Evaluation of Defects Depth for Metal Sheets Using Four-Coil Excitation Array Eddy Current Sensor and Improved ResNet18 Network

Lift-off effect, resulting in detection error, which is a significant challenge that needs to be addressed in defect detection using eddy current testing (ECT). A novel array eddy current (AEC) sensor, with each unit composed of four excitation coils and a receiving coil, is proposed to implement fast and large-area defect scanning for metal sheets without lift-off interference. In addition, theoretical analysis based on the Biot–Savart law is applied to illustrate the feasibility of the proposed sensor in eliminating the lift-off effect. However, the proposed array sensor has also an angular sensitivity which means that there are different signal responses for different defect orientations, but the feature is not conducive to evaluating the defect depths without knowing the angle difference as a prior, which can be addressed by deep-learning (DL) algorithms. Both simulation and experiments are implemented to verify the reliability and feasibility of the proposed array sensor. The proposed preprocessed method is utilized to attain significant signal feature differences for various defect depths. In addition, the improved ResNet18 network is proposed to train acquired experimental data, and its superior performance is demonstrated. The results show that the improved ResNet18 network with preprocessed data achieves the fastest training speed compared to other methods in this article. At the same time, the proposed DL network achieves high accuracy of 98.1% and 95.4% for defect depth for aluminum sheets and stainless-steel sheets, respectively. Additionally, when considering 16 label combinations of lift-off distances and angle differences during the process of inspection, the accuracy of lift-off classification for the two materials is 97.2% and 96.9%, respectively.