基于支持向量机回归的曲面零件涡流测距标定方法

doi:10.16183/j.cnki.jsjtu.2020.99.010

摘要/Abstract

摘要： 以燃料贮箱筒段外表面聚氨酯泡沫层厚度测量精度要求为例，开展4种常见曲率筒段试件标定试验；提出基于支持向量机回归的涡流测距标定方法，建立提离距离预测模型(LDPM)，用于曲面零件涡流测距；研究曲率对涡流测距测量误差的影响规律.根据测量误差产生的原因将测量误差分为两部分：表面曲率误差和其他误差，分析误差分量在传感器量程范围内相对大小的变化规律，为曲面测量误差补偿提供参考依据.此外，对比分析LDPM与常用标定方法获得的标定函数在测量精度、计算速率方面的优劣，为曲面零件涡流测距选用何种标定方法提供建议.研究结果表明：LDPM在传感器量程初始阶段，表面曲率误差对曲率不敏感；在量程中点附近，表面曲率误差绝对值随着曲率的增加，先减小后上升；在终点区域，表面曲率误差绝对值随着曲率的增加而上升.在整个量程范围内的不同测量区间，其他误差保持不变.此外，LDPM可以将测量误差控制在［-0.5, 0.5］mm，精度与5项多峰高斯拟合相当，高于4次多项式拟合，能够满足厚度测量精度要求，无损检测操作方便.

关键词: 涡流测距, 支持向量机回归, 误差补偿, 多峰高斯拟合

Abstract: Based on the accuracy requirements for the thickness of the polyurethane form layer on the outer surface of the fuel tank, the calibration testing of four common curvature section specimens is conducted. Besides, the eddy current ranging calibration method based on support vector machine regression analysis is proposed to establish the lifting distance prediction model (LDPM), which is used for curved surface eddy current distance measurement. The influence of curvature on the measurement errors of eddy current ranging is studied. The measurement errors are divided into the surface curvature errors and other errors according to the cause of the error. In the different ranges of the sensor range, the relative variation of the error components is analyzed, which provides a basis for surface measurement error compensation. In addition, the comparative analysis of LDPM and the calibration function obtained by using common calibration methods in terms of measurement accuracy and calculation rate are performed, which provides suggestions for the selection of the calibration method for eddy current ranging of curved parts. The results show that the surface curvature error is not sensitive to the curvature in the initial stage of the sensor range. Near the midpoint of the range, the absolute value of the surface curvature error decreases first and then increases with the increase of curvature. In the terminal region, the absolute value of the surface curvature error increases with the rise of curvature, while other errors remain constant within different measurement ranges over the entire range. Moreover, the LDPM can control the measurement error within ［-0.5, 0.5］mm, and the accuracy is comparable to five multi-peak Gaussian fitting, higher than the fourth-order polynomial fitting, which can meet the thickness measurement accuracy requirements and is convenient for non-destructive testing.

Key words: eddy current distance measurement, support vector machine regression, error compensation, multi-peak Gaussian fitting

中图分类号:

TG 156

陶正瑞, 党嘉强, 徐锦泱, 安庆龙, 陈明, 王力, 任斐. 基于支持向量机回归的曲面零件涡流测距标定方法[J]. 上海交通大学学报, 2020, 54(7): 674-681.

TAO Zhengrui, DANG Jiaqiang, XU Jinyang, AN Qinglong, CHEN Ming, WANG Li, REN Fei. Eddy Current Distance Measurement Calibration Method for Curved Surface Parts Based on Support Vector Machine Regression[J]. Journal of Shanghai Jiaotong University, 2020, 54(7): 674-681.

