Bleed air system is one of the most important components of air management system(AMS).It acts as transfer pipes responsible for air supply at high temperature and pressure.The thermal and flow performance of the blee...Bleed air system is one of the most important components of air management system(AMS).It acts as transfer pipes responsible for air supply at high temperature and pressure.The thermal and flow performance of the bleed air system is a key issue for the design of AMS since the characteristics of air source have a great influence on the anti-ice system,the environmental control system and other downstream system in need of high temperature pressurized air.Based on the one-dimensional lumped parameter technology,a computer analysis model of bleed air system is developed in order to analyze the thermal and flow behaviors of the nodal points in the pipeline network.The simulation are performed with a given flight assignment using the analysis model,and the results verify that the system meets the design requirements.展开更多
空调热交换器性能异常检测技术是快速判断民机空调系统运行状态并合理安排维修任务的关键,传统的异常检测方法难以有效处理高维时序数据,无法实现系统早期故障预警。为此,本文提出了一种基于长短期记忆网络(LSTM,long-short term memory...空调热交换器性能异常检测技术是快速判断民机空调系统运行状态并合理安排维修任务的关键,传统的异常检测方法难以有效处理高维时序数据,无法实现系统早期故障预警。为此,本文提出了一种基于长短期记忆网络(LSTM,long-short term memory)与自编码器(AE,autoencoder)模型的无监督异常检测方法,用以识别民机空调系统异常运行状态。首先,基于民机空调系统原始传感器参数构建表征空调热交换器性能的特征监测参数;其次,构建LSTM-AE模型进行数据特征重构并计算重构误差;最后,使用孤立森林(iForest, isolation forest)进行无监督异常监测。将本文构建的无监督异常检测方法与传统方法对比,并建立模型评估指标,验证结果表明,所构建的模型方法可以对民机空调热交换器性能异常状态进行有效检测。展开更多
文摘Bleed air system is one of the most important components of air management system(AMS).It acts as transfer pipes responsible for air supply at high temperature and pressure.The thermal and flow performance of the bleed air system is a key issue for the design of AMS since the characteristics of air source have a great influence on the anti-ice system,the environmental control system and other downstream system in need of high temperature pressurized air.Based on the one-dimensional lumped parameter technology,a computer analysis model of bleed air system is developed in order to analyze the thermal and flow behaviors of the nodal points in the pipeline network.The simulation are performed with a given flight assignment using the analysis model,and the results verify that the system meets the design requirements.
文摘空调热交换器性能异常检测技术是快速判断民机空调系统运行状态并合理安排维修任务的关键,传统的异常检测方法难以有效处理高维时序数据,无法实现系统早期故障预警。为此,本文提出了一种基于长短期记忆网络(LSTM,long-short term memory)与自编码器(AE,autoencoder)模型的无监督异常检测方法,用以识别民机空调系统异常运行状态。首先,基于民机空调系统原始传感器参数构建表征空调热交换器性能的特征监测参数;其次,构建LSTM-AE模型进行数据特征重构并计算重构误差;最后,使用孤立森林(iForest, isolation forest)进行无监督异常监测。将本文构建的无监督异常检测方法与传统方法对比,并建立模型评估指标,验证结果表明,所构建的模型方法可以对民机空调热交换器性能异常状态进行有效检测。
