基于GM(1,1)背景值重构的可靠性预测模型

Reliability Prediction Model Based on GM(1,1) Background Value Reconstruction

分析GM(1,1)模型,提出用复化Cotes公式和牛顿插值法重构GM(1,1)背景值,并对改进模型模拟精度进行检验,与传统梯形公式构造背景值的预测模型相比,改进模型从1次代数精度优化到6阶收敛并且无明显震荡现象产生.将改进的GM(1,1)模型运用到某部件的腐蚀寿命预测中,理论分析与应用实例都说明本文提出的改进方法具有有效性.

Analysis the GM(1,1)model,the background value is reconstructed by the complex cotes formula and newton interpolation method.The simulation model accuracy is tested and compared with the traditional trapezoidal formula to construct the background value prediction model.In comparison,the improved model is generated from 1 algebraic precision optimization to 6 th order convergence without significant oscillation.The improved GM(1,1)model is applied to the corrosion life prediction of a component.The theoretical analysis and application examples show that the improved method proposed in this paper is effective.