# US 2017/0254658 A1 · Fuel consumption predictions using associative memories

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2017/0254658 A1
- Document ID: US20170254658A1
- Status: Published application
- Kind: A1
- Application number: 15/061,699
- Filed: 2016-03-04
- Published: 2017-09-07
- Earliest claimed: 2016-03-04
- Assignees: The Boeing Company
- Applicants: The Boeing Company
- Inventors: John D. Whelan
- Web page: https://patentgrep.com/patent/US20170254658A1

## CPC

- G06Q 30/0202: Market predictions or forecasting for commercial activities
- G01C 21/20: Instruments for performing navigational calculations (G01C21/24, G01C21/26 take precedence)
- G07C 5/0808: {Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005)}
- G07C 5/085: {using electronic data carriers}
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)
- G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE

## Abstract

A method, system, and computer program product for predicting fuel consumption for a vehicle operation is provided. Data for historical vehicle operations is stored in an associative memory and includes values for different attribute categories. The values of the attribute categories for the historical vehicle operations are compared to values of the attribute categories for a planned vehicle operation to identify historical vehicle operations that are most similar to the planned vehicle operation. Historical vehicle operations that are most similar to the planned vehicle operation are returned from the associative memory and the fuel consumption values for the historical vehicle operations are used to generate a predicted fuel consumption for the planned vehicle operation. An average, weighted average, maximum, or minimum fuel consumption value from the historical vehicle operations could be used as the predicted fuel consumption value for the planned vehicle operation.

## Claims

### Claim 1

A computer-implemented method for calculating a predicted fuel consumption for a planned vehicle operation, the method comprising:
receiving an operation plan for the planned vehicle operation;
extracting attributes from the operation plan;
accessing an associative memory device, using the extracted attributes, to determine at least one historical vehicle operation from a plurality of historical vehicle operations that is most similar to the planned vehicle operation, wherein the associative memory device contains data for a plurality of attributes and collected from the plurality of historical vehicle operations, and wherein the at least one historical vehicle operation is determined by applying a respective weight defined within the associative memory device to data values for each of the plurality of attributes;
extracting historical fuel consumption data from the at least one historical vehicle operation;
predicting fuel consumption data for the planned vehicle operation based on the extracted historical fuel consumption data; and
outputting the predicted fuel consumption data.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising populating the associative memory device, by:
receiving instantiations of historical vehicle operations;
generating correlation values for different attributes of the instantiations of historical vehicle operations with fuel consumption for the instantiations of historical vehicle operations; and
determining the respective weightings of the attributes based on the correlation values.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein predicting fuel consumption for the planned vehicle operation based on the extracted historical fuel consumption data comprises:
calculating an average of the extracted historical fuel consumption data; and
assigning the calculated average as the predicted fuel consumption for the planned vehicle operation.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein determining the at least one historical vehicle operation from the plurality of historical vehicle operations that is most similar to the planned vehicle operation further comprises determining any historical vehicle operations from the plurality of historical vehicle operations with an attribute-matching score above a threshold value.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, wherein predicting fuel consumption for the planned vehicle operation based on the extracted historical fuel consumption data comprises:
calculating a weighted average of the extracted historical fuel consumption data, wherein the weightings are based on the attribute-matching scores of the returned historical vehicle operations; and
assigning the calculated weighted average as the predicted fuel consumption for the planned vehicle operation.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, further comprising automatically updating a fuel load of a vehicle operation plan for the planned vehicle operation based on the output predicted fuel consumption data.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the planned vehicle operation is a flight of a commercial aircraft, and further comprising automatically updating a load sheet for the flight based on the output predicted fuel consumption data.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein an amount of fuel determined by the predicted fuel consumption data is loaded in the vehicle.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein an amount of fuel determined by the predicted fuel consumption data plus a buffer of fuel is loaded in the vehicle.

### Claim 10

A system, comprising:
one or more computer processors;
an associative memory device containing data for a plurality of attributes and collected for a plurality of historical vehicle operations; and
a memory device containing computer program code that, when executed by operation of the one or more computer processors, performs an operation for calculating a predicted fuel consumption for a planned vehicle operation, the operation comprising:
receiving an operation plan for a planned vehicle operation;
extracting attributes from the operation plan;
accessing the associative memory device, using the extracted attributes, to determine at least one historical vehicle operation from a plurality of historical vehicle operations that is most similar to the planned vehicle operation, wherein the associative memory device contains data for a plurality of attributes and collected from the plurality of historical vehicle operations, and wherein the at least one historical vehicle operation is determined by applying a respective weight defined within the associative memory device to data values for each of the plurality of attributes;
extracting historical fuel consumption data from the at least one historical vehicle operation;
predicting fuel consumption data for the planned vehicle operation based on the extracted historical fuel consumption data; and
outputting the predicted fuel consumption data.

### Claim 11 (depends on 10)

The system of claim 10, wherein the operation further comprises populating the associative memory device, by:
receiving instantiations of historical vehicle operations;
generating correlation values for different attributes of the instantiations of historical vehicle operations with fuel consumption for the instantiations of historical vehicle operations; and
determining the weightings of the attributes based on the correlation values.

