# US 12,005,525 B2 · Method and device for operating a laser material processing machine > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,005,525 B2 - Document ID: US12005525B2 - Status: Granted - Kind: B2 - Application number: 17/234,044 - Filed: 2021-04-19 - Published: 2021-11-18 - Granted: 2024-06-11 - Earliest claimed: 2020-05-12 - Assignees: Robert Bosch GmbH - Applicants: Robert Bosch GmbH - Inventors: Adina Kerstin Dais; Alexander Kroschel; Alexander Ilin; Andreas Michalowski; Attila Reiss; Patrick Ganter; Paul Sebastian Baireuther; Stephanie Karg - Web page: https://patentgrep.com/patent/US12005525B2 ## CPC - B23K 26/382: by boring - B23K 26/03: Observing, e.g. monitoring, the workpiece - B23K 26/21: by welding - B23K 31/006: {relating to using of neural networks} - B23K 31/125: {Weld quality monitoring} - B23K: SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM ## Abstract A computer-implemented method for operating a laser material processing machine. An estimated result is ascertained as a function of predefined process parameters, which characterize how good an actual result of the laser material processing will be, and the process parameters are varied by means of Bayesian optimization with the aid of a data-based model, until an actual result of the laser material processing is sufficient enough. ## Claims ### Claim 1 A computer-implemented method for operating a laser material processing machine, the method comprising the following steps: performing laser material processing using first process parameters, and detecting a variable characterizing a result of the laser material processing; varying the process parameters by means of Bayesian optimization based on the first process parameters and the detected variable to produce second process parameters; ascertaining an estimated result of the laser material processing as a function of the second process parameters produced using the Bayesian optimization, which estimates the variable characterizing the result of the laser material processing; evaluating a cost function based on the estimated variable; when the evaluated cost function is above a threshold, further varying the process parameters by means of the Bayesian optimization based on the second process parameters and the estimated variable to produce third process parameters; and when the evaluated cost function is below the threshold, performing the laser material processing using the second process parameters. ### Claim 2 (depends on 1) The method as recited in claim 1, wherein a data-based model of the Bayesian optimization is trained as a function of the detected variable. ### Claim 3 (depends on 2) The method as recited in claim 2, wherein the data-based model is also trained as a function of the estimated variable. ### Claim 4 (depends on 1) The method as recited in claim 1, wherein the data-based model is a Gaussian process model. ### Claim 5 (depends on 1) The method as recited in claim 1, wherein the estimated variable is ascertained using a model of the laser material processing. ### Claim 6 (depends on 5) The method as recited in claim 5, wherein the estimated variable is ascertained using a model evaluated with the second process parameters and using the detected variable ascertained with other process parameters. ### Claim 7 (depends on 1) The method as recited in claim 1, wherein the laser material processing machine is a laser drilling machine. ### Claim 8 (depends on 7) The method as recited in claim 7, wherein the variable characterizes a geometry of a hole drilled by the laser drilling machine. ### Claim 9 (depends on 1) The method as recited in claim 1, wherein the laser material processing machine is a laser welding machine. ### Claim 10 (depends on 9) The method as recited in claim 9, wherein the variable characterizes a geometry of a weld seam welded by the laser welding machine. ### Claim 11 A test stand for a laser material processing machine, the test stand configured to: perform laser material processing using first process parameters, and detecting a variable characterizing a result of the laser material processing; vary the process parameters by means of Bayesian optimization based on the first process parameters and the detected variable to produce second process parameters; ascertain an estimated result of the laser material processing as a function of the second process parameters produced using the Bayesian optimization, which estimates the variable characterizing the result of the laser material processing; evaluating a cost function based on the estimated variable; when the evaluated cost function is above a threshold, further varying the process parameters by means of the Bayesian optimization based on the second process parameters and the estimated variable to produce third process parameters; and when the evaluated cost function is below the threshold, performing the laser material processing using the second process parameters. ### Claim 12 A non-transitory machine-readable memory medium on which is stored a computer program for operating a laser material processing machine, the computer program, when executed by a computer, causing the computer to perform the following steps: perform laser material processing using first process parameters, and detecting a variable characterizing a result of the laser material processing; vary the process parameters by means of Bayesian optimization based on the first process parameters and the detected variable to produce second process parameters; ascertain an estimated result of the laser material processing as a function of the second process parameters produced using the Bayesian optimization, which estimates the variable characterizing the result of the laser material processing; evaluating a cost function based on the estimated variable; when the evaluated cost function is above a threshold, further varying the process parameters by means of the Bayesian optimization based on the second process parameters and the estimated variable to produce third process parameters; and when the evaluated cost function is below the threshold, performing the laser material processing using the second process parameters.