ABSTRACT
We propose a deep-learning based deflectometric method for freeform surface measurement, in which a deep neural network is devised for freeform surface reconstruction. Full-scale skip connections are adopted in the network architecture to extract and incorporate multi-scale feature maps from different layers, enabling the accuracy and robustness of the testing system to be greatly enhanced. The feasibility of the proposed method is numerically and experimentally validated, and its excellent performance in terms of accuracy and robustness is also demonstrated. The proposed method provides a feasible way to achieve the general measurement of freeform surfaces while minimizing the measurement errors due to noise and system geometry calibration.
ABSTRACT
Sonic infrared (SIR) imaging is a hybrid nondestructive evaluation (NDE) method that uses ultrasonic excitation along with thermal imaging to detect defects in materials and structures. SIR NDE uses an ultrasonic pulse in the 15-40 kHz range from a transducer to produce localized heating at the defect while a thermal camera will record surface temperature during the inspection. In a previous article, we presented a model that describes heat diffusion from subsurface defects in a composite material. The model uses certain aspects of the temperature-time curve for defect depth profiling, namely, half-maximum power time, the peak slope time, and the second derivative peak time. In this study, we investigate the effect of defect size on the quantitative estimation of defect depth. The theoretical results are calculated and compared with the experimental data. We demonstrate that the experimental data have good correlation with the theoretical calculation. The peak slope time and the second derivative peak time are less sensitive to changes in defect size than the half-maximum power time in the defect depth assessment.
