Aircraft Fuel Quantity Prediction Using Orientation Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current aircraft fuel gauging systems rely on capacitance measurements and are prone to inaccuracies due to factors like aircraft orientation and non-fuel system states, which can lead to incorrect fuel quantity estimation and potential system faults.
Innovation Solution
A processor-based monitoring apparatus that receives and processes information on fuel parameters, fuel system configuration, aircraft orientation, and non-fuel system states, using machine learning algorithms to predict fuel quantity independently of primary gauging systems and detect potential faults.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If capacitance measurements from probes are used to estimate fuel quantity, then fuel gauging can be implemented, but measurement accuracy deteriorates due to aircraft orientation and non-fuel system states
Solution Approach 1:
The system segments the fuel measurement problem into multiple independent measurement sources: capacitance measurements from multiple probes, fuel level sensor outputs, and measurements of physical attributes (temperature, density, permittivity). Each measurement type is processed separately and then integrated to compensate for the limitations of individual methods, particularly regarding aircraft orientation effects.
Solution Approach 2:
The monitoring apparatus performs multiple functions: it processes capacitance measurements, integrates fuel level sensor data, measures physical attributes of fuel, compensates for aircraft orientation effects, and detects system faults. This multi-functional approach allows a single system to address various sources of measurement error and provide accurate fuel quantity estimation under diverse operating conditions.
2Measurement precision
If multiple data sources are integrated to improve fuel quantity accuracy, then measurement precision improves, but device complexity increases
Solution Approach 1:
The system merges multiple data sources (capacitance measurements from multiple probes, fuel level sensor outputs, physical attribute measurements, and aircraft orientation data) into a unified fuel quantity estimation. By combining these diverse measurements and processing them through an integrated monitoring apparatus, the system achieves accurate fuel quantity prediction while managing complexity through systematic data integration.
Solution Approach 2:
The monitoring apparatus acts as an intermediary that receives and processes data from various sensors and systems, then generates corrected fuel quantity estimates. This intermediary processing layer integrates information from capacitance probes, level sensors, and physical attribute measurements while compensating for orientation effects, providing a unified accurate output without requiring direct complex interactions between all sensor components.
3Reliability
If traditional fuel gauging systems are used, then fuel quantity can be monitored, but fault detection capability is insufficient
Solution Approach 1:
The system implements feedback by continuously monitoring multiple parameters (capacitance measurements, fuel level sensor outputs, physical attributes) and comparing them against expected relationships. When discrepancies are detected that indicate potential faults in the fuel system or non-fuel systems affecting measurement accuracy, the monitoring apparatus generates indications to alert operators, enabling timely fault detection and correction.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution provides accurate fuel quantity predictions and fault detection, enhancing fuel management and system reliability by integrating diverse data sources and machine learning for improved accuracy and fault identification.
Implementation Method 1
the processor is configured to use a machine learning algorithm to generate the prediction
Implementation Method 2
Fuel gauging systems in commercial aircraft typically estimate the current quantity of fuel in a given tank on the aircraft based on capacitance measurements from probes distributed around the tank
Data Source
AI summary
An aircraft fuel system monitoring apparatus is disclosed having a processor configured to receive first information indicative of one or more parameters relating to fuel present in an aircraft; receive second information relating to the configuration of a fuel system of the aircraft; receive third information indicative of an orientation of the aircraft; receive fourth information indicative of a state of one or more non-fuel-related systems of the aircraft; and generate a prediction of a quantity of fuel present in the aircraft based on the received first information, the received second information, and one or both of the received third information and the received fourth information.