System and method to predict calibration values based on existing calibrations

Patent metadata

Field	Value
Publication number	US-9803576-B2
Application number	US-201615045033-A
Country	US
Kind code	B2
Filing date	Feb 16, 2016
Priority date	Feb 16, 2016
Publication date	Oct 31, 2017
Grant date	Oct 31, 2017

Abstract

A system to predict calibration values for a vehicle. The system is configured to receive a plurality of training data sets for a component of the vehicle. Each of the plurality of training data sets includes one or more training inputs and one or more corresponding training outputs. The system is further configured to automatically develop a prediction model based on the plurality of training data sets. The system is further configured to receive an input data set and determine, using the prediction model, a predicted calibration value based on the input data set. The system is further configured to transmit the predicted calibration value to an electronic control unit of the vehicle.

First claim

What is claimed is:

1. A system for predicting a calibration value for a vehicle, the system comprising:
an electronic processor configured to;
receive a plurality of training data sets for a vehicle component;
automatically develop a prediction model based on the plurality of training data sets;
receive an input data set;
determine, using the prediction model, a predicted calibration value based on the input data set; and
transmit the predicted calibration value to an electronic control unit included in the vehicle;

wherein each of the plurality of training data sets includes one or more inputs and one or more corresponding outputs.

2. The system of claim 1 , wherein transmitting the predicted calibration value to the electronic control unit includes transmitting a lookup table to the electronic control unit, the lookup table including the input data set and the predicted calibration value.

3. The system of claim 1 , wherein the electronic processor is configured to transmit the predicted calibration value to the electronic control unit over at least one connection external to the vehicle.

4. The system of claim 1 , wherein automatically developing the prediction model includes selecting a learning engine from a plurality of learning engines.

5. The system of claim 4 , wherein the electronic processor is configured to select the learning engine from the plurality of learning engines based on the plurality of training data sets.

6. The system of claim 5 , wherein the electronic processor is configured to select the learning engine from the plurality of learning engines based on the plurality of training data sets by generating a histogram based on the plurality of training data sets.

7. The system of claim 4 , wherein the electronic processor is further configured to determine at least one value for a configuration parameter associated with the learning engine based on the plurality of training data sets.

8. The system of claim 7 , wherein the at least one value for the configuration parameter includes an iteration value.

9. The system of claim 1 , wherein the electronic processor is further configured to
select a testing data set from the plurality of training data sets, the testing data set including one or more inputs and one or more corresponding outputs;
determine, using the prediction model, a predicted test calibration value based on the one or more inputs included in the testing data set;
compare the predicted test calibration value to the one or more outputs included in the testing data set to determine an accuracy for the prediction model; and
refine the prediction model based on the testing data set when the accuracy does not satisfy a predetermined threshold.

10. The system of claim 1 , wherein the input data set includes a fuel density, a fuel rail pressure, and a number of fuel injectors and the predicted calibration value includes a fuel injection quantity.

11. A method of predicting a calibration value for a vehicle, the method comprising:
receiving, with an electronic processor, a plurality of training data sets for a component of the vehicle, wherein the each of the plurality of training data sets includes one or more training inputs and one or more corresponding training outputs;
automatically developing, with the electronic processor, a prediction model based on the plurality of training data sets;
receiving, with the electronic processor, an input data set;
determining, with the electronic processor using the prediction model, a predicted calibration value based on the input data set; and
transmitting, with the electronic processor, the predicted calibration value to an electronic control unit included in the vehicle.

12. The method of claim 11 , wherein transmitting the predicted calibration value to the electronic control unit includes transmitting a lookup table to the electronic control unit, the lookup table including the input data set and the predicted calibration value.

13. The method of claim 11 , further comprising:
transmitting, with the electronic processor, the predicted calibration value to the electronic control unit over at least one connection external to the vehicle.

14. The method of claim 11 , wherein automatically developing the prediction model includes selecting a learning engine from a plurality of learning engines.

15. The method of claim 14 , wherein selecting a learning engine from a plurality of learning engines includes selecting the learning engine from a plurality of learning engines based on the plurality of training data sets.

16. The method of claim 15 , wherein selecting the learning engine from a plurality of learning engines based on the plurality of training data sets includes generating a histogram based on the plurality of training data sets.

17. The method of claim 14 , further comprising:
determining, with the electronic processor, at least one value of a configuration parameter associated with the learning engine based on the plurality of training data sets.

18. The method of claim 17 , wherein determining the at least one value of the configuration parameter includes determining, with the electronic processor, an iteration value.

19. The method of claim 11 , further comprising:
selecting, with the electronic processor, a testing data set from the plurality of training data sets, the testing data set including one or more inputs and one or more corresponding outputs;
determining, with the electronic processor, using the prediction model, a predicted test calibration value based on the one or more inputs included in the testing data set;
comparing, with the electronic processor, the predicted test calibration value to the one or more outputs included in the testing data set to determine an accuracy for the prediction model; and
refining, with the electronic processor, the prediction model based on the testing data set when the accuracy does not satisfy a predetermined threshold.

20. The method of claim 11 , wherein the input data set includes a fuel density, a fuel rail pressure, and a number of fuel injectors and the predicted calibration value includes a fuel injection quantity.

Assignees

• Bosch Gmbh Robert

Inventors

• Commenda Roland
• Respondek Kevin
• Zink Jason
• Speer Lukas
• Srinivasan Soundararajan
• Janai Joel
• Vandam Courtland A

Classifications

• G07C5/0808

  Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005) · CPC title

• F02D41/04 Primary

  Introducing corrections for particular operating conditions (F02D41/14 takes precedence) · CPC title

• F02D41/30

  Controlling fuel injection {(F02D41/182, F02D41/24 take precedence)} · CPC title

• F02D41/1401

  characterised by the control or regulation method (F02D41/1473, F02D41/1477 take precedence) · CPC title

• F02D2041/1412

  using a predictive controller · CPC title