scholarly journals Metric Learning Method Aided Data-Driven Design of Fault Detection Systems

2014 ◽  
Vol 2014 ◽  
pp. 1-9
Author(s):  
Guoyang Yan ◽  
Jiangyuan Mei ◽  
Shen Yin ◽  
Hamid Reza Karimi
Keyword(s):  
Fault Detection ◽  
Feature Vector ◽  
Metric Learning ◽  
Principal Component ◽  
Industrial Applications ◽  
Data Driven ◽  
Detection Methods ◽  
Feature Extraction Method ◽  
Detection Systems ◽  
The Relationship

Fault detection is fundamental to many industrial applications. With the development of system complexity, the number of sensors is increasing, which makes traditional fault detection methods lose efficiency. Metric learning is an efficient way to build the relationship between feature vectors with the categories of instances. In this paper, we firstly propose a metric learning-based fault detection framework in fault detection. Meanwhile, a novel feature extraction method based on wavelet transform is used to obtain the feature vector from detection signals. Experiments on Tennessee Eastman (TE) chemical process datasets demonstrate that the proposed method has a better performance when comparing with existing methods, for example, principal component analysis (PCA) and fisher discriminate analysis (FDA).

Fault detection for parallel operating machines

2019 ◽  
Vol 26 (2) ◽  
pp. 335-348
Author(s):  
Dustin Helm ◽  
Markus Timusk
Keyword(s):  
Fault Detection ◽  
Design Methodology ◽  
Feature Vector ◽  
Detection Methods ◽  
Computationally Efficient ◽  
Content Type ◽  
Operational Conditions ◽  
Different Types ◽  
Vibration Signatures ◽  
The Relationship

Purpose The purpose of this paper is to demonstrate that by utilizing the relationship between redundant hardware components, inherent in parallel machinery, vibration-based fault detection methods can be made more robust to changes in operational conditions. This work reports on a study of fault detection on bearings operating in two parallel subsystems that experience identical changes in speed and load. Design/methodology/approach This study was carried out using two identical subsystems that operate on the same duty cycle. The systems were run with both healthy and a variety of common bearing faults. The faults were detected by analyzing the residual between the features of the two vibration signatures from the two subsystems. Findings This work found that by utilizing this relationship in parallel operating machinery the fault detection process can be improved. The study looked at several different types of feature vector and found that, in this case, features based on envelope analysis or autoregressive model work the best, whereas basic statistical features did not work as well. Originality/value The proposed method can be a computationally efficient and simple solution to monitoring non-stationary machinery where there is hardware redundancy present. This method is shown to have some advantages over non-parallel approaches.

scholarly journals Development and Field Evaluation of Data-driven Whole Building Fault Detection and Diagnosis Strategy

2018 ◽  
Vol 10 (1) ◽  
Author(s):  
Yimin Chen ◽  
Jin Wen
Keyword(s):  
Fault Detection ◽  
Principal Component ◽  
Field Evaluation ◽  
Fault Detection And Diagnosis ◽  
Data Driven ◽  
Machine Learning Techniques ◽  
Component Level ◽  
Automation Systems ◽  
Tightly Coupled ◽  
Detection And Diagnosis

Faults, i.e., malfunctioned sensors, components, control, and systems, in a building have significantly adverse impacts on the building’s energy consumption and indoor environment. To date, extensive research has been conducted on the development of component level fault detection and diagnosis (FDD) for building systems, especially the Heating, Ventilating, and Air Conditioning (HVAC) system. However, for faults that have multi-system impacts, component level FDD tools may encounter high false alarm rate due to the fact that HVAC subsystems are often tightly coupled together. Hence, the detection and diagnosis of whole building faults is the focus of this study. Here, a whole building fault refers to a fault that occurs in one subsystem but triggers abnormalities in other subsystems and have significant adverse whole building energy impact. The wide adoption of building automation systems (BAS) and the development of machine learning techniques make it possible and cost-efficient to detect and diagnose whole building faults using data-driven methods. In this study, a whole building FDD strategy which adopts weather and schedule information based pattern matching (WPM) method and feature based Principal Component Analysis (FPCA) for fault detection, as well as Bayesian Networks (BNs) based method for fault diagnosis is developed. Fault tests are implemented in a real campus building. The collected data are used to evaluate the performance of the proposed whole building FDD strategies.

scholarly journals Overview of fault detection methods for power plant control systems purposes

