飞机机电系统关键部件性能趋势分析方法  

Application of Combinatorial Prediction in Status Trend Analysis of Aircraft Generators

作　　者：崔建国 徐昕明 于明月 蒋丽英 CUI Jian-guo;XU Xin-ming;YU Ming-yue;JIANG Li-ying(School of Automation,Shenyang Aerospace University,Lianning Shenyang110136,China;Aviation Key Laboratory of Science and Technology on Fault Diagnosis and Health Management,Shanghai 201601,China)

机构地区：[1]沈阳航空航天大学自动化学院,辽宁沈阳110136 [2]航空工业上海航空测控技术研究所故障诊断与健康管理技术航空科技重点实验室,上海201601

出　　处：《机械设计与制造》2020年第8期184-187,共4页Machinery Design & Manufacture

基　　金：国家自然科学基金(51605309);航空科学基金(20153354005);航空科学基金(20163354004)。

摘　　要：飞机发电机作为飞机机电系统的关键部件之一,为飞机提供主要的电力来源,其运行状态在飞机的使用过程中至关重要。为改善和提升飞机发电机的性能变化趋势的预测精度,更好实现对飞机发电机性能变化的趋势分析,以某型真实飞机发电机为研究对象,提出一种由多项式趋势预测模型和ARMA模型相结合的组合预测方法来对该型飞机发电机进行性能趋势分析。首先,在专业试验平台上对该型飞机发电机进行了长期大量试验,获取了大量性能表征信息。在此基础上,将多项式趋势预测模型和ARMA模型进行组合,综合运用多项式趋势预测模型良好的趋势拟合能力和ARMA的时间序列分析功能,对该型飞机发电机进行性能趋势分析。试验验证结果表明,这种组合预测方法优于传统单一模型的预测方法,具有很高的预测精度,能够更好地实现对飞机发电机的性能趋势分析效能,具有较高的工程应用价值。As one of the key components of an aircraft’s electromechanical system,the Aircraft generator provides the main source of electricity for the aircraft and its operational status is of crucial importance in the aircraft’s use. In order to improve the prediction accuracy of the performance of the aircraft generator and better realize the trend analysis of the aircraft generator performance,taking a real aircraft generator as a research object,a combinational prediction method based on polynomial trend prediction model and ARMA model is proposed to analyze the performance trend of the aircraft generator.First of all,on the professional test platform for a long time a large number of aircraft test generator,access to a large number of performance characterization information. Based on this,the polynomial trend prediction model and the ARMA model are combined. Based on the trend fitting ability of the polynomial trend prediction model and the time series analysis function of ARMA,the performance trend of the aircraft generator is analyzed. The experimental results show that the combined prediction method is superior to the traditional single model prediction method and has a high prediction accuracy,which can better realize the performance trend analysis efficacy of the aircraft generator and has high engineering application value.

关 键 词：飞机发电机 多项式趋势预测 ARMA 组合预测 性能趋势 

分 类 号：TH16[机械工程—机械制造及自动化] TH17