20230125401. METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE AND COMPUTING DEVICE PERFORMING THE SAME simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE AND COMPUTING DEVICE PERFORMING THE SAME
Organization Name
Inventor(s)
Jonghyun Lee of Hwaseong-si (KR)
Gwangnae Gil of Yongin-si (KR)
Seyoung Park 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 20230125401 titled 'METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE AND COMPUTING DEVICE PERFORMING THE SAME
Simplified Explanation
The patent application describes a method for predicting the characteristics of a semiconductor device using simulation and deep learning techniques. Here is a simplified explanation of the abstract:
- The method involves generating a simulation current-voltage curve for a semiconductor device using compact models.
- Compact models simulate the device data and generate simulation result data that indicate the characteristics of the semiconductor devices.
- Simulation reference points are extracted from the simulation current-voltage curve.
- Basic training data is generated by combining the simulation reference points and the simulation current-voltage curve.
- A deep learning model, specifically a generative adversarial network, is trained using the basic training data.
- The trained deep learning model can then output a prediction current-voltage curve.
- A target prediction current-voltage curve is generated based on the deep learning model and target reference points for a specific semiconductor product.
Potential applications of this technology:
- Semiconductor device design and optimization
- Quality control in semiconductor manufacturing
- Predicting the performance of new semiconductor products
Problems solved by this technology:
- Traditional methods for predicting semiconductor device characteristics may be time-consuming and require extensive manual analysis.
- The use of deep learning and simulation techniques can provide more accurate and efficient predictions.
Benefits of this technology:
- Faster and more accurate prediction of semiconductor device characteristics
- Reduction in manual analysis and labor-intensive processes
- Improved design and optimization of semiconductor devices
- Enhanced quality control in semiconductor manufacturing.
Original Abstract Submitted
to predict characteristics of a semiconductor device, a simulation current-voltage curve of the semiconductor device is generated using compact models where each compact model generates simulation result data by performing a simulation based on device data. the simulation result data indicate characteristics of semiconductor devices corresponding to the device data. the compact models respectively corresponding to process data and semiconductor products. simulation reference points on the simulation current-voltage curve are extracted. basic training data corresponding to a combination of the simulation reference points and the simulation current-voltage curve are generated. a deep learning model is trained based on the basic training data such that the deep learning model outputs a prediction current-voltage curve. a target prediction current-voltage curve is generated based on the deep learning model and target reference points corresponding to the target semiconductor product. the deep learning model is a generative adversarial network.
