Research on Electrical Capacitance Tomography Lubricating Oil Monitoring Based on Elastic Net Method Optimized by the Relaxed Alternating Direction Method of Multipliers

Aiming at the problem of low accuracy of Electrical Capacitance Tomography(ECT) in the process of aviation oil monitoring,an elastic net method optimized by the relaxed Alternating Direction Method of Multipliers (EN-RADMM) is developed. The objective function consisted of the Least-Square term and elastic net regularization.Balancing sparseness and smoothness of results through flexible tuning of multiple regularization parameters.Relaxation,equivalent deformation directing at ill-posed equations,and LU decomposition were applied to accelerate algorithm convergence and improve solution accuracy. Simulation results show that compared with Landerweber, Tikhonov regularization algorithm,the image error of EN-RADMM algorithm is reduced by about 40%,the correlation coefficient increased by about 50%.Compared with the S-ADMM algorithm, the image error is r7educed by about 32%,the correlation coefficient increased by about 39.7%.The experimental results show that this method can effectively improve the image reconstruction accuracy.