Enhanced vehicle fuel quantity indication system
AssigneeRockwell Collins, Inc.
InventorsDarin M. Underwood, D. Mark Fejfar
Life of this patent
Estimating the term…
Abstract
A fuel quantity indicator system (FQIS) for an aircraft or other vehicle includes memory/data storage and a fuel quantity processing unit (FQPU). A neural network trained via machine learning and running on the FQPU receives fuel quantity (FQ) inputs from fuel tank sensors, e.g., tank density, fuel volume, water presence within the tank, at or near a given measurement time. The neural network additionally receives fuel flow (FF) inputs from flow sensors at the measurement time, indicating fuel flow to engines and auxiliary power units (APU) of the vehicle. Based on the FQ inputs and the FF inputs, the neural network calculates an estimated fuel quantity (EFQ) remaining, e.g., across all fuel tanks at or near a particular measurement time.
Claims17
A fuel quantity indicator system (FQIS) for a vehicle, comprising:
- a memory configured for storing processor-executable encoded instructions;
- a fuel quantity processing unit (FQPU) comprising one or more processors communicatively coupled with the memory and configurable by the encoded instructions;
- at least one neural network configured for execution on the FQPU and trained via one or more machine learning algorithms to:
- receive one or more fuel quantity (FQ) inputs from at least one FQ sensor associated with a fuel tank of a plurality of fuel tanks of the vehicle and with a measurement time, the one or more FQ inputs comprising at least one of:
- a tank density;
- a fuel volume;
- or
- a tank water content;
- receive one or more fuel flow (FF) inputs from at least one fuel flow sensor associated with the vehicle and with the measurement time, each fuel flow sensor corresponding to at least one of:
- an engine of the vehicle;
- or
- an auxiliary power unit (APU) of the vehicle;
- and
- based on the one or more FQ inputs and the one or more FF inputs, calculate an estimated fuel quantity (EFQ) corresponding to the plurality of fuel tanks and to the measurement time.
A vehicle-based method for fuel quantity monitoring, the method comprising:
- receiving, via a neural network running on a fuel quantity processor unit (FQPU) of a vehicle, at least one fuel quantity (FQ) input associated with a measurement time and sensed by one or more FQ sensors, each FQ sensor associated with at least one fuel tank of a plurality of fuel tanks of the vehicle;
- receiving, via the neural network, at least one fuel flow (FF) input associated with the measurement time and sensed by one or more fuel flow sensors, each fuel flow sensor associated with at least one of an engine of the vehicle or an auxiliary power unit (APU) of the vehicle;
- and
- calculating, via the neural network and based on the at least one FQ input and the at least one FF input, an estimated fuel quantity (EFQ) corresponding to the plurality of fuel tanks and to the measurement time.
Dependencies are inferred from the claim text.