MSCNN-LSTM method for monitoring the state of horizontal stabilizer system


	based on flight data

Abstract

Abstract:

To address the problems of insufficient fault samples, imbalanced data classes and lack of labeling in real flight data, a state monitoring method for a horizontal stabilizer system based on multi-scale convolutional neural network

(MSCNN) and long short-term memory (LSTM) network is proposed in this paper. This method does not rely on labeled data and uses unsupervised learning to monitor the state of the horizontal stabilizer system. Firstly, the quick

access recorder (QAR) data of the system in normal operation are extracted in both spatial and temporal dimensions

using MSCNN-LSTM to achieve rudder position prediction. Secondly, the residuals between the predicted and actual values of the rudder position are calculated and the distribution of the residuals is analyzed to determine the

threshold for the health state of the system. Finally, the QAR data of an aircraft is used for verification, and the experimental results show that the proposed method in this paper can accurately achieve the abnormal state identification of the horizontal stabilizer system at the flight level and can provide an abnormal alarm one flight cycle in

advance when system failure occurring.

Key words:

flight data, MSCNN-LSTM, horizontal stabilizer, state monitoring, unsupervised learning

CLC Number:

TP181

ZHANG Penga , HU Fangyub , DUAN Zhaobina , LIU Jingjingb.

MSCNN-LSTM method for monitoring the state of horizontal stabilizer system

based on flight data

[J]. Journal of Civil Aviation University of China, 2025, 43(1): 60-66.

References 20

[1]	房冠成, 贾大鹏, 刘毅飞, 等．基于飞行参数数据挖掘的军机健康评
	估技术[J]．航空学报, 2020, 41(6): 289-299．
	[2]
	ZHAO W Z, LI L S, ALAM S, et al． An incremental clustering method
	for anomaly detection in flight data[J]． Transportation Research Part C:
	Emerging Technologies, 2021, 132: 103406．
[3]	彭宇, 何永福, 王少军, 等．飞行数据异常检测技术综述[J]．仪器仪
	表学报, 2019, 40(3): 1-13．
[4]	王志刚, 王业光, 杨宁, 等．基于 LSTM 的飞行数据挖掘模型构建
	方法[J]．航空学报, 2021, 42(8): 255-264．
	[5]
	KONG Y X, MAHADEVAN S． Aircraft landing distance prediction: A
	multistep long short-term memory approach[J]． Journal of Aerospace
	Information Systems, 2022, 19(5): 344-354．
[6]	张其霄, 董鹏, 王科文, 等．基于贝叶斯优化 LSTM 的发动机剩余
	寿命预测[J]．火力与指挥控制, 2022, 47(4): 85-89．
	[7]
	FU J M, SUN C, YU Z, et al． A hybrid CNN-LSTM model based actua－
	tor fault diagnosis for six-rotor UAVs[C]//2019 Chinese Control and
	Decision Conference (CCDC), June 3-5, 2019, Nanchang, China． IEEE,
	2019: 410-414．
[8]	段照斌, 杜海龙, 张迪, 等．基于 KPCA 和 ELM 的新型民机舵机
	系统故障诊断[J]．计算机仿真, 2022, 39(1): 25-28, 55．
[9]	白玉轩, 杨建忠, 孙晓哲, 等．基于 GA-BP 的机电作动系统传感器
	故障诊断研究[J]．机床与液压, 2021, 49(15): 188-194．
[10]	QIN H, YANG R F, GUO C X, et al． Fault diagnosis of electric rudder
	system using PSOFOA-BP neural network[J]． Measurement, 2021, 186:
	110058．
[11]	金晓航, 许壮伟, 孙毅, 等．基于 SCADA 数据分析和稀疏自编码
	神经网络的风电机组在线运行状态监测[J]．太阳能学报, 2021, 42(6):
	321-328．
[12]	ZHANG W S, FU J, FU Y L, et al． System performance analysis for
	trimmable horizontal stabilizer actuator focusing on nonlinear effects:
	based on incremental modelling and parameter identification methodol－
	ogy[J]． Sensors, 2021, 21(19): 6464．
[13]	宫淑丽, 马广佑, 邓华佳, 等． QAR 数据飞行级异常检测研究[J]．机
	械设计与制造工程, 2021, 50(10): 68-73．
[14]	KIRANYAZ S, AVCI O, ABDELJABER O, et al． 1D convolutional neu－
	ral networks and applications: a survey[EB/OL]． (2019-05-09)[2023-
	02-10]. http: //arxiv．org/abs/1905.03554.
[15]	段照斌, 刘颖欣． CNN-SVM 在民机升降舵故障诊断中的应用[J]．电
	光与控制, 2021, 28(12): 97-101, 115．
[16]	刘建伟, 宋志妍．循环神经网络研究综述[J]．控制与决策, 2022, 37
(11)	: 2753-2768．
[17]	马敏, 李继伟, 曾田．基于双通道混合网络融合支持向量机的
	电容层析成像流型辨识[J]．电子测量技术, 2022, 45(4): 153-159．
[18]	ZHANG J W, LING Y, FU X B, et al． Model of the intrusion detection
	system based on the integration of spatial-temporal features[J]． Com－
	puters & Security, 2020, 89: 101681．
[19]	ZHONG J, ZHANG Y J, WANG J Y, et al． Unmanned aerial vehicle
	flight data anomaly detection and recovery prediction based on spatiotemporal correlation[J]． IEEE Transactions on Reliability, 2022, 71(1):
	457-468．
[20]	熊斌华, 赵红华, 朱晓炜．基于 WQAR 数据的飞机系统性能监控及
	预测维修[J]．航空维修与工程, 2021(9): 66-69．

MSCNN-LSTM method for monitoring the state of horizontal stabilizer system

based on flight data

Knowledge

Abstract

Cite this article

share this article

References 20

Related Articles 3

Recommended Articles

Metrics

Comments

[1]	DING Jianli, FENG Hao. Multi-Time prediction model of flight transit key nodes time based on GBDT [J]. Journal of Civil Aviation University of China, 2024, 42(6): 27-33.
[2]	XING Zhiwei, WU Zhe, LUO Qian. Dynamic passenger density prediction in baggage claim area for single flight [J]. Journal of Civil Aviation University of China, 2020, 38(5): 35-40.
[3]	XU Meng, XI Zexi, WANG Yongyun, LI Xiaolu. Aero-engine fault diagnosis based on ensemble learning algorithm [J]. , 2019, 37(2): 29-33,42.