High Frequency Sensor Data Integration for Aircraft Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Integrated Vehicle Health Management systems are inadequate in processing and analyzing high-frequency sensor data, leading to inefficiencies in diagnosing equipment failures and degradation in complex systems like vehicles, and are costly to maintain due to high false alarm rates and the need for frequent software and hardware upgrades.
Innovation Solution
A method that integrates high-frequency sensor data with low-frequency sensor data using a Model-Based Reasoner engine, which processes and analyzes sensor information from various sources, including high-frequency sensors, to identify anomalies and provide real-time diagnostic analysis, reducing false alarms and maintenance costs by using a physics-based approach and XML model configuration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If high-frequency sensor data is processed and integrated with low-frequency sensor data, then diagnostic accuracy and system reliability are improved, but device complexity and processing requirements increase
Solution Approach 1:
The patent segments sensor data processing by frequency characteristics, separating high-frequency sensor data processing from low-frequency sensor data processing. This allows the system to handle different data types with appropriate methods, improving diagnostic accuracy while managing complexity through modular architecture.
Solution Approach 2:
The patent adds a frequency dimension to sensor data processing, organizing data along the frequency spectrum rather than treating all sensor data uniformly. This dimensional organization enables more efficient processing and integration of diverse sensor inputs, balancing reliability improvement with complexity management.
2Ease of manufacture
If rules-based diagnostic approaches are used, then implementation is simple, but false alarm rates increase and effectiveness decreases
Solution Approach 1:
The patent replaces traditional rules-based diagnostic approaches with a model-based reasoning system that uses physics-based models and mathematical relationships. This substitution improves diagnostic effectiveness and reduces false alarms by using fundamental physical principles rather than empirical rules, while maintaining implementation feasibility through structured modeling approaches.
3Loss of energy
If traditional sensor processing methods are used, then processing cost is low, but high-frequency sensor data cannot be adequately handled
Solution Approach 1:
The patent introduces dynamic processing capabilities that adapt to the frequency characteristics of sensor data. The system dynamically adjusts processing methods based on whether data is high-frequency or low-frequency, enabling adequate handling of high-frequency data while managing processing costs through selective application of appropriate processing techniques.
Data Source
AI summary
A method implemented by a computing system identifies anomalies that represents potential off-normal behavior of components on an aircraft based on data from sensors during various modes of operations including in-flight operation of the aircraft. High-frequency sensor outputs monitor performance parameters of respective components. Anomaly criteria is dynamically selected and the high-frequency sensor outputs are compared with the anomaly criteria where the comparison results determine whether potentially off-normal behavior exists. A conditional anomaly tag is inserted in the digitized representations of first high-frequency sensor outputs where the corresponding comparison results indicate potentially off-normal behavior. At least the digitized representations of the first high-frequency sensor outputs containing the conditional anomaly tag are sent to a computer-based diagnostic system for a final determination of whether the conditional anomaly tag associated with the respective components represents off-normal behavior for the respective components.