Telemetry Rare Event Detection Using Dynamic Temporal Limits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The sheer volume of telemetry data from vehicles complicates processing and analysis, making it difficult for operators to identify potential issues before they escalate into hardware damage or mission failure, particularly in environments where manual intervention is not feasible.
Innovation Solution
A rare event detection system that calculates dynamic limits based on historical time-series data to identify anomalies early, using a segmentation pattern and machine learning techniques to detect rare events before they occur, providing operators with additional time to intervene.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional telemetry data processing methods are used, then all telemetry data can be collected, but the sheer volume of data complicates processing and analysis, making it difficult to identify potential issues
Solution Approach 1:
The patent segments the incoming telemetry stream into multiple temporal segments based on a temporal segmentation pattern derived from historical data. Each segment is then independently analyzed against dynamic limits, transforming the complex task of analyzing the entire large-volume data stream into simpler, manageable segment-level comparisons.
Solution Approach 2:
The system performs preliminary actions by pre-calculating the temporal segmentation pattern and dynamic limits from historical telemetry data before analyzing the incoming stream. This preparation work enables faster, more efficient real-time detection without requiring complex processing during the actual monitoring phase.
2Reliability
If manual monitoring of telemetry data is performed, then operators can identify issues, but the sheer amount of data makes it difficult for operators to readily address issues buried in the telemetry streams
Solution Approach 1:
The system performs self-service by automatically detecting rare events and generating alerts without requiring manual inspection of the vast telemetry data. The automated rare event detector continuously monitors the incoming stream, compares segments against dynamic limits, and identifies anomalies, freeing operators from manually sifting through large volumes of data and enabling faster response to critical issues.
3Reliability
If static thresholds are used for anomaly detection, then the detection process is simple, but static thresholds generate false positives and fail to adapt to changing operational conditions
Solution Approach 1:
The patent implements dynamic limits for each temporal segment that adapt to changing operational conditions. Instead of using fixed static thresholds, the system calculates time-varying dynamic limits based on the temporal segmentation pattern and historical data, allowing the detection criteria to evolve with different vehicle operational phases while maintaining high detection accuracy and reducing false positives.
Solution Approach 2:
The system changes the detection parameters by using dynamic limits that vary over time rather than static thresholds. The temporal segmentation pattern and corresponding dynamic limits are derived from historical telemetry data, allowing the detection parameters to automatically adjust to different operational conditions, vehicle states, and environmental factors throughout the mission.
Data Source
AI summary
A rare event detector can calculate a temporal segmentation pattern based on historical time-series data of historical telemetry streams from a first time period. The temporal segmentation pattern includes historical temporal segments. The system can identify sets of predicted events associated with the historical temporal segments based on the historical telemetry streams. The system can calculate dynamic limits for the respective historical temporal segments based on the shapes. The system can identify a set of active temporal segments of an incoming telemetry stream that correspond to a subset of the historical temporal segments. The active temporal segments are from a second time period after the first time period. The system can detect a rare event for an active temporal segment of the set of active temporal segments in response to the incoming telemetry stream exceeding the dynamic limits for a historical temporal segment corresponding to the active temporal segment.