Chiller fault detection by density weighted support vector data description

GU Xiaowei; WANG Zhiwei; WANG Zhanwei; HE Suowei; YAN Zengfeng

doi:10.11949/j.issn.0438-1157.20161077

您当前的位置：

首页 >

文章列表页 >

Chiller fault detection by density weighted support vector data description

更新时间：2025-12-10

- Chiller fault detection by density weighted support vector data description
- CIESC Journal Issue 3, Pages: 1099-1108(2017)
- 作者机构：
  
  1. 西安建筑科技大学环境学院,陕西,西安,710055
  2. 西安建筑科技大学建筑学院,陕西,西安,710055
- 作者简介：
- 基金信息：
- DOI：10.11949/j.issn.0438-1157.20161077
  CLC： B65
- Online First：05 March 2017，
  
  Published：05 March 2017
- 稿件说明：
移动端阅览
GU Xiaowei, WANG Zhiwei, WANG Zhanwei, et al. Chiller fault detection by density weighted support vector data description[J]. CIESC Journal, 2017, (3): 1099-1108.
DOI：

GU Xiaowei, WANG Zhiwei, WANG Zhanwei, et al. Chiller fault detection by density weighted support vector data description[J]. CIESC Journal, 2017, (3): 1099-1108. DOI： 10.11949/j.issn.0438-1157.20161077.

摘要

虚警率（FAR）是评价冷水机组故障检测性能的关键指标，用户无法接受过高的FAR。为了降低支持向量数据描述（SVDD）在冷水机组故障检测时的FAR，将密度权重集成到SVDD中，提出了一种基于密度权重支持向量数据描述（DW-SVDD）的冷水机组故障检测方法，该方法考虑了样本数据在真实空间中的密度分布情况。使用ASHRAE RP-1043冷水机组实验数据对提出的方法进行验证，并将检测结果与传统SVDD的冷水机组故障检测方法进行比较。结果表明，提出的方法将FAR从10.5%降低到7%，同比下降超过了30%，同时对4个劣化等级下的7种典型冷水机组故障有着优良的检测性能。

Abstract

False alarm rate (FAR) is a key indicator to evaluate performance of chiller fault detection methods

since customers cannot accept high FAR. In order to reduce FAR of support vector data description (SVDD)-based chiller fault detection

a density weighted support vector data description (DW-SVDD)-based chiller fault detection method was proposed by integration of density weight into SVDD with a consideration of density distribution of sample data in real space. The proposed method was validated with experimental data of RP-1043 ASHRAE and detection results were compared to those of traditional SVDD chiller fault detection methods. The results showed that the new method could reduce FAR from 10.5% to 7%

which was lowered about 30%

and had excellent detection performance for 7 typical chiller faults at 4 severity levels.

关键词

Keywords

references

Views

208

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

SVDD-based chiller sensor fault detection method and its detection efficiency

Prediction of scale factor of heat exchangers based on CNN-LSTM neural network

Industrial process fault detection using weighted deep support vector data description

Chiller fault diagnosis based on fusional Bayesian network

Fault detection method for uneven-length multimode batch processes

Related Author

LI Guannan

HU Yunpeng

CHEN Huanxin

LI Haorong

LI Jiong

HU Wenju

ZHANG Hanxiao

WANG Ruiqi

Related Institution

School of Energy and Power Engineering, Huazhong University of Science and Technology

University of Nebraska-, Lincoln

State Key Laboratory of Compressor Technology, Hefei General Machinery Research Institute

Beijing Municipality Key Laboratory of HVAC&R, Beijing University of Civil Engineering and Architecture

College of Chemistry and Chemical Engineering, Xi’an University of Science and Technology

⁰