Fault Detection Method Using Multi-mode Principal Component Analysis Based on Gaussian Mixture Model for Sewage Source Heat Pump System

Yoo, Youngjun

doi:10.1007/s12555-018-0758-6

Cited by 26 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, EEG is limited in simultaneous use with the brain stimulation device because recorded signals affect the electric and magnetic fields. However, specific signal-processing algorithms can remove interference components, such as principal component analysis, independent component analysis, and adaptive filter algorithms ( Deng et al, 2019 ; Hong and Pham, 2019 ; Yoo, 2019 ; Park et al, 2020 ). Thus, a technique free of limitation, such as a noninvasive neuroimaging modality (i.e., fNIRS), as a promising method, should be considered the first choice.…”

Section: Discussionmentioning

confidence: 99%

Systemic Review on Transcranial Electrical Stimulation Parameters and EEG/fNIRS Features for Brain Diseases

2021

View full text Add to dashboard Cite

BackgroundBrain disorders are gradually becoming the leading cause of death worldwide. However, the lack of knowledge of brain disease’s underlying mechanisms and ineffective neuropharmacological therapy have led to further exploration of optimal treatments and brain monitoring techniques.ObjectiveThis study aims to review the current state of brain disorders, which utilize transcranial electrical stimulation (tES) and daily usable noninvasive neuroimaging techniques. Furthermore, the second goal of this study is to highlight available gaps and provide a comprehensive guideline for further investigation.MethodA systematic search was conducted of the PubMed and Web of Science databases from January 2000 to October 2020 using relevant keywords. Electroencephalography (EEG) and functional near-infrared spectroscopy were selected as noninvasive neuroimaging modalities. Nine brain disorders were investigated in this study, including Alzheimer’s disease, depression, autism spectrum disorder, attention-deficit hyperactivity disorder, epilepsy, Parkinson’s disease, stroke, schizophrenia, and traumatic brain injury.ResultsSixty-seven studies (1,385 participants) were included for quantitative analysis. Most of the articles (82.6%) employed transcranial direct current stimulation as an intervention method with modulation parameters of 1 mA intensity (47.2%) for 16–20 min (69.0%) duration of stimulation in a single session (36.8%). The frontal cortex (46.4%) and the cerebral cortex (47.8%) were used as a neuroimaging modality, with the power spectrum (45.7%) commonly extracted as a quantitative EEG feature.ConclusionAn appropriate stimulation protocol applying tES as a therapy could be an effective treatment for cognitive and neurological brain disorders. However, the optimal tES criteria have not been defined; they vary across persons and disease types. Therefore, future work needs to investigate a closed-loop tES with monitoring by neuroimaging techniques to achieve personalized therapy for brain disorders.

show abstract

Section: Discussionmentioning

confidence: 99%

Systemic Review on Transcranial Electrical Stimulation Parameters and EEG/fNIRS Features for Brain Diseases

2021

View full text Add to dashboard Cite

show abstract

“…Fault Detection using ML: Many studies on vibration-related failures and predictive failure diagnosis have been conducted [3,[9][10][11][12][13][14][15][16][17][18][19][20][21]. Lee et al [3] proposed a rotating mechanism system-a mixture of feature extraction and selection classifies it as a Support Vector Machine (SVM) [4].…”

Section: Related Workmentioning

confidence: 99%

“…Zhang et al [18] proposed a clustering-based Principal Component Analysis (PCA) to propose a fault detection method for water heat pump systems. Yoo et al [19] proposed a Fault Detection method using multi-mode PCA and Gaussian mixed model in a sewage heat pump system. Kim et al [20] proposed the fault detection of photovoltaic current and voltage through the ANN-based modeling method.…”

Section: Related Workmentioning

confidence: 99%

A Study on Deep Learning Application of Vibration Data and Visualization of Defects for Predictive Maintenance of Gravity Acceleration Equipment

Lee

Yang

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Hypergravity accelerators are a type of large machinery used for gravity training or medical research. A failure of such large equipment can be a serious problem in terms of safety or costs. This paper proposes a prediction model that can proactively prevent failures that may occur in a hypergravity accelerator. An experiment was conducted to evaluate the performance of the method proposed in this paper. A 4-channel accelerometer was attached to the bearing housing, which is a rotor, and time-amplitude data were obtained from the measured values by sampling. The method proposed in this paper was trained with transfer learning, a deep learning model that replaced the VGG19 model with a Fully Connected Layer (FCL) and Global Average Pooling (GAP) by converting the vibration signal into a short-time Fourier transform (STFT) or Mel-Frequency Cepstral Coefficients (MFCC) spectrogram and converting the input into a 2D image. As a result, the model proposed in this paper has seven times decreased trainable parameters of VGG19, and it is possible to quantify the severity while looking at the defect areas that cannot be seen with 1D.

