Method for monitoring the condition of a laser machining head, and laser machining system for carrying out said method
AssigneePrecitec GmbH & Co. KG
InventorsMarian Weber, Niklas Weckenmann
Life of this patent
Estimating the term…
Abstract
A method for monitoring the condition of a laser machining head includes the steps of: detecting current measurement data by means of at least one sensor unit arranged within the laser machining head, determining an input vector based on the acquired current measurement data; and determining an output vector by applying a model trained by machine learning to the input vector, said output vector containing estimated current condition data of at least two elements of the laser machining head.
Claims14
A method for monitoring the condition of a laser machining head, said method comprising the steps of:
- acquiring measurement data by means of at least one sensor unit arranged on or in said laser machining head;
- determining an input vector based on the acquired measurement data;
- and
- determining an output vector by applying a model trained by machine learning to the input vector;
- wherein the output vector contains estimated condition data of at least two elements of said laser machining head for determining the overall condition of said laser machining head;
- wherein the model comprises a plurality of first models and a second model, wherein each of the plurality of first models is used to determine condition data of a respective element of the laser machining head, wherein the second model is used to determine condition of said laser machining head from the condition data of the elements obtained from the first models.
A laser machining system, comprising:
- a laser machining head having at least one sensor unit for acquiring measurement data which is arranged on or in a housing of said laser machining head;
- and
- a computing unit configured to determine an input vector based on the acquired measurement data and to determine an output vector by applying a model trained by machine learning to the input vector;
- wherein the output vector contains estimated condition data of at least two elements of said laser machining head for determining the overall condition of said laser machining head,
- wherein the model comprises a plurality of first models for determining condition data of one element of said laser machining head each and a second model for determining condition data of said laser machining head from the condition data of the elements obtained from the first models, and
- wherein the model is obtained using transfer learning and/or reinforcement learning.
A method for monitoring the condition of a laser machining head, said method comprising the steps of:
- acquiring measurement data by means of at least one sensor unit arranged on or in said laser machining head;
- determining an input vector based on the acquired measurement data;
- and
- determining an output vector by applying a model trained by machine learning to the input vector;
- wherein the output vector contains estimated condition data of at least two elements of said laser machining head for determining the overall condition of said laser machining head;
- wherein the model comprises a plurality of first models for determining condition data of one element of said laser machining head each and a second model for determining condition data of said laser machining head from the condition data of the elements obtained from the first models,
- wherein the first models and the second model are based on at least one of the following algorithms or combinations thereof:
- random forest, support vector machine, fuzzy logic, fuzzy decision tree, a decision tree, a neural network, a recurrent neural network, a convolutional
- neural network, and a deep convolutional neural network.
Dependencies are inferred from the claim text.