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
Terminal airspace(TMA)is the airspace centering several military and civil aviation airports with complex route structure,limited airspace resources,traffic flow,difficult management and considerable airspace complexi...Terminal airspace(TMA)is the airspace centering several military and civil aviation airports with complex route structure,limited airspace resources,traffic flow,difficult management and considerable airspace complexity.A scientific and rational sectorization of TMA can optimize airspace resources,and sufficiently utilize the control of human resources to ensure the safety of TMA.The functional sectorization model was established based on the route structure of arriving and departing aircraft as well as controlling requirements.Based on principles of sectorization and topological relations within a network,the arrival and departure sectorization model was established,using tree based ant colony algorithm(ACO)searching.Shanghai TMA was taken as an example to be sectorizaed,and the result showed that this model was superior to traditional ones when arrival and departure routes were separated at dense airport terminal airspace.展开更多
Prognostics and Health Management(PHM) has become a very important tool in modern commercial aircraft. Considering limited built-in sensing devices on the legacy aircraft model,one of the challenges for airborne syste...Prognostics and Health Management(PHM) has become a very important tool in modern commercial aircraft. Considering limited built-in sensing devices on the legacy aircraft model,one of the challenges for airborne system health monitoring is to find an appropriate health indicator that is highly related to the actual degradation state of the system. This paper proposed a novel health indicator extraction method based on the available sensor parameters for the health monitoring of Air Conditioning System(ACS) of a legacy commercial aircraft model. Firstly, a specific Airplane Condition Monitoring System(ACMS) report for ACS health monitoring is defined. Then a non-parametric modeling technique is adopted to calculate the health indicator based on the raw ACMS report data. The proposed method is validated on a single-aisle commercial aircraft widely used for short and medium-haul routes, using more than 6000 ACMS reports collected from a fleet of aircraft during one year. The case study result shows that the proposed health indicator can effectively characterize the degradation state of the ACS, which can provide valuable information for proactive maintenance plan in advance.展开更多
The vast potential of system health monitoring and condition based maintenance on modern commercial aircraft is being realized through the innovative use of Airplane Condition Monitoring System(ACMS) data.However ther...The vast potential of system health monitoring and condition based maintenance on modern commercial aircraft is being realized through the innovative use of Airplane Condition Monitoring System(ACMS) data.However there are few methods addressing the issues of failure prognostics and predictive maintenance for commercial aircraft Air Conditioning System(ACS).This study developed a Bayesian failure prognostics approach using ACMS data for predictive maintenance of ACS.First, a health index characterizing the ACS health state is inferred from a multiple sensor signals using a data driven method.Then a dynamic linear model is proposed to describe the degradation process for failure prognostics.Bayesian inference formulas are carried out for degradation estimation and prediction.The developed approach is applied on a passenger aircraft fleet with ACMS data recorded for one year.The analysis of the case study shows that the developed method can produce satisfactory prognostics results, where all the ACS failure precursors are identified in advance, and the relative errors for the failure time prediction made when just entering the degradation warning stage are less than 8%.This would allow operators to proactively plan future maintenance.展开更多
Large-scale cryogenic air separation units(ASUs),which are widely used in global petrochemical and semiconductor industries,are being developed with high operating elasticity under variable working conditions.Differen...Large-scale cryogenic air separation units(ASUs),which are widely used in global petrochemical and semiconductor industries,are being developed with high operating elasticity under variable working conditions.Different from discrete processes in traditional machinery manufacturing,the ASU process is continuous and involves the compression,adsorption,cooling,condensation,liquefaction,evaporation,and distillation of multiple streams.This feature indicates that thousands of technical parameters in adsorption,heat transfer,and distillation processes are correlated and merged into a large-scale complex system.A lumped parameter model(LPM)of ASU is proposed by lumping the main factors together and simplifying the secondary ones to achieve accurate and fast performance design.On the basis of material and energy conservation laws,the piecewise-lumped parameters are extracted under variable working conditions by using LPM.Takagi–Sugeno(T–S)fuzzy interval detection is recursively utilized to determine whether the critical point is detected or not by using different thresholds.Compared with the traditional method,LPM is particularly suitable for“rough first then precise”modeling by expanding the feasible domain using fuzzy intervals.With LPM,the performance of the air compressor,molecular sieve adsorber,turbo expander,main plate-fin heat exchangers,and packing column of a 100000 Nm3 O2/h large-scale ASU is enhanced to adapt to variable working conditions.The designed value of net power consumption per unit of oxygen production(kW/(Nm3 O2))is reduced by 6.45%.展开更多
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。
基金supported by the National Natural Science Foundation of China(Nos.U1233101,71271113)the Fundamental Research Funds for the Central Universities(No.NS2016062)
文摘Terminal airspace(TMA)is the airspace centering several military and civil aviation airports with complex route structure,limited airspace resources,traffic flow,difficult management and considerable airspace complexity.A scientific and rational sectorization of TMA can optimize airspace resources,and sufficiently utilize the control of human resources to ensure the safety of TMA.The functional sectorization model was established based on the route structure of arriving and departing aircraft as well as controlling requirements.Based on principles of sectorization and topological relations within a network,the arrival and departure sectorization model was established,using tree based ant colony algorithm(ACO)searching.Shanghai TMA was taken as an example to be sectorizaed,and the result showed that this model was superior to traditional ones when arrival and departure routes were separated at dense airport terminal airspace.