show abstract

“…According to Zhao et al, knowledge-based methods have been dominant from the 1980s till around 2005 and since then the data-based methods became more prominent. Shi and O'Brien also confirm that since 2010 research on building fault detection and diagnosis (FDD) systems has steadily increased with a specific focus on black-box modeling.The most widely used data-driven FDD technique for heat pump systems is principal component analysis (PCA), which is a multivariate statistical analysis approach [7,8]. This approach allows transformation of several related variables to a smaller set of uncorrelated variables.…”

mentioning

confidence: 99%

“…The most widely used data-driven FDD technique for heat pump systems is principal component analysis (PCA), which is a multivariate statistical analysis approach [7,8]. This approach allows transformation of several related variables to a smaller set of uncorrelated variables.…”

mentioning

confidence: 99%

An Energy Graph-Based Approach to Fault Diagnosis of a Transcritical CO2 Heat Pump

et al. 2020

View full text Add to dashboard Cite

The objective of this paper is to describe an energy-based approach to visualize, identify, and monitor faults that may occur in a water-to-water transcritical CO 2 heat pump system. A representation using energy attributes allows the abstraction of all physical phenomena present during operation into a compact and easily interpretable form. The use of a linear graph representation, with heat pump components represented as nodes and energy interactions as links, is investigated. Node signature matrices are used to present the energy information in a compact mathematical form. The resulting node signature matrix is referred to as an attributed graph and is populated in such a way as to retain the structural information, i.e., where the attribute points to in the physical system. To generate the energy and exergy information for the compilation of the attributed graphs, a descriptive thermal-fluid model of the heat pump system is developed. The thermal-fluid model is based on the specifications of and validated to the actual behavioral characteristics of a physical transcritical CO 2 heat pump test facility. As a first step to graph-matching, cost matrices are generated to represent a characteristic residual between a normal system node signature matrix and a faulty system node signature matrix. The variation in the eigenvalues and eigenvectors of the characteristic cost matrices from normal conditions to a fault condition was used for fault characterization. Three faults, namely refrigerant leakage, compressor failure and gas cooler fouling, were considered. The paper only aims to introduce an approach, with the scope limited to illustration at one operating point and considers only three relatively large faults. The results of the proposed method show promise and warrant further work to evaluate its sensitivity and robustness for small faults.Energies 2020, 13, 1783 2 of 34 Zogg also refers to a field survey [2] that indicates that the average energetic efficiencies of the heat pumps installed in Swiss buildings were about 10% lower than the efficiencies measured under standard laboratory conditions. It was also found that for some installations the performance degradation was as high as 30%. A similar study in the United States of over 55,000 air conditioning units showed that more than 90% were operating with one or more kinds of faults [3]. Yet another study surveying roof-top units indicates an operating efficiency of 80% of designed performance with 63% of these units having performance degradation due to refrigerant leakage [4]. These observations motivate the need for diagnostic techniques which ideally can monitor these energy conversion systems during transient and steady-state operating conditions.In the review papers by Zhao et al., and Shi and O'Brien [5,6] the classification of fault detection methods for energy systems are presented. Fault detection methods can be classified into two subcategories: data-based and knowledge-based. The knowledge-based methods rely on domain and prior knowledge to deri...

show abstract

Fault Detection Method Using Multi-mode Principal Component Analysis Based on Gaussian Mixture Model for Sewage Source Heat Pump System

Cited by 26 publications

References 20 publications

Systemic Review on Transcranial Electrical Stimulation Parameters and EEG/fNIRS Features for Brain Diseases

Systemic Review on Transcranial Electrical Stimulation Parameters and EEG/fNIRS Features for Brain Diseases

A Study on Deep Learning Application of Vibration Data and Visualization of Defects for Predictive Maintenance of Gravity Acceleration Equipment

An Energy Graph-Based Approach to Fault Diagnosis of a Transcritical CO2 Heat Pump

Contact Info

Product

Resources

About