机载设备故障率预测的灰色GM(1,N)与偏最小二乘组合模型

Grey GM(1,N)and PLS Combined Model for Failure Rate Prediction of Airborne Equipment

为解决传统机载设备故障率预测中可用历史数据有效样本量少和单一模型预测误差较大的问题,提出一种灰色GM(1,N)与偏最小二乘(PLS)组合模型。以机载设备故障率历史数据为原始数据,综合考虑多因素对机载设备故障率的影响,建立基于灰色GM(1,N)故障率模型,以及建立PLS的故障率模型,分别对故障率进行单一预测。在不增加复杂性的基础上,以误差平方和为目标函数建立最优组合预测模型。采用某航空机载设备进行算例分析,结果表明:该组合模型的预测精度优于单一预测模型,产生较大预测误差的风险较单一模型有所降低。

In order to solve the problem of small sample size of available historical data and large prediction error of single model in traditional airborne equipment failure rate prediction,a combined model of GREY GM(1,N)and partial least squares(PLS)is proposed.Taking the historical data of the failure rate of airborne equipment as the original data,the influence of multiple factors on the failure rate of airborne equipment is comprehensively considered.The failure rate model based on grey GM(1,N)and the failure rate model based on PLS are established to make a single prediction of the failure rate respectively.On the basis of no-adding complexity,the optimal combined prediction model is established by taking the sum of squares of errors as the objective function.A certain airborne equipment is used for example analysis,the results show that the prediction accuracy of the combined model is better than that of the single prediction model,and the caused risk of larger prediction error is reduced than that of the single model.