Injection Molding Machine State Estimation Across Different Specs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing state determination methods for injection molding machines face challenges in accurately diagnosing abnormalities across machines with different specifications, leading to incorrect diagnoses and high costs due to the need for extensive learning data collection and varied equipment combinations.
Innovation Solution
A state determination device and method that converts time-series physical quantities into a reference scale using specification data, allowing machine learning to estimate abnormality degrees without requiring extensive learning data from various machines, and provides alerts or operational adjustments based on abnormality thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If machine learning is performed using measured values from injection molding machines with different specifications, then learning data can be collected from multiple machines, but the divergence between measured values becomes too large to perform correct diagnosis
Solution Approach 1:
The patent transforms the learning approach by changing the parameters used for machine learning. Instead of using raw measured values that vary with machine specifications, the invention uses standardized parameters that are normalized across different machine types. This allows learning data from multiple machines to be combined while maintaining diagnosis accuracy, resolving the contradiction between data quantity and measurement precision.
2Measurement precision
If learning models are created for each combination of equipment specifications, then diagnosis accuracy can be maintained, but the cost and complexity of preparing learning data increases significantly
Solution Approach 1:
The patent creates a universal learning model that can handle multiple machine specifications through parameter standardization. This single model serves multiple functions across different injection molding machine types, eliminating the need to prepare separate learning models for each equipment combination. This reduces the complexity of learning model preparation while maintaining diagnosis accuracy through the standardized parameter approach.
3Measurement precision
If direct measurement of check ring dimension is performed by taking out the screw, then accurate wear measurement can be obtained, but production must be temporarily stopped
Solution Approach 1:
The patent replaces the mechanical measurement system (direct physical measurement by removing the screw) with a sensor-based measurement system. Load sensors and rotation torque sensors continuously monitor the injection molding process, enabling accurate check ring wear measurement without interrupting production. This substitution maintains measurement precision while ensuring production continuity.
Data Source
AI summary
A state determination device that determines an operation state of an injection molding machine stores respective specification data of a reference injection molding machine and an injection molding machine that is different from the reference injection molding machine, and acquires data related to the injection molding machine. Then, the state determination device converts the acquired data into yardstick data by a conversion formula set for every type of data, by using the stored specification data of the reference injection molding machine and the stored specification data of the injection molding machine and performs machine learning using the yardstick data obtained through the conversion so as to generate a learning model.