FinFET device performance prediction and structure optimization method based on neural network
A neural network and performance prediction technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as time-consuming, low efficiency, and difficulty in satisfying diversification, and achieve the effect of solving long development cycles
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0031] The performance prediction method of FinFET device based on neural network includes the following steps:
[0032] Step 1, obtaining the structural parameters of 4077 groups of FinFET devices and their corresponding electrical performance parameters as a sample set;
[0033] The structural parameters of the FinFET device include Fin width, Fin height, Gaussian doping concentration in the source region, Gaussian doping concentration in the drain region, and channel length; the electrical performance parameters of the FinFET device include DC characteristic parameters and AC characteristic parameters. The characteristic parameters include threshold voltage, average subthreshold swing, transconductance and current switching ratio, and the AC characteristic parameter is the cut-off frequency;
[0034] That is, each set of data includes Fin width, Fin height, Gaussian doping concentration of source region, Gaussian doping concentration of drain region, channel length, thresho...
Embodiment 2
[0069] The structure optimization method of FinFET device based on neural network includes the following steps:
[0070] Step 1, obtaining electrical performance parameters of multiple groups of FinFET devices and their corresponding structural parameters as a sample set;
[0071] The electrical performance parameters of the FinFET device include DC characteristic parameters and AC characteristic parameters, the DC characteristic parameters include threshold voltage, average sub-threshold swing, transconductance and current switching ratio, and the AC characteristic parameter is the cutoff frequency; FinFET device The structural parameters include Fin width, Fin height, source Gaussian doping concentration, drain Gaussian doping concentration and channel length;
[0072] That is, each set of data includes Fin width, Fin height, Gaussian doping concentration in the source region, Gaussian doping concentration in the drain region, channel length, threshold voltage, subthreshold ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More