Finite-Element Neural Network-Based Solving 3-D Differential Equations in MFL

Abstract

The solution of a differential equation contains the forward model and the inverse problem. The finite element method (FEM) and the iterative approach based on FEM are extensively used to solve varied differential equations. Although FEM could obtain an accurate solution, the shortcoming of the approach is the high computational costs. This paper proposes an improved finite-element neural network (FENN) embedding a FEM in a neural network structure for solving the forward model while a conjugate gradient (CG) method is employed as the learning algorithm. Taking the 3-D magnetic field analysis in magnetic flux leakage (MFL) testing as an example, the comparison between CG algorithm and the gradient descent (GD) algorithm is presented. The vector plot of magnetic field intensity is obtained, and the vertical components of magnetic flux density are respectively analyzed. The iterative approach based on FENN and parallel radial wavelet basis function neural network is also adopted to solve the inverse problem. This approach iteratively adjusts weights of the inverse network to minimize the error between the measured and predicted values of MFL signals. The forward and inverse results indicate that FENN and the iterative approach are feasible methods with rapidness, accuracy and stability associated with 3-D different equations in MFL testing.Index Terms-Conjugate gradient (CG) algorithm, finite-element method (FEM), finite-element neural network (FENN), forward model, inverse problem, magnetic flux leakage (MFL) testing.

Modeling of complex dynamic systems using differential neural networks with the incorporation of a priori knowledge

“…A number of regularization functionals classes is proposed by different authors [9,[25][26][27][28]. The Tikhonov regularization is extensively used in [9].…”

Defect Profile Estimation from Magnetic Flux Leakage Signal via Efficient Managing Particle Swarm Optimization

“…A physical model is usually employed as the forward model which mainly involve three classes: heuristic models (e.g., artificial neural network [6,7]), analytical models (e.g., dipole model [8,9]), and numerical models (e.g., finite element method [10,11]). Compared with numerical models and analytical models, the heuristic models are faster but less accurate.…”

“…An inversing procedure is often regarded as solving an optimization problem, and many optimization algorithms have been applied to the inversing techniques, such as gradient descent algorithm [6,7] and genetic algorithm (GA) [12,13]. It's proved that the efficiency of the iterative approach applied to solve optimization problem determines the computing time and solution accuracy of inversing technique.…”

Steel Coiled Tubing Defect Evaluation Using Magnetic Flux Leakage Signals

“…This is true not only for coiled tubing inspection, but also for inspection of other metal structures, such as pipelines, storage tanks, aircrafts, etc. The task remains challenging in quantitatively predicting the topology and severity of detected defects, as described in C. Breidenthal et al 10 , Ravan et al 11 , Rostamabad et al 12 , Amineh et al 13,14 , Priewald et al 15 , Xu et al 16 , McJunkin et al 17 , among others. Because of the intrinsic complexity, much of the defect characterization work still heavily depends on individual prove ups upon detection.…”