IP Library › Granted Patent US 12,539,564
Granted Patent B2
US 12,539,564 · App. 17/861,925 · Granted Feb 3, 2026

Method and device for demonstrating the influence of cutting parameters on a cut edge

Inventor: Leonie Felica Tatzel (Korntal, DE)
Assignee: TRUMPF Werkzeugmaschinen SE + Co. KG
B23K26/38B23K26/032B23K31/006G05B19/4155G06N3/084G05B2219/36199
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,539,564
App. No.
17/861,925
Granted
Feb 3, 2026
Kind
B2
Abstract

A method for recognizing cutting parameters which are particularly important for specific features of a cut edge. A recording of the cut edge is analyzed by an algorithm having a neural network for determining the cutting parameters. Those recording pixels which play a significant part for ascertaining the cutting parameters are identified by backpropagation of this analysis. An output in the form of a representation of these significant recording pixels, in particular in the form of a heat map, demonstrates to a user of the method which cutting parameters need to be changed in order to improve the cut edge. A computer program product and a device for carrying out the method.

Claims (33)

1 . A method for analyzing a cut edge created by a machine tool, the method comprising the following steps:

creating the cut edge with the machine tool, the cut edge having at least one feature based on cutting parameters;

reading in at least one recording of the cut edge, the recording having a multiplicity of recording pixels;

analyzing the recording by way of a trained neural network for determining at least one cutting parameter;

analyzing a backpropagation of the neural network for determining a relevance of the recording pixels for ascertaining the determined cutting parameters;

outputting the recording with identification of at least one of particularly relevant recording pixels or particularly irrelevant recording pixels, and adapting said at least one cutting parameter to change the at least one feature of the cut edge.

2 . The method according to claim 1 , wherein the trained neural network is a convolutional neural network having a plurality of layers.

3 . The method according to claim 2 , wherein each of the plurality of layers have a plurality of filters.

4 . The method according to claim 1 , wherein the backpropagation is a layer-wise relevance propagation.

5 . The method according to claim 4 , wherein an assignment of the relevance in the layer-wise relevance propagation is based on deep Taylor decomposition.

6 . The method according to claim 1 , wherein the identification of the particularly relevant and/or particularly irrelevant recording pixels is outputted as a heat map.

7 . The method according to claim 1 , wherein the recording is an RGB photograph or a 3 D point cloud.

8 . The method according to claim 1 , further comprising creating the recording via a camera.

9 . The method according to claim 8 , wherein the camera is a camera of the machine tool.

10 . The method according to claim 1 , wherein the machine tool is a laser cutting machine.

11 . The method according to claim 10 , wherein the at least one cutting parameter is:

beam parameters;

transport parameters;

gas dynamics parameters; and/or

material parameters.

12 . The method according to claim 11 , wherein the beam parameters are a focus diameter and/or laser power.

13 . The method according to claim 11 , wherein the transport parameters are focus position, nozzle-focus distance and/or feed.

14 . The method according to claim 11 , wherein the gas dynamics parameters are gas pressure and/or nozzle-workpiece distance.

15 . The method according to claim 11 , wherein the materials parameter are degree of gas purity and/or melting point of the workpiece.

16 . A device, comprising:

a machine tool configured for creating a cut edge, the cut edge having at least one feature based on cutting parameters;

a camera configured for creating at least one recording of the cut edge, the recording having a multiplicity of recording pixels;

a computer configured to

analyze the recording by way of a trained neural network for determining at least one cutting parameter,

analyze a backpropagation of the neural network for determining a relevance of the recording pixels for ascertaining the determined cutting parameters, and

output the recording with identification of at least one of particularly relevant recording pixels or particularly irrelevant recording pixels; and

said machine tool being configured for receiving an adapted cutting parameter to change the at least one feature of the cut edge based on the identification of the at least one particularly relevant recording pixel or particularly irrelevant recoding pixels.

