Statistical Modeling and Analysis of Fuel-Related Factors in Transportation Industries

• US 20120209579A1
• Filed: 01/02/2012
• Published: 08/16/2012
• Est. Priority Date: 12/31/2010
• Status: Active Grant

• Current Assignee: Trimble Inc.
• Original Assignee: Trimble Inc.
• Inventors: Fansler, Thomas S., Konezny, Ronald Edward
• Granted Patent: US 10,423,898 B2
• Time in Patent Office: Days
• US Class Current: 703/8
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202

Abstract

Techniques involving modeling and analysis of operational metrics in transportation industries are disclosed. Representative methods involve defining a set of fuel consumption performance factors having a potential to impact vehicle fuel economy. Fuel consumption performance factors are received, and categorical variables are identified from at least a subset of the fuel consumption performance factors to create one or more categorical groupings. The fuel consumption performance factors associated with at least one of the categorical groupings are processed to identify a hypothetical maximum fuel economy or “baseline” for the at least one of the categorical groupings, and to identify fuel economy deduction coefficients based on the fuel consumption performance factors that adversely impact the hypothetical maximum fuel economy. Models are created based on the hypothetical maximum fuel economy and the fuel economy deduction coefficients to predict fuel economy for vehicles in the at least one of the categorical groupings.

Claims

1. A method comprising:

defining a set of fuel consumption performance factors having a potential to impact vehicle fuel economy;

receiving a plurality of the fuel consumption performance factors, and identifying categorical variables from at least a subset of the fuel consumption performance factors to create one or more categorical groupings;

processing the fuel consumption performance factors associated with at least one of the categorical groupings to identify a hypothetical maximum fuel economy for the at least one of the categorical groupings, and to identify one or more fuel economy deduction coefficients based on the fuel consumption performance factors that adversely impact the hypothetical maximum fuel economy; and

creating a model based on the hypothetical maximum fuel economy and the one or more fuel economy deduction coefficients to predict fuel economy for vehicles in the at least one of the categorical groupings.

2. The method of claim 1, further comprising applying the model to a set of the fuel consumption performance factors relating to a particular vehicle to determine whether the vehicle had an unexpected volume of fuel in its fuel tank relative to an expected volume of fuel based on the predicted fuel economy.

3. The method of claim 2, wherein the expected volume of fuel is greater than the unexpected volume of fuel indicative of potential fuel theft.

4. The method of claim 2, wherein the expected volume of fuel is less than the unexpected volume of fuel.

5. The method of claim 1, further comprising applying the model to a set of the fuel consumption performance factors specific to each of a plurality of different equipment types to diminish an impact of differing ones of the fuel consumption performance factors on a comparison of the equipment types.

6. The method of claim 1, further comprising applying the model to a set of the fuel consumption performance factors to obtain a predicted fuel economy for a particular vehicle, and comparing the predicted fuel economy to an actual fuel economy for the particular vehicle to determine if the vehicle is underperforming relative to the predicted fuel economy.

7. The method of claim 1, wherein:

one of the fuel consumption performance factors comprises an idle time percentage;

the one or more fuel economy deduction coefficients comprises an idle time deduction coefficient;

creating a model comprises creating the model based on the hypothetical maximum fuel economy and the idle time deduction coefficient to predict fuel economy for vehicles in the at least one of the categorical groupings; and

further comprising applying the model to a particular vehicle'"'"'s idle time percentage to identify a deviation of the particular vehicle'"'"'s fuel economy from the predicted fuel economy as a result of the particular vehicle'"'"'s idle time percentage.

8. The method of claim 1, wherein:

one of the fuel consumption performance factors comprises an over-RPM percentage;

the one or more fuel economy deduction coefficients comprises an over-RPM deduction coefficient;

creating a model comprises creating the model based on the hypothetical maximum fuel economy and the over-RPM deduction coefficient to predict fuel economy for vehicles in the at least one of the categorical groupings; and

further comprising applying the model to a particular vehicle'"'"'s over-RPM percentage to identify a deviation of the particular vehicle'"'"'s fuel economy from the predicted fuel economy as a result of the particular vehicle'"'"'s over-RPM percentage.

9. The method of claim 1, wherein:

one of the fuel consumption performance factors comprises an over-speed percentage;

the one or more fuel economy deduction coefficients comprises an over-speed deduction coefficient;

creating a model comprises creating the model based on the hypothetical maximum fuel economy and the over-speed deduction coefficient to predict fuel economy for vehicles in the at least one of the categorical groupings; and

further comprising applying the model to a particular vehicle'"'"'s over-speed percentage to identify a deviation of the particular vehicle'"'"'s fuel economy from the predicted fuel economy as a result of the particular vehicle'"'"'s over-speed percentage.

10. The method of claim 1, wherein the fuel consumption performance factors comprise driver-related performance factors.

11. The method of claim 10, wherein the driver-related performance factors are selected from the group comprising an over-speed percentage, an over-RPM percentage, an idle time percentage, an out-of-route indication, and a hard braking rate.

12. The method of claim 1, wherein the fuel consumption performance factors comprise equipment-related performance factors.

13. The method of claim 12, wherein the equipment-related performance factors are selected from the group comprising a manufacturer, a manufacturer'"'"'s model, an engine type, a model year, a trailer type, and an APU indication.

14. The method of claim 1, wherein the fuel consumption performance factors are selected from the group comprising a load weight, an empty/loaded status, a stop frequency rate, and an urban/rural geographic percentage.

15. The method of claim 1, wherein the fuel consumption performance factors comprise environmental-related performance factors, and wherein the environmental-related factors are selected from the group comprising topography, an air temperature where the vehicle travels, and a road type.

16. The method of claim 1, further comprising generating reports relating to the application of the model to a set of the fuel consumption performance factors.

17. An apparatus comprising:

a communications module configured to receive data concerning vehicle actions impacting fuel economy;

a processor;

storage coupled to the processor, comprising;

a data input module executable by the processor and configured to receive and parse the received data;

a data integration module executable by the processor and configured to prepare the data for processing;

a data modeling module executable by the processor and configured to create data models based on the data to arrive at a predictive fuel consumption rate based on factors obtained from the prepared data;

an analysis model executable by the processor and configured to apply the data models to provide analyses of expected fuel consumption versus actual fuel consumption in view of the data models.

18. The apparatus of claim 17, wherein the communications module is configured to receive the data from data sources including any one or more of a vehicle communication device, dispatch software platform, fuel vendor, and mobile communications vendor.

19. A method comprising:

identifying fuel consumption impacting factors for a category of vehicles;

calculating an expected fuel consumption for a particular vehicle in the category of vehicles based on the identified fuel consumption impacting factors;

receiving actual vehicle operational data from at least one remote source;

calculating an actual fuel consumption for the vehicle based on the collected actual vehicle operational data; and

comparing the calculated actual fuel consumption and the expected fuel consumption.