This paper focuses on the application of ultrasonic guided waves in the defect inspection of buried pipelines, selecting circumferential cracks as the research object. Based on the three-dimensional finite element pipeline model, numerical simulation methods are employed to obtain defect echo signals for investigating the circumferential positioning accuracy, and the quantitative identification of the circumferential length and depth of crack geometries. For the circumferential positioning, a new circumferential positioning method is proposed. By introducing the circumferential position coefficient, the central angle is determined between the defect center point and the node corresponding to the maximum peak-to-peak amplitude of the echo signal. The maximum positioning error reaches 0.89% of the angle of the entire circle, achieving precise circumferential positioning of defects, and providing technical support for the development of future defect detection devices that use circumferential positioning. Regarding the identification of defect geometries, a back propagation (BP) neural network model is built for realizing the inversion of defect geometries, which is trained by using 13 feature indicators of numerical simulation datasets of defect echo signals in the time, frequency, and time–frequency domains. The trained model is then used to predict both the circumferential length and depth of cracks excluded from the dataset. The results demonstrate a maximum error of 0.46% of the pipe circumference for length and of 4% of the pipe wall thickness for depth. This high-precision inversion of the circumferential length and depth of cracks demonstrates that the model can significantly improve the detection accuracy of defect geometries in engineering applications.
Ren et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: