Production Scheduling With Real-Time Progress Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional production planning systems often deviate from actual production due to changes in worker concentration, proficiency differences, and outdated master data, requiring manual adjustments that are time-consuming and inefficient.
Innovation Solution
A production management device that uses real-time progress data from imaging and detection systems to revise short-term plans, predict future progress, and update long-term plans, incorporating neural networks for accurate predictions and template matching for task estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a production plan is generated using a conventional production scheduler, then the plan can be created, but the plan deviates from actual production due to changes in worker concentration, proficiency differences, and outdated master data
Solution Approach 1:
The system continuously monitors actual production progress and feeds this information back to the production scheduler, which automatically adjusts the production plan based on the feedback. This closed-loop control eliminates the need for manual plan adjustments while maintaining high accuracy by adapting to real-time changes in worker performance and production conditions.
Solution Approach 2:
The production scheduler performs self-adjustment by automatically revising production plans based on monitored progress data and predicted worker performance. The system serves itself by detecting deviations and generating corrected plans without human intervention, thereby eliminating time loss associated with manual adjustments while maintaining plan reliability.
2Reliability
If real-time monitoring and prediction systems are implemented to improve production plan accuracy, then deviations are reduced, but system complexity increases
Solution Approach 1:
The system introduces an intermediary prediction function that estimates worker performance and task completion times based on historical data and current conditions. This intermediary layer simplifies the overall system by providing pre-calculated predictions to the production scheduler, reducing the complexity of real-time decision-making while maintaining high plan accuracy through data-driven forecasts.
3Reliability
If manual adjustments are made to production plans to account for worker proficiency differences and concentration changes, then plan accuracy improves, but productivity decreases due to time-consuming adjustments
Solution Approach 1:
The production scheduler automatically detects deviations caused by worker proficiency differences and concentration changes, and self-corrects the production plan without human intervention. This eliminates the time loss associated with manual adjustments while maintaining plan accuracy, thereby preserving production efficiency and preventing productivity degradation.
Solution Approach 2:
The system continuously monitors actual production progress and worker performance, providing real-time feedback to the production scheduler. This enables automatic plan adjustments that account for worker proficiency and concentration variations without requiring manual intervention, thus maintaining high plan accuracy while preventing productivity loss from adjustment delays.
Data Source
AI summary
According to one embodiment, a production management device acquires a first short-term plan generated based on a first long-term plan. The first long-term plan is of a plan of production in a prescribed period. The first short-term plan is of a plan of production in a first period. The device acquires first progress data of a progress in a task, and acquires first prediction data by using the first progress data. The first prediction data is of a prediction of a progress in the task. The device revises the first short-term plan based on the first prediction data, and acquires second prediction data by using second progress data. The second progress data is of a progress in the task. The second prediction data is of a prediction of a progress of the production in the prescribed period. The device generates a second long-term plan in the prescribed period.