Abdelkader Chaari

Support vector machine based decision for mechanical fault condition monitoring in induction motor using an advanced Hilbert-Park transform

In this work we suggest an original fault signature based on an improved combination of Hilbert and Park transforms. Starting from this combination we can create two fault signatures: Hilbert modulus current space vector (HMCSV) and Hilbert phase current space vector (HPCSV). These two fault signatures are subsequently analysed using the classical fast Fourier transform (FFT). The effects of mechanical faults on the HMCSV and HPCSV spectrums are described, and the related frequencies are determined. The magnitudes of spectral components, relative to the studied faults (air-gap eccentricity and outer raceway ball bearing defect), are extracted in order to develop the input vector necessary for learning and testing the support vector machine with an aim of classifying automatically the various states of the induction motor.

A novel fuzzy c-regression model algorithm using a new error measure and particle swarm optimization

Abstract This paper presents a new algorithm for fuzzy c-regression model clustering. The proposed methodology is based on adding a second regularization term in the objective function of a Fuzzy C-Regression Model (FCRM) clustering algorithm in order to take into account noisy data. In addition, a new error measure is used in the objective function of the FCRM algorithm, replacing the one used in this type of algorithm. Then, particle swarm optimization is employed to finally tune parameters of the obtained fuzzy model. The orthogonal least squares method is used to identify the unknown parameters of the local linear model. Finally, validation results of two examples are given to demonstrate the effectiveness and practicality of the proposed algorithm.

Comparative investigation of diagnosis media for induction machine mechanical unbalance fault

For an induction machine, we suggest a theoretical development of the mechanical unbalance effect on the analytical expressions of radial vibration and stator current. Related spectra are described and characteristic defect frequencies are determined. Moreover, the stray flux expressions are developed for both axial and radial sensor coil positions and a substitute diagnosis technique is proposed. In addition, the load torque effect on the detection efficiency of these diagnosis media is discussed and a comparative investigation is performed. The decisive factor of comparison is the fault sensitivity. Experimental results show that spectral analysis of the axial stray flux can be an alternative solution to cover effectiveness limitation of the traditional stator current technique and to substitute the classical vibration practice.

An improved spectral analysis of the stray flux component for the detection of air-gap irregularities in squirrel cage motors

For machines׳ monitoring purpose, the classical motor current signature analysis has shown its weakness in distinguishing the eccentricity occurrence in presence of others mechanical faults. Although Park׳s vector approach can cover this drawback, the high cost due to the requirement to use three current sensors associated with an advanced processing technique, makes it less desired by industrialists. In this paper, we suggest an alternative diagnosis method based on a suitable processing of the stray flux data. The experimental results have revealed the potential of a simple search coil for the detection and the distinction of the accurate eccentricity nature even in presence of similar mechanical faults.

Electric Drive Control with Rotor Resistance and Rotor Speed Observers Based on Fuzzy Logic

Many scientific researchers have proposed the control of the induction motor without speed sensor. These methods have the disadvantage that the variation of the rotor resistance causes an error of estimating the motor speed. Thus, simultaneous estimation of the rotor resistance and the motor speed is required. In this paper, a scheme for estimating simultaneously the rotor resistance and the rotor speed of an induction motor using fuzzy logic has been developed. We present a method which is based on two adaptive observers using fuzzy logic without affecting each other and a simple algorithm in order to facilitate the determination of the optimal values of the controller gains. The control algorithm is proved by the simulation tests. The results analysis shows the characteristic robustness of the two observers of the proposed method even in the case of variation of the rotor resistance.

Artificial Intelligence Tools Aided-decision for Power Transformer Fault Diagnosis

This paper presents an intelligent fault classification approach for power transformer dissolved gas analysis (DGA). Fault diagnosis methods by the DGA and artificial intelligence (AI) techniques are implemented to improve the interpretation accuracy for DGA of power transformers. The DGA traditional methods are utilized to choose the most appropriate gas signature. AI techniques are applied to establish classification features for faults in the transformers based on the collected gas data. The features are applied as input data to fuzzy logic, artificial neural network (ANN) and support vector machine (SVM) classifiers for faults classification. The experimental data from Tunisian Company of Electricity and Gas (STEG) is used to evaluate the performance of proposed method. The results of the various DGA methods are classified using AI techniques and the results are compared with the empirical test. In comparison to the results obtained from the AI techniques, the ratios DGA method has been shown to possess the most excellent performance in identifying the transformer fault type. The test results indicate that the SVM approach can significantly improve the diagnosis accuracies for power transformer fault classification.. General Terms Key gas, graphical representation, ratios, multi-layer perceptron, radial basis function.

Performance analysis of FOC and DTC for PMSM drives using SVPWM technique

The aim of this article is to present the performance of field oriented control (FOC) and direct torque control (DTC) of a permanent magnet synchronous motor (PMSM) using the technique of space vector pulse width modulation (SVPWM). First, after developing a mathematical model of PMSM we present the principle of space vector modulation technique to use in commands. Secondly, we developed a field oriented control and direct torque control strategy. Finally, we proposed a failover system between direct torque control and field oriented control in the event of default or loss of information.

Induction motor mechanical fault identification using Park's vector approach

In this work we have shown that the extended Parks vector spectrum is rich in harmonics characteristics of mechanical defects (air-gap eccentricity and outer raceway bearing fault). About the use of Parks Lissajous curves to identify mechanical defects, we have demonstrated that this type of index can only detect the occurrence of a fault, but it cannot identify.

A new approach rotor speed estimation for PMSM based on sliding mode observer

This paper proposes a sensorless speed control strategy for a permanent-magnet synchronous motor (PMSM) based on a sliding-mode observer (SMO). In order to apply a sensorless PMSM control which is robust against parameter fluctuations and disturbances, a high-speed SMO is proposed, which estimates the rotor position and the angular velocity. The stability of the proposed SMO was verified using the Lyapunov method to determine the observer gain. At standstill, the type of sliding mode observer is not able to detect the rotor position. For this reason, we use the method of voltage pulses to detect it. The simulation results show the effectiveness of the observer with sliding mode. They are characterized by a very small estimation error for the various rotational speeds (high speed, low speed).

Detection of brushless exciter rotating diodes failures by spectral analysis of main output voltage

Rotating rectifier is a basic part of synchronous generators. Inappropriate operation of this component can prove costly for the machines owner. This paper presents theoretical analysis and experimental validation for detecting failure of brushless exciter rotating diodes that can fail either open circuit or short circuit. Harmonic analysis of the alternator output voltage waveform is performed when machine is unloaded as well as when it runs around its rated load. Apparition of characteristic frequencies can be useful to distinguish the rotating diodes state. By considering the relative amplitudes at specific harmonics, it is possible to discriminate short circuit diode failure case from open circuit diode breakdown.