A Pipeline Burial Depth Inversion Method Based on Noncontact Magnetic Detection

Noncontact magnetic detection technology has great application potential in the depth detection of buried steel pipelines. However, the connection between burial depth and noncontact magnetic signals is unclear, restricting the application of this technology in pipeline burial depth detection. In this study, the full-sized pressurized steel pipeline system was constructed. The propagation factor <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${f}_{G}$ </tex-math></inline-formula> is defined to quantitatively analyze the relationship between the magnetic gradient modulus and the burial depth of the pipeline with different probe orientations, pipe diameters, and internal pressures. The finite element model is established to obtain the attenuation law of magnetic signals in space under more pipe diameters and pressure conditions. The results indicate that within the range of 0.1–2 m, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${f}_{G}$ </tex-math></inline-formula> decreases exponentially with increasing detection height, and the pipe diameter is the main controlling factor affecting the variation law of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${f}_{G}$ </tex-math></inline-formula>. The genetic algorithm optimized backpropagation (GA-BP) neural network model was established to invert pipeline burial depth based on pipeline parameters and operating parameters. The maximum relative error of model and burial depth inversion is within 10%. Moreover, the inversion deviation of the model is less than 15%, while the signal-to-noise ratio (SNR) is greater than 28 dB.