scholarly journals Fault Diagnosis of Rotating Electrical Machines Using Multi-Label Classification

2019 ◽  
Vol 9 (23) ◽  
pp. 5086 ◽  
Author(s):  
Adrienn Dineva ◽  
Amir Mosavi ◽  
Mate Gyimesi ◽  
Istvan Vajda ◽  
Narjes Nabipour ◽  
...  
Keyword(s):  
Fault Detection ◽  
Efficient Solutions ◽  
Fault Detection And Diagnosis ◽  
Machine Learning Techniques ◽  
Electrical Machine ◽  
Multiple Faults ◽  
Detection Techniques ◽  
Sensory Data ◽  
Vibration Data ◽  
Drive Systems

Fault Detection and Diagnosis of electrical machine and drive systems are of utmost importance in modern industrial automation. The widespread use of Machine Learning techniques has made it possible to replace traditional motor fault detection techniques with more efficient solutions that are capable of early fault recognition by using large amounts of sensory data. However, the detection of concurrent failures is still a challenge in the presence of disturbing noises or when the multiple faults cause overlapping features. Multi-label classification has recently gained popularity in various application domains as an efficient method for fault detection and monitoring of systems with promising results. The contribution of this work is to propose a novel methodology for multi-label classification for simultaneously diagnosing multiple faults and evaluating the fault severity under noisy conditions. In this research, the Electrical Signature Analysis as well as traditional vibration data have been considered for modeling. Furthermore, the performance of various multi-label classification models is compared. Current and vibration signals are acquired under normal and fault conditions. The applicability of the proposed method is experimentally validated under diverse fault conditions such as unbalance and misalignment.

scholarly journals Multi-Label Classification for Fault Diagnosis of Rotating Electrical Machines

2019 ◽  
Author(s):  
Adrienn Dineva ◽  
Amir Mosavi ◽  
Mate Gyimesi ◽  
Istvan Vajda
Keyword(s):  
Fault Detection ◽  
Efficient Solutions ◽  
Fault Detection And Diagnosis ◽  
Machine Learning Techniques ◽  
Electrical Machine ◽  
Multiple Faults ◽  
Detection Techniques ◽  
Sensory Data ◽  
Fault Recognition ◽  
Drive Systems

Primary importance is devoted to Fault Detection and Diagnosis (FDI) of electrical machine and drive systems in modern industrial automation. The widespread use of Machine Learning techniques has made it possible to replace traditional motor fault detection techniques with more efficient solutions that are capable of early fault recognition by using large amounts of sensory data. However, the detection of concurrent failures is still a challenge in the presence of disturbing noises or when the multiple faults cause overlapping features. The contribution of this work is to propose a novel methodology using multi-label classification method for simultaneously diagnosing multiple faults and evaluating the fault severity under noisy conditions. Performance of various multi-label classification models are compared. Current and vibration signals are acquired under normal and fault conditions. The applicability of the proposed method is experimentally validated under diverse fault conditions such as unbalance and misalignment.

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.

LEARNING PROCESS BEHAVIOR FOR FAULT DETECTION

2011 ◽  
Vol 20 (05) ◽  
pp. 969-980 ◽  
Author(s):  
CÁSSIO M. M. PEREIRA ◽  
RODRIGO F. DE MELLO
Keyword(s):  
Machine Learning ◽  
Fault Detection ◽  
Linear Models ◽  
Moving Average ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Self Healing ◽  
Detection Techniques ◽  
Process Behavior ◽  
Changes Over Time

Recently, there has been an increased interest in self-healing systems. These types of systems are able to cope with failures in the environment they execute and work continuously by taking proactive actions to correct these problems. The detection of faults plays a prominent role in self-healing systems, as faults are the original causes of failures. Fault detection techniques proposed in the literature have been based on three mainstream approaches: process heartbeats, statistical analysis and machine learning. However, these approaches present limitations. Heartbeat-based techniques only detect failures, not faults. Statistical approaches generally assume linear models. Most machine learning techniques assume the data is independent and identically distributed. In order to overcome all these limitations we propose a new approach to address fault detection, which also gives insight into how process behavior changes over time in the presence of faults. Experiments show that the proposed approach achieves a twofold increase in F -measure when compared to Support Vector Machines (SVM) and Auto-Regressive Integrated Moving Average (ARIMA).

Model-based diagnosis of electronic cooling fan drive systems

2018 ◽  
Author(s):  
Michael Pagel
Keyword(s):  
Fault Detection ◽  
Fault Detection And Diagnosis ◽  
Equivalent Series Resistance ◽  
Efficient Design ◽  
Model Based ◽  
Cooling Fan ◽  
Internal States ◽  
Detection And Diagnosis ◽  
Drive Systems

Kurzzusammenfassung: Model-based diagnosis of electric cooling fan drive systems is a contribution to the field of fault detection and diagnosis for electrically driven engine cooling fans. Its main focus is on the online gathering and determination of important parameters and internal states. The developed methods for fault detection and diagnosis are characterized by resource and computing efficient design and by a low application effort, drastically reducing the costs for transferring them to other applications. Novel algorithms are presented for determination of the winding resistance, the flux linkage over angle and the equivalent series resistance. Based on these algorithms, a new and innovative approach for determination of the magnet temperature is proposed, utilizing the winding temperature, which is derived without requiring an additional temperature sensor. Furthermore, methods are presented for detection of a demagnetization event, detection of an aged DC-link capacitor and...

scholarly journals Detection and Identification of Loss of Efficiency Faults of Flight Actuators

2015 ◽  
Vol 25 (1) ◽  
pp. 53-63 ◽  
Author(s):  
Daniel Ossmann ◽  
Andreas Varga
Keyword(s):  
Fault Detection ◽  
Surface Damage ◽  
Fault Detection And Diagnosis ◽  
Identification Algorithm ◽  
Detection Techniques ◽  
Fast Detection ◽  
Detection And Identification ◽  
Robust Fault Detection ◽  
Input Signals ◽  
Detection And Diagnosis

Abstract We propose linear parameter-varying (LPV) model-based approaches to the synthesis of robust fault detection and diagnosis (FDD) systems for loss of efficiency (LOE) faults of flight actuators. The proposed methods are applicable to several types of parametric (or multiplicative) LOE faults such as actuator disconnection, surface damage, actuator power loss or stall loads. For the detection of these parametric faults, advanced LPV-model detection techniques are proposed, which implicitly provide fault identification information. Fast detection of intermittent stall loads (seen as nuisances, rather than faults) is important in enhancing the performance of various fault detection schemes dealing with large input signals. For this case, a dedicated fast identification algorithm is devised. The developed FDD systems are tested on a nonlinear actuator model which is implemented in a full nonlinear aircraft simulation model. This enables the validation of the FDD system’s detection and identification characteristics under realistic conditions.

Sign in / Sign up

Export Citation Format

Share Document