Vitor Fernão Pires

Unsupervised Neural-Network-Based Algorithm for an On-Line Diagnosis of Three-Phase Induction Motor Stator Fault

In this paper, an automatic algorithm based an unsupervised neural network for an on-line diagnostics of three-phase induction motor stator fault is presented. This algorithm uses the alfa-beta stator currents as input variables. Then, a fully automatic unsupervised method is applied in which a Hebbian-based unsupervised neural network is used to extract the principal components of the stator current data. These main directions are used to decide where the fault occurs and a relationship between the current components is calculated to verify the severity of the fault. One of the characteristics of this method, given its unsupervised nature, is that it does not need a prior identification of the system. The proposed methodology has been experimentally tested on a 1kW induction motor. The obtained experimental results show the effectiveness of the proposed method

Narrow Pulse Elimination PWM for Multilevel Digital Audio Power Amplifiers Using Two Cascaded H-Bridges as a Nine-Level Converter

This paper presents a methodology to reduce total harmonic distortion (THD) in digital audio power amplifiers, using two new approaches: 1) a multilevel converter made of two cascaded full-bridges, with suitable power supplies to operate as a nine-level hybrid type converter and 2) a new pulsewidth modulation (PWM) technique called narrow pulse elimination (NPE) PWM. The proposed nine-level converter uses only eight MOSFETs. Unlike conventional PWM, the NPE PWM does not generate excessively narrow pulses, so that power semiconductors nonideal delays and switching times are still negligible. Therefore, the nine-level output voltage THD, mostly introduced in the power stage, is strongly reduced. With the NPE technique, the resolution of the generated PWM is no longer limited by the switching speed of the output switches, but only by the frequency of digital processing circuit. Simulation and experimental results from a laboratory prototype are presented in order to show the effectiveness of the proposed approaches

A DFIG Sensorless Rotor-Position Detector Based on a Hysteresis Controller

A simple sensorless method for the detection of the mechanical rotor position of the wound-rotor induction machine in order to implement stator-flux orientation is described and evaluated in this paper. The method is based on the phase comparison of the actual and the estimated rotor currents using the classical model of the machine. It can be conceptually implemented in the rotor or in the stator reference frames. It has some similarity to the model reference adaptive system methodology, but uses a hysteresis comparator instead of a proportional integral (PI) controller. In this way, the method does not need parameter determination for the controllers and shows a considerable independence of parameter uncertainties. Simulation and experimental results show that the method is appropriate for the vector control of the doubly fed induction generator (DFIG) because it leads to the decoupling of active and reactive power chains. It is also appropriate for the control of the DFIG in transients like those when voltage dips occur.

Three-phase single-stage four-switch PFC buck-boost-type rectifier

This paper proposes a new three-phase single-stage power-factor corrector buck-boost-type rectifier topology. The typical topology uses a bridge configuration with six switches. This new topology only requires four switches, improving the rectifier efficiency as only one reverse-blocking power semiconductor conducts at any time. A vector-based sliding-mode control method for the three-phase input currents is also proposed. This fast and robust technique uses sliding mode to generate /spl alpha//spl beta/ space-vector modulation, which forces the input line currents to track a suitable sinusoidal reference. A near-unity power-factor operation of the rectifier is obtained using a sinusoidal reference in phase with the input source voltages. A proportional-integral controller is adopted to regulate the output voltage of the converter. This external voltage controller modulates the amplitude of the current references. The characteristics of the new rectifier are verified with experimental results.

Distance-Learning Power-System Protection Based on Testing Protective Relays

The study of power system of relays requires some previous experience in this field. Laboratories focusing on teaching and researching the area of power-system protection have therefore been amply reported. However, these facilities require the actual presence of the students in the laboratories. To overcome this problem, a power-system-relaying remote laboratory has been developed. To implement this laboratory, a testing system of the relay operating characteristic, together with Matlab-based software, was developed. This remote laboratory enables real power-system-relaying experiments through the Internet. In fact, the user can remotely test a real relay disoperation. This system will therefore allow proficient analysis of sensitivities to relay settings and network configurations.

A network distribution power system fault location based on neural eigenvalue algorithm

A new approach to fault location for distribution network power system is presented. This approach uses the eigenvalue and an artificial neural network based learning algorithm. The neural network is trained to map the nonlinear relationship existing between fault location and characteristic eigenvalue The proposed approach is able to identify, to classify and to locate different types of faults such as: single-line-to-ground, double-line-to-ground, double-line and three-phase. Using the eigenvalue as neural network inputs the proposed algorithm is able to locate the fault distance. The results presented show the effectiveness of the proposed algorithm for correct fault diagnosis and fault location on a distribution power system networks.

Helicopter motion control using adaptive neuro-fuzzy inference controller

This paper proposes an adaptive neuro-fuzzy inference controller using a feed forward neural network based on nonlinear regression. The general regression neural network is used to construct the base of an adaptive neuro-fuzzy system. This neural network uses a different learning capability when compared with the classical clustering algorithm. The parameters of the general regression neural network are obtained using the gradient descent and least squares algorithms. The simplification of the neuro-fuzzy architecture is done throw the elimination of the rules, maintaining the performance of the controller. In the simulation, the adaptive neuro-fuzzy controller is used to control the helicopter motion in the hover flight mode position. The longitudinal and lateral cyclic, the collective and pedals are used to enable the helicopter to maintain its position fixed in space. Results show the effectiveness of the proposed method.

Image Processing to a Neuro-Fuzzy Classifier for Detection and Diagnosis of Induction Motor Stator Fault

In this paper a new algorithm for the detection of three-phase induction motor stator fault is presented. This diagnostic technique is based on the identification of a specified current pattern obtained from the transformation of the three- phase stator currents to an equivalent two-phase system. This new algorithm proposes a pattern recognition method to identify induction motor stator faults. The proposed neuro-fuzzy approach is based on the index of compactness, and also indicates the extension of the stator fault. This feature is obtained throw the image processing and used as an input in the neuro-fuzzy classifier. Using the neuro-fuzzy strategy, a better linguistic knowledge and an accurate learning capability underlying the motor faults detection and diagnosis process can be achieved. Simulation and experimental results are presented in order to verify the effectiveness of the proposed method.

PCA-Based On-Line Diagnosis of Induction Motor Stator Fault Feed by PWM Inverter

In this paper an automatic PCA (principal component analysis) based algorithm is presented for an on-line diagnostics of three-phase PWM feed induction motor stator fault. The analysis of the fault is derived from the two first principal components of the power inverter output current alphabeta-vector patterns. The obtained eigenvalues are used to discern if the motor is healthy or not, and the correspondent eigenvectors can infer the phase in which the fault occurs. The method is simple to implement and is able to indicate the extend of the fault; rather then only detect its presence

Single-Stage Double-Buck Topologies with High Power Factor

This paper presents two topologies for single-stage single-phase double-buck type PFC converters, designed to operate at high power factor, near sinusoidal input currents and adjustable output voltage. Unlike the known buck type PFC topologies, in which the output voltage is always lower than the maximum input voltage, the proposed converters can operate at output voltages higher than the ac input peak voltage. A reduced number of switches on the main path of the current are another characteristic of the two proposed topologies. To shape the input line currents, a fast and robust controller based on a sliding mode approach is proposed. This active non-linear control strategy, applied to these converters allows high quality input currents. A Proportional Integral (PI) controller is adopted to regulate the output voltage of the converters. This external voltage controller modulates the amplitude of the sinusoidal input current references. The performances of the presented rectifiers are verified with experimental results.