ANN based CMOS ASIC design for improved temperature-drift compensation of piezoresistive micro-machined high resolution pressure sensor
| Autor: | Hiranmay Saha, N.P. Futane, C. Roy Chowdhury, S. Roy Chowdhury |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Engineering
Adder Quantitative Biology::Neurons and Cognition Artificial neural network Mean squared error business.industry Biological neuron model Condensed Matter Physics Pressure sensor Atomic and Molecular Physics and Optics Surfaces Coatings and Films Electronic Optical and Magnetic Materials CMOS Application-specific integrated circuit Electronic engineering Feedforward neural network Electrical and Electronic Engineering Safety Risk Reliability and Quality business |
| Zdroj: | Microelectronics Reliability. 50:282-291 |
| ISSN: | 0026-2714 |
| DOI: | 10.1016/j.microrel.2009.09.012 |
| Popis: | The paper investigates the temperature-drift compensation of a high resolution piezoresistive pressure sensor using ANN based on conventional neuron model as also the inverse delayed function model of neuron. Using the delayed neuron model, an improvement in temperature-drift compensation has been obtained compared to the conventional neuron model. The CMOS analog ASIC design of a feed forward neural network using the inverse delayed function model of self connectionless neuron for the precise temperature-drift compensation has been presented. The inverse tan-sigmoid function is realized in CMOS implementation by Gilbert multiplier, differential adder and a cubing circuit. The entire design of the circuit has been done using AMS 0.35 μm CMOS model and simulated using Mentor Graphics ELDO simulator. Using the inverse delayed function model of neuron a mean square error of the order of 10−7 of the neural network has been obtained against a mean square error of the order of 10−3 using conventional neuron model for the same architecture of ANN. This brings down the error from 9% for uncompensated sensor to 0.1% only for compensated sensor using the delayed model of neuron in the temperature range of 0–70 °C. Using conventional neuron based ANN compensation, the error is reduced to 1% error. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect