基于数据驱动的结构钢表面应力磁巴克豪森噪声表征方法  

Data-driven method for characterization of structural steel surface stress of magnetic Barkhausen noise

作　　者：崔西明 邱志鹏 魏嘉 张弛 宋凯[1] 李喆 王树鹏 CUI Ximing;QIU Zhipeng;WEI Jia;ZHANG Chi;SONG Kai;LI Zhe;WANG Shupeng(Key Laboratory of Nondestructive Testing,Ministry of Education,Nanchang Hangkong University,Nanchang 330063,China;AECC Shenyang Liming Aero Engine Co.,Ltd.,Shenyang 110043,China)

机构地区：[1]南昌航空大学无损检测技术教育部重点实验室,南昌330063 [2]中国航发沈阳黎明航空发动机有限责任公司,沈阳110043

出　　处：《航空学报》2023年第8期246-257,共12页Acta Aeronautica et Astronautica Sinica

基　　金：无损检测技术教育部重点实验室开放基金(EW201908438);南昌航空大学博士启动基金(EA201908420)。

摘　　要：磁巴克豪森噪声(MBN)技术可用于定量评估铁磁材料的表面应力。当前MBN法应力评估技术存在特征量选取较难、定量预测模型复杂且对标定数据集的拟合精度较低的不足。提出一种数据驱动的非线性映射算法拟合MBN噪声和应力的关系,研究了基于小波包变换系数的时频特征替代统计特征量,减少了样本数据计算量。采用MBN噪声在小波包变换时-频域内的小波包变换系数作为特征向量,利用基于奇异值分解的数据降维算法降低特征向量的维数,将经过数据降维后的特征向量输入反向传播(BP)神经网络进行模型训练以建立预测模型。结果表明:采用基于奇异值分解的数据降维算法可降低模型的复杂度,利用降维后的小波包变换系数特征向量训练BP神经网络可实现铁磁材料表面应力的高精度预测。建立的表征方法有效解决了铁磁构件应力分布成像问题,在预防应力腐蚀、提高疲劳强度等损伤预警方面具有广阔的应用前景。Magnetic Barkhausen Noise(MBN)technique can be used to quantitatively evaluate the surface stress of ferromagnetic materials.The current MBN stress assessment technology has the disadvantages of difficult feature se⁃lection,complex quantitative prediction model and low fitting accuracy of the calibration data set.A data-driven nonlin⁃ear mapping algorithm is proposed to fit the relationship between MBN noise and stress.The time-frequency feature based on wavelet packet transform coefficients is used to replace the statistical feature,which reduces the amount of sample data calculation.The wavelet packet transform coefficients of MBN noise in the wavelet packet transform timefrequency domain are used as eigenvectors.The dimensionality reduction algorithm based on singular value decom⁃position is used to reduce the dimension of the eigenvectors,and the eigenvectors after data dimension reduction are input into the Back Pagation(BP)neural network.Model training is performed to build predictive models.The results show that the data dimensionality reduction algorithm based on singular value decomposition can reduce the complex⁃ity of the model,and the BP neural network can be trained by using the eigenvectors of the wavelet packet transform coefficients after dimensionality reduction to achieve high-precision prediction of surface stress of ferromagnetic materi⁃als.The characterization method proposed can effectively solve the problem of stress distribution imaging of ferromag⁃netic components,and has great potential in application in stress corrosion prevention,fatigue strength improvement,and other damage early warning.

关 键 词：数据驱动 磁巴克豪森噪声 结构钢 应力 奇异值分解 小波包分解 

分 类 号：V214.32[航空宇航科学与技术—航空宇航推进理论与工程]