Flight Data Anomaly Detection Using Local Outlier Factor
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current flight data analysis methods rely on predetermined thresholds and are limited in identifying anomalies across multiple flights and phases, missing potential issues that do not exceed individual parameter thresholds, and require extensive human expertise to analyze large datasets.
Innovation Solution
A computer-implemented method using the local outlier factor (LOF) algorithm to map flight data into a multi-dimensional space, allowing for the identification of anomalous data points without predefined thresholds, by calculating outlier scores based on spatial variation and local density, and adjusting sensitivity through statistical distribution calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional flight data analysis methods using predetermined thresholds are used, then the analysis process is simple and easy to implement, but the ability to identify anomalies is limited and many potential issues are missed
Solution Approach 1:
The patent transforms the analysis approach by changing from fixed threshold parameters to dynamic statistical parameters. Instead of comparing individual flight data points against predetermined thresholds, the system calculates statistical parameters (mean, standard deviation) from multiple flights and uses these to dynamically determine anomaly thresholds, significantly improving detection accuracy
Solution Approach 2:
The patent creates a universal anomaly detection system that can identify anomalies across different flight phases and multiple flights simultaneously. The statistical parameter comparison method is applicable to various flight conditions and parameters, making the system multi-functional rather than requiring separate threshold settings for each scenario
2Reliability
If analysis is performed on large quantities of flight data from multiple flights, then more anomalies can be detected, but the analysis time and computational resources increase significantly
Solution Approach 1:
The patent segments the large dataset by dividing flights into different phase segments (takeoff, climb, cruise, descent, landing). This segmentation allows the system to process and compare data within each phase separately, reducing the computational burden while maintaining detection reliability across the entire flight
3Ease of operation
If predetermined thresholds are used for each flight parameter, then the analysis method is straightforward, but anomalies that do not exceed individual thresholds are missed
Solution Approach 1:
The patent merges multiple flight data points across different flights and phases into a unified statistical analysis. By combining data and calculating overall statistical parameters, the system can detect anomalies that represent deviations from the norm even when individual parameter thresholds are not exceeded, thus improving sensitivity while maintaining operational simplicity
Data Source
AI summary
A computer implemented method of identifying anomalous flight data is provided. The method comprises: receiving a plurality of flight data units in a time series from each of a plurality of different flights, wherein each flight data unit comprises a value for each of a plurality of flight parameters at the same time point; mapping the flight data units as respective data points to a multi-dimensional space, wherein the dimensions of the multi-dimensional space comprise a dimension for each of the plurality of flight parameters; and identifying one or more anomalous flight data units in the received plurality of flight data units by applying a local outlier factor algorithm to the mapped flight data units. A method of maintaining an aircraft, a flight data analyzer, a computer program and a computer-readable storage medium is also provided.