Virtual-Actual Correction for Injection Molding Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current injection molding simulation technologies face challenges in accurately simulating physical information of the melt in mold cavities, leading to inconsistencies between simulated and actual molding results, prolonged development times, and the inability to use simulation data as a direct reference for monitoring production parameters.
Innovation Solution
A machine learning-assisted learning method and apparatus that performs virtual-actual correction by using an autoencoder to extract features from actual and simulated production data, and a multilayer perceptron (MLP) to generate a correction model for improving the accuracy of simulation data, allowing for the adjustment of process parameters and real-time monitoring of production status.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If injection molding simulation software is used to optimize product design and process parameters, then manufacturing precision and productivity are improved, but the simulation results are inconsistent with actual molding results due to simplified mathematical models and incorrect processing conditions
Solution Approach 1:
The patent implements a feedback mechanism by comparing simulation results with actual molding results and using the discrepancies to iteratively optimize the simulation model parameters. This closed-loop approach continuously improves virtual-actual consistency by adjusting mathematical models and processing conditions based on real-world performance data.
Solution Approach 2:
The patent systematically adjusts and optimizes simulation model parameters including mathematical models, material properties, and processing conditions to better match actual molding scenarios. By changing and refining these parameters iteratively, the simulation accuracy and reliability are simultaneously improved.
2Reliability
If simulation parameters are repeatedly adjusted in actual use to match real production, then virtual-actual consistency is improved, but product development time is prolonged
Solution Approach 1:
The patent performs preliminary optimization of simulation parameters and models during the development phase by conducting comparative studies between simulation and actual results. This advance preparation establishes accurate baseline parameters that reduce the need for repeated adjustments during actual production, thereby shortening overall development time while maintaining high virtual-actual consistency.
3Productivity
If simulation data is used as reference for monitoring production parameters, then productivity is improved, but measurement precision is reduced due to inconsistencies between simulated and actual data
Solution Approach 1:
The patent transforms simulation data into reliable monitoring references by systematically optimizing simulation parameters and applying correction factors derived from actual production data. This ensures that simulation-based monitoring maintains both high productivity and accurate measurement precision for critical parameters such as cavity pressure and temperature.
Data Source
AI summary
Disclosed is a learning method for performing virtual-actual correction by machine learning-assisted simulation of a pressure numerical value, the method including: in a pre-step: obtaining actual production data of executing a process parameter by a production device; in a first extraction step: analyzing the actual production data using an autoencoder to obtain a plurality of first features; in a simulation step: executing simulated production data of the process parameter using a production prediction model; in a second extraction step: analyzing the simulated production data using the autoencoder to obtain a plurality of second features; and in a training step: training the plurality of first features and the plurality of second features using a multilayer perceptron (MLP) to obtain a correction model, wherein the correction model can be provided for the MLP to correct the simulated production data into the corresponding actual production data.