基于鲁棒正则化极限学习机的电容层析成像图像重建

doi:10.3969/j.issn.1000-1158.2022.08.11

摘要
图/表
参考文献(18)
相关文章 (15)

全文: PDF (2098 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要电容层析成像图像重建是一个非线性及病态性逆问题。基于此,提出了基于迭代重加权最小二乘法的鲁棒正则化极限学习机(RELM-IRLS)算法的电容层析成像图像重建方法,以油/气两相流为研究对象,通过有限元仿真构建随机分布流型,对RELM-IRLS算法完成训练,并与Landweber迭代算法及极限学习机算法进行对比,RELM-IRLS算法的测试集平均误差相比极限学习机算法减小4.6%。仿真及静态实验结果均表明, RELM-IRLS算法所得重建图像质量得到明显提升,且算法具有良好的泛化性能。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张立峰
	戴力

关键词 ：计量学, 电容层析成像, 迭代重加权, 极限学习机, Landweber迭代算法

Abstract：Image reconstruction of electrical capacitance tomography is a nonlinear and ill-posed inverse problem. Robust regularized extreme learning machine combined with iterative reweighted least squares is proposed for the image reconstruction of electrical capacitance tomography. Oil/gas two-phase flow is selected as research object, and the randomly distribution flow regimes are obtained using finite element simulation. RELM-IRLS network is trained, and the reconstructed images are compared with Landweber iterative algorithm and extreme learning machine algorithm. The average error of the test set of the RELM-IRLS algorithm is reduced by 4.6% compared with extreme learning machine algorithm. Simulation and static experiment results show that the quality of the reconstructed images is improved obviously using RELM-IRLS algorithm, which also has good generalization ability.

Key words： metrology electrical capacitance tomography iterative reweight extreme learning machine Landweber iterative algorithm

收稿日期: 2021-01-29 发布日期: 2022-08-20

PACS:

TB937

基金资助:国家自然科学基金(61973115)

作者简介: 张立峰(1979-), 男, 江西临川人, 华北电力大学副教授, 博士, 主要从事多相流检测及电学层析成像技术方面研究。Email: lifeng.zhang@ncepu.edu.cn

引用本文:

张立峰,戴力. 基于鲁棒正则化极限学习机的电容层析成像图像重建[J]. 计量学报, 2022, 43(8): 1044-1049.
ZHANG Li-feng,DAI Li. Image Reconstruction Based on Robust Regularized Extreme Learning Machine for Electrical Capacitance Tomography. Acta Metrologica Sinica, 2022, 43(8): 1044-1049.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2022.08.11 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2022/V43/I8/1044

［1］张立峰, 朱炎峰. 电容层析成像系统阵列电极三维优化设计［J］. 计量学报, 2020, 41(8): 947-952.
Zhang L F, Zhu Y F. Three-dimensional optimization design of array electrodes for electrical capacitance tomography system［J］. Acta Metrologica Sinica, 2020, 41(8): 947-952.
［2］温银堂, 贾瑶, 张玉燕, 等. 基于改进ECT的隔热材料胶层无损检测研究［J］. 仪器仪表学报, 2016, 37(7): 1596-1602.
Wen Y T, Jia Y, Zhang Y Y, et al. Research on non-destructive testing of thermal insulation material adhesive layer based on improved ECT［J］. Chinese Journal of Scientific Instrument, 2016, 37(7): 1596-1602.
［3］Sun S J, Xu L J, Cao Z, et al. Signal Demodulation Methods for Electrical Tomography: A Review［J］. IEEE Sensors Journal, 2019, 19(20): 9026-9035.
［4］张立峰, 蒋玉虎. 电容层析成像三维图像重建研究［J］. 计量学报, 2019, 40(3): 462-465.
Zhang L F, Jiang Y H. Study on 3D Image Reconstruction of Electrical Capacitance Tomography［J］. Acta Metrologica Sinica, 2019, 40(3): 462-465.
［5］Gao X, Cao Z, Tian Y, et al. Inverse Radon Method Based on Electrical Field Lines for Dual-Modality Electrical Tomography ［J］. IEEE Transactions on Instrumentation and Measurement, 2020, 69(10): 8250-8260.
［6］Huang G B, Zhu Q Y, Siew C K. Extreme Learning Machine: Theory and Applications［J］. Neurocomputing, 2006, 70(1-3): 489-501.
［7］Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: a new learning scheme of feedforward neural networks［J］. IEEE International Joint Conference on Neural Networks, 2004, 2: 985-990.
［8］Huang G B, Chen L. Enhanced Random Search Based Incremental Extreme Learning Machine［J］. Neurocomputing, 2008, 71(16-18): 3460-3468.
［9］张立峰, 朱炎峰. 极限学习机在电容层析成像中的应用［J］. 电测与仪表, 2020, 57, (9): 146-152.
Zhang L F, Zhu Y F. The application of extreme learning machine in electrical capacitance tomography［J］. Electrical Measurement and Instrumentation, 2020, 57(9): 146-152.
［10］Chen K, Lü Q, Lu Y, et al. Robust regularized extreme learning machine for regression using iteratively reweighted least squares［J］. Neurocomputing, 2017, 230: 345-358.
［11］张立峰, 王化祥. 基于SVM及电容层析成像的两相流流型识别［J］. 仪器仪表学报, 2009, 30(4): 812-816.
Zhang L F, Wang H X. Identification of two-phase flow regime based on support vector machine and electrical capacitance tomography technique［J］. Chinese Journal of Scientific Instrument, 2009, 30(4): 812-816.
［12］张立峰, 朱炎峰. 基于MO-PLP-ELM及电容层析成像的两相流流型辨识［J］. 计量学报, 2021, 42(3): 334-338.
Zhang L F, Zhu Y F. Identification of Two-phase Flow Based on MO-PLP-ELM and Electrical Capacitance Tomography［J］. Acta Metrologica Sinica, 2021, 42(3):334-338.
［13］张立峰, 李佳, 田沛. Kalman滤波在电容层析成像图像重建中的应用［J］. 计量学报, 2017, 38(3): 315-318.
Zhang L F, Li J, Tian P. Application of Kalman Filter for Image Reconstruction of Electrical Capacitance Tomography［J］. Acta Metrologica Sinica, 2017, 38(3): 315-318.
［14］Ye J M, Yang W Q, Wang C. Investigation of Spatial Resolution of Electrical Capacitance Tomography Based on Coupling Simulation［J］. IEEE Transactions on Instrumentation and Measurement, 2020, 69(11): 8919-8929.
［15］Zhao J Y, Xu L J, Cao Z. Direct Image Reconstruction for Electrical Capacitance Tomography Using Shortcut D-Bar Method［J］. IEEE Transactions on Instrumentation and Measurement, 2019, 68(2): 483-492.
［16］Cui Z Q, Xia Z H, Wang H X. Electrical Capacitance Tomography Sensor Using Internal Electrodes［J］. IEEE Sensors Journal, 2020, 20(6): 3207-3216.
［17］Wang C, Guo Q, Wang H X, et al. ECT Image Reconstruction Based on Alternating Direction Approximate Newton Algorithm［J］. IEEE Transactions on Instrumentation and Measurement, 2020, 69(7): 4873-4886.
［18］张立峰, 刘晶, 田沛. 一种电容层析成像系统电极组合激励测量方法［J］. 计量学报, 2017, 38(4): 469-472.
Zhang L F, Liu J, Tian P. An Exciting-measuring Mode for Electrical Capacitance Tomography System［J］. Acta Metrologica Sinica, 2017, 38(4): 469-472.