Sea water desalination system fault diagnosis method based on improved selective evolution random network

A random network and system failure technology, applied in the field of fault diagnosis of seawater desalination systems, can solve problems such as affecting HLO exploration and mining functions, lack of general applicability, etc., achieve good practical application prospects, improve global optimization capabilities, and improve the accuracy of fault diagnosis. rate effect

Pending Publication Date: 2021-11-23
SHANGHAI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among the three operating operators, the random learning operator with pr as the control parameter plays an important role in maintaining population diversity and performing local search, which directly affects the explo

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
  • Sea water desalination system fault diagnosis method based on improved selective evolution random network
  • Sea water desalination system fault diagnosis method based on improved selective evolution random network
  • Sea water desalination system fault diagnosis method based on improved selective evolution random network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] In this example, see figure 1 , a seawater desalination system fault diagnosis method based on improved selective evolution stochastic network, including the following steps:

[0072] Step 1: Select several typical classification data sets with large feature differences and preprocess them to generate data sets for constructing the original network PNN;

[0073] Step 2: Generate an initial random single hidden layer feed-forward neural network with the number of middle layer nodes L. The number of input layer nodes is determined by the data set with the largest number of features in the PNN construction data set. The weight between the input layer and the middle layer for W=[w 1 ,...,w L ] T , the offset of the middle layer node is b=[b 1 ,...,b L ] T ;

[0074] Step 3: Encode the weight W between the input layer and the intermediate layer of the initial random single hidden layer feedforward neural network and the bias b of the intermediate layer nodes, construc...

Embodiment 2

[0078] This embodiment is basically the same as Embodiment 1, especially in that:

[0079] In this example, if figure 1 As shown, a fault diagnosis method based on improved selective evolution random network, the steps are as follows:

[0080] First, several classification data sets with large feature differences are selected as the PNN construction data set; an initial random single hidden layer feedforward neural network is generated; the data set is constructed based on the PNN, and the AHLOPID algorithm is used to optimize the network to obtain the PNN; the PNN is used for specific Fault diagnosis, based on the fault data of the seawater desalination system, the AHLOPID algorithm is used to jointly optimize the actual working network and feature selection; finally, the optimal classifier obtained is used for fault diagnosis of the actual seawater desalination system; the AHLOPID algorithm is as follows: figure 2 As shown, the specific steps are as follows:

[0081] (1.1...

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 sea water desalination system fault diagnosis method based on an improved selective evolution random network, and relates to the technical field of fault diagnosis, and the method comprises the following steps: selecting a plurality of classification data sets with large feature differences as an original network (PNN) to construct a data set; generating an initial random single hidden layer feedforward neural network; constructing a data set based on the PNN, and optimizing the network by adopting an adaptive human learning optimization algorithm (AHLOPID) based on intelligent PID control to obtain the PNN; enabling the PNN to be used for specific fault diagnosis, and carrying out actual working network optimization and feature selection through AHLOPID cooperation based on fault data of the sea water desalination system; and finally, enabling the obtained optimal classifier to be used for actual fault diagnosis. According to the method, the fault diagnosis generalization performance is improved by constructing the PNN, and the AHLOPID is used for network design to overcome instability caused by randomization in practical application of the random feedforward neural network, so that the fault diagnosis accuracy of the sea water desalination system is improved, and stable operation of the system is ensured.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to a fault diagnosis method for a seawater desalination system based on an improved selective evolution random network. Background technique [0002] With the development of ocean-going ship technology, its scale and devices have gradually become larger and more complex, and the demand for fresh water has also increased accordingly. Seawater desalination systems are increasingly used on ocean-going ships. The failure of the seawater desalination system will not only cause economic losses, but may also affect the voyage of the ship. Therefore, higher requirements are put forward for the stability and reliability of the seawater desalination system of the ship. It is of great significance to carry out fault diagnosis for the seawater desalination system . [0003] Random Feedforward Neural Network (RFNN) is a network training method based on randomization, which can effective...

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
IPC IPC(8): G06F30/27G06F111/06G06F119/02
CPCG06F30/27G06F2111/06G06F2119/02
Inventor 王灵胡雪莲贾以豪黄博文
Owner SHANGHAI UNIV
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