Wire EDM Disconnection Prediction Using Machining State Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wire disconnection during electric discharge machining occurs frequently due to various machining situations, such as changes in workpiece thickness and the presence of impurities, leading to inefficient machining and reduced productivity, as existing methods require trial processes and labor-intensive adjustments.
Innovation Solution
A wire disconnection prediction device using machine learning, specifically the Mahalanobis Taguchi method, to analyze machining data and predict disconnection risks, allowing for real-time optimization of machining conditions to prevent wire disconnection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional methods (trial machining, bypassing switches) are used to prevent wire disconnection, then wire disconnection can be avoided in some situations, but it requires extensive trial processes, labor-intensive adjustments, and cannot cope with complex combinations of machining situations
Solution Approach 1:
The system performs preliminary learning by collecting machining data during normal machining processes and using this data to create a learning model that predicts wire disconnection risks. This preliminary data collection and model creation enables the system to proactively identify and prevent wire disconnections before they occur, rather than reacting after problems arise or requiring trial-and-error approaches.
Solution Approach 2:
The system continuously monitors machining data during operation and compares it against the learned model to detect situations indicating high wire disconnection risk. This feedback mechanism allows real-time adjustment of machining conditions based on actual machining state, enabling the system to adapt dynamically without requiring manual trial processes or bypassing switches.
2Reliability
If machining conditions are changed to prevent wire disconnection in various situations, then wire disconnection frequency decreases, but machining efficiency and productivity are reduced due to frequent condition adjustments and suspensions
Solution Approach 1:
The system dynamically adjusts machining conditions in real-time based on predicted wire disconnection risk. Rather than using fixed or pre-determined conditions, the control device continuously modifies parameters such as feed rate or discharge conditions according to the current machining state and learned patterns, optimizing both wire reliability and machining efficiency simultaneously.
Solution Approach 2:
The system changes machining parameters (such as feed rate, discharge current, or pulse duration) based on the predicted wire disconnection risk level. By selectively adjusting parameters only when necessary according to learned risk patterns, the system prevents wire disconnections while minimizing interruptions to the machining process and maintaining high productivity.
3Reliability
If trial machining processes are performed for each workpiece type and plate thickness to determine appropriate machining conditions, then wire disconnection can be prevented, but the setup time and labor requirements increase significantly
Solution Approach 1:
The system performs self-learning by automatically collecting machining data during normal operations and using this data to build its own predictive model. This eliminates the need for manual trial machining processes or expert intervention to determine appropriate conditions for different workpiece types, as the system autonomously improves its predictive capability over time through accumulated experience.
Solution Approach 2:
The learning model is designed to handle multiple workpiece types, plate thicknesses, and machining situations universally. Rather than requiring separate trial processes for each specific case, the system learns from diverse machining data and applies the learned patterns across different workpiece configurations, enabling one system to serve multiple functions without increasing setup complexity.
Data Source
AI summary
A wire disconnection prediction device includes: a data acquisition part configured to acquire data relating to machining of a workpiece in a state where a wire is not disconnected during machining of the workpiece by a wire electric discharge machine; a preprocessing part configured to create, machining condition data of a condition relating to a machining condition commanded in machining of the workpiece, machining member data relating to a member used in the machining, and machining state data during machining of the workpiece, as state data indicating a state of the machining; and a learning part configured to generate, based on the state data created by the preprocessing part, a learning model indicating correlation between the state data and the state where the wire of the wire electric discharge machine is not disconnected.