Wire EDM Machine Learning Control for Machining Stability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wire electric discharge machines face challenges in achieving consistent machining speed and accuracy due to variations in machining energies caused by differences in electrical resistances, leading to the need for manual adjustment of machining conditions and additional machining operations, which are time-consuming and labor-intensive.
Innovation Solution
The integration of machine learning technology into wire electric discharge machines to automatically adjust machining conditions based on environment and machining state information, using reinforcement learning algorithms to optimize voltage, current, and fluid supply, thereby eliminating differences in machining energies and enhancing reproducibility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual adjustment of machining conditions is performed by operator skill, then machining accuracy can be improved, but it takes time and labor
Solution Approach 1:
The machining condition adjustment device automatically adjusts machining conditions based on machining state data without requiring operator intervention. The system self-diagnoses deviations from reference values and self-corrects by adjusting parameters such as voltage, current, and machining fluid supply amount, eliminating the need for manual operator skill while maintaining machining accuracy.
Solution Approach 2:
The system continuously monitors machining state data (voltage, current, machining speed, etc.) and compares it with reference value data. Based on the deviation detected through this feedback mechanism, the system automatically adjusts machining conditions to maintain optimal performance, replacing manual operator feedback with automated real-time monitoring and adjustment.
2Manufacturing precision
If additional machining and remachining are performed to compensate for energy differences, then machining accuracy is maintained, but productivity decreases
Solution Approach 1:
The system performs preliminary adjustment of machining conditions by detecting deviations from reference values during machining and proactively adjusting parameters before significant errors occur. This prevents the need for additional machining operations by maintaining optimal machining energy throughout the process.
Solution Approach 2:
The machining condition adjustment device automatically compensates for differences in machining energy by adjusting voltage, current, and other parameters in real-time, eliminating the need for additional machining and remachining operations while maintaining machining accuracy and improving productivity.
3Productivity
If theoretical machining conditions are used without adjustment, then setup time is reduced, but machining accuracy varies due to machine differences and position variations
Solution Approach 1:
The system starts with theoretical machining conditions but automatically adjusts parameters (voltage, current, machining fluid supply) based on real-time monitoring of machining state data. This allows the system to maintain setup efficiency while achieving consistent machining accuracy across different machines and positions by dynamically adapting parameters to actual machining conditions.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables automatic adjustment of machining conditions, reducing the need for additional machining and remachining, improving stability and reproducibility, and allowing for sharing of data across machines to enhance learning outcomes.
Implementation Method 1
applies a voltage between a wire-type electrode stretched between upper and lower nozzles, and a workpiece so as to generate electric discharge
Data Source
AI summary
A wire electric discharge machine according to the present invention includes a machine learning device which performs machine learning for adjustment of a machining condition of the wire electric discharge machine, the machine learning device includes a state observation unit which acquires data related to a machining state of a workpiece, a reward calculation unit which calculates a reward based on data related to a machining state, a machining condition adjustment learning unit which determines an adjustment amount of a machining condition based on a machine learning result and data related to a machining state, and a machining condition adjustment unit which adjusts a machining condition based on the determined adjustment amount of a machining condition, and the machining condition adjustment learning unit performs machine learning for adjustment of a machining condition based on the determined adjustment amount of a machining condition, data related to a machining state and acquired by the state observation unit, and a reward which is calculated by the reward calculation unit.