Wire EDM Core Welding Position Adjustment via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional wire electric discharge machines face issues with core dropping and machining efficiency due to inadequate calculation of welding positions and lengths, which do not account for the core's shape, leading to imbalance, retention, and machining difficulties.
Innovation Solution
A machine learning device employing reinforcement learning adjusts welding positions and lengths based on state data and reward conditions to optimize welding parameters, ensuring balanced support and efficient machining.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If conventional methods evenly arrange welding parts on the machining path, then welding parts are uniformly distributed, but the core support balance is poor and retention ability is insufficient
Solution Approach 1:
The patent changes the parameters of welding part arrangement from uniform distribution to non-uniform distribution based on core shape characteristics. The welding part positions and lengths are adjusted according to parameters such as core cross-sectional area, perimeter, and centroid position, thereby improving core support balance and retention ability while adapting to different core geometries
Solution Approach 2:
The patent performs preliminary calculation of welding part positions and lengths before actual machining based on the core shape data. The welding program is pre-optimized by calculating the optimal arrangement of welding parts according to the core geometry, ensuring proper support balance before the machining process begins
2Reliability
If the number of welding parts is increased to improve core retention, then core retention ability improves, but machining time increases
Solution Approach 1:
The patent optimizes the number, positions, and lengths of welding parts by changing arrangement parameters based on core shape characteristics. This allows achieving sufficient core retention with a minimized number of welding parts, thereby maintaining machining efficiency while ensuring reliable core retention
Solution Approach 2:
The patent uses evaluation functions that provide feedback on core retention ability based on welding part arrangement. The system evaluates different welding configurations and selects the optimal one that achieves sufficient retention with the fewest welding parts, balancing reliability and productivity
3Reliability
If welding parts are positioned to optimize core support, then core retention improves, but machining complexity increases
Solution Approach 1:
The patent automatically adjusts welding part parameters (positions, lengths, numbers) based on core shape parameters such as cross-sectional area, perimeter, and centroid. This automated parameter adjustment optimizes core retention while the system manages the programming complexity through algorithmic calculation rather than manual configuration
4Reliability
If welding part lengths are extended to improve core support, then core retention ability improves, but machining time increases
Solution Approach 1:
The patent optimizes welding part lengths by changing parameters based on core shape characteristics. The system calculates the minimal required welding part lengths at specific positions to achieve sufficient core retention, avoiding excessive length that would increase machining time while ensuring adequate support
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 automatically determines optimal welding positions and numbers, generating a tailored welding program that enhances core retention and machining efficiency by balancing support forces and minimizing unnecessary operations.
Implementation Method 1
a wire electric discharge machine that performs machining to cut out a core from a workpiece
Implementation Method 2
welding parts to weld the core and the workpiece to each other using a molten material made by melting the wire electrode
Data Source
AI summary
A machine learning device, performing machine learning for adjusting a position and a length of a welding part when a core is welded to a workpiece in a wire electric discharge machine, acquires the position and the length of the welding part as state data; sets reward conditions; calculates a reward based on the state data and the reward conditions; performs the machine learning of the adjustment; determines and outputs an adjustment target and its adjustment amounts based on the state data and a result of the machine learning; performs the machine learning of the adjustment based on the output adjustment action, the state data acquired based on the recalculated position and the recalculated length of the welding part, and the reward based on the state data; and outputs an optimum position of the welding part, the reward conditions being set as a positive or negative reward.