A General Neural Network-Based Approach to Modeling Sensors in PSPICE Simulation

Most sensors can not be modeled easily, which leads to the problem that a circuit with sensors can not be simulated in PSPICE. A method based on the neural network for modeling sensors in PSPICE is presented to solve the problem. Firstly, a multi-layer feedforward neural network is used to approxima...

Full description

Saved in:
Bibliographic Details
Main Authors: Lian Ming Wang, Ling Yun Ma, Ying Huang
Format: Conference Proceeding
Language:English
Subjects:
Circuit simulation
Feedforward neural networks
Feeds
Libraries
Multi-layer neural network
Neural networks
Piecewise linear approximation
Sensor phenomena and characterization
SPICE
Thermistors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most sensors can not be modeled easily, which leads to the problem that a circuit with sensors can not be simulated in PSPICE. A method based on the neural network for modeling sensors in PSPICE is presented to solve the problem. Firstly, a multi-layer feedforward neural network is used to approximate the characteristics of a sensor. Secondly, the achieved structure of the neural network is described in the PSPICE language to form a subcircuit. Finally, the subcircuit is used as the sensor model when the changes of a non-electric quantity imposed on the sensor in real applications is replaced with that of an electric quantity in PSPICE simulation. The availability of this method is exemplified by modeling a negative temperature coefficient (NTC) thermistor.
ISSN:2157-9555
DOI:10.1109/ICNC.2007.32