Molding Machine Condition Correction Using Multi-Learner Direction Checks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine learning-based systems for correcting operating conditions in industrial machines, such as injection molding machines, often produce reverse proposals that worsen product defects due to incomplete correction accuracy.
Innovation Solution
An operating condition correction method and device that acquire measurement and inspection data, use multiple learners to calculate correction quantities, determine the appropriateness of correction directions, and exclude reverse proposals by selecting only accurate correction quantities for adjusting operating conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single learner is used to calculate correction quantity, then the device complexity is reduced, but the reliability of correction decreases due to reverse proposals
Solution Approach 1:
The system segments the correction calculation task by employing multiple learners (e.g., first learner, second learner, third learner) that each independently calculate correction quantities for different aspects of the molding conditions. This segmentation allows the system to evaluate multiple correction directions and select the most appropriate one, thereby improving reliability while managing complexity through modular architecture
Solution Approach 2:
The system merges the outputs of multiple learners by integrating their correction quantities through a unified selection process. The correction quantity calculation unit combines the results from multiple learners and selects the most appropriate correction quantity, achieving improved reliability through collective decision-making while maintaining systematic organization
2Reliability
If multiple learners are used to calculate correction quantity, then the reliability of correction improves, but the device complexity increases
Solution Approach 1:
The system segments the correction calculation task by employing multiple learners (e.g., first learner, second learner, third learner) that each independently calculate correction quantities for different aspects of the molding conditions. This segmentation allows the system to evaluate multiple correction directions and select the most appropriate one, thereby improving reliability while managing complexity through modular architecture
Solution Approach 2:
Multiple learners are designed with universal functionality to handle different types of defects and molding conditions. Each learner can process measurement data and inspection data to generate correction quantities, making the system versatile and adaptable to various scenarios while maintaining a consistent operational framework that manages complexity
3Manufacturing precision
If correction quantity is calculated without verifying correction direction, then the processing speed is improved, but the manufacturing precision decreases due to reverse proposals
Solution Approach 1:
The system performs preliminary verification of correction directions before finalizing correction quantities. The correction quantity calculation unit checks whether correction quantities from multiple learners have consistent correction directions (e.g., all positive or all negative for the same molding condition). This preliminary action prevents reverse proposals from being applied, ensuring manufacturing precision while minimizing time loss through efficient validation logic
Data Source
AI summary
An operating condition correction method of an industrial machine, comprises: acquiring measurement data obtained by measuring a state of the industrial machine and inspection data obtained by inspecting a state of a product manufactured by the industrial machine; calculating a correction quantity of the operating condition based on the acquired measurement data and inspection data using a plurality of learners trained with an association between the measurement data as well as the inspection data and a correction quantity of the operating condition; determining appropriateness of a correction direction of each of a plurality of the correction quantities calculated using the plurality of learners; and correcting the operating condition based on one or more of the correction quantities determined as having the correction direction being appropriate.