基于改进人工蜂群算法的漏磁缺陷轮廓重构

Profiles Reconstruction of Magnetic Flux Leakage Based on Improved Artificial Bee Colony Algorithm

漏磁缺陷重构是指由检测到的漏磁信号重构缺陷轮廓及参数,是实现漏磁反演的关键。将局部最优解和全局最优解引入到人工蜂群算法(Artificial Bee Colony Algorithm,ABC)中,提出了一种基于改进人工蜂群算法的缺陷重构模型。在该模型中,径向基函数神经网络作为前向模型求解漏磁信号,改进人工蜂群算法用于求解反演问题中的优化问题。将改进人工蜂群算法和基本人工蜂群算法作为反演算法进行了比较,实验结果表明,改进人工蜂群反演算法精度较高,速度较快,同时对实测信号具有鲁棒性,是一种有效可行的漏磁反演新方法。

The reconstruction of magnetic flux leakage （MFL） defect profiles means the reconstruction of defect profiles and parameters from MFL inspection signals. It is the key for the inversion of MFL inspection signals. The local optimal solution and the global optimal solution have been introduced into the artificial bee colony algorithm,and a kind of defect reconstruction model based on improved artificial bee colony algorithm is proposed. In the model,radial-basis function neural network is utilized as forward model,and the improved artificial bee colony algorithm is used to solve the optimization problem in the inverse problem. The comparison between basic artificial bee colony algorithm and proposed improved artificial bee colony algorithm which indicate that the proposed method has high accuracy and robustness against the real measure signals,and it is an effective and feasible approach for solving inverse problems.