Reinforcement Learning Injection Molding System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current injection molding systems require significant operator time and skill to calculate optimum operating conditions, leading to inconsistencies and increased energy consumption, as existing technologies rely on manual adjustments and stored molding data without effective automation.
Innovation Solution
An injection molding system equipped with artificial intelligence and machine learning capabilities, utilizing a reinforcement learning algorithm to observe and adjust operating conditions based on physical data, reward calculations, and learning results, allowing for rapid adjustment of molding parameters and reduced energy consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual adjustment of operating conditions by operator is used, then operating conditions can be calculated, but it takes significant time and shows inconsistency depending on operator skills
Solution Approach 1:
The system performs self-learning through reinforcement learning, automatically adjusting operating conditions without requiring manual operator intervention. The machine learning model continuously improves by learning from observed molding results and physical amount data, enabling the system to calculate optimal operating conditions autonomously and consistently.
Solution Approach 2:
The patent replaces the manual mechanical adjustment process with an automated information processing system. The reinforcement learning algorithm substitutes the operator's experience-based decision-making with data-driven automatic calculation, eliminating human variability and significantly reducing the time required to determine optimal operating conditions.
2Use of energy by moving object
If manual adjustment of operating conditions is used, then molding can be performed, but energy consumption is high
Solution Approach 1:
The reinforcement learning system optimizes multiple operating parameters simultaneously (injection pressure, temperature, timing, etc.) to find the energy-efficient combination that maintains product quality. By continuously learning from physical amount data and molding results, the system identifies parameter settings that minimize energy consumption while preserving manufacturing precision.
3Extent of automation
If stored molding data is used for reference, then some assistance is provided, but it does not enable automatic optimization of operating conditions
Solution Approach 1:
The system implements closed-loop feedback by observing physical amounts during molding, comparing results with target values, and using the difference (reward signal) to guide further adjustments. This feedback mechanism enables automatic optimization without requiring complex external systems, as the learning process is driven by the system's own operational data and performance metrics.
Data Source
AI summary
Disclosed is an injection molding system including: a state observation section observing, when injection molding is performed, physical-amounts relating to the injection molding that is being performed; a physical-amount data storage section storing the physical-amount data; a reward-conditions setting section setting reward conditions for machine learning; a reward calculation section calculating a reward based on the physical-amount data and the reward conditions; an operating-conditions adjustment learning section performing machine learning of adjusting operating conditions based on the reward calculated by the reward calculation section, the operating conditions, and the physical-amount data; a learning-result storage section storing a learning result of the machine learning by the operating-conditions adjustment learning section; and an operating-conditions adjustment-amount output section determining and outputting an operating condition to be adjusted and an adjustment amount based on the machine learning by the operating-conditions adjustment learning section.