2019 ◽  
pp. 127-129
Author(s):  
Dmytro Shram ◽  
Oleksandr Stepanets
Keyword(s):  
Fault Detection ◽  
Control Systems ◽  
Power Plants ◽  
Fault Detection And Isolation ◽  
Data Driven ◽  
Detection Methods ◽  
Model Free ◽  
Power Plant Control ◽  
Technical Details ◽  
Plant Control

The main objective of this paper is to review of fault detection and isolation (FDI) methods and applications on various power plants. Due to the focus of the topic, on model and model-free FDI methods, technical details were kept in the references. We will overview the methods in terms of model-based, data driven and signal based methods further in the paper. Principles of three FDI methods are explained and characteristics of number of some popular techniques are described. It also summarizes data-driven methods and applications related to power generation plants. Parts of control system applications of FDI in TPPs with possible faults are shown in the Table I. Some popular techniques for the various faults in TPPs are discussed also.

A data-driven method of health monitoring for spacecraft

2018 ◽  
Vol 90 (2) ◽  
pp. 435-451 ◽  
Author(s):  
Xu Kang ◽  
Dechang Pi
Keyword(s):  
Health Monitoring ◽  
Attitude Control ◽  
Principal Component ◽  
Data Driven ◽  
Detection Methods ◽  
Content Type ◽  
Orbit Control ◽  
Mode Decomposition ◽  
Squared Prediction Error ◽  
Pca Method

Purpose The purpose of this paper is to detect the occurrence of anomaly and fault in a spacecraft, investigate various tendencies of telemetry parameters and evaluate the operation state of the spacecraft to monitor the health of the spacecraft. Design/methodology/approach This paper proposes a data-driven method (empirical mode decomposition-sample entropy-principal component analysis [EMD-SE-PCA]) for monitoring the health of the spacecraft, where EMD is used to decompose telemetry data and obtain the trend items, SE is utilised to calculate the sample entropies of trend items and extract the characteristic data and squared prediction error and statistic contribution rate are analysed using PCA to monitor the health of the spacecraft. Findings Experimental results indicate that the EMD-SE-PCA method could detect characteristic parameters that appear abnormally before the anomaly or fault occurring, could provide an abnormal early warning time before anomaly or fault appearing and summarise the contribution of each parameter more accurately than other fault detection methods. Practical implications The proposed EMD-SE-PCA method has high level of accuracy and efficiency. It can be used in monitoring the health of a spacecraft, detecting the anomaly and fault, avoiding them timely and efficiently. Also, the EMD-SE-PCA method could be further applied for monitoring the health of other equipment (e.g. attitude control and orbit control system) in spacecraft and satellites. Originality/value The paper provides a data-driven method EMD-SE-PCA to be applied in the field of practical health monitoring, which could discover the occurrence of anomaly or fault timely and efficiently and is very useful for spacecraft health diagnosis.

scholarly journals Recognition of Acoustic Signals of Commutator Motors

2018 ◽  
Vol 8 (12) ◽  
pp. 2630 ◽  
Author(s):  
Adam Glowacz
Keyword(s):  
Fault Detection ◽  
Extraction Method ◽  
Acoustic Signals ◽  
Rotor Blades ◽  
Gear Train ◽  
Detection Methods ◽  
Support Vector ◽  
Total Efficiency ◽  
Feature Extraction Method ◽  
Selection Of

Most faults can stop a motor, and time is lost in fixing the damaged motor. This is a reason why it is essential to develop fault-detection methods. This paper describes the acoustic-based fault detection of two commutator motors: the commutator motor of an electric impact drill and the commutator motor of a blender. Acoustic signals were recorded by a smartphone. Five states of the electric impact drill and three states of the blender were analysed: for the electric impact drill, these states were healthy, damaged gear train, faulty fan with five broken rotor blades, faulty fan with 10 broken rotor blades, and shifted brush (motor off); for the blender, these states were healthy, faulty fan with two broken rotor blades, and faulty fan with five broken rotor blades. A feature extraction method, MSAF-RATIO-27-MULTIEXPANDED-4-GROUPS (Method of Selection of Amplitudes of Frequency Ratio of 27% Multiexpanded 4 Groups), was developed and used for the computation of feature vectors. The nearest mean (NM) and support vector machine (SVM) classifiers were used for data classification. Analysis of the recognition of acoustic signals was carried out. The analysed value of TEEID (the total efficiency of recognition of the electric impact drill) was equal to 96% for the NM classifier and 88.8% for SVM. The analysed value of TEB (the total efficiency of recognition of the blender) was equal to 100% for the NM classifier and 94.11% for SVM.

