scholarly journals Wavelet-Based Analysis of MCSA for Fault Detection in Electrical Machine

10.5772/61532 ◽  
2015 ◽  
Author(s):  
Mohammad Rezazadeh Mehrjou ◽  
Norman Mariun ◽  
Mahdi Karami ◽  
Samsul Bahari Mohd. Noor ◽  
Sahar Zolfaghari ◽  
...  
Keyword(s):  
Fault Detection ◽  
Electrical Machine

Data-Driven Fault Detection of Electrical Machine

2018 ◽  
Author(s):  
Zhao Xu ◽  
Jinwen Hu ◽  
Changhua Hu ◽  
Sivakumar Nadarajan ◽  
Chi-keong Goh ◽  
...  
Keyword(s):  
Fault Detection ◽  
Data Driven ◽  
Electrical Machine

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 STATIC ECCENTRICITY FAULT DETECTION METHOD FOR ELECTRICAL ROTATING MACHINES BASED ON THE MAGNETIC FIELD ANALYSIS IN THE AIR GAP BY MEASURING COILS

2020 ◽  
Vol 69 (4) ◽  
pp. 3-7
Author(s):  
Stjepan Tvorić ◽  
Miroslav Petrinić ◽  
Ante Elez ◽  
Mario Brčić
Keyword(s):  
Magnetic Field ◽  
Fault Detection ◽  
Air Gap ◽  
Field Analysis ◽  
Detection Methods ◽  
Electrical Machine ◽  
Rotating Machines ◽  
Static Eccentricity ◽  
Machine Fault ◽  
The Magnetic Field

Electrical rotating machines have a great economic significance as they enable conversion of energy between mechanical and electrical state. Reliability and operation safety of these machines can be greatly improved by implementation of continuous condition monitoring and supervisory systems. Especially important feature of such systems is the ability of early fault detection. For this reason, several methods for detection and diagnosis of the machine faults have been developed and designed. As fault detection methods can largely differ in the types of detectable faults, machine adoptability and price of the system, a novel method was developed that can be used for cost-effective detection of various faults of electrical machine. Machine fault detection technique presented in this paper is based on the measurement of magnetic field in the air gap. Numerous studies have proven that crucial information about the machine condition can be determined based on measurement and analysis of the magnetic field in the air gap. It has also been confirmed that analysis of the air gap magnetic field can be used to detect, diagnose and recognize various electrical faults in their very early stage. Proposed method of positioning and installation of the measuring coils on ferromagnetic core parts within the air gap region of the machine enables differentiation of various faults. Furthermore, different faults can be detected if measuring coils are placed on the stator teeth then when placed on the rotor side. The paper presents method on how to analyse and process the measured voltages acquired from measuring coils placed within the machine, especially in the case of rotor static eccentricity detection. The methodology is explained by means of finite element method (FEM) calculations and verified by measurements that were performed on the induction machine. FEM calculation model was used to predict measurement coil output of the induction motor for healthy and various faulty states (at different amounts of static eccentricity). These results were then confirmed by measurements performed in the laboratory on the induction traction motor that was specially modified to enable measurements of faulty operation states of the machine. Measurements comprised of several machine fault conditions broken one rotor bar, broken multiple rotor bars, broken rotor end ring and various levels of rotor static eccentricity. Other methods used for faults detection are primarily based on the monitoring of quantities such as current and vibration and their harmonic analysis. This new system is based on the tracing the changes of induced voltage of the measuring coils installed on the stator teeth. Faults can be detected and differentiated based on RMS value of these voltages and the number of voltage spikes of voltage waveform i.e. without the need of harmonic analyses. If these coils are installed on the rotor it is possible to detect the stator winding faults in a similar manner.

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.

Sign in / Sign up

Export Citation Format

Share Document