A whole building fault detection using weather based pattern matching and feature based PCA method

2017 ◽  
Author(s):  
Yimin Chen ◽  
Jin Wen
Keyword(s):  
Fault Detection ◽  
Pattern Matching ◽  
Feature Based ◽  
Pca Method

Using Weather and Schedule based Pattern Matching and Feature based PCA for Whole Building Fault Detection — Part I Development of the Method

2021 ◽  
pp. 1-23
Author(s):  
Yimin Chen ◽  
Jin Wen ◽  
L. James Lo
Keyword(s):  
Fault Detection ◽  
Pattern Matching ◽  
Selection Process ◽  
Principal Component ◽  
Component Level ◽  
Operation Performance ◽  
Modeling Process ◽  
Baseline Status ◽  
Feature Based ◽  
Using Data

Abstract A whole building fault (WBF) refers to a fault occurring in one component, but may cause impacts on other components or subsystems, or arise impacts of significant energy consumption and thermal comfort. Conventional methods which targeted at the component level fault detection cannot be successfully employed to detect a WBF because of the fault propagation among the closely coupled equipment or subsystems. Therefore, a novel data-driven method named weather and schedule-based pattern matching (WPM) and feature based principal component analysis (FPCA) method for WBF detection is developed. Three processes are established in the WPM-FPCA method to address three main issues in the WBF detection. First, a feature selection process is used to pre-select data measurements which represent a whole building's operation performance under a satisfied status, namely baseline status. Secondly, a WPM process is employed to locate weather and schedule patterns in the historical baseline database, that are similar to that from the current/incoming operation data, and to generate a WPM baseline. Lastly, PCA models are generated for both the WPM baseline data and the current operation data. Statistic thresholds used to differentiate normal and abnormal (faulty) operations are automatically generated in this PCA modeling process. The PCA models and thresholds are used to detect WBF. This paper is the first of a two-part study. Performance evaluation of the developed method is conducted using data collected from a real campus building and will be described in the second part of this paper.

Using Weather and Schedule based Pattern Matching and Feature based PCA for Whole Building Fault Detection — Part II Field Evaluation

2021 ◽  
pp. 1-16
Author(s):  
Yimin Chen ◽  
Jin Wen ◽  
L. James Lo
Keyword(s):  
Fault Detection ◽  
Pattern Matching ◽  
Detection Method ◽  
Principal Component ◽  
Field Evaluation ◽  
Interval Data ◽  
Automation System ◽  
Hvac System ◽  
High Detection Rate ◽  
Feature Based

Abstract In a heating, ventilation and air conditioning (HVAC) system, a whole building fault (WBF) refers to a fault that occurs in one component but may trigger additional faults/abnormalities on different components or subsystems resulting in impacts on the energy consumption or indoor air quality in buildings. At the whole building level, interval data collected from various components/subsystems can be employed to detect WBFs. In the Part I of this study, a novel data-driven method which includes weather and schedule-based Pattern Matching (WPM) procedure and a feature based principal component analysis PCA (FPCA) procedure was developed to detect the WBF. This article is the second of a two-part study of the development of the whole building fault detection method. In the Part II of the study (this paper), various WBFs were designed and imposed in the HVAC system of a campus building. Data from both imposed fault and naturally-occurred faults were collected through the Building Automation System to evaluate the developed fault detection method. Evaluation results show that the developed WPM-FPCA method reaches a high detection rate and a low false alarm rate.

scholarly journals High Dimensional Feature for Hyperspectral Image Classification

2018 ◽  
Vol 246 ◽  
pp. 03041
Author(s):  
Cailing Wang ◽  
Hongwei Wang ◽  
Yinyong Zhang ◽  
Jia Wen ◽  
Fan Yang
Keyword(s):  
Image Classification ◽  
Hyperspectral Image ◽  
Texture Feature ◽  
High Dimensional ◽  
Support Vector ◽  
Hyperspectral Image Classification ◽  
Feature Based ◽  
Pca Method ◽  
The One ◽  
Low Dimensional

Making a high dimensional (e.g., 100k-dim) feature for hyperspectral image classification seems not a good idea because it will bring difficulties on consequent training, computation, and storage. In this paper, we study the performance of a high-dimensional feature by texture feature. The texture feature based on multi-local binary pattern descriptor, can achieve significant improvements over both its tradition version and the one we proposed in our previous work. We also make the high-dimensional feature practical, we employ the PCA method for dimension reduction and support vector machine for hyperspectral image classification. The two real hyperspectral image datasets are employed. Our experimental results with real hyperspectral images indicate that the high dimensional feature can enhance the classification accuracy than some low dimensional.

scholarly journals A Novel Decentralized Weighted ReliefF-PCA Method for Fault Detection

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 140478-140487 ◽  
Author(s):  
Yinghua Yang ◽  
Xiangming Chen ◽  
Yue Zhang ◽  
Xiaozhi Liu
Keyword(s):  
Fault Detection ◽  
Pca Method

Structural Feature-Based Fault-Detection Approach for the Recipes of Similar Products

2010 ◽  
Vol 23 (2) ◽  
pp. 273-283 ◽  
Author(s):  
Jong Myoung Ko ◽  
Chang Ouk Kim ◽  
Seung Jun Lee ◽  
Joo Pyo Hong
Keyword(s):  
Fault Detection ◽  
Structural Feature ◽  
Detection Approach ◽  
Feature Based
Sign in / Sign up

Export Citation Format

Share Document