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

A chiller fault detection method based on improved fastica

A fault detection and chiller technology, applied in the testing of refrigerators, refrigeration components, mechanical components, etc., can solve problems such as few reports, and achieve the effects of reducing sensitivity, improving stability, and relaxing dependencies

Active Publication Date: 2017-11-03
BEIJING UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although ICA has been well applied in biomedical signal processing, mixed speech signal separation, blind source separation, etc., its application in chiller process monitoring has rarely been reported.

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
  • A chiller fault detection method based on improved fastica
  • A chiller fault detection method based on improved fastica
  • A chiller fault detection method based on improved fastica

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] The experimental data in the present invention comes from ASHRAE 1043-RP, and the experimental object is a 90-ton (about 316kW) centrifugal chiller. Under laboratory conditions, 7 typical gradual failures of chillers are simulated by a specially designed test bench. Each failure is tested under 27 working conditions, and a large amount of experimental data is collected. These data include data under normal operation and failure operation. In this paper, modeling and analysis of 7 kinds of gradual faults that are difficult to detect in chillers are carried out, as shown in Table 1.

[0069] Table 1 Failure modes of chillers

[0070]

[0071] The data collection interval is 10s, and 64 parameters are obtained, 16 of which are calculated in real time by VisSim software, and 48 are directly measured by sensors, including 29 temperature, 5 pressure, 5 flow, 7 valve positions, compressor power and Current, cooling coefficient of performance (COP), compressor efficiency, ...

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

An improved FastICA-based chiller fault detection method, on the basis of traditional FastICA, introduces a relaxation factor, changes the original iteration method, and effectively reduces the dependence of the algorithm on the initial value. The present invention includes two stages of "offline modeling" and "online detection". "Offline modeling" includes: first, the normal data samples are processed in a steady state; then the independent component information of the data is extracted by using the FastICA algorithm that introduces the relaxation factor; finally, the statistics I2 and SPE are calculated, and the control limits are determined by the kernel density estimation method. "Online detection" includes: process the newly collected refrigeration process data according to the model, calculate its statistics and compare with the control limit to judge whether the refrigeration process is running normally. The invention reduces the dependence of the FastICA algorithm on the initial value, and ensures the safety and stability of the refrigeration process of the chiller.

Description

technical field [0001] The invention relates to the technical field of data-driven fault diagnosis, in particular to a fault detection method for the refrigeration process of a chiller in the field of HVAC. Background technique [0002] Modern industrial and civil buildings generally use large water-cooled chillers as the cold source of central air conditioning. During the operation of the unit, various failures will inevitably occur. If they are not eliminated in time, the system operation parameters will seriously deviate from the required set values, which will bring discomfort to the indoor personnel and increase the energy consumption of the system. , to shorten the service life of the equipment. Therefore, it is very important to detect and diagnose the fault of the chiller, prevent and eliminate the fault in time, and maintain the normal and efficient operation of the chiller. In the past few decades, the fault detection and diagnosis of the chiller (fault The develo...

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): G01M13/00F25B49/00
Inventor 王普辛娇娇张楠华高学金
Owner BEIJING UNIV OF TECH
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