scholarly journals Dynamic Principal Component Analysis with Nonoverlapping Moving Window and Its Applications to Epileptic EEG Classification

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
Shengkun Xie ◽  
Sridhar Krishnan
Keyword(s):  
Principal Component Analysis ◽  
Single Channel ◽  
Principal Component ◽  
Component Analysis ◽  
Classification Performance ◽  
Detection Methods ◽  
Moving Window ◽  
Feature Extraction Method ◽  
Epilepsy Diagnosis ◽  
Dynamic Principal Component Analysis

Classification of electroencephalography (EEG) is the most useful diagnostic and monitoring procedure for epilepsy study. A reliable algorithm that can be easily implemented is the key to this procedure. In this paper a novel signal feature extraction method based on dynamic principal component analysis and nonoverlapping moving window is proposed. Along with this new technique, two detection methods based on extracted sparse features are applied to deal with signal classification. The obtained results demonstrated that our proposed methodologies are able to differentiate EEGs from controls and interictal for epilepsy diagnosis and to separate EEGs from interictal and ictal for seizure detection. Our approach yields high classification accuracy for both single-channel short-term EEGs and multichannel long-term EEGs. The classification performance of the method is also compared with other state-of-the-art techniques on the same datasets and the effect of signal variability on the presented methods is also studied.

Research of Face Recognition Methods Based on Binding Feature Extraction

2014 ◽  
Vol 568-570 ◽  
pp. 668-671
Author(s):  
Yi Long ◽  
Fu Rong Liu ◽  
Guo Qing Qiu
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Extraction Method ◽  
Local Binary Pattern ◽  
Feature Vector ◽  
Recognition Rate ◽  
Principal Component ◽  
Face Image ◽  
Feature Extraction Method ◽  
Histogram Feature

To address the problem that the dimension of the feature vector extracted by Local Binary Pattern (LBP) for face recognition is too high and Principal Component Analysis (PCA) extract features are not the best classification features, an efficient feature extraction method using LBP, PCA and Maximum scatter difference (MSD) has been introduced in this paper. The original face image is firstly divided into sub-images, then the LBP operator is applied to extract the histogram feature. and the feature dimensions are further reduced by using PCA. Finally,MSD is performed on the reduced PCA-based feature.The experimental results on ORL and Yale database demonstrate that the proposed method can classify more effectively and can get higher recognition rate than the traditional recognition methods.

scholarly journals NARX NETWORK BASED DATA-DRIVEN ALGORITHM FOR DETECTION OF TRAY FAULTS IN NONLINEAR DYNAMIC DISTILLATION COLUMN

2020 ◽  
Vol 82 (5) ◽  
Author(s):  
Syed Ali Ammar Taqvi ◽  
Haslinda Zabiri ◽  
Lemma Dendena Tufa ◽  
Fahim Uddin ◽  
Syeda Anmol Fatima ◽  
...  
Keyword(s):  
Fault Detection ◽  
Process Monitoring ◽  
Nonlinear Dynamic ◽  
Distillation Column ◽  
Fault Detection And Diagnosis ◽  
Data Driven ◽  
Detection Methods ◽  
Maintenance Cost ◽  
Monitoring And Control ◽  
Process Industries

Efficient monitoring of highly complex process industries is essential for better management, safer operations and high-quality production. Timely detection of various faults helps to improve the performance of the complex industries, prevent various unfavorable consequences and reduce the maintenance cost. Fault Detection and Diagnosis (FDD) for process monitoring and control has been an active field of research for the past two decades. Distillation columns are inherently nonlinear, and thus to have an accurate and robust performance, the fault detection methods should be based on nonlinear dynamic methods. The paper presents a robust data-driven fault detection approach for realistic tray upsets in the distillation column. The detection of tray faults in the distillation column is conducted by Nonlinear AutoRegressive with eXogenous Input (NARX) network with Tapped Delay Lines (TDL). Aspen Plus® Dynamic simulation has been used to generate normal and faulty datasets. The study shows that the proposed method can be used for the detection of tray faults in distillation column for dynamic process monitoring. The performance of the proposed method has been evaluated by the Missed Detection Rate (MDR) and the Detection Delay (DD).

Sign in / Sign up

Export Citation Format

Share Document