data-Constrained Training Environments. Sensors. 2024; 24(20):6553. https://doi.org/10.3390/s24206553
Chicago/Turabian StyleMohandas, Reenu, Patrick Mongan, and Martin Hayes. 2024. "Ultrasonic Weld Quality Inspection Involving Strength Prediction and Defect Detection in Data-Constrained Training Environments" Sensors 24, no. 20: 6553. https://doi.org/10.3390/s24206553
APA StyleMohandas, R., Mongan, P., & Hayes, M. (2024). Ultrasonic Weld Quality Inspection Involving Strength Prediction and Defect Detection in Data-Constrained Training Environments. Sensors, 24(20), 6553. https://doi.org/10.3390/s24206553