基金supported by the National Natural Science Foundation of China (61403198)the Jiangsu Province Natural Science Foundation of China (BK20140827)China Postdoctoral Science Foundation (2015M581792)
文摘Prognostics and Health Management(PHM) has become a very important tool in modern commercial aircraft. Considering limited built-in sensing devices on the legacy aircraft model,one of the challenges for airborne system health monitoring is to find an appropriate health indicator that is highly related to the actual degradation state of the system. This paper proposed a novel health indicator extraction method based on the available sensor parameters for the health monitoring of Air Conditioning System(ACS) of a legacy commercial aircraft model. Firstly, a specific Airplane Condition Monitoring System(ACMS) report for ACS health monitoring is defined. Then a non-parametric modeling technique is adopted to calculate the health indicator based on the raw ACMS report data. The proposed method is validated on a single-aisle commercial aircraft widely used for short and medium-haul routes, using more than 6000 ACMS reports collected from a fleet of aircraft during one year. The case study result shows that the proposed health indicator can effectively characterize the degradation state of the ACS, which can provide valuable information for proactive maintenance plan in advance.
基金supported by National Natural Science Foundation of China(91860139)China Postdoctoral Science Foundation(2015M581792)。
文摘The vast potential of system health monitoring and condition based maintenance on modern commercial aircraft is being realized through the innovative use of Airplane Condition Monitoring System(ACMS) data.However there are few methods addressing the issues of failure prognostics and predictive maintenance for commercial aircraft Air Conditioning System(ACS).This study developed a Bayesian failure prognostics approach using ACMS data for predictive maintenance of ACS.First, a health index characterizing the ACS health state is inferred from a multiple sensor signals using a data driven method.Then a dynamic linear model is proposed to describe the degradation process for failure prognostics.Bayesian inference formulas are carried out for degradation estimation and prediction.The developed approach is applied on a passenger aircraft fleet with ACMS data recorded for one year.The analysis of the case study shows that the developed method can produce satisfactory prognostics results, where all the ACS failure precursors are identified in advance, and the relative errors for the failure time prediction made when just entering the degradation warning stage are less than 8%.This would allow operators to proactively plan future maintenance.
基金This work was funded by the National Natural Science Foundation of China(Grant Nos.51775494,51821093,and 51935009)the National Key Research and Development Project(Grant No.2018YFB1700701)Zhejiang Key Research and Development Project(Grant No.2019C01141).
文摘Large-scale cryogenic air separation units(ASUs),which are widely used in global petrochemical and semiconductor industries,are being developed with high operating elasticity under variable working conditions.Different from discrete processes in traditional machinery manufacturing,the ASU process is continuous and involves the compression,adsorption,cooling,condensation,liquefaction,evaporation,and distillation of multiple streams.This feature indicates that thousands of technical parameters in adsorption,heat transfer,and distillation processes are correlated and merged into a large-scale complex system.A lumped parameter model(LPM)of ASU is proposed by lumping the main factors together and simplifying the secondary ones to achieve accurate and fast performance design.On the basis of material and energy conservation laws,the piecewise-lumped parameters are extracted under variable working conditions by using LPM.Takagi–Sugeno(T–S)fuzzy interval detection is recursively utilized to determine whether the critical point is detected or not by using different thresholds.Compared with the traditional method,LPM is particularly suitable for“rough first then precise”modeling by expanding the feasible domain using fuzzy intervals.With LPM,the performance of the air compressor,molecular sieve adsorber,turbo expander,main plate-fin heat exchangers,and packing column of a 100000 Nm3 O2/h large-scale ASU is enhanced to adapt to variable working conditions.The designed value of net power consumption per unit of oxygen production(kW/(Nm3 O2))is reduced by 6.45%.
