金属磁记忆预测井下套管故障系统的研究

Study on systems of forecast the malfunction of borehole casing by metal magnetic memory technique

金属磁记忆技术可有效判断套管应力集中区域。对井下磁记忆检测仪的硬件、软件、信号处理、故障分类识别进行研究,为仪表的最终实用化提供理论基础和方法。在信号处理中,应用了数字平滑技术和小波分析,消除了高频噪声;在硬件中用HONEYWELL公司的HMC1022磁阻传感器来获取铁磁性工件表面的磁记忆信号,并使用BP神经网络实现了套管危险等级的非线性定量识别。实验验证了该方案的可行性和有效性。

Metal magnetic memory technique was an effective method to find stress concentration zone. Introduce the software and the hardware structures of the magnetic memory detecting instrument. Study on the hardware, software, quantitative recognition for malfunction, signal proceeding of metal magnetic memory systems, the method and theory are presented for applied instrument. Wavelet denoising method and data smoothing are introduced in test systems of metal magnetic memory for well. By using HONEYWELL company＇s magnetism sensor HMC1022 to obtain magnetic memory signals on the surface of the ferromagnetic parts. BP neural network was applied to deal with the problem of nonlinear mappling for quantitative recognition. The validity and feasibility of the scheme is demonstrated by experiment.