17 . The device according to claim 16 , wherein the machine tool is a laser cutting machine.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 15, 2022
From: TATZEL, LEONIE FELICA
To: TRUMPF WERKZEUGMASCHINEN SE + CO. KG
Reel/Frame 060513/0858 →
Priority Claims (1)
DE 10 2020 212 510.4 · Oct 2, 2020 · national
Continuity (2)
Continuation PCTEP2021077086 · Oct 1, 2021
Related Publication 20220339739A1 · Oct 27, 2022
References Cited (47)
US 10664767B2 · Takigawa et al. · 2020 [cited by applicant]
US 20130178952A1 · Wersborg et al. · 2013 [cited by applicant]
US 20130184839A1 · Bauer et al. · 2013 [cited by applicant]
US 20140294284A1 · Bryll · 2014 [cited by applicant]
US 20190351512A1 · Izumi · 2019 [cited by applicant]
US 20200285711A1 · Zimanyi · 2020 [cited by examiner]
US 20210245295A1 · Fahrni et al. · 2021 [cited by applicant]
US 20210245298A1 · Kiefer et al. · 2021 [cited by applicant]
US 20220011240A1 · Schwarz · 2022 [cited by applicant]
US 20220019870A1 · Gu · 2022 [cited by applicant]
US 20220043421A1 · Wittwer · 2022 [cited by applicant]
CN 105057899A · 2015 [cited by applicant]
CN 107272015A · 2017 [cited by applicant]
CN 108340088A · 2018 [cited by applicant]
CN 108875740A · 2018 [cited by applicant]
CN 109014626A · 2018 [cited by applicant]
DE 102014205726A1 · 2014 [cited by applicant]
DE 102017105224A1 · 2017 [cited by applicant]
DE 102019112379A1 · 2019 [cited by applicant]
DE 102018216873A1 · 2020 [cited by applicant]
DE 102018129425A1 · 2020 [cited by applicant]
EP 3654248A1 · 2020 [cited by applicant]
JP 2020121338A · 2020 [cited by applicant]
WO 2012000995A1 · 2012 [cited by applicant]
WO 2020064589A1 · 2020 [cited by applicant]
WO WO2020077694A1 · 2020 [cited by examiner]
WO 2020127004A1 · 2020 [cited by applicant]
Verification of the Nonparametric Characteristics of Backpropagation Neural Networks for Image, Zhou et al., Classification (Year: 1999). [cited by examiner]
Quick Roughness Evaluation of Cut Edges using a Convolutional Neural Network, Stahl et al., 2019. [cited by examiner]
Bach et al: “On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer—Wise Relevance Propagation” PLOS ONE, US, vol. 10, No. 7, Jan. 1, 2015 (Jan. 1, 2015), DOI: 10.1371/journal.pone.O130140, ISSN: 1932-6… [cited by applicant]
Stahl et al: “Quick roughness evaluation of cut edges using a convolutional neural network”, SPIE Proceedings; [Proceedings of SPIE ISSN 0277-786X], SPIE, US, vol. 11172, Jul. 16, 2019 (Jul. 16, 2019), pp. 111720P-11172… [cited by applicant]
Petring et al: “Some answers to frequently asked questions and open issues of laser beam cutting”, International Congress on Applications of Lasers & Electro-Optics. ICALEOR, Laser Institute of America, (2012), pp. 43-4… [cited by applicant]
Lecun et al.: “Deep learning”, Nature, (2015), vol. 521, pp. 436-444, XP055574086 DOI: http://dx.doi.org/10.1038/nature14539. [cited by applicant]
Lin et al.: “Automated defect inspection of LED chip using deep convolutional neural network”, Journal of Intelligent Manufacturing (Mar. 29, 2018), vol. 30, doi:10.1007/s10845-018-1415-x, pp. 2525-2534, XP036830977. [cited by applicant]
Fu et al.: “A deep-learning-based approach for fast and robust steel surface defects classification”, Optics Laser in Engineering, 121, (2019), pp. 397-405. [cited by applicant]
Lee et al.: “A Convolutional Neural Network for Fault Classification and Diagnosis in Semiconductor Manufacturing Processes”, IEEE Transactions on Semiconductor Manufacturing, (Mar. 1, 2017), vol. 30, doi: 10.1109/TSM.2… [cited by applicant]
Goncalves et al.: “A convolutional neural network approach on bead geometry estimation for a laser cladding system”, The International Journal of Advanced Manufacturing Technology 106 (5-6):1-11 (Jan. 11, 2020) DOI 10.1… [cited by applicant]
Karatas et al.: “Development of a Convolutional Autoencoder using deep neuronal networks for defect detection and generating ideal references for cutting edges” Munich, Germany, Proc. of SPIE vol. 11056 (2019) DOI 10.11… [cited by applicant]
Samek et al.: “Evaluating the Visualization of What a Deep Neural Network Has Learned”, IEEE Transactions on Neural Networks and Learning Systems 28(11):2660-2673 (2017), DOI 10.1109/ TNNLS.2016.2599820. [cited by applicant]
Montavon et al: Explaining NonLinear Classification Decisions with Deep Taylor Decomposition; Pattern Recognition 65 (2017) 211-222, DOI 10.1016/j. patcog.2016.11.008. [cited by applicant]
Montavon et al.: “Explaining NonLinear Classification Decisions with Deep Taylor Decomposition” arXiv preprint (Dec. 8, 2015) URL https://arxiv.org/pdf/1512.02479.pdf. [cited by applicant]
Montavon et al.: “Layer-Wise Relevance Propagation: An Overview” Sep. 2019, In book: Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (pp. 193-209) DOI:10.1007/978-3-030-28954-6_101 Springer, Cham,… [cited by applicant]
Abadi et al.: “TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems” arXiv preprint (Mar. 16, 2016), URL https://arxiv.org/pdf/1603.04467.pdf. [cited by applicant]
Keras 2.2.4 (see Chollet F (2015) Keras), URL https://keras.io). [cited by applicant]
Alber et al.: “iNNvestigate neural networks!”, Journal of Machine Leaning Research 20 (2019), 1-8. [cited by applicant]
Steen et al.: “Laser Material Processing”, Fourth Edition, Springer Verlag, 2010-e-ISBN 978-1-84996-062-5. [cited by applicant]
Huegel et al.: “Laser in der Fertigung: Strahlquellen, Systeme, Fertigungsverfahren”, [Laser in manufacturing: beam, sources, systems, manufacturing methods], Wiesbaden: Vieweg + Teubner, 2009—English abstract. [cited by applicant]