Learning Program Extraction for Machine Tool Motor Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Machine learning for devices with driving units, such as machine tools and robots, requires extensive time and memory resources when using actual machining programs for learning, especially when dealing with large datasets.
Innovation Solution
An information processing device and method that generates a learning program by extracting partial machining programs with characteristic elements from existing machining programs, allowing for faster and more efficient learning without the need for large memory capacities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If learning is performed using the actual machining program for machining works, then the learning accuracy is improved, but the learning time increases considerably
Solution Approach 1:
The invention extracts only the necessary characteristic elements (acceleration, deceleration, reversal points, positioning operations) from the complete machining program to create a learning program. This extraction process removes unnecessary data while preserving the essential motor operating characteristics needed for accurate learning, thereby reducing learning time while maintaining learning accuracy.
Solution Approach 2:
The machining program is segmented into discrete characteristic elements such as acceleration phases, deceleration phases, reversal points, and positioning operations. Each segment represents a specific motor operating pattern that can be independently analyzed and learned, allowing the system to focus on critical patterns rather than processing the entire program sequentially.
2Reliability
If the amount of data of the machining program is large, then the learning comprehensiveness is improved, but the memory capacity requirement increases
Solution Approach 1:
The system extracts only the essential characteristic elements from the large-volume machining program data, identifying and isolating key patterns such as acceleration profiles, deceleration patterns, reversal points, and positioning operations. This extraction reduces the data volume requiring memory storage while preserving the comprehensive motor operating characteristics needed for reliable learning.
Solution Approach 2:
The large dataset is segmented into discrete, manageable characteristic elements that can be stored and processed efficiently. Each segment represents a specific motor operating pattern that contributes to learning comprehensiveness without requiring proportional increases in memory capacity.
3Reliability
If the complete machining program is used for learning, then all operating characteristics are covered, but the processing complexity increases
Solution Approach 1:
The system extracts only the relevant characteristic elements from the complete machining program, removing unnecessary data while preserving all essential motor operating characteristics. This extraction simplifies the processing complexity by focusing computational resources on critical patterns rather than analyzing every instruction in the complete program.
Solution Approach 2:
The complete machining program is segmented into distinct characteristic elements (acceleration, deceleration, reversal, positioning) that can be processed independently. This segmentation reduces processing complexity by allowing parallel or sequential analysis of discrete patterns rather than requiring complex analysis of the entire program as a single unit.
Data Source
AI summary
Learning related to a device having a driving unit is performed more easily. An information processing device includes: a storage unit that stores a machining program for operating a motor of a machine tool, a robot, or an industrial machine; and a generation unit that generates a learning program for performing learning based on operating characteristics of the motor by extracting a partial machining program including a characteristic element from the machining program stored in the storage unit.