Decoding nonlinear ultrasonic time-frequency characteristics for fatigue crack quantification and localisation via CNN

Early detection of fatigue cracks is crucial to guarantee the safe operation of engineering structures. Nonlinear ultrasonic technique (NUT) is widely used for closed crack characterisation as it breaks through the detection sensitivity limit upon closed defects that are usually invisible to linear ultrasonic techniques. The nonlinearity parameter is generally defined as the damage index (DI) to qualitatively detect these cracks. However, DI-based methods are underdetermined for quantifying and localising cracks in most circumstances. In this study, a deep learning method for intelligently decoding nonlinear ultrasonic time-frequency characteristics is developed to quantify and localise fatigue cracks. The nonlinear ultrasonic time-frequency spectrogram, which includes features characterising crack severity and location, is obtained by cleverly selecting the excitation frequency. The convolutional neural networks (CNNs) establish a mapping relationship between the nonlinear ultrasonic time-frequency characteristics and the crack length and location. It is worth mentioning that frequency-dependent convolutional kernels are proposed to more competitively decode nonlinear ultrasonic time-frequency characteristics. The results indicate that the CNNs with the frequency-correlation kernels are particularly robust and effective in both noiseless and noisy environments. The study demonstrated the potential of the proposed nonlinear ultrasonic time-frequency characteristic decoding method for accurate and efficient characterisation of damage.