参考文献

［1］刘振作. 涡流涂镀层测厚仪开发与应用现状［J］. 上海涂料, 2004, 42(3): 34-36. LIU Zhenzuo. Development application of eddy current thickness meter［J］. Shanghai Coatings, 2004, 42(3): 34-36. ［2］陆兴旺, 王伟杰, 潘超. 涡流测厚传感器阻抗特性分析［J］. 传感器与微系统, 2009, 28(9): 38-39. LU Xingwang, WANG Weijie, PAN Chao. Analysis of impedance characteristics of eddy thichness measurement sensor［J］. Transducer and Microsystem Technologies, 2009, 28(9): 38-39. ［3］张玉华, 孙慧贤, 罗飞路. 涡流探头提离效应的理论分析与实验研究［J］. 电机与控制学报, 2009, 13(2): 197-202. ZHANG Yuhua, SUN Huixian, LUO Feilu. Theoretical and experimental analysis of lift-off effects on probe impedance in eddy-current testing［J］. Electric Machines and Control, 2009, 13(2): 197-202. ［4］THOMPSON J G. Subsurface corrosion detection in aircraft lap splices using a dual frequency eddy current inspection technique［J］. Materials Evaluation, 1993, 51(12): 1398-1401. ［5］MITRA S, URALI P S, UZAL E, et al. Eddy-current measurements of corrosion-related thinning in aluminium lap splices［M］∥Review of progress in quantitative nondestructive evaluation. Boston, MA, USA: Springer, 1993: 2003-2010. ［6］曾亮. 特种复合材料涂厚度涡流法量技术的研究［D］. 南昌: 南昌航空大学, 2012. ZENG Liang. The researchment of the thickness measurement techniques for special composite’s coating by eddy-current testing［D］. Nanchang: Nanchang Hangkong University, 2012. ［7］姜磊, 王黎明, 张小章. 应力作用对电涡流法测试碳纤维复合材料位移的影响机理［J］. 原子能科学技术, 2019, 53(3): 518-524. JIANG Lei, WANG Liming, ZHANG Xiaozhang. Influence of mechanism of load on displacement measurement of carbon fiber reinforced composite with eddy current sensor［J］. Atomic Energy Science and Technology, 2019, 53(3): 518-524. ［8］胡鹏. 基于平板标定法的曲面涂层涡流测厚精度分析［D］. 太原: 中北大学, 2013. HU Peng. The measuring precision analysis of coating thickness on curved steel shells using the EC sensor calibrated on a plate［D］. Taiyuan: North University of China, 2013. ［9］李德维, 周文祥, 涂军. 电涡流位移传感器检测车轮外形的研究［J］. 电力机车与城轨车辆, 2005, 28(6): 31-33. LI Dewei, ZHOU Wenxiang, TU Jun. Study on the measurement of wheel’s profile with eddy current sensor［J］. Electric Locomotives & Mass Transit Vehicles, 2005, 28(6): 31-33. ［10］高宽厚, 于亚婷, 杨姣, 等. 双层导电涂层厚度的涡流无损检测方法研究［J］. 机械工程学报, 2017, 53(14): 114-119. GAO Kuanhou, YU Yating, YANG Jiao, et al. Study on eddy-current nondestructive testing method of the double-layers conductive coating thickness［J］. Journal of Mechanical Engineering, 2017, 53(14): 114-119. ［11］岳秀芳, 王召巴, 张东利. 涡流检测的厚涂层高精度方法［J］. 仪表技术与传感器, 2014(2): 99-101. YUE Xiufang, WANG Zhaoba, ZHANG Dongli. Study on high-precision methods for thickness measurement of coating with eddy current testing［J］. Instrument Technique and Sensor, 2014(2): 99-101. ［12］刘苏苏, 孙立民. 支持向量机与 RBF 神经网络回归性能比较研究［J］. 计算机工程与设计, 2011, 32(12): 4202-4205. LIU Susu, SUN Limin. Performance comparsion of regression prediction on support vector machine and RBF neural network［J］. Computer Engineering and Design, 2011, 32(12): 4202-4205. ［13］刘方园, 王水花, 张煜东. 支持向量机模型与应用综述［J］. 计算机系统应用, 2018, 27(4): 1-9. LIU Fangyuan, WANG Shuihua, ZHANG Yudong. Overview on models and applications of support vector machine［J］. Computer Systems & Applications, 2018, 27(4): 1-9. ［14］周木春, 赵琦, 陈延如, 等. 基于炉口辐射光谱支持向量机回归的转炉终点碳含量检测［J］. 光谱学与光谱分析, 2018, 38(6): 1804-1808. ZHOU Muchun, ZHAO Qi, CHEN Yanru, et al. Carbon content measurement of BOF by radiation spectrum based on support vector machine regression［J］. Spectroscopy and Spectral Analysis, 2018, 38(6): 1804-1808. ［15］蒋学. 支持向量机及其在铁路工程中的应用研究［D］.成都: 西南交通大学, 2008. JIANG Xue. Support vector machine and the application in railway engineering［D］. Chengdu: Southwest Jiaotong University, 2008. ［16］宋杰, 李光林, 杨晓东. 基于四方对称光源透射光谱的脐橙可溶性固形物检测［J］. 农业工程学报, 2019, 35(10): 267-273. SONG Jie, LI Guanglin, YANG Xiaodong. Detecting soluble solids content of navel orange based on transmission spectrum of tetragonal symmetric light source［J］. Transaction of the Chinese Society of Agricultural Engineering, 2019, 35(10): 267-273.

