Removal Tool Prediction for Reliable Workpiece Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In metal and sheet-material processing machines, particularly in automated laser cutting/punching machines, the selection of removal tools for workpieces is often inefficient, leading to machine downtime due to incorrect parameter settings, especially when handling new or differently positioned workpieces, resulting in laborious manual adjustments and potential removal failures.
Innovation Solution
A method that generates parameters for a removal tool based on workpiece information and characteristic variables, creates a removal prediction using a removal result store, assesses the prediction, and executes the removal process only if positive, with the ability to store and improve the prediction accuracy over time by detecting and storing removal results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If parameters for removal tool are manually selected based on workpiece dimensions, weight and center of gravity, then the removal process can be automated, but incorrect parameter selection leads to machine downtime and laborious manual adjustments
Solution Approach 1:
The system implements feedback by detecting actual removal results and using this information to generate improved removal predictions for future operations. The removal result detection unit monitors whether workpieces are successfully removed, and this feedback is stored and used to refine parameter selection for similar workpieces, creating a self-learning system that improves reliability over time
Solution Approach 2:
The system performs preliminary actions by generating removal predictions before actual removal operations. The removal prediction generation unit creates predicted removal outcomes based on workpiece characteristics and stored historical data, allowing the system to pre-determine appropriate parameters and avoid incorrect selections that would cause downtime
2Reliability
If removal parameters are determined through testing for new workpiece types, then successful removal can be achieved, but considerable time and effort is required
Solution Approach 1:
The system uses copying by storing removal results and parameters from previously successfully removed workpieces in a database. When a new workpiece type is encountered, the system copies relevant parameter sets from similar workpieces in the database, eliminating the need to determine parameters from scratch through time-consuming testing
Solution Approach 2:
The system performs preliminary actions by pre-storing removal results and parameters in the database during initial testing phases. This preliminary data collection enables rapid parameter determination for future workpieces without repeating the time-consuming testing process
3Productivity
If standard removal parameters are used for regular operation, then automated removal can proceed, but failures may occur that require manual intervention
Solution Approach 1:
The system implements feedback by continuously monitoring removal results during regular operation and using this information to refine predictions. When removal failures occur, the system learns from these outcomes and adjusts parameters for future operations, reducing the need for manual intervention while maintaining high productivity
Solution Approach 2:
The system applies dynamics by making removal parameters adaptive rather than static. The removal prediction generation unit dynamically adjusts parameters based on real-time feedback from removal result detection and historical data, allowing the system to respond to varying workpiece conditions while maintaining consistent success rates
Data Source
AI summary
A method handles a workpiece with a removal tool. The method includes: generating at least one parameter for the removal tool; determining at least one characteristic variable from the at least one parameter and at least one item of workpiece information; creating a removal prediction taking into account the characteristic variable and at least one removal result from a removal result store; assessing the removal prediction; removing the workpiece in the event of a positive removal prediction; detecting the removal result; and storing the removal result in the removal result store.