Invention Grant
- Patent Title: Monitoring a laser machining process using deep folding neural networks
-
Application No.: US17295904Application Date: 2019-10-10
-
Publication No.: US12013670B2Publication Date: 2024-06-18
- Inventor: Joachim Schwarz
- Applicant: Precitec GmbH & Co. KG
- Applicant Address: DE Gaggenau
- Assignee: Precitec GmbH & Co. KG
- Current Assignee: Precitec GmbH & Co. KG
- Current Assignee Address: DE Gaggenau
- Agency: DINSMORE & SHOHL LLP
- Priority: DE 2018129441.7 2018.11.22
- International Application: PCT/EP2019/077485 2019.10.10
- International Announcement: WO2020/104103A 2020.05.28
- Date entered country: 2021-05-21
- Main IPC: G05B13/02
- IPC: G05B13/02 ; G06N3/08 ; G06N3/082 ; G06T7/00

Abstract:
A system for monitoring a laser machining process for machining a workpiece includes a computing unit configured to determine an input tensor on the basis of current data of the laser machining process and to determine an output tensor on the basis of the input tensor using a transfer function. The output tensor contains information on a current machining result. The transfer function between the input tensor and the output tensor is formed by a trained neural network.
Public/Granted literature
- US20220011726A1 MONITORING A LASER MACHINING PROCESS USING DEEP FOLDING NEURAL NETWORKS Public/Granted day:2022-01-13
Information query