Virtual Temperature Model for Thermal Displacement Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In machine tools, there are areas like spindles and ball screws where temperature sensors cannot be mounted, leading to difficulties in calculating thermal displacement, which affects machining precision due to the inability to acquire accurate temperature data.
Innovation Solution
A machine learning device with a virtual temperature model calculating unit and a thermal displacement model calculating unit estimates temperatures using heat generation and dissipation coefficients, and minimizes errors by adjusting coefficients through machine learning, allowing for thermal displacement compensation even without direct temperature sensing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If temperature sensors are mounted on all machine elements to accurately measure temperature, then measurement precision is improved, but device complexity and ease of manufacture deteriorate due to installation difficulties in certain areas
Solution Approach 1:
The patent creates a virtual temperature model that copies the thermal behavior of machine elements without requiring physical temperature sensors in difficult-to-access areas. The virtual model reproduces temperature distributions based on heat generation factors and thermal conduction relationships, allowing accurate temperature estimation where direct measurement is impractical
Solution Approach 2:
The patent introduces a virtual temperature model as an intermediary between heat generation sources and thermal displacement calculations. This mediator translates heat generation factors into temperature distributions through learned thermal conduction relationships, enabling indirect temperature measurement without physical sensors in all locations
2Ease of manufacture
If virtual temperature modeling is implemented for areas without sensors, then ease of manufacture is improved, but measurement precision deteriorates due to estimation rather than direct measurement
Solution Approach 1:
The patent employs feedback mechanisms where the virtual temperature model is continuously refined using actual temperature measurements from available sensors. The system learns thermal conduction relationships by comparing virtual temperature predictions with real measurements, progressively improving estimation accuracy through iterative optimization
Solution Approach 2:
The patent transforms the temperature measurement problem by changing from direct physical measurement parameters to indirect estimation parameters based on heat generation factors. By measuring easily obtainable parameters (heat generation, ambient temperature) and using learned thermal models, the system achieves accurate temperature estimation without requiring difficult-to-obtain direct measurements
3Manufacturing precision
If machine learning is used to optimize thermal displacement compensation, then manufacturing precision is improved, but device complexity increases due to additional calculation requirements
Solution Approach 1:
The patent performs preliminary machine learning training to establish optimal thermal conduction relationships and virtual temperature models before actual machining operations. By pre-learning thermal behaviors from historical data, the system reduces online calculation complexity while maintaining high compensation accuracy during production
Solution Approach 2:
The patent creates a universal virtual temperature model that serves multiple functions: estimating temperatures in sensor-less areas, predicting thermal displacement, and optimizing compensation parameters. This multi-functional approach reduces overall system complexity by consolidating multiple specialized systems into a single integrated solution
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 enables precise estimation of temperatures and thermal displacements in areas without temperature sensors, improving machining precision and compensating for thermal issues in machine tools.
Implementation Method 1
a virtual temperature calculation equation including a first coefficient for determining a heat generation amount
Implementation Method 2
a second coefficient for determining a heat dissipation amount
Implementation Method 3
there is a problem in that relative thermal displacement occurs between the tool and the workpiece due to thermal expansion of the machine element
Data Source
AI summary
A machine learning device includes a virtual temperature model calculating unit having an equation including a first coefficient for determining a heat generation amount and a second coefficient for determining a heat dissipation amount. The virtual temperature model calculating unit is configured to calculate virtual temperature data by estimating a temperature of a specific portion of a machine by the equation using heat generation factor data. A thermal displacement model calculating unit is configured to calculate, using the calculated virtual temperature data and actual temperature data acquired from at least one temperature sensor mounted to a portion other than the specific portion, an error between thermal displacement estimated by the equation and actually measured thermal displacement, in which the virtual temperature model calculating unit performs machine learning to search for the first coefficient and the second efficient so that the error is minimized.