Avionics Anomaly Prediction Display for Faulty Sensor Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In aircraft systems, determining reliable data sources during anomalies is challenging, especially when redundant sensors output faulty data, leading to potential safety risks due to increased stress and sub-optimal decision-making by pilots.
Innovation Solution
A method and system that predict and depict avionics data anomalies by receiving time series data, calculating future anomaly thresholds, and displaying this information on a display device, including uncertainty and animation, to enhance pilot situational awareness and reduce surprise reactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If redundant sensors are used to detect anomalies, then reliability of data source identification is improved, but difficulty of detecting and measuring anomalies increases when all sensors output faulty data
Solution Approach 1:
The system performs preliminary actions by continuously monitoring sensor data quality metrics and predicting future anomaly conditions before they occur. The prediction module analyzes current sensor outputs and forecasts when anomalies will develop, allowing pilots to prepare in advance rather than reacting to sudden failures.
Solution Approach 2:
The patent introduces an intermediary prediction module that acts as a mediator between raw sensor data and pilot decision-making. This module processes sensor outputs, predicts anomaly conditions, and presents interpreted information to pilots, bridging the gap between complex sensor data and human comprehension.
2Reliability
If conventional anomaly detection methods are used, then current anomalies are detected, but pilot stress increases due to sudden unexpected anomalies
Solution Approach 1:
The system performs preliminary actions by continuously monitoring sensor data quality metrics and predicting future anomaly conditions before they occur. The prediction module analyzes current sensor outputs and forecasts when anomalies will develop, allowing pilots to prepare in advance rather than reacting to sudden failures.
Solution Approach 2:
The system applies preliminary anti-action by predicting anomaly conditions and alerting pilots before the anomalies occur. This preemptive warning allows pilots to take countermeasures or prepare mentally, reducing the shock and stress of sudden anomalies during critical flight phases.
3Reliability
If redundant sensors are used, then coverage of data sources is improved, but ability to determine reliable source decreases when sensors are frozen or stuck
Solution Approach 1:
The system changes parameters by monitoring multiple data quality metrics including rate of change, variance, and consistency across sensors. When sensors are frozen or stuck, these parameter changes become detectable, allowing the system to identify unreliable sources even when output values appear consistent.
Solution Approach 2:
The patent replaces traditional mechanical comparison methods with sophisticated data analysis algorithms. Instead of simply comparing sensor readings, the system analyzes temporal patterns, rate of change, and statistical properties of sensor outputs to identify frozen or stuck sensors that would be indistinguishable using conventional methods.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods and systems for depicting avionics data anomalies in an aircraft. Time series data is received from the avionics data source, a future time is predicted when a first anomaly threshold will be crossed based on the time series data, and the future time when the first anomaly threshold will be crossed is depicted on a display device associated with the aircraft.