Machine Learning Acceleration Controller for Machine Tool Surface Quality
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine tool control techniques fail to optimize acceleration and deceleration based on actual machined surface quality, requiring pre-calculated threshold values for vibration data and lacking direct feedback on surface quality during machining.
Innovation Solution
A machine learning-based acceleration and deceleration controller that learns the Nth-order time-derivative component of axis speeds in relation to machining accuracy, surface quality, and machining time, using state observation and determination data to automatically adjust speed distributions for optimal machining without pre-set threshold values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If pre-calculated threshold values for vibration data are used to control acceleration and deceleration, then the control system is simple to implement, but the machined surface quality cannot be directly optimized and requires test machining to determine thresholds
Solution Approach 1:
The patent implements feedback by using the actual machined surface quality as determination data to evaluate and adjust acceleration and deceleration control. The machine learning apparatus continuously learns from the relationship between speed derivatives and surface quality, creating a closed-loop system where the output (machined surface) feeds back to optimize the input parameters (acceleration and deceleration), eliminating the need for pre-calculated thresholds and test machining.
2Manufacturing precision
If machine learning is used to learn the relationship between speed derivatives and surface quality, then optimal acceleration and deceleration can be achieved, but the system complexity increases
Solution Approach 1:
The machine learning apparatus performs self-service by automatically learning and optimizing the acceleration and deceleration control parameters without requiring external intervention for threshold setting or parameter tuning. The system autonomously processes determination data from machined surfaces and adjusts control parameters independently, reducing the need for complex external calibration systems and expert intervention.
Solution Approach 2:
The patent changes the control parameters from fixed pre-calculated thresholds to dynamically learned parameters based on the actual machined surface quality. By using the Nth-order time-derivative components of speed as learnable parameters that adapt to specific machining conditions, the system achieves optimal control for each situation without requiring complex manual configuration or multiple fixed threshold sets.
3Reliability
If test machining is performed to determine threshold values, then appropriate thresholds can be obtained, but the machining time increases and productivity decreases
Solution Approach 1:
The machine learning apparatus performs preliminary learning during the machining process itself, using determination data from actual machined surfaces to establish accurate control parameters for subsequent operations. This eliminates the need for separate pre-machining test runs, as the system continuously adapts and optimizes parameters in real-time, ensuring both accuracy and productivity without sacrificing one for the other.
Data Source
AI summary
A controller for a machine tool includes a machine learning apparatus configured to learn an Nth-order time-derivative component of a speed of each axis of the machine tool. The machine learning apparatus includes: a state observation section configured to observe first state data representing the Nth-order time-derivative component of the speed of each axis as a state variable representing a current state of an environment; a determination data acquisition section configured to acquire determination data representing a properness determination result of at least any one of machining accuracy, surface quality, and machining time of the machined workpiece; and a learning section configured to learn the Nth-order time-derivative component of the speed of each axis in relation to at least any one of the machining accuracy, the surface quality, and the machining time of the machined workpiece using the state variable and the determination data.