Method and device for setting operating parameters of a laser material processing machine
A method for setting operating parameters of a system, in particular, a manufacturing machine, with the aid of Bayesian optimization of a data-based model, which (in the Bayesian optimization) is trained to output a model output variable, which characterizes an operating mode of the system, as a function of the operating parameters. The training of the data-based model takes place as a function of at least one experimentally ascertained measured variable of the system and the training also taking place as a function of at least one simulatively ascertained simulation variable. The measured variable and the simulation variable each characterize the operating mode of the system. The measured variable and/or the simulation variable is transformed during training with the aid of an affine transformation.
1. A method for setting operating parameters of a laser material processing machine, using Bayesian optimization of a data-based model, the method comprising the following steps:
receiving via an input interface of a test stand, from sensors of the laser material processing machine, at least one experimentally ascertained measured variable of the laser material processing machine;
training the data-based model, in the Bayesian optimization, to output a model output variable which characterizes an operating mode of the laser material processing machine, as a function of the operating parameters, the training of the data- based model taking place as a function of the at least one experimentally ascertained measured variable of the laser material processing machine, and the training also taking place as a function of at least one simulatively ascertained simulation variable, the measured variable and the simulation variable each characterizing the operating mode of the laser material processing machine, the measured variable and/or the simulation variable being transformed during the training using an affine transformation, wherein the measured variable and/or the simulation variable is multiplied during the affine transformation by a factor, and the factor is selected as a function of a simulative model uncertainty and as a function of an experimental model uncertainty;
setting, via an output interface of the test stand, the operating parameters of the laser material processing machine using the trained data-based model;
the laser material processing machine performing laser material processing based on the set operating parameters.
2. The method as recited in claim 1 , wherein the factor is selected as a function of a quotient of the simulative model uncertainty and of the experimental model uncertainty.
3. The method as recited in claim 1 , wherein the data-based model includes a simulatively trained first submodel which is a first Gaussian process model, and an experimentally trained second submodel which is a second Gaussian process model, the simulative model uncertainty being ascertained using the first submodel and the experimental model uncertainty being ascertained using the second submodel.
4. The method as recited in claim 3 , wherein the data-based model includes an experimentally trained third submodel which is a third Gaussian process model, and which is trained to output a difference between the experimentally ascertained measured variable and an output variable of the first submodel.
5. The method as recited in claim 3 , wherein the second submodel is not trained using the transformed measured variable, but is trained using the measured variable.
6. The method as recited in claim 5 , wherein the third submodel is trained using the transformed measured variable.
7. The method as recited in claim 4 , wherein when ascertaining the transformed measured variable, the measured variable is transformed using the affine transformation, the difference being multiplied by the factor.
8. The method as recited in claim 4 , wherein to ascertain the model output variable of the data-based model, an output variable of the first submodel and an output variable of the third submodel are added up and are transformed with an inverse of the affine transformation.
9. The method as recited in claim 4 , wherein to ascertain an uncertainty of the model output variable of the data-based model, the uncertainty is ascertained using the second submodel.
10. The method as recited in claim 1 , wherein the measured variable and the variable simulated by the simulation variable are different physical variables and include different physical units.
11. The method as recited in claim 1 , wherein the laser material processing by the laser material processing machine includes performing by the laser material processing machine, based on the set operating parameters, laser welding or laser drilling.
12. A test stand for a laser material processing machine, the test stand configured to set operating parameters of the laser material processing machine, using Bayesian optimization of a data-based model, the test stand comprising:
an input interface configured to receive from sensors of the laser material processing machine, at least one experimentally ascertained measured variable of the laser material processing machine;
a processor;
a computer-readable memory medium; and
an output interface,
wherein the test stand is configured to:
train the data-based model, in the Bayesian optimization, to output a model output variable which characterizes an operating mode of the laser material processing machine, as a function of the operating parameters, the training of the data-based model taking place as a function of the at least one experimentally ascertained measured variable of the laser material processing machine received via the input interface, and the training also taking place as a function of at least one simulatively ascertained simulation variable, the measured variable and the simulation variable each characterizing the operating mode of the laser material processing machine, the measured variable and/or the simulation variable being transformed during the training using an affine transformation, wherein the measured variable and/or the simulation variable is multiplied during the affine transformation by a factor, and the factor is selected as a function of a simulative model uncertainty and as a function of an experimental model uncertainty;
wherein the test stand is further configured to:
set, via the output interface, the operating parameters of the laser material processing machine using the trained data-based model;
wherein the laser material processing machine is configured to perform laser material processing, based on the set operating parameters.
13. A non-transitory machine-readable memory medium on which is stored a computer program for setting operating parameters of a laser material processing machine, using Bayesian optimization of a data-based model, the computer program, when executed by a computer, causing the computer to perform the following steps:
receiving via an input interface of a test stand, from sensors of the laser material processing machine, at least one experimentally ascertained measured variable of the laser material processing machine;
training the data-based model, in the Bayesian optimization, to output a model output variable which characterizes an operating mode of the laser material processing machine, as a function of the operating parameters, the training of the data- based model taking place as a function of the at least one experimentally ascertained measured variable of the laser material processing machine, and the training also taking place as a function of at least one simulatively ascertained simulation variable, the measured variable and the simulation variable each characterizing the operating mode of the laser material processing machine, the measured variable and/or the simulation variable being transformed during the training using an affine transformation, wherein the measured variable and/or the simulation variable is multiplied during the affine transformation by a factor, and the factor is selected as a function of a simulative model uncertainty and as a function of an experimental model uncertainty;
setting, via an output interface of the test stand, the operating parameters of the laser material processing machine using the trained data-based model;
the laser material processing machine performing laser material processing based on the set operating parameters.
14. The non-transitory machine-readable memory medium as recited in claim 13 , wherein the laser material processing by the laser material processing machine includes performing by the laser material processing machine, based on the set operating parameters, laser welding or laser drilling.