AI Injection Molding Conditions With Feedback Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing injection molding systems rely heavily on expert intervention to set variables like temperature, speed, and pressure, leading to inconsistent product quality and long simulation times using simulation techniques.
Innovation Solution
An AI-based injection molding system utilizing a deep-learning-based molding condition generation model that extracts target standard data from mold information, generates molding conditions, and improves model performance by learning from incorrect outputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If expert intervention is used to set molding variables, then molding conditions can be established, but product quality consistency deteriorates due to variability between different experts
Solution Approach 1:
The system enables self-service through automated AI-based molding condition generation. The molding condition generation model automatically determines optimal molding conditions based on product design data and mold information, eliminating the need for expert intervention and ensuring consistent quality outcomes regardless of operator variability.
Solution Approach 2:
The patent replaces the mechanical expert judgment process with an AI-based computational system. The molding condition generation model uses machine learning algorithms to analyze design data and generate molding conditions, substituting human expert reasoning with automated intelligent processing that provides consistent and reproducible results.
2Manufacturing precision
If simulation technique is used to determine molding conditions, then accuracy can be improved, but processing time increases significantly to 30 minutes to 2 hours
Solution Approach 1:
The system performs preliminary action by pre-training the molding condition generation model using simulation data and expert knowledge before actual production. Once trained, the model can rapidly generate accurate molding conditions without requiring real-time simulation, thus preserving accuracy while dramatically reducing processing time for actual molding operations.
Solution Approach 2:
The patent creates a simplified copy of the complex simulation process through the trained AI model. The molding condition generation model learns from simulation results and expert data to create a surrogate model that replicates simulation accuracy but executes much faster, enabling rapid determination of optimal molding conditions.
3Device complexity
If traditional molding condition setting is used, then process simplicity is maintained, but dependency on experts increases and quality varies
Solution Approach 1:
The system implements self-service by enabling the molding condition generation model to autonomously determine optimal conditions based on input data. The model automatically processes product design data and mold information to generate reliable molding conditions without requiring expert operators, thus improving reliability while maintaining operational simplicity.
Solution Approach 2:
The patent incorporates feedback mechanisms where the system learns from actual molding results and manufacturing data. The molding condition generation model is continuously improved by incorporating feedback from production outcomes, ensuring that the system becomes increasingly reliable and accurate over time while maintaining its automated, expert-independent operation.
Data Source
AI summary
An artificial intelligence-based injection molding system comprising a standard data extraction unit for extracting target standard data of a product produced by a mold from mold information about the mold to which a molding material is supplied; a molding condition output unit inputting the extracted target standard data into a pre-learned molding condition generation model to output a molding condition; an injection molding device, supplying the molding material to the mold according to the molding condition to produce the product; and a determination unit, comparing production standard data of the produced product and the target standard data to determine whether the molding condition is appropriate, wherein, if the determination unit determines that the molding condition is inappropriate, the molding condition output unit generates the production standard data and the molding condition as one set of feedback data, and trains the molding condition generation model with the set of feedback data.