Diagnosis Model for Refrigerant Charge Fault under Heating Conditions based on Multi-layer Convolution Neural Network

This paper presents a fault diagnosis model based on a convolution neural network. The kernel size and number of neurons of a3-layerconvolutionnetwork were optimized by an orthogonal experiment method. The performance of the refrigerant charge fault diagnosis model of variable refrigerant flow (VRF)...

Full description

Saved in:
Bibliographic Details
Main Authors: Cheng Hengda, Chen Huanxin, Li Zhengfei, Cheng Xiangdong
Format: Article
Language:zho
Published: Journal of Refrigeration Magazines Agency Co., Ltd. 2020-01-01
Series:Zhileng xuebao
Subjects:
Online Access:http://www.zhilengxuebao.com/thesisDetails#10.3969/j.issn.0253-4339.2020.01.040
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849707776547225600
author Cheng Hengda
Chen Huanxin
Li Zhengfei
Cheng Xiangdong
author_facet Cheng Hengda
Chen Huanxin
Li Zhengfei
Cheng Xiangdong
author_sort Cheng Hengda
collection DOAJ
description This paper presents a fault diagnosis model based on a convolution neural network. The kernel size and number of neurons of a3-layerconvolutionnetwork were optimized by an orthogonal experiment method. The performance of the refrigerant charge fault diagnosis model of variable refrigerant flow (VRF) system was evaluated with graphed experimental data. The results show that the model established by the "data graphing & multi-layer convolutional network" method can be effectively used for the refrigerant charge fault diagnosis of the VRF system. With 20 chosen input features, the accuracy of the 9 level refrigerant charge fault diagnosis reached 91%,surpassing the performance of traditional back propagation neural networks(BPNN).This is the first time to achieve VRF system refrigerant charge fault diagnosis by using a convolutional network, laying a foundation for the expansion of related research.
format Article
id doaj-art-155c8a93cefa4880a9dbfdac00d2f5f1
institution DOAJ
issn 0253-4339
language zho
publishDate 2020-01-01
publisher Journal of Refrigeration Magazines Agency Co., Ltd.
record_format Article
series Zhileng xuebao
spelling doaj-art-155c8a93cefa4880a9dbfdac00d2f5f12025-08-20T03:15:50ZzhoJournal of Refrigeration Magazines Agency Co., Ltd.Zhileng xuebao0253-43392020-01-014166508299Diagnosis Model for Refrigerant Charge Fault under Heating Conditions based on Multi-layer Convolution Neural NetworkCheng HengdaChen HuanxinLi ZhengfeiCheng XiangdongThis paper presents a fault diagnosis model based on a convolution neural network. The kernel size and number of neurons of a3-layerconvolutionnetwork were optimized by an orthogonal experiment method. The performance of the refrigerant charge fault diagnosis model of variable refrigerant flow (VRF) system was evaluated with graphed experimental data. The results show that the model established by the "data graphing & multi-layer convolutional network" method can be effectively used for the refrigerant charge fault diagnosis of the VRF system. With 20 chosen input features, the accuracy of the 9 level refrigerant charge fault diagnosis reached 91%,surpassing the performance of traditional back propagation neural networks(BPNN).This is the first time to achieve VRF system refrigerant charge fault diagnosis by using a convolutional network, laying a foundation for the expansion of related research.http://www.zhilengxuebao.com/thesisDetails#10.3969/j.issn.0253-4339.2020.01.040VRF systemfault diagnosisconvolutional neural networkrefrigerant charge faultorthogonal experiment
spellingShingle Cheng Hengda
Chen Huanxin
Li Zhengfei
Cheng Xiangdong
Diagnosis Model for Refrigerant Charge Fault under Heating Conditions based on Multi-layer Convolution Neural Network
Zhileng xuebao
VRF system
fault diagnosis
convolutional neural network
refrigerant charge fault
orthogonal experiment
title Diagnosis Model for Refrigerant Charge Fault under Heating Conditions based on Multi-layer Convolution Neural Network
title_full Diagnosis Model for Refrigerant Charge Fault under Heating Conditions based on Multi-layer Convolution Neural Network
title_fullStr Diagnosis Model for Refrigerant Charge Fault under Heating Conditions based on Multi-layer Convolution Neural Network
title_full_unstemmed Diagnosis Model for Refrigerant Charge Fault under Heating Conditions based on Multi-layer Convolution Neural Network
title_short Diagnosis Model for Refrigerant Charge Fault under Heating Conditions based on Multi-layer Convolution Neural Network
title_sort diagnosis model for refrigerant charge fault under heating conditions based on multi layer convolution neural network
topic VRF system
fault diagnosis
convolutional neural network
refrigerant charge fault
orthogonal experiment
url http://www.zhilengxuebao.com/thesisDetails#10.3969/j.issn.0253-4339.2020.01.040
work_keys_str_mv AT chenghengda diagnosismodelforrefrigerantchargefaultunderheatingconditionsbasedonmultilayerconvolutionneuralnetwork
AT chenhuanxin diagnosismodelforrefrigerantchargefaultunderheatingconditionsbasedonmultilayerconvolutionneuralnetwork
AT lizhengfei diagnosismodelforrefrigerantchargefaultunderheatingconditionsbasedonmultilayerconvolutionneuralnetwork
AT chengxiangdong diagnosismodelforrefrigerantchargefaultunderheatingconditionsbasedonmultilayerconvolutionneuralnetwork