NC Tool Path Generation Using Machine-Learned Surface Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Generating a desired tool path in NC machining is difficult, especially for complex workpieces, when the operator lacks experience.
Innovation Solution
A method and device that utilize machine learning to generate a tool path based on geometric information of machining surfaces and tool path patterns of known workpieces, using a neural network to automatically create a new tool path for a target workpiece.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If tool path is generated by inputting various data into CAM software based on operator experience, then the tool path can be generated using existing methods, but it is difficult to generate a desired tool path when the operator is inexperienced or the workpiece has a complex shape
Solution Approach 1:
The patent copies successful tool path patterns from multiple known workpieces with similar geometric characteristics. By storing and reusing proven tool path patterns from a database, the system replicates the expertise of skilled operators without requiring them to manually create paths for each new workpiece, thereby improving reliability while reducing operator experience requirements.
Solution Approach 2:
The patent transforms tool path generation from a manual parameter-input process to an automated pattern-matching process. By changing the input parameters from operator-specified values to geometric information-based pattern selection, the system adapts to complex workpiece shapes automatically, improving both reliability and ease of operation.
2Extent of automation
If machine learning is used to automatically generate tool path patterns based on geometric information, then a new tool path can be generated based on multiple examples, but the system complexity increases
Solution Approach 1:
The patent replaces the mechanical/manual process of tool path creation with a machine learning-based automated system. By substituting human operator actions with an automated neural network that learns from geometric information, the system achieves high automation while managing complexity through software-based pattern recognition rather than complex hardware configurations.
Solution Approach 2:
The patent performs preliminary machine learning training using geometric information and tool path patterns from multiple known workpieces before actual tool path generation. This preliminary action creates a trained model that can automatically generate tool paths without requiring complex real-time decision-making, thereby increasing automation while keeping the operational system relatively simple.
3Measurement precision
If multiple tool path patterns are generated and stored for different machining surfaces, then the accuracy of tool path generation improves, but the data processing complexity increases
Solution Approach 1:
The patent segments the tool path generation process by creating separate tool path patterns for different machining surface types (e.g., planar, inclined, curved surfaces). By dividing the overall tool path into surface-specific patterns, the system achieves higher accuracy for each surface type while managing data complexity through organized categorization and selective application of patterns based on geometric information.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This method comprises a step for performing machine learning and a step for generating a new tool path. The step for performing machine learning includes, for each of a plurality of known workpieces: acquiring shape data; acquiring geometric information for each of a plurality of machining faces; acquiring a tool path pattern selected for each of the plurality of machining faces from among a plurality of tool path patterns; and performing machine learning by using the geometric data for the plurality of known workpieces and the tool path patterns wherein the input is the geometric information for the machining faces and the output is the tool path pattern for the machining faces. The step for generating a new tool path includes: acquiring shape data for the workpiece to be machined; acquiring geometric information for each of the plurality of machining faces of the workpiece to be machined; and generating a tool path pattern for each of the plurality of machining faces on the workpiece to be machined on the basis of the results of the machine learning using the geometric information of the workpiece to be machined.