Wire EDM Feed Rate Correction Using Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing control systems for wire electric discharge machines face challenges in maintaining a constant discharge gap, leading to machining precision issues due to the complexity of correlating inter-electrode average voltage and discharge delay time with discharge gap, requiring extensive experimentation to determine correction parameters, which is time-consuming and not adaptable to varying machining conditions.
Innovation Solution
A machine learning device is implemented to autonomously learn and determine the optimal correction parameter for feed rate control by observing machining conditions, acquiring data on machining precision, and using supervised learning algorithms to establish correlations between variables such as wire diameter, workpiece thickness, and machining shape, thereby reducing the need for extensive experimentation and enabling quick adaptation to different machining scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If control is performed based on detected values of alternative indicators (inter-electrode average voltage and discharge delay time), then the discharge gap can be maintained constant in linear portions, but the correlation between these indicators and discharge gap collapses at corner portions leading to machining precision degradation
Solution Approach 1:
The invention applies different correction parameters specifically for corner portions versus linear portions. The control device detects whether the wire electrode is machining a corner portion or linear portion, and selectively applies appropriate correction parameters to maintain discharge gap constancy in each specific location, rather than using a uniform control approach
Solution Approach 2:
The invention changes the control parameters (correction parameters) based on the machining portion type. By detecting the machining portion type and switching between different correction parameters, the system adapts the control characteristics to match the specific requirements of corner versus linear machining, resolving the correlation collapse issue
2Manufacturing precision
If correction parameters are determined through extensive experimentation based on empirical rules, then machining precision can be improved for specific conditions, but the time required to determine these parameters increases significantly and the system cannot adapt to varying machining conditions
Solution Approach 1:
The control device automatically detects whether the current machining is on a corner portion or linear portion and autonomously selects the appropriate correction parameter. This self-service capability eliminates the need for manual empirical rule application and extensive experimentation for each machining condition, significantly reducing parameter determination time while maintaining precision
3Manufacturing precision
If the feed rate is increased for outer corner machining to maintain discharge gap, then machining precision at corners is improved, but the control system requires complex empirical rules and extensive experimentation to determine the appropriate feed rate adjustments
Solution Approach 1:
The control device uses feedback from the machining state detection to automatically adjust the feed rate. By detecting the machining portion type in real-time and applying appropriate correction parameters, the system provides automatic feedback-based control that simplifies the overall control logic while achieving the required precision for corner machining
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
The machine learning device allows for the automatic and accurate determination of optimal correction parameters, improving machining precision and reducing the time required for setting these parameters, enabling the control system to respond effectively to various machining conditions without relying on empirical rules or extensive experimentation.
Implementation Method 1
wire electrical discharge machining process
Data Source
Figure 1
Figure 2
Figure 3A~3B
AI summary
A control device of a wire electric discharge machine and a machine learning device are provided that can appropriately and readily determine a correction parameter. The control device, which optimizes the correction parameter for wire electrical discharge machining process, includes a machine learning device configured to learn the correction parameter for the wire electrical discharge machining process. The machine learning device includes a state observation unit configured to observe, as a state variable, condition data indicative of a condition for the wire electrical discharge machining process, a determination data acquisition unit configured to acquire determination data indicative of the correction parameter of the case where machining precision is favorable in the wire electrical discharge machining process, and a learning unit configured to learn the correction parameter in association with the condition for the wire electrical discharge machining process using the state variable and the determination data.