Aircraft Sensor Data Clustering for Air-to-Ground Traffic Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Commercial aircraft often face limitations in transmitting health-related information due to limited radio frequency (RF) bandwidth, leading to incomplete insight into aircraft operations, as only critical sensor data is communicated, while other data is stored locally for later retrieval during maintenance.
Innovation Solution
An equipment monitoring system (EMS) processes sensor data using a multivariate time-series data clustering algorithm to identify operational states, reducing the need for real-time transmission of vast sensor data by communicating operational state information instead, which is determined through training data from multiple flights with appended buffer data to establish consistent clustering.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If all sensor data is transmitted from aircraft to ground control system, then complete insight into aircraft operations is achieved, but RF bandwidth requirements exceed system capabilities
Solution Approach 1:
The patent extracts and transmits only the essential operational state information (cluster labels) from the complete sensor data, separating the critical health monitoring information from the voluminous raw sensor measurements. This allows complete operational insight to be achieved through transmission of minimal data subsets.
Solution Approach 2:
The system creates simplified copies of the operational data in the form of cluster labels that represent complex sensor patterns. These compact representations capture the essential operational states without requiring transmission of the full sensor datasets, enabling complete monitoring with minimal bandwidth.
2Quantity of substance
If only critical sensor data is transmitted, then RF bandwidth constraints are satisfied, but insight into aircraft operations becomes incomplete
Solution Approach 1:
The patent transforms the data representation from raw sensor values to clustered operational states, changing the parameter space from continuous sensor measurements to discrete operational categories. This transformation enables comprehensive monitoring while transmitting minimal data, as cluster labels efficiently encode complex operational patterns.
3Loss of information
If extensive sensor data is stored locally on aircraft, then complete operational data is preserved, but memory requirements increase significantly
Solution Approach 1:
The system extracts only the essential operational state identifiers (cluster labels) from the complete sensor datasets, storing and transmitting minimal data representations. This extraction approach preserves complete operational information while requiring minimal onboard memory capacity.
4Device complexity
If clustering is performed without buffer data appending, then processing is simpler, but clustering consistency across multiple flights deteriorates
Solution Approach 1:
The system performs preliminary actions by appending buffer data to training datasets before clustering, preparing the data in advance to ensure consistent clustering results across multiple flights. This preliminary data preparation stabilizes the clustering process without significantly increasing processing complexity during operation.
Data Source
AI summary
A method includes receiving, by an equipment monitoring system (EMS), first training data and second training data from a plurality of sensors of an article over a first operating interval and over a second operating interval of the article, respectively, appending buffer data to the first training data, and the second training data to the buffer data to provide extended training data, and clustering the extended training data into a plurality of data clusters associated with operational states of the article. Subsequent to clustering, the EMS receives operational data associated with the plurality of sensors of the article over a third operating interval. The EMS determines a particular data cluster of the plurality of data clusters to which the operational data belongs, and communicates data indicative of an operational state of the article associated with the particular data cluster to a control system.