Method and device for creating a model of a technical system from measurements
AssigneeRobert Bosch GmbH
InventorsAndrej Junginger, Holger Ulmer, Jens Stefan Buchner, Patrick Engel, Sebastian Boblest
Life of this patent
Estimating the term…
Abstract
A method for creating a model of a technical system as a function of measured sensor data of the technical system. The method includes the following steps: initializing a symbolic regression problem. A list of mathematical functions is established, including at least one linear and/or non-linear function and/or at least a one-dimensional parameterizable characteristic curve. The at least one-dimensional characteristic curve is implemented by a Smoothed Grid Regression (SGR) model. Solving the symbolic regression problem with the aid of a genetic algorithm.
Claims11
A computer-implemented method for creating a model of a technical system as a function of measured sensor data of the technical system, the method comprising the following steps:
- providing the measured sensor data, which have been detected using different sensors;
- initializing a model generator;
- providing a list of mathematical functions including at least one linear and/or non-linear function and an at least one-dimensional parameterizable characteristic curve, the at least one-dimensional characteristic curve being implemented by a Smoothed Grid Regression Model (SGR);
- combining, using a genetic algorithm, multiple models with the mathematical functions from the list;
- optimizing each of the combined models in such a way that the models are able to calculate one of the measured sensor data as a function of others of the measured sensor data;
- assessing, by the genetic algorithm, each of the optimized models as a function of a fitness function, the fitness function being a function of an efficiency of the model to be assessed and a function of a complexity of the model;
- and
- outputting best ones of the models with respect to the fitness function as a function of their complexity.
A non-transitory machine-readable memory element on which is stored a computer program for creating a model of a technical system as a function of measured sensor data of the technical system, the computer program, when executed by a computer, causing the computer to perform the following steps:
- providing the measured sensor data, which have been detected using different sensors;
- initializing a model generator;
- providing a list of mathematical functions including at least one linear and/or non-linear function and an at least one-dimensional parameterizable characteristic curve, the at least one-dimensional characteristic curve being implemented by a Smoothed Grid Regression Model (SGR);
- combining, using a genetic algorithm, multiple models with the mathematical functions from the list;
- optimizing each of the combined models in such a way that the models are able to calculate one of the measured sensor data as a function of others of the measured sensor data;
- assessing, by the genetic algorithm, each of the optimized models as a function of a fitness function, the fitness function being a function of an efficiency of the model to be assessed and a function of a complexity of the model;
- and
- outputting best ones of the models with respect to the fitness function as a function of their complexity.
A device configured to create a model of a technical system as a function of measured sensor data of the technical system, the device configured to:
- provide the measured sensor data, which have been detected using different sensors;
- initialize a model generator;
- provide a list of mathematical functions including at least one linear and/or non-linear function and an at least one-dimensional parameterizable characteristic curve, the at least one-dimensional characteristic curve being implemented by a Smoothed Grid Regression Model (SGR);
- combine, using a genetic algorithm, multiple models with the mathematical functions from the list;
- optimize each of the combined models in such a way that the models are able to calculate one of the measured sensor data as a function of others of the measured sensor data;
- assess, by the genetic algorithm, each of the optimized models as a function of a fitness function, the fitness function being a function of an efficiency of the model to be assessed and a function of a complexity of the model;
- and
- output best ones of the models with respect to the fitness function as a function of their complexity.
Dependencies are inferred from the claim text.