17724009. METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE AND COMPUTING DEVICE PERFORMING THE SAME simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
Contents
- 1 METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE AND COMPUTING DEVICE PERFORMING THE SAME
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE AND COMPUTING DEVICE PERFORMING THE SAME - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Original Abstract Submitted
METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE AND COMPUTING DEVICE PERFORMING THE SAME
Organization Name
Inventor(s)
Gwangnae Gil of Yongin-si (KR)
Seyoung Park of Hwaseong-si (KR)
Jonghyun Lee of Hwaseong-si (KR)
METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE AND COMPUTING DEVICE PERFORMING THE SAME - A simplified explanation of the abstract
This abstract first appeared for US patent application 17724009 titled 'METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE AND COMPUTING DEVICE PERFORMING THE SAME
Simplified Explanation
The abstract describes a method for predicting the characteristics of a semiconductor device using a combination of input data and simulation results. Here are the key points:
- The method uses a technology computer aided design (TCAD) simulator to generate basic training data.
- The TCAD simulator performs simulations based on input data to generate simulation result data.
- The simulation result data indicates the characteristics of semiconductor devices corresponding to the input data.
- A deep learning model is trained using the basic training data to predict the characteristics of semiconductor devices.
- The deep learning model is configured to output prediction data indicating the characteristics of the semiconductor devices.
- Target prediction data is generated based on the deep learning model and input data for a specific semiconductor product.
- The target prediction data indicates the characteristics of the semiconductor device included in the target product.
Potential Applications
This technology has potential applications in various fields related to semiconductor device design and manufacturing, including:
- Semiconductor industry: The method can be used to predict the characteristics of semiconductor devices, helping in the design and optimization of new devices.
- Electronics manufacturing: By accurately predicting device characteristics, manufacturers can ensure the quality and performance of their products.
- Research and development: Researchers can use this method to explore new semiconductor device designs and analyze their characteristics before fabrication.
Problems Solved
This technology addresses several challenges in the semiconductor industry:
- Time-consuming simulations: Traditional simulation methods can be time-consuming, especially for complex devices. This method uses deep learning to speed up the prediction process.
- Accuracy of predictions: Deep learning models can learn complex patterns and relationships from training data, leading to more accurate predictions of device characteristics.
- Design optimization: By predicting device characteristics early in the design process, engineers can optimize their designs for better performance and efficiency.
Benefits
The use of deep learning and TCAD simulation in predicting semiconductor device characteristics offers several benefits:
- Faster prediction: The deep learning model can quickly generate predictions without the need for time-consuming simulations.
- Improved accuracy: The model can learn from a large amount of training data, leading to more accurate predictions of device characteristics.
- Cost savings: By accurately predicting device characteristics, manufacturers can avoid costly design iterations and reduce time-to-market.
- Enhanced design optimization: Engineers can use the predictions to optimize their designs for better performance and efficiency.
Original Abstract Submitted
To predict characteristics of a semiconductor device, basic training data corresponding to a combination of input data and simulation result data are generated using a technology computer aided design (TCAD) simulator. The TCAD simulator generates the simulation result data by performing a simulation based on the input data of the TCAD simulator such that the simulation result data indicates characteristics of semiconductor devices corresponding to the input data of the TCAD simulator. A deep learning model is trained based on the basic training data such that the deep learning model is configured to output prediction data indicating the characteristics of the semiconductor devices. Target prediction data is generated based on the deep learning model and input data corresponding to the target semiconductor product such that the target prediction data indicates the characteristics of the semiconductor device included in the target semiconductor product.
