Fault detection method and system based on EEMD combined neural network air processing system
An air treatment system and neural network technology, which is applied in the field of air treatment system fault detection, can solve the problems of low accuracy and large fault detection error, and achieve the advantages of reducing false alarm rate, high fault detection accuracy and improving fault detection rate. Effect
Active Publication Date: 2021-01-26
XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the technical problems existing in the prior art, the present invention provides a fault detection method and system based on EEMD-combined neural network air treatment system, to solve the problem of large fault detection error and low accuracy of the existing air treatment system technical problem
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0082] In this embodiment, taking the central air-conditioning system as an example, the sensor parameters of the central air-conditioning system are collected in real time, specifically 1000 groups of sensor parameters of a certain central air-conditioning system are obtained, and a kind of air processing system based on EEMD-combined neural network described in the present invention is used Fault detection method for fault diagnosis, the specific steps include the following:
[0083] Step 1. Collect 1000 sets of sensor parameters of a central air-conditioning system in real time, wherein each set of sensor parameters includes fresh air temperature, fresh air humidity, supply air temperature, supply air humidity, return air humidity, and return air temperature of the central air-conditioning system at the same time Perform the EEMD data processing method on the six sensor parameters of the central air-conditioning system at the same time according to the sensor data types, per...
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
Login to View More Abstract
The invention discloses a fault detection method and system based on an EEMD combined neural network air processing system, and the method comprises the steps: obtaining sensor parameters, collected in real time, in the air processing system, carrying out the noise reduction of the collected sensor parameters through an EEMD data processing method, and obtaining a sensor data sample; inputting thesensor data sample into a combined neural network constructed by a basic neural network and an auxiliary neural network; calculating absolute errors of the basic neural network and the auxiliary neural network respectively, and respectively obtaining relative errors of the basic neural network and the auxiliary neural network; constructing a comprehensive error model of the combined neural network by utilizing the relative error of the basic neural network and the auxiliary neural network, and obtaining a comprehensive error value of the combined neural network; judging the fault informationof the air handling system by utilizing the comprehensive error value of the combined neural network, and obtaining the fault detection result of the air handling system, so that the false alarm rateis greatly reduced, the fault detection rate is effectively improved, and the accuracy is relatively high.
Description
technical field [0001] The invention belongs to the technical field of fault detection of an air processing system, in particular to a fault detection method and system for an air processing system based on an EEMD-combined neural network. Background technique [0002] With the continuous development of building equipment, the development of automatic control systems for heating, heating, ventilation and air conditioning systems is increasingly advanced. Under the requirement of providing more accurate thermal comfort, the requirements for energy saving and emission reduction are also increasing; therefore, every Each control component needs to make control actions under a comprehensive and complex control strategy. If a part of the control system fails, it will directly affect the output of the heating, heating, ventilation and air conditioning system, and affect the optimal operation of the system. Even damage; the sensor is the outpost of the control system. If the sensor...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G05B23/02G06N3/04G06N3/08
CPCG05B23/0243G06N3/084G05B2219/24065G06N3/045
Inventor 闫秀英张伯言
Owner XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY