基于PSO-LS-SVM的储罐底板缺陷量化方法研究

程迪; 黄松岭; 赵伟; 王珅

程迪,黄松岭,赵伟,王珅.基于PSO-LS-SVM的储罐底板缺陷量化方法研究[J].电测与仪表,2018,55(4):87-92.
Cheng di,Huang Songling,Zhao Wei,Wang Shen.Research on quantification of defects on tank floor based on particle swarm optimization-least square support vector machine[J].Electrical Measurement & Instrumentation,2018,55(4):87-92.

基于PSO-LS-SVM的储罐底板缺陷量化方法研究

Research on quantification of defects on tank floor based on particle swarm optimization-least square support vector machine

DOI：

中文关键词: 漏磁检测粒子群算法最小二乘支持向量机缺陷量化

英文关键词:magnetic flux leakage detection, PSO, LS-SVM, defect sizing

基金项目:国家重大仪器设备开发专项-铁磁性材料缺陷三维漏磁成像检测仪

作者中文名	作者英文名	单位
程迪	Cheng di	清华大学电机系电力系统国家重点实验室
黄松岭	Huang Songling	清华大学电机系电力系统国家重点实验室
赵伟	Zhao Wei	清华大学电机系电力系统国家重点实验室
王珅	Wang Shen	清华大学电机系电力系统国家重点实验室

摘要点击次数: 1871

中文摘要:

为能准确量化油气储罐底板上的缺陷，本文提出一种最小二乘支持向量机缺陷量化方法，并以该方法模型建立了缺陷的三维漏磁场信号与缺陷的长度、宽度、深度之间的映射关系。为提高该方法对储罐底板缺陷的量化精度，采用粒子群算法对模型参数进行了优化。仿真结果及分析表明，与BP神经网络方法相比，结合了粒子群优化的最小二乘支持向量机缺陷量化方法的网络训练时间短、缺陷量化精度高，具有较强的工程应用优势。

英文摘要:

This paper applies least square-support vector machine(LS-SVM) to quantify the defects on tank floor of oil and gas, this method build the relationship between the three-axial magnetic flux leakage(MFL) of defects and the length, width and depth of defects. In order to accurately quantify the defect, particle swarm optimization（PSO）is adopted to optimize the model parameter of LS-SVM. According to the simulation results, PSO-LS-SVM needs less training time and has better accuracy for the quantification of defects than BP neural network method, and PSO-LS-SVM has better application advantages on the engineering.

查看全文查看/发表评论下载PDF阅读器

关闭