Method for analysing a laser machining process, system for analysing a laser machining process and laser machining system comprising a system of this type

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional laser processing monitoring systems are complex and require expert adjustment, unable to quantify physical properties of processing results like strength or conductivity without destructive testing, limiting precision and efficiency in quality assessment.

Innovation Solution

A procedure using a learned neural network to determine physical properties of laser processing results from sensor data sets, allowing for non-destructive prediction of values such as strength, conductivity, and welding depth without separate measuring devices, enabling real-time monitoring and regulation of the process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional monitoring systems are used to analyze laser processing data, then quality assessment can be performed, but the system complexity increases and requires expert adjustment

Engineering Contradiction:
Improvequality assessment reliabilityVSAvoidmonitoring system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system uses automated machine learning models and algorithms that self-adjust and optimize without requiring expert intervention. The monitoring system performs self-service by automatically calibrating parameters and adapting to different processing conditions through trained models, eliminating the need for manual expert adjustment while maintaining high reliability

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces complex manual expert analysis with automated computational algorithms and machine learning models. The mechanical/electrical complexity of manual monitoring is substituted with software-based intelligent systems that automatically process sensor data and provide quality assessments without human intervention

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If conventional monitoring systems are used, then processing can be monitored, but the ability to quantify physical properties like strength and conductivity is limited

Engineering Contradiction:
Improvephysical property quantification precisionVSAvoidsystem implementation ease
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

The patent introduces machine learning models as intermediaries between sensor data and physical property quantification. These models act as mediators that translate raw sensor measurements into accurate predictions of physical properties like strength and conductivity, enabling precise measurement without direct physical contact or complex measurement apparatus

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system changes the parameter representation from raw sensor data to processed physical property values through trained models. By transforming the data parameters through machine learning algorithms, the system enables precise quantification of physical properties while maintaining ease of implementation through software-based transformation

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If destructive testing is used to determine physical properties, then accurate measurements can be obtained, but production efficiency decreases

Engineering Contradiction:
Improvephysical property measurement accuracyVSAvoidproduction efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent creates a virtual copy or digital twin of the physical property measurement process through machine learning models. Instead of physically destroying the workpiece for testing, the system uses trained models to predict physical properties from sensor data, providing accurate measurements while preserving the workpiece for continued production

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces physical destructive testing mechanisms with computational prediction models. The mechanical process of physical testing is substituted with software-based analysis that provides equivalent or superior measurement accuracy without the need for physical destruction of test samples

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

4Reliability

If expert adjustment is required for monitoring parameters, then reliable monitoring can be achieved, but operational ease decreases

Engineering Contradiction:
Improvemonitoring reliabilityVSAvoidsystem operation ease
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system performs self-service by automatically adjusting monitoring parameters and adapting to different processing conditions through pre-trained machine learning models. The system self-calibrates and optimizes without requiring expert intervention, maintaining high reliability while being easy to operate

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent applies preliminary action by pre-training machine learning models with extensive data before deployment. This preliminary training phase captures expert knowledge and optimizes parameters in advance, so that during actual operation the system automatically applies these pre-optimized settings without requiring real-time expert adjustment

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4146426B1Method for analysing a laser machining process, system for analysing a laser machining process and laser machining system comprising a system of this type
Publication Date: 2025.01.29 PRECITEC GMBH
  • EP4146426B1 patent drawingFigure 1
  • EP4146426B1 patent drawingFigure 2
  • EP4146426B1 patent drawingFigure 3

AI summary

The invention relates to a method for analysing a laser machining process for machining workpieces, said method comprising the following steps: detecting at least one sensor data set for the laser machining process; and determining a value of at least one physical property of a machining result of the laser machining process, based on the at least one sensor data set by means of a transfer function, wherein the transfer function is formed by a trained neural network. The invention also relates to a system (200) for analysing a laser machining process and a laser machining process (100) comprising a system (200) of this type.