Thermal Displacement Compensation Using Temperature Difference Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing thermal displacement compensation methods for electric discharge machines require significant labor and data measurement across various environmental conditions, making it challenging to create an accurate model for thermal displacement estimation, especially when transitioning between rough and finishing machining or non-machining states.
Innovation Solution
A thermal displacement compensator that utilizes a temperature difference calculation unit to generate input data for machine learning, allowing for the creation of a thermal displacement compensation model that estimates thermal displacement amounts by incorporating the difference between room temperature and water temperature, reducing the need for extensive data measurement across different machining states.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If thermal displacement compensation is performed by measuring temperatures under various environmental conditions and using machine learning, then machining accuracy is improved, but the labor and time required for data measurement and model creation increase significantly
Solution Approach 1:
The patent extracts only the essential temperature parameter (water temperature in the machining tank) that has the most significant impact on thermal displacement, eliminating the need to measure multiple environmental temperatures (room temperature, column temperature, etc.). This extraction approach maintains compensation accuracy while dramatically reducing measurement complexity and time requirements.
Solution Approach 2:
The patent performs preliminary action by pre-calculating thermal displacement amounts based on water temperature measurements and storing them in a lookup table. During actual machining, the system simply retrieves pre-computed compensation values based on current water temperature, avoiding real-time complex calculations and extensive data measurement requirements.
2Measurement precision
If thermal displacement compensation model is created to adapt to various environmental conditions and machining states, then compensation accuracy is improved, but the complexity of the system increases
Solution Approach 1:
The patent extracts and focuses on the single most critical parameter (water temperature) that dominates thermal displacement behavior in electric discharge machining. By eliminating the need to monitor and process multiple temperature sensors and environmental conditions, the system achieves accurate compensation with minimal measurement infrastructure.
Solution Approach 2:
The patent changes the approach from using multiple environmental parameters (room temperature, column temperature, machining fluid temperature) to using a single dominant parameter (water temperature in the machining tank). This parameter simplification maintains compensation accuracy while reducing system complexity.
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 reduces the operational labor required for thermal displacement compensation by enabling accurate estimation of thermal displacement in various temperature patterns, allowing for effective compensation without the need for extensive data measurement across multiple machining states.
Implementation Method 1
These mechanical elements have different coefficients of thermal expansion. For this reason, when the temperatures of the mechanical elements rise to cause thermal strain due to a change in the ambient temperature
Data Source
AI summary
A thermal displacement compensator measures a temperature of an environment in which a machine is installed and a temperature of each part of the machine, and calculates a temperature difference between at least two temperatures among measured temperatures. Furthermore, the thermal displacement amount of the machine is acquired. Then, based on teacher data using the measured temperatures and the calculated temperature difference as input data and using the acquired thermal displacement amount as output data, a thermal displacement compensation model that estimates the output data from the input data is created by machine learning.