Recent Advances in Anomaly Detection Methods Applied to Aviation

Basora, Luis; Olivé, Xavier; Dubot, Thomas

doi:10.3390/aerospace6110117

Cited by 112 publications

(42 citation statements)

References 96 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The increasing availability of large volumes of sensor data generated daily by aircraft in flight calls for technologies to make the best of recent progresses made in the field of machine learning (ML) and anomaly detection [1]. This data can be exploited by algorithms in order to extract patterns or anomalies to be linked with the degradation of the system.…”

Section: Introductionmentioning

confidence: 99%

Aircraft Fleet Health Monitoring with Anomaly Detection Techniques

et al. 2021

Self Cite

View full text Add to dashboard Cite

Predictive maintenance has received considerable attention in the aviation industry where costs, system availability and reliability are major concerns. In spite of recent advances, effective health monitoring and prognostics for the scheduling of condition-based maintenance operations is still very challenging. The increasing availability of maintenance and operational data along with recent progress made in machine learning has boosted the development of data-driven prognostics and health management (PHM) models. In this paper, we describe the data workflow in place at an airline for the maintenance of an aircraft system and highlight the difficulties related to a proper labelling of the health status of such systems, resulting in a poor suitability of supervised learning techniques. We focus on investigating the feasibility and the potential of semi-supervised anomaly detection methods for the health monitoring of a real aircraft system. roposed methods are evaluated on large volumes of real sensor data from a cooling unit system on a modern wide body aircraft from a major European airline. For the sake of confidentiality, data has been anonymized and only few technical and operational details about the system had been made available. We trained several deep neural network autoencoder architectures on nominal data and used the anomaly scores to calculate a health indicator. Results suggest that high anomaly scores are correlated with identified failures in the maintenance logs. Also, some situations see an increase in the anomaly score for several flights prior to the system’s failure, which paves a natural way for early fault identification.

show abstract

Section: Introductionmentioning

confidence: 99%

Aircraft Fleet Health Monitoring with Anomaly Detection Techniques

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, Hegde and Rokseth [9] have conducted a survey of ML applications to engineering risk assessment. However, prior studies have mostly used machine learning techniques to perform retrospective analyses of flight data records to detect anomalies during routine operations [10][11][12][13][14][15][16][17]. In all these anomaly detection approaches, identification of precursors or causal factors is conducted a-posteriori by SME analysis.…”

Section: Introductionmentioning

confidence: 99%

Critical Parameter Identification for Safety Events in Commercial Aviation Using Machine Learning

et al. 2020

View full text Add to dashboard Cite

In recent years, there has been a rapid growth in the application of data science techniques that leverage aviation data collected from commercial airline operations to improve safety. This paper presents the application of machine learning to improve the understanding of risk factors during flight and their causal chains. With increasing complexity and volume of operations, rapid accumulation and analysis of this safety-related data has the potential to maintain and even lower the low global accident rates in aviation. This paper presents the development of an analytical methodology called Safety Analysis of Flight Events (SAFE) that synthesizes data cleaning, correlation analysis, classification-based supervised learning, and data visualization schema to streamline the isolation of critical parameters and the elimination of tangential factors for safety events in aviation. The SAFE methodology outlines a robust and repeatable framework that is applicable across heterogeneous data sets containing multiple aircraft, airport of operations, and phases of flight. It is demonstrated on Flight Operations Quality Assurance (FOQA) data from a commercial airline through use cases related to three safety events, namely Tire Speed Event, Roll Event, and Landing Distance Event. The application of the SAFE methodology yields a ranked list of critical parameters in line with subject-matter expert conceptions of these events for all three use cases. The work concludes by raising important issues about the compatibility levels of machine learning and human conceptualization of incidents and their precursors, and provides initial guidance for their reconciliation.

show abstract

“…Autoencoder learns a compressed input representation, which is recommended for the high dimensional data collected from smart home. Therefore, the motivation to select our deep learning models is due to their high performance accuracy in terms of abnormal behavior detection in different research areas [12,13].This property is of great importance in smart homes in order to understand people's behaviors, which change over time and particularly any deviations from normal execution of activities of daily living.In this paper, we investigate this variety of deep learning models such as LSTM, CNN, CNN-LSTM and Autoencoder-CNN-LSTM to identify and predict elderly people's abnormal behaviors. The rationale of using deep learning models is fourfold: (1) the models are capable of handling multivariate sequential time-series data, (2) they can identify and accurately predict abnormal behavior in time-series data [14,15] and (3) they can automatically extract temporal and spatial features, from massive time-series data, making it easily generalizable to other types of data and (4) minimizing computation time.Therefore, the contributions of our paper can be summarized as follows:…”

mentioning

confidence: 99%

mentioning

confidence: 99%

Spatio-Temporal Abnormal Behavior Prediction in Elderly Persons Using Deep Learning Models

Zerkouk

Chikhaoui

2020

Sensors

View full text Add to dashboard Cite

The ability to identify and accurately predict abnormal behavior is important for health monitoring systems in smart environments. Specifically, for elderly persons wishing to maintain their independence and comfort in their living spaces, abnormal behaviors observed during activities of daily living are a good indicator that the person is more likely to have health and behavioral problems that need intervention and assistance. In this paper, we investigate a variety of deep learning models such as Long Short Term Memory (LSTM), Convolutional Neural Network (CNN), CNN-LSTM and Autoencoder-CNN-LSTM for identifying and accurately predicting the abnormal behaviors of elderly people. The temporal information and spatial sequences collected over time are used to generate models, which can be fitted to the training data and the fitted model can be used to make a prediction. We present an experimental evaluation of these models performance in identifying and predicting elderly persons abnormal behaviors in smart homes, via extensive testing on two public data sets, taking into account different models architectures and tuning the hyperparameters for each model. The performance evaluation is focused on accuracy measure.However, dependent persons are often exposed to problems of various types that may cause them to perform activities of daily living incorrectly. Detecting abnormal behaviors is thus of great importance for dependent people, in order to ensure that activities are performed correctly without errors [5]. This will also ensure their safety and well-being.Detecting an anomaly in a person's activities of daily living (ADL) is usually done by detecting nonconformities with their usual ADL patterns. Various authors have used classical machine learning algorithms to achieve this [6,7]. Tele-health care requires systems with high accuracy, low computational time and minimal user intervention because data are becoming larger and more complex [8]. Deep learning architectures provide a way to automatically extract useful and meaningful spatial and temporal features from raw data without the need for data labeling, which is time consuming, complex and error prone [9,10]. This makes deep learning models easily generalizable to different contexts. LSTM is a powerful deep learning model for sequence prediction and anomaly detection in sequential data [11]. The LSTM model is able to extract temporal features with long-term relationships. CNN has powerful spatial feature extraction capabilities and the ability to detect abnormality, which is considered as a classification problem. The advantage in the use of CNN with LSTM is to combine their capabilities in terms of spatial and temporal features extraction. Autoencoder learns a compressed input representation, which is recommended for the high dimensional data collected from smart home. Therefore, the motivation to select our deep learning models is due to their high performance accuracy in terms of abnormal behavior detection in different research areas [12,13].This propert...

show abstract

Recent Advances in Anomaly Detection Methods Applied to Aviation

Cited by 112 publications

References 96 publications

Aircraft Fleet Health Monitoring with Anomaly Detection Techniques

Aircraft Fleet Health Monitoring with Anomaly Detection Techniques

Critical Parameter Identification for Safety Events in Commercial Aviation Using Machine Learning

Spatio-Temporal Abnormal Behavior Prediction in Elderly Persons Using Deep Learning Models

Contact Info

Product

Resources

About