#### DMCA

## Fault Detection and Diagnosis of Induction Machines based on Wavelet and Probabilistic Neural Network

### Citations

3769 | Particle Swarm Optimization
- Kennedy, Eberhart
- 1942
(Show Context)
Citation Context ...tionary computation technique motivated by the simulation of social behaviour and has attracting attentions in both research field and industrial applications due to its evolutionary algorithms (EAs) =-=[15]-=- [16] [17]. It is characterized as a simple heuristic of well balanced mechanism with flexibility stochastic search technique to enhance and adapt to both global and local exploration abilities [17]. ... |

1228 |
On estimation of a probability density function and mode.
- Parzen
- 1962
(Show Context)
Citation Context ...ilities and costs of misclassifications are treated as being equal. The probability density function for each data class for a univariate case can be estimated by the Parzen’s nonparametric estimator =-=[21]-=-: � � g x x�x 1 1 n � i � � �W � � n� i� � � where n is the sample size, sigma is a scaling parameter which defines the width of the bell curve that surrounds each compound, W(d) is a weight function ... |

816 |
The Wavelet Transform, Time-Frequency Localization and
- Daubechies
- 1990
(Show Context)
Citation Context ... the wavelet � layer are derived from a mother wavelet � x� , suppose 2 ��x��L�R�, which represents the collection of all measurable functions in the real space, satisfies the admissibility condition =-=[13]-=- 44International Journal of Computer Applications (0975 – 8887) Volume 69– No.14, May 2013 � �� �� � � � 2 � � d� �� � Where ��� � indicates the Fourier transform of � x� . The output of the wavelet ... |

367 |
Probabihstic Neural Networks,
- Specht
- 1990
(Show Context)
Citation Context ...ximum iteration number. 3. PROBABILISTIC NEURAL NETWORK (PNN) The probabilistic neural network (PNN) was first introduced by Specht in 1990 and is a form of neural network designed for classification =-=[19]-=-. A PNN is implemented by using the probabilistic models, such as Bayesian classifiers and has distinct features from those of other network in the learning processes. A PNN is guaranteed to converge ... |

235 | Wavelet networks,”
- Zhang, Benveniste
- 1992
(Show Context)
Citation Context ... ability as a novel universal approach for functional approximation, which shows surprising effectiveness in solving the conventional problem of poor convergence as well as increase convergence speed =-=[9]-=- [10] [11] [12]. This paper proposes an on-line current monitoring system to perform the diagnosis task in a supervisory system. In section 2, the architectures of wavelet neural networks and the trai... |

211 | Recent Approaches to Global Optimization Problems Through Particle Swarm Optimization".
- Parsopoulos, Vrahatis
- 2002
(Show Context)
Citation Context ...en the velocity on that dimension is limited to V max. V max influences PSO performance sensitively. A larger V max facilitates global exploration, while a smaller V max encourages local exploitation =-=[18]-=-. The constants c1 and c2 represent the weighting of the stochastic acceleration terms that pull each particle toward pbest and gbest positions. Low values allow particles to roam far from target regi... |

89 |
Estimation of a multivariate density.
- Cacoullos
- 1966
(Show Context)
Citation Context ...s largest value at d=0 and (x-x i) is the distance between a given compound and a compound in the training set. The Parzen’s nonparametric estimator is expanded by Cacoullos for the multivariate case =-=[22]-=-. � kj � � � � 1 �x � x x g( x1, , xp ) W , , � (7) � x (8) n 1 1, i p p, i � � � n� 1 � � � p i�1 �1 � � p � (6) � (9) The Gaussian function is frequently used as the weight function because it is we... |

70 |
Optimal design of power system stabilizers using particle swarm optimization”,
- Abido
- 2009
(Show Context)
Citation Context ...mputation technique motivated by the simulation of social behaviour and has attracting attentions in both research field and industrial applications due to its evolutionary algorithms (EAs) [15] [16] =-=[17]-=-. It is characterized as a simple heuristic of well balanced mechanism with flexibility stochastic search technique to enhance and adapt to both global and local exploration abilities [17]. PSO conduc... |

