利用最小二乘支持向量机求解潜艇内外磁场映射模型

Least squares support vector machine for solving reflection model of submarine′s internal and external magnetic field

为提高潜艇磁隐身能力,应对潜艇固定磁场进行实时监测,提出利用最小二乘支持向量机的潜艇内外磁场映射方法。结合内外映射法和最小二乘支持向量机原理,通过交叉验证优化模型参数,建立由内到外的潜艇磁场映射模型。以潜艇外部垂向固定磁场变化量为分析对象,仿真和实验结果均与标准值吻合良好。与径向基神经网络算法相比,该方法的泛化能力和推算精度有明显提高,且更符合工程实际,对闭环消磁技术的研究具有指导意义。

For the promotion of submarine′s magnetic silencing ability,it is necessary to monitor the submarine′s permanent magnetic field immediately,and a reflection method of submarine′s internal and external magnetic field based on LS-SVM(least squares support vector machine)was proposed.Combined with internal and external reflection method and LS-SVM theory,an inside-out reflection model of submarine′s magnetic field was established by optimizing the model parameter with CV(cross validation).With the variation in the vertical component of the submarine′s external permanent magnetic field as an object of analysis,the extrapolation answers of simulation and hull experiment agreed well with the standard value.Compared to the RBFNN(radius basis function neural network),the proposed method has better generalization ability and extrapolation accuracy apparently,fits more in engineering facts,and can provide useful guidance in the research for closed-loop degaussing technology.