Back to results
US 11,615,658 B2Granted
Vehicle fuel tank modeling systems and methods
AssigneeFord Global Technologies, LLC
InventorsHyongju Park, Ben Bulat, Richard Gordon, Arnold Babila
Life of this patent
Estimating the term…
Abstract
Vehicle fuel tank modeling systems and methods are provided herein. An example method includes introducing known volumes of fuel into the fuel tank, determining correlations of fuel level percentage values relative to the known volumes of fuel placed into the fuel tank, offsetting the correlations to compensate for unusable fuel volume of the fuel tank, selecting a non-linear fuel tank model that fits the offset correlations, and applying the non-linear fuel tank model to a target vehicle having a fuel tank with a fuel tank part number.
Claims20
A method, comprising:
- introducing known volumes of fuel into a fuel tank of a first vehicle, wherein the fuel tank of the first vehicle comprises a fuel tank part number;
- determining correlations of fuel level percentage values relative to the known volumes of fuel placed into the fuel tank of the first vehicle;
- offsetting the correlations to compensate for unusable fuel volume of the fuel tank of the first vehicle;
- selecting a non-linear fuel tank model that fits the offset correlations;
- and
- applying the non-linear fuel tank model to a fuel tank comprising the fuel tank part number of a target vehicle,
- wherein generating the fuel tank model comprises determining an estimate of unusable fuel volume left in the fuel tank, the offsetting of the correlations being based on the unusable fuel volume.
4 more elements
A method, comprising:
- emptying a fuel tank of a vehicle;
- determining a fuel level percentage value for the fuel tank when the fuel tank is empty to determine an offset;
- incrementally filling the fuel tank with known volumes of fuel until the fuel tank is full;
- determining correlations between fuel level percentage values and the known volumes of fuel;
- applying the offset to the correlations;
- selecting a non-linear model for the correlations;
- determining a plurality of fuel tank models for a plurality of vehicles that comprise a similar or identical fuel tank to the fuel tank;
- selecting a non-linear model candidate for the fuel tank;
- performing non-linear regression analysis on the fuel level percentage values and the known volumes of fuel using the non-linear model candidate;
- and
- evaluating the non-linear model candidate by determining at least one of a cross-validation error, mean absolute deviation, and/or a model error tolerance.
8 more elements
A system, comprising:
- a processor;
- and
- a memory for storing instructions, the processor executing the instructions to:
- determining an estimate of unusable fuel volume left in a fuel tank of a first vehicle when the fuel tank is empty;
- incrementally filling the fuel tank with known volumes of fuel;
- determining correlations between fuel level percentage values and the known volumes of fuel;
- applying an offset to the fuel level percentage values to compensate for the estimate of the unusable fuel volume;
- determining a best-performing non-linear model candidate from a plurality of non-linear model candidates that matches the correlations between the fuel level percentage values and the known volumes of fuel;
- and
- determining a fuel level volume for a second vehicle having a similar or same fuel tank using the best-performing non-linear model candidate.
7 more elements
A method, comprising:
- introducing known volumes of fuel into a fuel tank of a first vehicle, wherein the fuel tank of the first vehicle comprises a fuel tank part number;
- determining correlations of fuel level percentage values relative to the known volumes of fuel placed into the fuel tank of the first vehicle;
- offsetting the correlations to compensate for unusable fuel volume of the fuel tank of the first vehicle;
- selecting a non-linear fuel tank model that fits the offset correlations;
- and
- applying the non-linear fuel tank model to a fuel tank comprising the fuel tank part number of a target vehicle,
- wherein selecting the non-linear fuel tank model comprises:
- determining non-linear model candidates for the fuel tank;
- performing non-linear regression analysis on the fuel level percentage values and the known volumes of fuel using the non-linear model candidates;
- and
- evaluating the non-linear model candidates by determining at least one of a cross-validation error, mean absolute deviation, and/or a model error tolerance.
8 more elements
A method, comprising:
- introducing known volumes of fuel into a fuel tank of a first vehicle, wherein the fuel tank of the first vehicle comprises a fuel tank part number;
- determining correlations of fuel level percentage values relative to the known volumes of fuel placed into the fuel tank of the first vehicle;
- offsetting the correlations to compensate for unusable fuel volume of the fuel tank of the first vehicle;
- selecting a non-linear fuel tank model that fits the offset correlations;
- applying the non-linear fuel tank model to a fuel tank comprising the fuel tank part number of a target vehicle,
- draining the fuel tank to empty;
- determining, based on the fuel tank being empty, a fuel level percentage value of the fuel level percentage values;
- and
- wherein the known volumes of fuel vary in amount.
6 more elements
A method, comprising:
- emptying a fuel tank of a vehicle;
- determining a fuel level percentage value for the fuel tank when the fuel tank is empty to determine an offset;
- incrementally filling the fuel tank with known volumes of fuel until the fuel tank is full;
- determining correlations between fuel level percentage values and the known volumes of fuel;
- applying the offset to the correlations;
- and
- selecting a non-linear model for the correlations,
- wherein an amount of each of the known volumes of fuel is varied.
5 more elements
Dependencies are inferred from the claim text.