Gantt Chart Image Preprocessing for AI Manufacturing Dispatching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing manufacturing systems rely heavily on heuristic methods for scheduling, which require human intervention and limit operational efficiency, and there is a need for more efficient dispatching strategies that can leverage artificial intelligence to analyze manufacturing system states.
Innovation Solution
A device and method for preprocessing images, such as Gantt charts, to generate basic and conditioned images that can be input to an artificial neural network for improved dispatching strategies, utilizing a DEVS-based manufacturing system simulation device with reinforcement learning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If heuristic solutions based on human expertise are used for scheduling, then scheduling can be established with human intervention, but operational efficiency is limited due to requiring human intervention each time
Solution Approach 1:
The patent replaces the mechanical system of human expert intervention with an artificial neural network that processes Gantt chart images. The neural network automatically analyzes the visual representation of manufacturing system state and generates scheduling decisions, eliminating the need for repeated human intervention while maintaining or improving scheduling quality.
Solution Approach 2:
The patent creates a visual copy of the manufacturing system state through Gantt charts, which are then processed by the neural network. This copying approach allows the system to analyze and learn from historical scheduling patterns without requiring human experts to be present for each scheduling decision.
2Loss of information
If Gantt chart images are generated with multiple colors representing different conditions, then comprehensive manufacturing system state information is provided, but image complexity increases
Solution Approach 1:
The patent applies different colors to specific regions of the Gantt chart based on local conditions such as job type, equipment state, or priority. Each color represents a specific attribute or condition at that location, allowing the neural network to extract meaningful features while maintaining a structured and interpretable visual representation.
Data Source
AI summary
A manufacturing system state image preprocessing device in accordance with one embodiment of the present disclosure includes: a basic image generator configured to generate a basic image that visually represents a manufacturing system state based on manufacturing system state data, wherein the basic image includes a Gantt chart; and a conditioned image generator configured to generate one or more conditioned images in which one or more sets of conditions have been applied to the basic image, wherein an output image including at least one of the basic image and the one or more conditioned images is provided as input to an artificial neural network module.