Neural network space mapping modeling method used for large signal power transistor

A power transistor and neural network technology, applied in the field of microwave circuit and device modeling, can solve problems such as increasing the difficulty of optimization, achieve the effects of shortening the modeling cycle, avoiding repeated adjustments, and simple neural network structure

Active Publication Date: 2018-09-18
成都手创科技有限公司
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These existing Neuro-SM modeling methods increase the difficulty of optimization by using the same neural network to improve the DC and AC characteristics of the model, so the large-signal modeling with high precision and simple operation is still to be studied

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Neural network space mapping modeling method used for large signal power transistor
  • Neural network space mapping modeling method used for large signal power transistor
  • Neural network space mapping modeling method used for large signal power transistor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to make the object, technical solution and advantages of the present invention clearer, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0029] Such as figure 2 As shown, in a kind of neural network space mapping modeling method for large-signal power transistors of the present invention, the large-signal input sample data is input power, source impedance, load impedance, fundamental frequency, voltage, denoted as [P in ,Z S ,Z L , freq, V gf , V df ] T ; Large signal output sample data are output power, gain, power efficiency, power added power, denoted as [P out , Gain, η, PAE] T .

[0030] build as figure 1 The neural network structure shown. At this time, the model fitted by the measured data in the DC and S-parameter simulation is used as the existing rough model. The mapping network adopts a 3-layer perceptron structure, and the input signal is [i dc_DC , i dc_AC ] T , ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the field of microwave circuit and device modeling, and provides a neural network space mapping modeling method used for a large signal power transistor. The method comprisesthe steps of firstly building a neural network space mapping model with capacitors and inductors, and changing direct current and alternating current characteristics of the model; secondly extractingadditional current signals by adopting a novel nonlinear function to improve large signal characteristics of an existing device model, and meanwhile, keeping an S parameter unchanged; and finally quickly training the built neural network space mapping model by adopting a stepwise training method. Therefore, variables are prevented from being repeatedly adjusted and the modeling cycle is shortened.

Description

technical field [0001] The invention relates to the field of modeling of microwave circuits and devices, in particular to the application of neural network space mapping technology in the field of microwave modeling. Background technique [0002] With the development of semiconductor manufacturing process, it is necessary to establish an accurate computer-aided design model of large-signal power transistors. Large-signal power transistor models used in commercial microwave circuit simulation software play a decisive role in circuit and system design. The integration of circuits is getting higher and higher. In order to shorten the cycle of design and production of circuits, the demand for efficient large-signal modeling is increasing. [0003] Recently, Neural Network Space Mapping (Neuro-SM) technology has been considered as an effective method to replace traditional methods in the field of microwave modeling. The technology uses neural networks to map voltage and current...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/50G06N3/04G06N3/08
CPCG06N3/08G06F30/367G06N3/045
Inventor 闫淑霞靳晓怡张垚芊
Owner 成都手创科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap