POD算法在飞机RAT舱温度预测中的应用研究  

Application of POD algorithm for temperature prediction in aircraft RAT bay

作　　者：洪烨 杨溢炜 刘虔 浦程楠 HONG Ye;YANG Yiwei;LIU Qian;PU Chengnan(Electronic Control Integration Institute,Shanghai Aircraft Design and Research Institute,Shanghai 201210,China)

机构地区：[1]上海飞机设计研究院电控集成所,上海201210

出　　处：《航空工程进展》2024年第1期127-134,共8页Advances in Aeronautical Science and Engineering

摘　　要：冲压空气涡轮(RAT)系统是飞机的应急发电系统,在飞机失去主交流电源后为飞机供电,RAT平时回收在非气密区的RAT舱内,在应急工况下释放到气流中。RAT舱温度很大程度上决定了RAT的释放时间,进而影响飞机在应急工况下的安全性,RAT舱的温度预测对于应急供电下的安全性具有重要意义。通过本征正交分解(POD)将RAT舱温度与高度、大气静温、飞行速度、RAT舱周围舱温度作为模型整体进行统一分析,并通过RAT舱温度简化模型及简化模型与完整模型的映射关系,选取试验数据作为样本数据,利用POD算法进行RAT舱温度预测。结果表明:1阶模态占据所有模态的比重超过99%,归一化处理后预测结果的平均绝对误差最小可达到0.063,均方根误差最小达到0.07;POD算法可以在样本数据基础上,通过模态重构有效预测RAT舱的温度信息。Ram air turbine(RAT)system is the emergency power generation system of the aircraft.It supplies power to the aircraft after the main AC power of the aircraft is cut off.RAT is stowed in the RAT bay in the non air tight area normally and deployed into the air flow under emergency conditions.The temperature of the RAT bay determines the deploy time of the RAT,thus affects the safety of the aircraft under emergency conditions.The temperature prediction of the RAT bay is of significance for the safety under emergency condition.The temperature,altitude,atmospheric static temperature,flight speed,and cabin temperatures around the RAT bay are analyzed as a whole through the proper orthogonal decomposition(POD),the POD algorithm is used to predict the temperature of the RAT bay.The results show that the energy distribution of the first order mode exceeds 99%of energy of all modals.After data normalization,the mean absolute error of the prediction results could reach 0.063 as the minimum,and the root square mean error could reach 0.07 as the minimum.The POD algorithm can effectively predict the temperature information of RAT bay through modal reconstruction based on the sample data.

关 键 词：本征正交分解 冲压空气涡轮舱 温度预测 模态分析 

分 类 号：V216.51[航空宇航科学与技术—航空宇航推进理论与工程] V242