A Pinning Actor-Critic Structure-Based Algorithm for Sizing Complex-Shaped Depth Profiles in MFL Inspection with High Degree of Freedom

One of the most efficient nondestructive methods for pipeline in-line inspection is magnetic flux leakage (MFL) inspection. Estimating the size of the defect from MFL signal is one of the key problems of MFL inspection. As the inspection signal is usually contaminated by noise, sizing the defect is an ill-posed inverse problem, especially when sizing the depth as a complex shape. An actor-critic structure-based algorithm is proposed in this paper for sizing complex depth profiles. By learning with more information from the depth profile without knowing the corresponding MFL signal, the algorithm proposed saves computational costs and is robust. A pinning strategy is embedded in the reconstruction process, which highly reduces the dimension of action space. The pinning actor-critic structure (PACS) helps to make the reward for critic network more efficient when reconstructing the depth profiles with high degrees of freedom. A nonlinear FEM model is used to test the effectiveness of algorithm proposed under 20 dB noise. The results show that the algorithm reconstructs the depth profile of defects with good accuracy and is robust against noise.

Dynamics and Control of a Delayed Oscillator Network by Pinning Strategy

Large scale networks may exhibit complicated dynamical behaviors, such as instability, bifurcation, and chaos. It is not easy to get which nodes or links need to be controlled for ensuring the desired dynamical behavior. This paper presents a detailed analysis on the dynamics and control of a delayed network by a pinning strategy. The network system is first mapped to a simple system by means of an orthogonal transformation. The control signals are then exerted only on a fraction of nodes in the transformed system. We analyze how to get the desired dynamics of the original controlled system (such as zeros solutions, periodic solutions, quasi-periodic solutions and chaos) via controlling the transformed system. It shows that the solutions of the original system can be obtained by the local dynamical behavior exhibiting in the transformed system. The results show that the proposed pinning control strategy is an effective approach for dynamics control.

A DEGREE-BASED STRATEGY FOR CONSTRAINED PINNING CONTROL OF COMPLEX NETWORKS

In this paper, a modified degree-based strategy is proposed for pinning control of complex networks under constrained control capacity. Limited by the total control strength, the pinning strategy design problem is reconsidered as a constrained optimization problem. To provide a fast and effective solution, a decrease-and-conquer approach has been designed to assign the best control strengths to the pinned highest-degree nodes. Simulation results have demonstrated that the obtained strategy provides an outperformed control effect on various kinds of complex networks, as compared with strategies derived from degree, betweenness or closeness using evenly-distributed control strength.