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

Discrete Bayesian network water chilling unit fault diagnosis method based on information entropy

A Bayesian network and chiller technology, applied in computer components, instruments, calculations, etc., can solve problems such as information loss, Bayesian classifiers are not easy to handle continuous attributes, and sensor feature information is not fully utilized. Achieve the effect of improving the accuracy rate, overcoming the main limitations, and reducing information loss

Active Publication Date: 2019-06-07
XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still limitations in existing research: Bayesian classifiers are not easy to deal with continuous attributes. One way to solve this problem is to discretize continuous attributes, but the traditional discretization process based on expert surveys is accompanied by significant information loss, making The characteristic information from the sensor is not fully utilized

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
  • Discrete Bayesian network water chilling unit fault diagnosis method based on information entropy
  • Discrete Bayesian network water chilling unit fault diagnosis method based on information entropy
  • Discrete Bayesian network water chilling unit fault diagnosis method based on information entropy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0094] Embodiment: The historical fault data used in this embodiment comes from the ASHRAE RP-1043 fault experiment. It is a 90-ton (about 316kW) centrifugal chiller. The designed test bench simulates 7 types of typical faults (including 4 Deterioration levels), see Table 1 for details. The test data of 64 features are obtained, and the data acquisition time interval is 10s.

[0095] Table 1 Typical faults and their degradation levels

[0096]

[0097] Step 1: Data collection.

[0098] The historical fault data used in this embodiment comes from ASHRAE RP-1043 fault experiments. In the RP-1043 fault simulation experiment, a total of 64 characteristic parameters can be collected, 48 of which are directly measured by sensors, and 16 are calculated in real time by VisSim software.

[0099] Step 2: Use the existing steady-state filtering method to perform steady-state screening on the original data.

[0100] Step 3: Feature Selection.

[0101] From the foregoing, each samp...

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 discrete Bayesian network water chilling unit fault diagnosis method based on information entropy, and the method comprises the steps: obtaining the historical data of a fault through the historical data stored in an experiment or on site, and carrying out the steady-state screening and feature selection; carrying out discretization processing on historical data by utilizing an information entropy-based discretization algorithm, carrying out statistics on frequency to determine conditional probability, and constructing a network model; and verifying the performance ofthe model. According to the method, the main limitation of traditional Bayesian network water chilling unit fault diagnosis based on expert discretization is effectively overcome, and the possibilityof field application of a fault diagnosis system is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of water chillers in air conditioning systems, and in particular relates to a fault diagnosis (FD) method for chillers based on information entropy discrete Bayesian network (EBD-DBN). Background technique [0002] The chiller is the main energy-consuming equipment in the HVAC system. When a failure occurs, the performance of the unit will gradually deteriorate and the life will be reduced. By applying FD technology to the chiller, the fault can be found and eliminated in time, which is beneficial to the HVAC system. Reliable operation and energy saving are of great significance. [0003] The core of the fault diagnosis system is how to quickly locate the first fault point of the fault and carry out preventive maintenance according to the diagnosis results. The Bayesian network has great reasoning advantages for solving failures caused by uncertain factors in complex systems. It is consid...

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): G06F17/50G06K9/62
Inventor 王智伟王亚兰王占伟丁书久
Owner XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com