Method for setting up a functionality for a control unit

• US 9,952,567 B2
• Filed: 07/19/2012
• Issued: 04/24/2018
• Est. Priority Date: 08/22/2011
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Markert, Heiner, Kruse, Thomas, Imhof, Volker, Huber, Thorsten, Diener, Rene, Kloppenburg, Ernst, Streichert, Felix, Ulmer, Holger, Angermaier, Stefan
• Primary Examiner(s): Craig, Dwin M
• Application Number:
  US14/240,312
• Publication Number:
  US 20140330400A1
• Time in Patent Office: 2,105 Days
• Field of Search: 703 2, 703 13
• CPC Class Codes: G05B 13/04 involving the use of models or simulators
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06F 30/30 Circuit design
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A method is provided for populating a function for a control unit with data, in which method measurements are performed on a system at different measuring points on a test stand, and a global data-based model is set up based on the obtained measured values, and virtual measurements which simulate real measurements on the test stand are carried out on the global data-based model, and uncertainties for virtual measured values of the virtual measurements are determined from the global data-based model, the uncertainties of the virtual measured values being taken into account when populating the function for the control unit with data.

Claims

1. A method for populating a function implemented in a control unit with data, comprising:

performing a measurement on a test stand on a system at different measuring points to produce obtained measured values;

setting up a global data-based model on the basis of the obtained measured values;

performing a virtual measurement that simulates a real measurement on the test stand on the global data-based model,

ascertaining an uncertainty for a virtual measured value of the virtual measurement is ascertained from the global data-based model;

taking into account the uncertainty of the virtual measured value when populating the function for the control unit with data;

detecting on the basis of the uncertainty of the virtual measured value whether a quality of the data-based model is insufficient in at least one range of the measuring points for populating the function with data;

if the quality of the data-based model is insufficient in at least the one range of the measuring points, obtaining an improvement of the data-based model on the basis of a supplementary measured value from a supplementary measurement on the test stand;

if the quality of the data-based model offers a required quality for populating the function with data, populating the function implemented in the control unit with data in that a measured values from the virtual measurement is entered into a tool, in which an optimization of a label of the function implemented in the control unit is performed; and

operating a physical process of an engine by causing the control unit to execute the populated function.

2. The method as recited in claim 1, wherein the uncertainty is determined for each virtual measured value.

3. The method as recited in claim 1, wherein the uncertainty of at least one of the virtual measured values is used to decide whether the at least one of the virtual measured values is to be utilized for populating the function with data.

4. The method as recited in claim 1, wherein the global data-based model includes a Bayesian regression model.

5. The method as recited in claim 1, wherein the global data-based model includes a Gaussian process model.

6. The method as recited in claim 1, further comprising implementing a smooth regression between the measuring points.

7. The method as recited in claim 1, further comprising visualizing a behavior of a measured system on the basis of the global data-based model.