Enhanced chiller fault detection using Bayesian network and principal component analysis

•An enhanced method based on combination of BN and PCA is proposed for chiller FD.•The residual subspace from PCA are used to develop the BN model.•FD accuracies is improved significantly, especially for faults at slight levels.•The proposed PCA-R-BN method is proved to be very effective for chiller...

Full description

Saved in:
Bibliographic Details
Published in:Applied thermal engineering 2018-08, Vol.141, p.898-905
Main Authors: Wang, Zhanwei, Wang, Lin, Liang, Kunfeng, Tan, Yingying
Format: Article
Language:English
Subjects:
Bayesian analysis
Bayesian network
Chiller
Combination
Control systems
Energy consumption
Energy efficiency
Fault detection
Principal component analysis
Principal components analysis
Refrigeration
Residual
Subspaces
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•An enhanced method based on combination of BN and PCA is proposed for chiller FD.•The residual subspace from PCA are used to develop the BN model.•FD accuracies is improved significantly, especially for faults at slight levels.•The proposed PCA-R-BN method is proved to be very effective for chiller FD. Applying the fault detection (FD) techniques to chiller is beneficial to reduce energy use in buildings and to enhance the energy efficiency of refrigeration plants. The purpose of this study is to propose an enhanced chiller FD method with higher accuracies for field applications by combining Bayesian network (BN) and principal component analysis (PCA). The key paths are as follows: first, the data space represented by the normal data is decomposed into two subspaces by the PCA, i.e., principle component (PC) subspace and residual (R) subspace; second, instead of PC subspace, the score matrixes in R subspace are used to develop the BN model. The performance of the proposed method is evaluated by using the experimental data from ASHRAE RP-1043. Test results show that the accuracies are significantly improved by 43% at most (for condenser fouling at Level 1), especially for these faults at slight severity levels.
ISSN:1359-4311
1873-5606
DOI:10.1016/j.applthermaleng.2018.06.037