Machine Tool Thermal Displacement Correction via Remote ML Calibration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing machine learning-based methods for estimating thermal displacement in machine tools require extensive data collection, which is impractical for users as it necessitates stopping the machine tool and may not account for varying user environments, leading to inaccurate thermal displacement corrections.

Innovation Solution

A method that uses backpropagation-based supervised machine learning with a neural network to calculate thermal displacement parameters on the manufacturer side, replicating the user's operational status without stopping the machine tool, and updates these parameters remotely, allowing for accurate thermal displacement corrections in the user's environment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If thermal displacement correction is performed using machine learning with measured data, then manufacturing precision is improved, but productivity deteriorates due to machine tool stoppage for data collection

Engineering Contradiction:
Improvethermal displacement correction accuracyVSAvoidmachine tool availability
Core Design Contradiction:
Manufacturing precisionVSProductivity

Solution Approach 1:

The patent applies preliminary action by pre-collecting and storing thermal displacement data during machine operation phases before actual machining. Temperature sensors and displacement sensors continuously monitor and store thermal displacement amounts during movement phases, so that when correction is needed, the data is already available without requiring machine stoppage. This resolves the contradiction by preparing correction data in advance during normal operation.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements continuity of useful action by enabling thermal displacement correction to be performed continuously during machine operation rather than requiring stoppage. The system continuously collects temperature and displacement data during movement phases, continuously updates thermal displacement amounts using machine learning models, and continuously applies corrections to positioning positions, maintaining both productivity and precision.

Inventive Principle:
Principle #20Continuity of useful action

2Measurement precision

If extensive data collection is performed to train machine learning models, then thermal displacement estimation accuracy is improved, but device complexity increases due to additional measurement devices and data management systems

Engineering Contradiction:
Improvethermal displacement measurement accuracyVSAvoidmeasurement and data management system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies universality by designing a data collection system that serves multiple functions simultaneously. The temperature sensors and displacement sensors are used not only for thermal displacement correction but also for general machine monitoring, maintenance scheduling, and operational analysis. This multi-functionality reduces the need for dedicated separate systems, thereby limiting the increase in device complexity while still enabling extensive data collection for improved measurement precision.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent implements self-service by enabling the machine tool to automatically collect, store, and process its own thermal and displacement data during normal operation. The system uses its existing sensors and control systems to gather data without requiring external measurement devices or complex external data management infrastructure. The machine essentially monitors and corrects itself, reducing overall system complexity.

Inventive Principle:
Principle #25Self-service

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

Enables accurate thermal displacement corrections without reducing machine tool availability, improving machining accuracy by leveraging larger datasets for more precise parameter calculation.

Implementation Method 1

calculating thermal displacement parameters on the manufacturer side, replicating the user's operational status without stopping the machine tool, and updates these parameters remotely, allowing for accurate thermal displacement corrections in the user's environment

Methodology Applied
Scientific EffectBackpropagation-based supervised machine learning:

Implementation Method 2

structures constituting the machine tool are thermally deformed by the ambient temperature in which the machine tool is installed and by heat generated by motion mechanisms of the machine tool operating

Methodology Applied
Scientific EffectThermal expansion: Thermal Expansion

Data Source

PatentEP3871832B1Thermal displacement correction method for a machine tool
Publication Date: 2024.03.13 DMG MORI CO LTD
  • EP3871832B1 patent drawingFigure 1~2
  • EP3871832B1 patent drawingFigure 3~4
  • EP3871832B1 patent drawing

AI summary

Provided is a thermal displacement correction method using a machine learning method but making it possible to, on a user side, calculate a thermal displacement amount appropriate to a machine tool of the user and correct the thermal displacement. In a machine tool on a target user side, a thermal displacement amount between workpiece and tool corresponding to a temperature at a preset measurement point is calculated based on a parameter defining a relation between the temperature and the thermal displacement amount, and a positioning position for workpiece and tool is corrected in accordance with the calculated thermal displacement amount. On a manufacturer side, operational status information of the machine tool on the target user side is obtained, an operational status identical to the obtained operational status on the target user side is reproduced with a machine tool of a same type as the machine tool on the target user side based on the obtained operational status information, a temperature at a measurement point identical to the measurement point on the machine tool on the target user side and a thermal displacement amount between workpiece and tool are measured during reproduction, and the parameter is calculated by machine learning based on the measured temperature and thermal displacement amount. The parameter in the machine tool on the target user side is updated with the calculated parameter.