Injection Molding Dataset Creation for Automated Defect Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing methods for creating datasets for machine learning models that adjust molding condition parameters in injection molding machines require excessive time and labor, as operators need to manually induce and correct molding defects to collect relevant data.
Innovation Solution
A method and device that automatically create datasets by systematically changing molding condition parameters to degrade and then improve product quality, storing associated physical quantity data to generate a learning model dataset, allowing for automated machine learning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual methods are used to create datasets by inducing and correcting molding defects, then the dataset can be created with detailed quality control, but excessive time and labor are required
Solution Approach 1:
The system performs self-testing by automatically inducing molding defects through controlled parameter changes and self-correcting by adjusting parameters to eliminate defects. This automated self-service approach eliminates manual operator intervention while maintaining comprehensive quality control of the collected dataset
Solution Approach 2:
The system pre-establishes a testing framework with predetermined defect-inducing parameter changes and automated correction protocols. By preparing the testing structure in advance, the system can systematically collect high-quality data without manual intervention during actual data collection
2Loss of time
If automated parameter changing is implemented to create datasets, then time and labor are reduced, but the complexity of the system increases
Solution Approach 1:
The system implements automated feedback loops where quality detection results are fed back to control the parameter changing process. This feedback mechanism enables the system to automatically adjust parameters based on detected defects, reducing the need for complex external control systems while maintaining automation
Solution Approach 2:
The molding machine system performs multiple functions: it produces molded products, detects defects, changes parameters automatically, and collects training data. By making the system multi-functional, the patent reduces the need for separate dedicated devices for each function, thereby managing complexity while achieving automation
Data Source
AI summary
Physical quantity data indicating the state of a molded product produced by changing a first molding condition parameter set in a molding machine such that the quality of the molded product is degraded or the state of the molding machine is acquired, physical quantity data indicating the state of a molded product produced by changing a second molding condition parameter set in the molding machine or the state of the molding machine is acquired, the second molding condition parameter before change, the physical quantity data obtained at this time, the second molding condition parameter after change, and the physical quantity data obtained when setting the second molding condition parameter after change are stored in association with each other, and a dataset for machine learning is created by repeating the change of the first and second molding condition parameters and the acquisition of the physical quantity data.