52 |
Advanced Algorithms for Neural Networks: A C++ Sourcebook,
- Masters
- 1995
(Show Context)
Citation Context ...ing speed of the PNN model is very fast, making it suitable for fault diagnosis and signal classification problems in real time. PNN can be implemented as a neural network, which is shown in Figure 2 =-=[20]-=-. The network architecture of a PNN is determined by the number of compounds and descriptors in the training set. There are 4 layers in a PNN. The input layer provides input values to all neurons in t... |

49 |
Wavelet neural networks for function learning,”
- Zhang, Walter, et al.
- 1995
(Show Context)
Citation Context ...as a novel universal approach for functional approximation, which shows surprising effectiveness in solving the conventional problem of poor convergence as well as increase convergence speed [9] [10] =-=[11]-=- [12]. This paper proposes an on-line current monitoring system to perform the diagnosis task in a supervisory system. In section 2, the architectures of wavelet neural networks and the training algor... |

41 |
Analysis and synthesis of feedforward neural networks using discrete affine wavelet transform.
- Pati, Krishnaprasad
- 1993
(Show Context)
Citation Context ...lity as a novel universal approach for functional approximation, which shows surprising effectiveness in solving the conventional problem of poor convergence as well as increase convergence speed [9] =-=[10]-=- [11] [12]. This paper proposes an on-line current monitoring system to perform the diagnosis task in a supervisory system. In section 2, the architectures of wavelet neural networks and the training ... |

33 |
A robust backpropagation learning algorithm for function approximation. Neural Networks,
- Chen, Jain
- 1994
(Show Context)
Citation Context ...ion. Among these artificial networks, the multilayer perception (MLP), and the back-propagation (BP) training algorithm are probably the most frequently used neural networks in practical applications =-=[8]-=-. However, both these two networks have some inherent defects, such as low learning speed, easy trapped in local minima, and difficult to choose proper parameters of network. To overcome these drawbac... |

32 |
Vibration and current monitoring for detecting airgap eccentricity in large induction motors," Electric Power Applications,
- Cameron, Thomson, et al.
- 1986
(Show Context)
Citation Context ...r axial flux by using search coils to detection broken rotor bars [2]. Cameron and Thomson proposed to use vibration and current monitoring for detecting airgap eccentricity in large induction motors =-=[3]-=-. Schoen, et al. introduced an unsupervised, on-line system for induction motor fault detection using motor stator current spectrum signature analysis [4]. Cruz, et al. and Nejjari, et al. presented p... |

27 |
An Unsupervised, On-line System For Induction Motor Fault Detection Using Stator Current Monitoring
- Schoen, Lin, et al.
- 1994
(Show Context)
Citation Context ...airgap eccentricity in large induction motors [3]. Schoen, et al. introduced an unsupervised, on-line system for induction motor fault detection using motor stator current spectrum signature analysis =-=[4]-=-. Cruz, et al. and Nejjari, et al. presented park’s vector current approach to monitor and diagnosis of induction motors separately [5] [6]. Salles, et al. proposed artificial intelligence based techn... |

26 |
Accuracy analysis for wavelet approximations,”
- Delyon, Juditsky, et al.
- 1995
(Show Context)
Citation Context ...novel universal approach for functional approximation, which shows surprising effectiveness in solving the conventional problem of poor convergence as well as increase convergence speed [9] [10] [11] =-=[12]-=-. This paper proposes an on-line current monitoring system to perform the diagnosis task in a supervisory system. In section 2, the architectures of wavelet neural networks and the training algorithm ... |

23 |
A J M. Stator winding fault diagnosis in three-phase synchronous and asynchronous motors by the extended Parks vector approach
- Cruz, Cardoso
(Show Context)
Citation Context ...detection using motor stator current spectrum signature analysis [4]. Cruz, et al. and Nejjari, et al. presented park’s vector current approach to monitor and diagnosis of induction motors separately =-=[5]-=- [6]. Salles, et al. proposed artificial intelligence based techniques to monitor induction motor load [7] Among different detection approaches proposed in the literature, those based on stator curren... |

22 | A novel method for modeling dynamic air-gap eccentricity in synchronous machines based onmodified winding function theory,” - Al-Nuaim, Toliyat - 1998 |

