Process Condition Prediction for Target Shape Semiconductor Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional semiconductor manufacturing processes are slowed down due to the use of control setting values that are not directly aimed at achieving desired shape processing and surface treatment, leading to inefficiencies in device development and process treatment.
Innovation Solution
An information processing device that determines predetermined process conditions by inputting initial and target state data of a workpiece, using model data elements to predict the end state and select optimal control setting values for the semiconductor manufacturing apparatus.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If control setting values are used to control the semiconductor manufacturing process, then the process can be executed with standardized parameters, but the development speed of devices is slowed down
Solution Approach 1:
The invention changes the control parameters from indirect control setting values to direct shape control parameters. By using shape control parameters that directly represent the desired workpiece geometry, the system enables rapid device development without requiring iterative adjustments of complex manufacturing parameters, thus resolving the contradiction between productivity and control complexity
Solution Approach 2:
The invention inverts the conventional control approach by specifying the desired end shape first and then deriving the manufacturing parameters, rather than starting with control parameters and obtaining the resulting shape. This reverse engineering approach accelerates device development by directly targeting the desired outcome
2Manufacturing precision
If conventional control setting values are used, then the manufacturing process can be standardized, but the precision of achieving desired shape and surface treatment is reduced
Solution Approach 1:
The invention transitions from using indirect control setting values to direct shape control parameters that explicitly define the desired workpiece geometry. This parameter change enables precise control of the manufacturing process to achieve accurate shape and surface treatment while maintaining ease of operation through intuitive shape specification
3Reliability
If multiple model parameters are used to optimize the computerized model, then the association between etched feature profile and input parameters is improved, but the complexity of the model increases
Solution Approach 1:
The invention extracts and uses only the essential shape control parameters from the complex model parameters, focusing on the critical geometric features that directly influence the workpiece shape. This extraction approach maintains high prediction accuracy while reducing model complexity by eliminating redundant parameters
Data Source
AI summary
An information processing device includes: a recording means storing model data that reproduces a change of a workpiece, the model data being constructed, as an effect of process treatment, from differential data between initial state data and end state data of the workpiece, the end state data representing state of the workpiece to which the process treatment is applied under a predetermined process condition; an input receiving means for receiving an input of the initial state data and target end state data of the workpiece; a predicting means for predicting the end state data from the received initial state data, by using the model data and a combination of multiple model data in the recording means; and a determining means for determining a process condition of process treatment to be applied to the workpiece, based on a proximity between the predicted end state data and the target end state data.