The metal magnetic memory detection technology can detect early stress concentration and invisible damage of the pipeline. It can be detected under the action of the geomagnetic field, without the need to magnetize the pipeline in advance, which has the advantage of non-destructive testing. Since the magnetic memory signal is relatively weak, the actual detected signal will be affected by environmental noise, sensor jitter, and pipeline surface deposits. Therefore, the magnetic memory signal needs to be denoised. In this article, the translation invariant wavelet denoising method, which is improved based on the wavelet threshold denoising method, is used to denoise the collected pipeline magnetic memory signals. The experimental results show that the signal-to-noise ratio (SNR) obtained by this method is 1.15% higher than the unmodified wavelet threshold denoising, and the signal obtained is more stable. To solve the problem of fewer data samples for magnetic memory detection, three methods including support vector regression machine, back propagation (BP) neural network, and particle swarm optimization multiple output least-squares support vector regression (MLS-SVR) are compared and analyzed to inverse the overall defect size of pipeline defects. The experiments show that the MLS-SVR inversion result based on particle swarm optimization is the best, and the overall mean square error reaches 0.27 mm. In the end, a pipeline damage detection system is built to detect the magnetic memory signals of pipelines with different sizes of defects, and the defect depth and radius are inverted.

中文翻译：

---

基于金属磁记忆的管道损伤检测

金属磁记忆检测技术可检测管道早期应力集中和不可见损伤。可在地磁场作用下进行检测，无需预先对管道进行磁化，具有无损检测的优点。由于磁记忆信号相对较弱，实际检测到的信号会受到环境噪声、传感器抖动、管道表面沉积物的影响。因此，需要对磁记忆信号进行去噪。本文采用在小波阈值去噪方法基础上改进的平移不变小波去噪方法对采集到的管道磁记忆信号进行去噪。实验结果表明，该方法得到的信噪比（SNR）为1。比未修改的小波阈值去噪高15%，得到的信号更稳定。针对磁记忆检测数据样本较少的问题，对支持向量回归机、反向传播(BP)神经网络、粒子群优化多输出最小二乘支持向量回归(MLS-SVR)三种方法进行比较分析反演管道缺陷的整体缺陷大小。实验表明，基于粒子群优化的MLS-SVR反演结果最好，整体均方误差达到0.27 mm。最后构建了管道损伤检测系统，对不同大小缺陷的管道进行磁记忆信号检测，并反演缺陷深度和半径。针对磁记忆检测数据样本较少的问题，对支持向量回归机、反向传播(BP)神经网络、粒子群优化多输出最小二乘支持向量回归(MLS-SVR)三种方法进行比较分析反演管道缺陷的整体缺陷大小。实验表明，基于粒子群优化的MLS-SVR反演结果最好，整体均方误差达到0.27 mm。最后构建了管道损伤检测系统，对不同大小缺陷的管道进行磁记忆信号检测，并反演缺陷深度和半径。针对磁记忆检测数据样本较少的问题，对支持向量回归机、反向传播(BP)神经网络、粒子群优化多输出最小二乘支持向量回归(MLS-SVR)三种方法进行比较分析反演管道缺陷的整体缺陷大小。实验表明，基于粒子群优化的MLS-SVR反演结果最好，整体均方误差达到0.27 mm。最后构建了管道损伤检测系统，对不同大小缺陷的管道进行磁记忆信号检测，并反演缺陷深度和半径。和粒子群优化多输出最小二乘支持向量回归 (MLS-SVR) 进行比较和分析，以求逆管道缺陷的整体缺陷大小。实验表明，基于粒子群优化的MLS-SVR反演结果最好，整体均方误差达到0.27 mm。最后构建了管道损伤检测系统，对不同大小缺陷的管道进行磁记忆信号检测，并反演缺陷深度和半径。和粒子群优化多输出最小二乘支持向量回归 (MLS-SVR) 进行比较和分析，以求逆管道缺陷的整体缺陷大小。实验表明，基于粒子群优化的MLS-SVR反演结果最好，整体均方误差达到0.27 mm。最后构建了管道损伤检测系统，对不同大小缺陷的管道进行磁记忆信号检测，并反演缺陷深度和半径。