Thermal Displacement Correction in Machine Tools Using Machine Learning
Here’s PatSnap Eureka !
Summary
Problems
Existing machine tools face challenges in accurately correcting thermal displacement caused by various heat sources, leading to inaccuracies in positioning between the cutting edge of a tool and a workpiece.
Innovation solutions
A controller and machine tool system that utilizes data collection circuitry for machining data, temperature circuitry for temperature data, dimension data input circuitry, learning data generation circuitry, and machine learning circuitry to generate a correction coefficient for thermal displacement based on temperature data and learning data.
TRIZ Analysis
Specific contradictions:
General conflict description:
Principle concept:
If multiple temperature sensors are mounted on components to correct thermal displacement, then the correction accuracy improves, but the device complexity increases
Why choose this principle:
The patent divides thermal displacement correction into separate components: drive-system thermal displacement correction and environment temperature-system thermal displacement correction. Each component is measured and corrected independently, allowing complex thermal effects to be broken down into manageable segments that can be addressed with appropriate sensing and calculation methods.
Principle concept:
If multiple temperature sensors are mounted on components to correct thermal displacement, then the correction accuracy improves, but the device complexity increases
Why choose this principle:
The patent introduces a thermal displacement correction amount setting changer as an intermediary device that coordinates between multiple temperature sensors and the control system. This intermediary processes temperature data from multiple sensors and generates appropriate correction amounts, reducing the complexity of directly managing multiple sensors and their data.
Application Domain
Data Source
AI summary:
A controller and machine tool system that utilizes data collection circuitry for machining data, temperature circuitry for temperature data, dimension data input circuitry, learning data generation circuitry, and machine learning circuitry to generate a correction coefficient for thermal displacement based on temperature data and learning data.
Abstract
A controller includes data collect circuitry configured to collect machining data including a date and a time when at least one machined portion of a workpiece has been machined by a machine tool, temperature circuitry configured to obtain, at predetermined time intervals, temperature data at positions on the machine tool, dimension data input circuitry configured to receive dimension measurement data which includes a dimension of the machined portion after the machined portion has been machined, learning data generate circuitry configured to generate learning data based on the machining data and the dimension measurement data, and machine learning circuitry configured to execute a machine learning based on the temperature data and the learning data to obtain a correction coefficient based on which a displacement caused by a change in a temperature of the machine tool is corrected according to a thermal displacement correction equation.