Molding Machine Condition Correction via Multi-Learner Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing operating condition correction methods using machine learners often result in reverse proposals, leading to inappropriate corrections in molding conditions, which worsen the defects of molded products.
Innovation Solution
An operating condition correction method that involves acquiring measurement and inspection data, using multiple learners to calculate correction quantities, determining the appropriateness of these quantities, and correcting the conditions based on those determined to be accurate, thereby excluding reverse proposals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single learner is used to calculate correction quantities, then the device complexity is reduced, but the reliability of correction decreases due to reverse proposals
Solution Approach 1:
The patent divides the correction calculation into multiple independent learners (first learner and second learner), each calculating correction quantities separately. This segmentation allows for individual evaluation and filtering of reverse proposals from each learner, improving overall correction reliability while maintaining manageable complexity through modular architecture
Solution Approach 2:
The patent introduces an appropriateness determination unit as an intermediary between the learners and the correction application. This mediator evaluates the correction quantities from multiple learners, determines their appropriateness, and filters out reverse proposals before applying corrections, thereby resolving the contradiction between using multiple learners and maintaining system simplicity
2Reliability
If multiple learners are used to calculate correction quantities, then the correction reliability improves, but the device complexity increases
Solution Approach 1:
The patent merges the results from multiple learners through the appropriateness determination unit, which combines and evaluates correction quantities from different learners. This merging approach leverages the strengths of multiple learners to improve correction reliability while the unified evaluation mechanism prevents exponential complexity growth
Solution Approach 2:
The patent implements a feedback mechanism where the appropriateness determination unit evaluates correction quantities and provides feedback on their suitability. This feedback loop allows the system to learn from previous corrections and improve future correction reliability without requiring increasingly complex learner architectures
3Manufacturing precision
If correction quantities are applied without verification, then the productivity is maintained, but the manufacturing precision deteriorates due to reverse proposals
Solution Approach 1:
The patent performs preliminary evaluation of correction quantities through the appropriateness determination unit before applying them to molding conditions. This preliminary action filters out reverse proposals in advance, ensuring that only appropriate corrections are applied, thereby maintaining manufacturing precision without requiring repeated correction cycles that would reduce productivity
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An operating condition correction method is provided that can exclude reverse proposals by learners (40) and correct operating conditions more appropriately. 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 (40) 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 (40); and correcting the operating condition based on one or more of the correction quantities determined as having the correction direction being appropriate.