1. |
- Gavrilis, Dimitris, et al.
(författare)
-
A One-Class Approach to Cardiotocogram Assessment
- 2015
-
Ingår i: 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. - Piscataway, NJ : IEEE Communications Society. - 9781424492718 ; , s. 518-521
-
Konferensbidrag (refereegranskat)abstract
- Cardiotocogram (CTG) is the most widely used means for the assessment of fetal condition. CTG consists of two traces one depicting the Fetal Heart Rate (FHR), and the other the Uterine Contractions (UC) activity. Many automatic methods have been proposed for the interpretation of the CTG. Most of them rely either on a binary classification approach or on a multiclass approach to come up with a decision about the class that the tracing belongs to. This work investigates the use of a one-class approach to the assessment of CTGs building a model only for the healthy data. The preliminary results are promising indicating that normal traces could be used as part of an automatic system that can detect deviations from normality.
|
|
2. |
- Georgoulas, George, et al.
(författare)
-
A Data Fusion Approach to Bearing Fault Detection and Diagnosis
- 2015
-
Ingår i: IEEE International Conference on Power Engineering, Energy and Electrical Drives, POWERENG 2015, May 11-13, Riga, Latvia, 2015. - Piscataway, NJ : IEEE Communications Society. ; , s. 109-113
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a data fusion approach for the diagnosis of bearing faults under different seeded fault scenarios. The approach is based on the extraction of three simple and intuitive features that fuse the information that comes from two accelerometers placed at two different sites of the test bed. The analysis shows that in the case of the occurrence of a fault even in an early stage the “footprint” left at the scatter plot of the measurements coming from the two accelerometers can effectively turned into features/descriptors by simple statistical measures such as the elements of the covariance matrix. Those features when fed to a k-nearest neighbor classifier or an ensemble of one class detectors can lead to a remarkably high detection/diagnostic performance.
|
|
3. |
- Karvelis, Petros, et al.
(författare)
-
Symbolic time series analysis of the soft starting transient in induction machines
- 2015
-
Ingår i: 2015 IEEE International Conference on Industrial Technology (ICIT 2015) to be held in Seville, Spain, March 17-19, 2015.. - Piscataway, NJ : IEEE Communications Society. - 9781479978007 ; , s. 3243-3248
-
Konferensbidrag (refereegranskat)abstract
- Induction motors are in the heart of almost every production line especially due to their robustness under harsh environments. Nevertheless, even induction machines are prone to faults. Among them, the faults related to the breakage of rotor bars have received special attention by the research community with a number of methods proposed both for the case of steady state as well as for transient operation. For the latter, methods relying on the analysis of the start-up transient have proven to be able to effectively isolate the faulty component that is created by the asymmetry caused by the bar breakage. However, very little work has been done concerning the soft starting of induction machines. In this work, preliminary results of the application of a symbolic time series technique for the analysis of the transient, when the motor is controlled by a soft starter, will be presented and experimentally evaluated.
|
|
4. |
- Mustafa, Mohammed Obaid, et al.
(författare)
-
Fault classification of Broken Rotor Bars in Induction Motors Based on Envelope Current Analysis
- 2015
-
Ingår i: IEEE 13th International Conference on Industrial Informatics (INDIN), 2015. - Piscataway, NJ : IEEE Communications Society. - 9781479966493 ; , s. 795-800
-
Konferensbidrag (refereegranskat)abstract
- In this article a method for the fault classification of one, two, and three broken bars in induction motors under full load condition is presented. The proposed methodology is based on the current envelope analysis, which in the past has been also widely utilized in analyzing the rotor faults at low slips. As it will be presented, the information obtained from the envelope current is valuable in manifesting and validating the presence of fault, since the current envelope and its characteristics often contains important information about the existence of a fault and the corresponding fault type. The proposed method mainly focuses on the case of steady-state operation under full load. In the established fault detection scheme, from the stator’s current six statistical features are extracted and utilized for the fault detection and classification. In more detail, three classifiers, a linear, a quadratic and a Nearest Neighbor have been investigated for the diagnosis of broken rotor bar faults of an induction motor. The presented approach have manifested promising results using experimental data.
|
|
5. |
- Mustafa, Mohammed Obaid, et al.
(författare)
-
Principal Component Analysis Anomaly Detector for Rotor Broken Bars
- 2015
-
Ingår i: IECON 2014. - Piscataway, NJ : IEEE Communications Society. - 9781479940332 ; , s. 3462-3467
-
Konferensbidrag (refereegranskat)abstract
- In this article a method for the detection of broken rotor bars in asynchronous machines operating under full load is presented. Unlike most Motor Current Signature Analysis (MCSA) approaches, which operate in the frequency domain, our method operates in the time domain. The scheme is based on the use of a Principal Component Analysis (PCA) fault/anomaly detector applied on the three stator currents to calculate the Q statistic which is employed for detecting a fault. The efficiency of the proposed scheme was experimentally evaluated using different fault severity levels, ranging from 1/4 of a broken bar to three broken bars. The obtained results indicate that the method can detect the caused asymmetry with a very restricted amount of data.
|
|