Aircraft Anomaly Detection Using Algorithmic Model and Data Model Trained on FOQA Data

被引:0
|
作者
Megatroika, Alvin [1 ]
Galinium, Maulahikmah [1 ]
Mahendra, Adhiguna [2 ]
Ruseno, Neno [2 ]
机构
[1] Swiss German Univ, Fac Engn & Informat Technol, Bumi Serpong Damai, Indonesia
[2] Aerotrack Pte Ltd, Jakarta, Indonesia
关键词
anomaly detection; algorithmic modeling; data modeling; Self-Organizing Map; One-Class SVM; FOQA; aircraft performance anomaly;
D O I
暂无
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Two models of anomaly detection are put to use in detecting anomalies in aircraft operation. Self-Organizing Map Neural Network (SOM NN) is used from the culture of algorithmic modeling and One-Class Support Vector Machine (SVM) is used from the culture of data modeling. The goal of the research is to find anomalies within the data of aircraft operation or otherwise known as Flight Operations Quality Assurance (FOQA) data, and to find out which model performs better. SOM NN found 8800 data points of anomalies over 69 flights and One-Class SVM found 40392 data points of anomalies over 651 flights. The anomalies are divided into three categories: performance anomaly, sensor anomaly, and miscellaneous anomaly, each happened because of different causes. It is concluded that both models could detect anomalies within FOQA data and the One-Class SVM outperforms SOM NN in number of anomalies found, however in runtime length, SOM NN performs better, the best choice of model is then concluded according to computing resource availability since SOM NN could still be improved without an expensive resource compared to One-Class SVM
引用
收藏
页码:42 / 47
页数:6
相关论文
共 50 条
  • [31] Detection and tracking of RC model aircraft in LWIR microgrid polarimeter data
    Ratliff, Bradley M.
    LeMaster, Daniel A.
    Mack, Robert T.
    Villeneuve, Pierre V.
    Weinheimer, Jeffrey J.
    Middendorf, John R.
    POLARIZATION SCIENCE AND REMOTE SENSING V, 2011, 8160
  • [32] DATA ANOMALY IDENTIFICATION IN COMPLEX STRUCTURES USING MODEL FREE DATA STATISTICAL ANALYSIS
    Lanata, Francesca
    Posenato, Daniele
    Inaudi, Daniele
    PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON STRUCTURE HEALTH MONITORING & INTELLIGENT INFRASTRUCTURE: STRUCTURAL HEALTH MONITORING & INTELLIGENT INFRASTRUCTURE, 2007,
  • [33] Anomaly Detection Using Data Rate of Change on Medical Data
    Rim, Kwang-Cheol
    Yoon, Young-Min
    Kim, Sung-Uk
    Kim, Jeong-In
    CMC-COMPUTERS MATERIALS & CONTINUA, 2024, 80 (03): : 3903 - 3916
  • [34] Data Augmentation Based on Pre-trained Language Model for Event Detection
    Zhang, Meng
    Xie, Zhiwen
    Liu, Jin
    CCKS 2021 - EVALUATION TRACK, 2022, 1553 : 59 - 68
  • [35] A Data-Driven Anomaly Detection Approach for Acquiring Baseline of Aircraft Engine Measurement Data
    Sun, Hao
    Guo, Ying-Qing
    PROCEEDINGS OF THE 36TH CHINESE CONTROL CONFERENCE (CCC 2017), 2017, : 7225 - 7229
  • [36] PUNet: A Semi-Supervised Anomaly Detection Model for Network Anomaly Detection Based on Positive Unlabeled Data
    Long, Gang
    Zhang, Zhaoxin
    CMC-COMPUTERS MATERIALS & CONTINUA, 2024, 81 (01): : 327 - 343
  • [37] Data-Driven Anomaly Detection for UAV Sensor Data Based on Deep Learning Prediction Model
    Wang, Benkuan
    Wang, Zeyang
    Liu, Liansheng
    Liu, Datong
    Peng, Xiyuan
    2019 PROGNOSTICS AND SYSTEM HEALTH MANAGEMENT CONFERENCE (PHM-PARIS), 2019, : 286 - 290
  • [38] Improved Deep Support Vector Data Description Model Using Feature Patching for Industrial Anomaly Detection
    Huang, Wei
    Li, Yongjie
    Xu, Zhaonan
    Yao, Xinwei
    Wan, Rongchun
    SENSORS, 2025, 25 (01)
  • [39] Multiclass Anomaly Detection in Flight Data Using Semi-Supervised Explainable Deep Learning Model
    Memarzadeh, Milad
    Matthews, Bryan
    Templin, Thomas
    JOURNAL OF AEROSPACE INFORMATION SYSTEMS, 2021, 19 (02): : 83 - 97
  • [40] Decision Boundary-Based Anomaly Detection Model Using Improved AnoGAN From ECG Data
    Shin, Dong-Hoon
    Park, Roy C.
    Chung, Kyungyong
    IEEE ACCESS, 2020, 8 : 108664 - 108674