Signal Feature Extraction and Quantitative Evaluation of Metal Magnetic Memory Testing for Oil Well Casing Based on Data Preprocessing Technique
Signal Feature Extraction and Quantitative Evaluation of Metal Magnetic Memory Testing for Oil Well Casing Based on Data Preprocessing Technique
复制标题
DOI：
10.1155/2014/902304
复制
发表时间：
2014-06
影响因子：
--
通讯作者：
Zhilin Liu;Lutao Liu;Jun Zhang
中科院分区：
文献类型：
--
作者：
Zhilin Liu;Lutao Liu;Jun Zhang
金属磁记忆（MMM）技术是实现油井套管应力集中区检测的有效方法。它可以提供早期诊断的微损伤，预防性保护。MMM是一种自然的空间域信号，信号微弱，易受噪声干扰。因此，特别是在高温、高压、高湿、多干扰源的井下恶劣环境下，很难实现有效的MMM信号特征提取。本文在数据预处理技术的基础上，提出了一种中值滤波预处理的方法，以消除MMM中的野值点。并将基于小波变换的自适应小波去噪方法和数据平滑算法应用于MMM系统的测试中。通过数据预处理技术，保留了数据，降低了信号的噪声。因此，可以实现SC区的正确定位。同时，提出了新诊断方法中的特征参数，通过最小二乘支持向量机（LS-SVM）和非线性定量映射关系，保证了套管危险等级的可靠确定。通过实验验证了该方法的有效性和可行性。
Metal magnetic memory (MMM) technique is an effective method to achieve the detection of stress concentration (SC) zone for oil well casing. It can provide an early diagnosis of microdamages for preventive protection. MMM is a natural space domain signal which is weak and vulnerable to noise interference. So, it is difficult to achieve effective feature extraction of MMM signal especially under the hostile subsurface environment of high temperature, high pressure, high humidity, and multiple interfering sources. In this paper, a method of median filter preprocessing based on data preprocessing technique is proposed to eliminate the outliers point of MMM. And, based on wavelet transform (WT), the adaptive wavelet denoising method and data smoothing arithmetic are applied in testing the system of MMM. By using data preprocessing technique, the data are reserved and the noises of the signal are reduced. Therefore, the correct localization of SC zone can be achieved. In the meantime, characteristic parameters in new diagnostic approach are put forward to ensure the reliable determination of casing danger level through least squares support vector machine (LS-SVM) and nonlinear quantitative mapping relationship. The effectiveness and feasibility of this method are verified through experiments.