基于智能计算与通量衰减的缪子三维成像算法

Three-dimensional absorption muographic reconstruction algorithm based on intelligent computation

针对大规模缪子成像场景,设计一种新型的反演模型,将基于通量衰减的缪子成像技术与智能计算中限制内存的拟牛顿法相结合,避开了矩阵求伪逆和海森矩阵存储的操作,降低了计算复杂度和内存占用.在已知被测物体密度区间时,合理的上、下限约束和参考模型可提高结果的准确性.针对具有上、下限约束的反演问题,设计一种内点罚函数,将约束优化问题转换为无约束优化问题.结果表明,设计的反演模型在大规模反演问题中效果良好,内点罚函数能起到很好的约束作用.

For large-scale imaging scenarios,we designed the first time a new inversion model and combined the muon tomography technique based on flux attenuation with the limited memory Broyden-Fletcher-Goldfarb-Shanno method for intelligent computing.It eliminates the need for matrix pseudo inverses and storing Hessian matrices,and reduces the computational complexity and the occupation of memory resources.When the density interval of the measured object was known,using reasonable upper and lower limit constraints and reference models improve the accuracy of the results.For inversion problems with upper and lower limits constraints,an interior penalty function was designed to transform constrained optimization problems into unconstrained ones.The simulation results showed that the proposed inversion algorithm has satisfactory performance in large-scale inversion problems,and the interior penalty function can also play a good constraint role.