基于BP神经网络的航磁补偿方法研究

Research on aeromagnetic compensation method based on BP neural network

摘要:

水中未爆弹危害极大，航空磁探因探测效率高的优势，常用于水中未爆弹的探测。飞机干扰磁场的存在限制了航空磁探的发展。传统的T-L模型待求参数间具有很强的复共线性，难以满足高精度磁补偿的要求。神经网络算法具有容错率高、求解精度高的特点。首先使用BP神经网络建立干扰磁场的数学模型。随后，通过仿真生成干扰磁场以及未爆弹目标磁场信号对算法进行验证。最后，利用四旋翼无人机平台进行目标探测试验，补偿改善比超过20，补偿精度优于0.5 nT。试验结果表明算法具有一定的工程应用价值。

Abstract:

Unexploded bombs in water are extremely harmful, and aerial magnetic detection is often used for the detection of unexploded bombs in water due to the advantages of high detection efficiency. The presence of an airplane's interfering magnetic field limits the development of aeromagnetic probing. The traditional T-L model has strong complex collinearity between the parameters to be sought, which is difficult to meet the requirements of high-precision magnetic compensation. The neural network algorithm has the characteristics of high error tolerance rate and high solution accuracy. First, the BP neural network is used to establish a mathematical model of the interfering magnetic field. Subsequently, the algorithm is verified by generating the interference magnetic field and the magnetic field signal of the unexploded bomb target by simulation. Finally, the target detection test is carried out by using the quadrotor UAV platform, and the compensation improvement ratio exceeds 20, and the compensation accuracy is better than 0.5 nT. The experimental results show that the algorithm has certain engineering application value.