### Claim 12 (depends on 10)

The system of claim 10, wherein the fuel prediction application predicts fuel consumption for the planned vehicle operation based on the extracted historical fuel consumption data by:
calculating an average of the extracted historical fuel consumption data; and
assigning the calculated average as the predicted fuel consumption data for the planned vehicle operation.

### Claim 13 (depends on 10)

The system of claim 10, wherein determining the at least one historical vehicle operation from the plurality of historical vehicle operations that is most similar to the planned vehicle operation further comprises determining any historical vehicle operations from the plurality of historical vehicle operations with an attribute-matching score above a threshold value.

### Claim 14 (depends on 13)

The system of claim 13, wherein the fuel prediction application predicts fuel consumption for the planned vehicle operation based on the extracted historical fuel consumption data by:
calculating a weighted average of the extracted historical fuel consumption data, wherein the weightings are based on the attribute-matching scores of the returned historical vehicle operations; and
assigning the calculated weighted average as the predicted fuel consumption data for the planned vehicle operation.

### Claim 15 (depends on 13)

The system of claim 13, wherein the fuel prediction application, when further executed by the computer processor, automatically updating a fuel load of a vehicle operation plan for the planned vehicle operation based on the output predicted fuel consumption data.

### Claim 16

A computer program product for calculating a predicted fuel consumption for a planned vehicle operation, the computer program product comprising:
a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to:
receive an operation plan for the planned vehicle operation;
extract attributes from the operation plan;
access an associative memory device, using the extracted attributes, to determine at least one historical vehicle operation from a plurality of historical vehicle operations that is most similar to the planned vehicle operation, wherein the associative memory device contains data for a plurality of attributes and collected from the plurality of historical vehicle operations, and wherein the at least one historical vehicle operation is determined by applying a respective weight defined within the associative memory device to data values for each of the plurality of attributes;
extract historical fuel consumption data from the at least one historical vehicle operation;
predict fuel consumption data for the planned vehicle operation based on the extracted historical fuel consumption data; and
output the predicted fuel consumption data.

### Claim 17 (depends on 16)

The computer program product of claim 16, further comprising populating the associative memory device, by:
receiving instantiations of historical vehicle operations;
generating correlation values for different attributes of the instantiations of historical vehicle operations with fuel consumption for the instantiations of historical vehicle operations; and
determining the weightings of the attributes based on the correlation values.

### Claim 18 (depends on 16)

The computer program product of claim 16, wherein the computer program product predicts fuel consumption for the planned vehicle operation based on the extracted historical fuel consumption data by:
calculating an average of the extracted historical fuel consumption data; and
assigning the calculated average as the predicted fuel consumption for the planned vehicle operation.

### Claim 19 (depends on 16)

The computer program product of claim 16, wherein determining the at least one historical vehicle operation from the plurality of historical vehicle operations that is most similar to the planned vehicle operation further comprises determining any historical vehicle operations from the plurality of historical vehicle operations with an attribute-matching score above a threshold value.

### Claim 20 (depends on 19)

The computer program product of claim 19, wherein the computer program product predicts fuel consumption for the planned vehicle operation based on the extracted historical fuel consumption data by:
calculating a weighted average of the extracted historical fuel consumption data, wherein the weightings are based on the attribute-matching scores of the returned historical vehicle operations; and
assigning the calculated weighted average as the predicted fuel consumption for the planned vehicle operation.

### Claim 21 (depends on 16)

The computer program product of claim 16, wherein the computer-readable program code is further executable to automatically update a fuel load of a vehicle operation plan for the planned vehicle operation based on the output predicted fuel consumption data.

### Claim 22 (depends on 16)

The computer program product of claim 16, wherein the planned vehicle operation is a flight of a commercial aircraft, and wherein the computer-readable program code is further executable to:
initiate execution of a flight planning application; and
automatically update a load sheet for the flight in the executing flight planning application based on the output predicted fuel consumption data.

### Claim 23

A computer-implemented method for calculating a predicted fuel consumption for planned vehicle operation, the method comprising:
receiving an operation plan for the planned vehicle operation;
extracting attributes from the operation plan;
issuing a request that includes the extracted attributes, to a memory containing historical vehicle operations, wherein the historical vehicle operations in the memory include attributes, and wherein the memory includes weightings of different ones of the attributes relative to other ones of the attributes;
responsive to the request, receiving from the memory at least one historical vehicle operation that is most similar from among the historical vehicle operations to the planned vehicle operation based on a comparison of the attributes of the historical vehicle operations and the extracted attributes of the operation plan with consideration of the respective weightings of the attributes;
extracting historical fuel consumption data from the received at least one historical vehicle operation;
predicting fuel consumption data for the planned vehicle operation based on the extracted historical fuel consumption data; and
outputting the predicted fuel consumption data,
wherein an amount of fuel determined by the predicted fuel consumption data plus a buffer of fuel is loaded in a vehicle for the planned vehicle operation.