21 | Analysis of a concentrated winding induction machine for adjustable speed drive applications. II. Motor design and performance,” - Toliyat, Lipo, et al. - 1991 |

13 |
Monitoring and Diagnosis of Induction Motors Electrical Faults Using a Current Park’s Vector Pattern Learning Approach,
- Nejjari, Benbouzid
- 2000
(Show Context)
Citation Context ...ction using motor stator current spectrum signature analysis [4]. Cruz, et al. and Nejjari, et al. presented park’s vector current approach to monitor and diagnosis of induction motors separately [5] =-=[6]-=-. Salles, et al. proposed artificial intelligence based techniques to monitor induction motor load [7] Among different detection approaches proposed in the literature, those based on stator current mo... |

12 | Multiple coupled circuit modeling of induction machines,” - Luo, Liao, et al. - 1995 |

10 |
Methodologies of Using Neural Network and Fuzzy LogicTechnologies for Motor Incipient Fault Detection,” World Scientific Library
- Chow
- 1997
(Show Context)
Citation Context ...upply frequency and s is the slip, k= 1, 2, 3,… This phenomenon is related to amplitude modulation (AM) of stator current induced by rotor structure modification due to broken rotor bars as stated in =-=[23]-=-. However, the presence of stator current AM cannot be detected without accurate time or frequency analysis. Tradition Flourier transform method of analysis of the steady state current involves some i... |

7 | Effects of Rotor Eccentricity on Acoustic Noise from - Ellison, Yang - 1971 |

4 | On-line residual compensation in robust fault diagnosis of dynamic systems - Patton, Chen - 1992 |

4 | Determination of interbar current effects in the detection of broken rotor bars in squirrel cage induction motors - Walliser, Landy - 1994 |

3 | Effects of eccentricity in induction motors - Verma, Natarajan - 1982 |

3 | Complex vector model of the squirrel-cage induction machine including instantaneous rotor bar currents - Munoz, Lipo - 1999 |

2 |
et al., “Non-invasive detection of broken rotor bars in operating induction motors
- Kliman
- 1988
(Show Context)
Citation Context ...rements, infrared recognition, radio frequency emissions, noise monitoring or chemical analysis [1]. Kliman, et al. monitored the motor axial flux by using search coils to detection broken rotor bars =-=[2]-=-. Cameron and Thomson proposed to use vibration and current monitoring for detecting airgap eccentricity in large induction motors [3]. Schoen, et al. introduced an unsupervised, on-line system for in... |

2 | Air-gap flux analysis for cage rotor diagnosis - Morita - 1992 |

2 | Transsient analysis of cage induction machines under stator rotor bar and endring faults - Toliyat, Lipo - 1995 |

2 | Modélisation des moteurs asynchrones triphasés en régime Transitoire avec saturation et harmoniques d’espace. Application au diagnostic - Ah-jaco - 1997 |

2 | Feasibility study of a converter optimized induction motor - Lipo, Toliyat - 1989 |

2 | Coupled Magnetic Circuit Modeling of the Stator Windings Faults of Induction Machines Including Saturation Effect - Houdouin, Baraket, et al. - 2004 |

1 |
Fault diagnosis of electrical machine-a review
- Nandi, Toliyat
- 1999
(Show Context)
Citation Context ... discrimination of the enumerated faults have been proposed. Nandi and Toliyat studied temperature measurements, infrared recognition, radio frequency emissions, noise monitoring or chemical analysis =-=[1]-=-. Kliman, et al. monitored the motor axial flux by using search coils to detection broken rotor bars [2]. Cameron and Thomson proposed to use vibration and current monitoring for detecting airgap ecce... |

1 |
et al., Monitoring of induction motor load by neural network techniques
- Salles
(Show Context)
Citation Context ...sented park’s vector current approach to monitor and diagnosis of induction motors separately [5] [6]. Salles, et al. proposed artificial intelligence based techniques to monitor induction motor load =-=[7]-=- Among different detection approaches proposed in the literature, those based on stator current monitoring are advantageous due to its non-invasive characteristic. From all these approaches proposed i... |

1 | et al., "Detection of stator core faults in large electrical machines - Bertenshaw - 2012 |