Pressure sensor temperature compensating method based on FOA-optimized SOM-RBF

A technology of pressure sensor and temperature compensation, applied in fluid pressure measurement by changing ohmic resistance, fluid pressure measurement, neural learning method, etc., can solve problems such as complex network and many random parameters, and achieve fast convergence speed and good real-time performance , to avoid the effect of data mismatch

Inactive Publication Date: 2017-05-17
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] BP neural network can be used for temperature compensation of sensors. Using the principle of error back propagation, a certain output accuracy can be achieved, but the network is relatively complex and has many random parameters.

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
  • Pressure sensor temperature compensating method based on FOA-optimized SOM-RBF
  • Pressure sensor temperature compensating method based on FOA-optimized SOM-RBF
  • Pressure sensor temperature compensating method based on FOA-optimized SOM-RBF

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] Such as Figures 1 to 3 shown. The invention discloses a pressure sensor temperature compensation method based on an FOA-optimized SOM-RBF, which can be realized through the following steps.

[0050] (1) Establish RBF network to determine the number of hidden layer nodes:

[0051] The structure of the RBF network is attached figure 1 Shown:

[0052] If the input vector X m =[x 1 ,x 2 ,...,x m ] T is a column vector of m, and the hidden layer has n hidden nodes, then the output of the i-th hidden node is is the center of the basis function. The output layer consists of several linear units, and each linear unit is connected to all hidden nodes, ωij is the weight from the i-th hidden layer to the j-th output layer, and the final output of the network is the linear weighted sum of hidden node outputs. Let the actual output be Y k =[y k1 ,y k2 ,...,y km ] T , then when the training sample is X k When , the output of the Jth output neuron of the network is: ...

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 discloses a pressure sensor temperature compensating method based on an FOA-optimized SOM-RBF. The method comprises the following steps of (1), normalizing sample data which are acquired through a pressure calibration experiment and randomly dividing the sample data into training data and testing data, establishing a basic RBF network model by means of the training data, determining the number of hidden layer nodes of the RBF network by means of iteration convergence speed and precision stability; (2), establishing an adaptive SOM network by means of testing data and the hidden layer node number for obtaining a central value of the RBF network; and (3), performing optimization searching on an RBF network expansion parameter by means of FOA for obtaining a whole optimized RBF network, and finally inputting the testing data into the network for obtaining compensated output.

Description

technical field [0001] The invention relates to a pressure sensor temperature compensation method, in particular to a pressure sensor temperature compensation method based on FOA-optimized SOM-RBF. Background technique [0002] Among pressure sensors, silicon piezoresistive pressure sensors are the most widely used and the most mature. It uses the piezoresistive effect of semiconductor materials to measure pressure, with small size and high sensitivity. In engineering applications, due to the influence of temperature on the silicon material and the packaging medium, the actual output of the sensor will drift. The problem of sensor temperature compensation is a key link to improve the performance of the sensor. There are two main temperature compensation methods for pressure sensors: hardware compensation and software compensation. The hardware compensation method has disadvantages such as difficulty in debugging, low precision, high cost, and poor versatility, which is not...

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): G01L19/04G01L1/26G01L1/18G01L9/06G06N3/04G06N3/08
CPCG06N3/086G06N3/088G01L1/18G01L1/26G01L9/065G01L19/04G06N3/045
Inventor 李开林杨松胡国清李冀周永宏邹崇
Owner SOUTH CHINA UNIV OF TECH
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