摘要
基于B样条神经网络算法实现新机航材备件的消耗预测,由于新机航材备件历史消耗数据少,提出首先利用B样条进行数据拟合以增加样本数;其次根据航材消耗特点建立基于BP神经网络的航材备件消耗模型,最后以某场站航材消耗进行Matalb算例仿真,检验模型的可行性。
Aiming at the difficulties caused by little history consumption data of new aircraft spare parts on spare parts predica⁃tion,BP network based on B spline is presented to predict new aircraft spare parts.Firstly the least square method combined with BP neural network is used to increase the amount of samples.Secondly,according to the features of air materials consuming,a new aircraft spare parts demand prediction model based on BP network is established.At last,example simulation by Matalb is carried out to test the feasibility of the model.
作者
王艳艳
刘金波
孙志红
WANG Yanyan;LIU Jinbo;SUN Zhihong(Department of Basic Courses,Air Force Logistics College,Xuzhou 221000)
出处
《舰船电子工程》
2020年第11期125-127,140,共4页
Ship Electronic Engineering
基金
空军勤务学院青年科研基金项目(编号:KY2018D030C)资助。
关键词
航材消耗
小样本
BP神经网络
B样条数据拟合
consuming prediction of air materials
small sample
BP neural network
B spline least square