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

Method for diagnosing HVAC (heating, ventilation and air conditioning) system gradual failure based on deep learning

A deep learning and fault diagnosis technology, applied in general control systems, control/regulation systems, testing/monitoring control systems, etc., can solve problems such as high dependence on fault data, inability to predict the development trend of gradual faults, and inability to accurately measure systems. , to reduce the difficulty of data acquisition, achieve high-precision diagnosis, and facilitate maintenance time.

Inactive Publication Date: 2019-01-15
ZHEJIANG UNIV OF TECH
View PDF10 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the deficiencies of the existing HVAC system gradient fault diagnosis methods, which rely on on-site diagnosis, low precision, and poor universality, the present invention provides a deep learning-based HVAC system gradient with high precision and good universal adaptability. Fault diagnosis method; the present invention focuses on solving three problems of existing HVAC system gradual fault diagnosis: (1) large dependence on fault data; (2) unable to accurately measure the system in an unsteady state; (3) unable to accurately measure gradual faults Forecast the development trend

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
  • Method for diagnosing HVAC (heating, ventilation and air conditioning) system gradual failure based on deep learning
  • Method for diagnosing HVAC (heating, ventilation and air conditioning) system gradual failure based on deep learning
  • Method for diagnosing HVAC (heating, ventilation and air conditioning) system gradual failure based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0040] In order to achieve accurate modeling of the system, we use a large amount of health system data to train the RNN model. Since there is basically no gradual failure in the initial stage of the HVAC system, a large amount of health data can be obtained. The specific training steps are as follows:

[0041] 2.1) First select the input and output parameters for model training. Among them, the output parameters are the target parameters of the failure, and the input parameters are all system parameters that will affect the target parameters.

[0042] 2.2) Organize the health system data set collected in advance, extract the input parameter data as the input data set, and extract the output parameter data as the output data set.

[0043] 2.3) Use input and output data sets to train the RNN model to obtain a system model for the fault.

[0044] Because the RNN structure is complex enough, when the amount of data is large enough, we can get a model with high enough accuracy. This pro...

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 method for recognizing and diagnosing a HVAC system gradual fault based on the deep learning. The method uses the operational data of the health system to train the principalcomponent analysis (PCA) and the cyclic neural network (RNN) model, uses the PCA model to recognize the system fault, and uses the RNN model to diagnose the system change process and the gradual fault, thereby judging the specific fault of the system. Since the RNN belongs to the deep neural network, and has the characteristic of history information storing, the model can well fit a highly nonlinear time-varying system similar to HVAC. The method has high precision for early gradual fault diagnosis, and can accurately predict parameters of a unsteady system; and the data acquisition difficulty is greatly reduced. The method has a good effect on the gradual fault diagnosis, and is a feasible and high-precision gradual fault recognizing and diagnosing method.

Description

Technical field [0001] The invention relates to the field of operation and maintenance of heating, ventilation and air conditioning (HVAC) systems. Specifically, it includes deep learning, sensor technology, testing technology, and refrigeration principles. Background technique [0002] With the rapid development of the world economy, energy consumption is increasing day by day, and the problem of energy shortage has become increasingly prominent. Building energy consumption accounts for a considerable proportion of total energy consumption. In Europe and America, building energy consumption accounts for more than 40% of total energy consumption. With the development of the economy, the share of China's building energy consumption is also increasing year by year. As of 2010, China's building energy consumption accounted for 27.3%, making China the world's second largest building energy consumer after the United States. In building energy consumption, nearly half of the energy...

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): G05B23/02
CPCG05B23/024
Inventor 顾江萍金华强沈希黄跃进孙哲王俞朱宏卫
Owner ZHEJIANG 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