Semiconductor Equipment Schedule Control Using Sub-Operation Timing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Optimizing the equipment operation schedule in semiconductor processing equipment to improve productivity and reduce bottlenecks in wafer processing is challenging due to varying parameters and times required for different operations.
Innovation Solution
A control method for semiconductor processing equipment that involves obtaining and comparing times for unit operations under different setting values, using emulation and machine learning models to determine the optimal schedule for minimizing processing time, and controlling the equipment accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple different setting values are tested to find the optimal operation schedule, then productivity is improved, but the time and computational resources required for optimization increase
Solution Approach 1:
The system performs preliminary actions by obtaining discrete time values for each sub-operation before actual equipment operation. These time values are stored and used for future schedule optimizations, avoiding the need to repeatedly measure actual operation times and enabling faster determination of optimal schedules in subsequent operations.
Solution Approach 2:
The system creates a virtual model (copy) of the equipment operation by using discrete time values to represent actual operation durations. This virtual model allows for simulated testing of multiple schedules and setting values without requiring physical equipment operation, significantly reducing optimization time while maintaining accuracy.
2Productivity
If the operation schedule is optimized to reduce processing time, then productivity improves, but the complexity of schedule determination increases
Solution Approach 1:
The system segments the unit operation into multiple sub-operations, each with its own discrete time value. This segmentation allows for independent measurement and optimization of each sub-operation's time consumption, making the overall schedule optimization more manageable and less complex than treating the entire operation as a single unit.
Solution Approach 2:
The system changes parameters by testing different setting values (combinations of process parameters) and their corresponding schedules. By systematically varying these parameters and measuring their impact on total operation time, the system identifies optimal parameter combinations without requiring complex analytical models.
3Measurement precision
If discrete time values are obtained for multiple sub-operations to enable precise scheduling, then schedule optimization accuracy improves, but the data collection and processing complexity increases
Solution Approach 1:
The system performs preliminary measurement of discrete time values for each sub-operation before actual scheduling decisions are made. These pre-collected time values are stored for reuse, eliminating the need for repeated measurement and reducing the complexity of real-time data processing while maintaining high measurement precision.
Data Source
AI summary
A control method for semiconductor processing equipment, may include: obtaining a first time taken for the semiconductor processing equipment to perform a unit operation according to a first setting value including a plurality of parameters for controlling the semiconductor processing equipment; obtaining a second time taken for the semiconductor processing equipment to perform the unit operation according to a second setting value having at least one parameter different from at least one of the parameters of the first setting value; and controlling the semiconductor processing equipment with the first setting value set, based on the first time being smaller than the second time. The obtaining of the first time may include obtaining the first time taken for the semiconductor processing equipment to perform a plurality of sub-operations constituting the unit operation sequentially, according to a first schedule determined by the first setting value.