[1]	. 低渗油井节能生产参数多目标优化方法[J]. J Shanghai Jiaotong Univ Sci, 2026, 31(2): 486-498.
[2]	牛牧, 许黎明, 赵达, 范帆. 基于工件轮廓图像的砂轮磨损在线检测方法[J]. 上海交通大学学报, 2021, 55(3): 221-228.
[3]	胡一星，许黎明，范帆，张哲. 曲线磨削砂轮廓形的原位视觉检测和误差补偿[J]. 上海交通大学学报, 2019, 53(6): 654-659.
[4]	付钊, 贾立. 基于即时学习的间歇过程复合模型[J]. 上海交通大学学报, 2016, 50(6): 937-942.
[5]	冯文龙，黄奕乔，拓占宇，李慧敏，杨建国. 基于温度积分方法的大型数控机床光栅定位热误差建模及实时补偿[J]. 上海交通大学学报（自然版）, 2016, 50(05): 710-715.
[6]	荆旭1，邱世广1，范秀敏1,2，何其昌1,2. 基于关节自由度约束的上臂轴旋转跟踪误差补偿[J]. 上海交通大学学报（自然版）, 2014, 48(12): 1667-1674.
[7]	王维，杨建国. 基于插值算法的数控机床复合误差补偿技术[J]. 上海交通大学学报（自然版）, 2014, 48(1): 12-21.
[8]	许建国，张志利，周召发. 交互式地图匹配算法在组合导航中的应用[J]. 上海交通大学学报（自然版）, 2013, 47(08): 1323-1328.
[9]	李冬冬1, 2, 查体建1, 许明明1, 胡德金1, 许黎明1. 传统展成式球面磨削中球面形状误差分析与补偿 [J]. 上海交通大学学报（自然版）, 2012, 46(07): 1011-1014.
[10]	李冬冬，许明明，侯海云,胡德金,许黎明. 高硬度球面磨削中球面形状误差分析与补偿[J]. 上海交通大学学报（自然版）, 2011, 45(11): 1690-1694.
[11]	张毅,杨建国. 基于灰色神经网络的机床热误差建模[J]. 上海交通大学学报（自然版）, 2011, 45(11): 1581-1586.
[12]	蔡念, 张海员, 张楠. 基于Contourlet的改进加权抛物线插值图像超分辨率算法[J]. 上海交通大学学报（自然版）, 2011, 45(10): 1509-1515.
[13]	叶萍，张炎华，翟传润，战兴群. 磁干扰误差补偿算法在舰船及水下航向测量技术中的应用 [J]. 上海交通大学学报（自然版）, 2010, 44(09): 1297-1301.
[14]	许开州，魏臣隽，胡德金. 展成法球面磨床的几何误差补偿[J]. 上海交通大学学报（自然版）, 2010, 44(04): 478-0483.