Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fault diagnosis method of wireless sensor based on convolutional neural network

A convolutional neural network and wireless sensor technology, applied in neural learning methods, biological neural network models, network topology, etc., can solve problems such as high requirements for neighbor nodes, error-prone fault diagnosis, and inability of nodes to communicate

Active Publication Date: 2022-02-08
FUJIAN NORMAL UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] (2) Hard failure node: the node cannot communicate, so the sensing data of the node cannot be received;
Although the distributed fault diagnosis method alleviates the problem of excessive energy consumption of network nodes, the algorithm has high requirements on the neighbor nodes. Accurate fault detection for nodes in wireless sensor networks with high rate

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
  • Fault diagnosis method of wireless sensor based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Such as figure 1 Shown, the wireless sensor fault diagnosis method based on convolutional neural network of the present invention, it comprises the following steps:

[0029] 1) Construct a wireless sensor network system model, which consists of a base station, a mobile car and several rechargeable wireless sensor nodes statically arranged in the monitoring area;

[0030] 2) Construct a convolutional neural network at the base station. The structure of the convolutional neural network is a sequentially connected input layer, hidden layer, fully connected layer, and output layer, where the hidden layer consists of at least one set of sequentially connected convolutional layers and pooling layers;

[0031] 3) Use the mobile car to collect the sensing data of all nodes in the wireless sensor network and transmit it to the base station. The base station stores the sensing data of all nodes and converts it into a matrix and inputs it into the convolutional neural network;

...

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 present invention relates to a wireless sensor fault diagnosis method based on a convolutional neural network. The steps are as follows: 1) Construct a wireless sensor network system model composed of a base station, a mobile car and several rechargeable wireless sensor nodes; 2) Construct a convolutional neural network sequentially connected to the input layer, hidden layer, fully connected layer and output layer at the base station; 3) Use the mobile car to collect the sensory data of all nodes and transmit it to the base station for storage, and convert it into a matrix form; 4 ) Input the perceptual data in the form of matrix into the convolutional neural network for training and self-learning, extract data features through the convolutional layer convolution kernel, compress the data features in the pooling layer, connect the last two layers in the fully connected layer, and output the layer Output the final data classification results; 5) According to the data classification results, the convolutional neural network performs fault diagnosis for each category corresponding to the corresponding sensor fault type, and outputs the node diagnosis status through the output layer.

Description

technical field [0001] The invention relates to the technical field of wireless sensors, in particular to a convolutional neural network-based wireless sensor fault diagnosis method. Background technique [0002] A wireless sensor network is composed of several wireless sensor nodes in the form of self-organization. A wireless sensor node is mainly composed of four parts: sensor module, CPU module, wireless communication module and power module. Among them, the sensor module is mainly used to sense data, and the CPU module The role of the sensor is to process and calculate data, the wireless communication module ensures that the sensor node communicates with other sensor nodes, and the power supply module carries limited energy to provide energy for the sensor node. Due to the small size, easy deployment, and low price of wireless sensor nodes, they are widely used in all aspects of life. With the enhancement of wireless sensor computing power and storage capacity, wireless ...

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 Patents(China)
IPC IPC(8): H04W16/22H04W24/04H04W40/02H04W40/10G06N3/04G06N3/08H04W84/18
CPCH04W16/225H04W24/04H04W40/02H04W40/10H04W84/18G06N3/08G06N3/045
Inventor 陈志德马梦莹龚平郑金花许力黄欣沂
Owner FUJIAN NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products