An extended L-curve method for choosing a regularization parameter in electrical resistance tomography

作者：Xu, Yanbin^*; Pei, Yang; Dong, Feng

来源：Measurement Science and Technology, 2016, 27(11): 114002.

DOI：10.1088/0957-0233/27/11/114002

• electrical resistance tomography
• inverse problem
• Tikhonov regularization
• extended L-curve
• Krylov subspace

The L-curve method is a popular regularization parameter choice method for the ill-posed inverse problem of electrical resistance tomography (ERT). However the method cannot always determine a proper parameter for all situations. An investigation into those situations where the L-curve method failed show that a new corner point appears on the L-curve and the parameter corresponding to the new corner point can obtain a satisfactory reconstructed solution. Thus an extended L-curve method, which determines the regularization parameter associated with either global corner or the new corner, is proposed. Furthermore, two strategies are provided to determine the new corner-one is based on the second-order differential of L-curve, and the other is based on the curvature of L-curve. The proposed method is examined by both numerical simulations and experimental tests. And the results indicate that the extended method can handle the parameter choice problem even in the case where the typical L-curve method fails. Finally, in order to reduce the running time of the method, the extended method is combined with a projection method based on the Krylov subspace, which was able to boost the extended L-curve method. The results verify that the speed of the extended L-curve method is distinctly improved. The proposed method extends the application of the L-curve in the field of choosing regularization parameter with an acceptable running time and can also be used in other kinds of tomography.

• 出版日期2016-11
• 单位天津大学