基於混沌粒子群優化的航空發動機多參數預測模型

Multi-Parameter Prediction Model of the Aeroengine Based on Chaos Particle Swarm Optimization

牛偉(Wei Niu) ； 成娟(Juan Cheng) ； 王國慶(Guo-Ging Wang) ； 翟正軍(Zheng-Jun Zhai)

《航空太空及民航學刊.系列B》 44卷1期 (2012/04) Pp. 43-48

https://doi.org/10.6124/JAAA.201204_44(1).05

摘要

隨著武器裝備結構的複雜性、運行環境的獨特性和故障類型的多元性，故障預測變得愈發困難，針對當前主要的故障預測方法在實際故障預測中雖取得了一定的效果，但均存在不足之處。在GM（1,1）模型中，從離散形式到白化形式的轉變，以及GM（1,1）模型預測穩定性問題，一直困擾著灰色系統理論的研究者。本文以此為研究出發點，從由離散到離散的角度解決這一理論問題，進一步分析了離散灰色模型建模中的不足，考慮多個特徵參數間的相互關係以及預測序列的實際特點，基於混沌粒子群優化方法重構了初始基值，建立了小樣本情況下的自適應多參數預測模型。並以某型號飛機發動機的資料為例進行了預測分析，結果表明該模型具有很高的實用性和準確性。

關鍵字

GM(1,1)模型 ； 離散灰色理論 ； 多參數 ； 初始值 ； 混沌粒子群

並列摘要

The fault prediction of weapon is getting more difficult for its complex structure, unique operating environment and multi-plicate faults. Currently although the main fault prediction methods have achieved certain success in practical application, they all fall short in some aspects. In grey forecasting model, the theoretical basis of transformation from discrete form to continuous form and the forecasting stability, which puzzled those who are absorbed in grey theory. Many scholars used all kinds of methods to revise the model, and they have made some progress, but they didn't solve it absolutely in principle. Based on the discrete grey prediction theory and with an analysis of the disadvantages of the discrete grey model, an adaptive prediction model with several characteristic parameters for small samples is proposed. This model reconstructs the initial value based on chaos particle swarm optimization and takes into account the interrelations of the parameters and characteristics of prediction series. The data of a certain aeroengine are taken as an example for prediction and analysis, and the results showed that the model had high availability and precision.

並列關鍵字

GM(1,1) model ； Discrete grey theory ； Multi-parameter ； The initial value ； Chaos particle swarm