Semiconductor Production Schedule Estimation for Dynamic Cycle Times
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional production scheduling inference methods for semiconductor processes lack accuracy due to their inability to respond to changes in machine cycle times caused by varying product combinations and conditions.
Innovation Solution
A production schedule estimation method and system that utilizes a prediction model to calculate current-day cycle time data and move volume for each station in a machine group, based on current-day work-in-process data, machine group cycle time data, and productivity data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional fixed cycle time calculation method is used, then calculation simplicity is maintained, but production schedule accuracy deteriorates due to inability to respond to changes in machine cycle times
Solution Approach 1:
A prediction model is introduced as an intermediary between historical data and production scheduling. The model processes work-in-process data, cycle time data, and productivity data to generate accurate production schedules, acting as a mediator that translates raw data into actionable scheduling information while adapting to changing machine conditions
Solution Approach 2:
The system implements feedback by continuously inputting current work-in-process data, cycle time data, and productivity data into the prediction model. This creates a closed-loop system where actual production conditions are fed back into the scheduling system, enabling dynamic adjustment and improving accuracy over time
2Adaptability or versatility
If traditional production scheduling method is used, then system simplicity is maintained, but adaptability to different product combinations and conditions deteriorates
Solution Approach 1:
The prediction model transforms the static fixed cycle time approach into a dynamic system that automatically adjusts to changing conditions. The model processes current-day work-in-process data, cycle time data, and productivity data to generate adaptive production schedules that respond to varying product combinations and machine conditions
Solution Approach 2:
The system changes the parameter of cycle time from a fixed historical value to a dynamic predicted value based on current conditions. By inputting current work-in-process data, cycle time data, and productivity data into the prediction model, the system generates updated cycle time predictions that reflect current machine states and product combinations
Data Source
AI summary
A production schedule estimation method and a production schedule estimation system are provided. The production schedule estimation method includes the following steps. Current-day work-in-process data, machine group cycle time data of a machine group, and productivity data of the machine group are obtained. The current-day work-in-process data, the cycle time data of the machine group, and the productivity data of the machine group are inputted into a prediction model. Current-day cycle time data and a current-day move volume for each of multiple stations in the machine group are calculated through the prediction model. And, current-day move data is calculated according to the current-day cycle time data and the current-day move volume for each of the multiple stations in the machine group.