Alessandro Goedtel

Harmonic identification using parallel neural networks in single-phase systems

In this paper, artificial neural networks are employed in a novel approach to identify harmonic components of single-phase nonlinear load currents, whose amplitude and phase angle are subject to unpredictable changes, even in steady-state. The first six harmonic current components are identified through the variation analysis of waveform characteristics. The effectiveness of this method is tested by applying it to the model of a single-phase active power filter, dedicated to the selective compensation of harmonic current drained by an AC controller. Simulation and experimental results are presented to validate the proposed approach.

Synchronous reference frame based controllers applied to shunt active power filters in three-phase four-wire systems

This work presents compensation algorithm schemes used for shunt active power filters applied to three-phase four-wire systems, allowing harmonic current suppression and reactive power compensation, which results in an effective power factor correction. The strategies used to extract the three-phase reference currents are based on the synchronous reference frame method. Although this method is based on balanced three-phase loads, it can also be used for single-phase loads, allowing independent control of all three phases. Accordingly, a fictitious quadrature current needs to be generated through software implementation, and be orthogonal to the measured load current. This creates the fictitious balanced currents in the two-phase stationary reference frame system, allowing the choice of an adequate compensation strategy which will result in either balanced or unbalanced sinusoidal source currents. Three shunt APF topologies are evaluated under unbalanced load conditions: Split-Capacitor (S-C), Four-Leg (F-L) and Three Full-Bridge (3F-B). The proposed algorithms applied to the three APF topologies are evaluated and discussed. Mathematical analyses of the SRF-based algorithms are presented and simulation results are performed to validate the theoretical development and confirm the performance of the shunt APFs.

Evaluation of stator winding faults severity in inverter-fed induction motors

Graphical abstractDisplay Omitted HighlightsPresent a comprehensive evaluation of intelligent classifiers to identify stator faults in inverter-fed induction motors are presented.Proposed methodology uses the current signal in time domain as the inputs of the pattern classifiers for fault diagnosis.Experimental results with different inverters, operating frequencies and mechanical loads are presented.Three different intelligent methods are presented and compared for multiple faults under dynamic sampling rate. Three-phase induction motor are one of the most important elements of electromechanical energy conversion in the production process. However, they are subject to inherent faults or failures under operating conditions. The purpose of this paper is to present a comparative study among intelligent tools to classify short-circuit faults in stator windings of induction motors operating with three different models of frequency inverters. This is performed by analyzing the amplitude of the stator current signal in the time domain, using a dynamic acquisition rate according to machine frequency supply. To assess the classification accuracy across the various levels of faults severity, the performance of three different learning machine techniques were compared: (i) fuzzy ARTMAP network; (ii) multilayer perceptron network; and (iii) support vector machine. Results obtained from 2.268 experimental tests are presented to validate the study, which considered a wide range of operating frequencies and load conditions.

Compensation Algorithms Applied to Power Quality conditioners in three-phase four-wire systems

This work presents compensation algorithm schemes used in power quality conditioners applied to three-phase fourwire systems, allowing harmonic current suppression and reactive power compensation which results in an effective power factor correction. The strategies used to extract the three-phase compensation currents are based on the synchronous reference frame method. Although this method is itself based on balanced three-phase loads, it can also be used for single-phase loads, allowing independent control of all three phases. The compensation algorithms presented are implemented for two power conditioners, such as the Unified Power Quality Conditioner (UPQC) and the line-interactive Uninterruptible Power Supply (UPS) system, which allow the choice of a suitable compensation strategy resulting in either balanced or unbalanced sinusoidal source currents under balanced or unbalanced load conditions, respectively. Two, four-leg PWM converters are used to implement the UPQC and the UPS system to simultaneously perform the compensation of the load harmonic currents, utility voltage harmonics and the current and voltage unbalances. Mathematical analyses of the Synchronous Reference Frame (SRF)-based algorithms are presented and simulation results are performed to validate the theoretical development and confirm the performance of the power quality conditioners.

Harmonic distortion monitoring for nonlinear loads using neural-network-method

Nowadays, harmonic distortion in electric power systems is a power quality problem that has been attracting significant attention of engineering and scientific community. In order to evaluate the total harmonic distortion caused by particular nonlinear loads in power systems, the harmonic current components estimation becomes a critical issue. This paper presents an efficient approach to distortion metering, based on artificial neural networks applied to harmonic content estimation of load currents in single-phase systems. The harmonic content is computed using the estimation of amplitudes and phases of the first five odd harmonic components, which are carried out considering the waveform variations of current drained by nonlinear loads, within previously known limits. The proposed online monitoring method requires low computational effort and does not demand a specific number of samples per period at a fixed sampling rate, resulting in a low cost harmonic tracking system. The results from neural networks harmonic identification method are compared to the truncated fast Fourier transform algorithm. Besides, simulation and experimental results are presented to validate the proposed approach.

A novel multi-agent approach to identify faults in line connected three-phase induction motors

Graphical abstractDisplay Omitted HighlightsPresent a novel multi-agent approach to identify stator, rotor and bearing faults in three-phase induction motors.Proposed methodology uses the current amplitudes signal in time domain as the inputs of the multi-agent system for fault diagnosis.The multi-agent system incorporates pattern recognition techniques with better results for each type of fault.Experimental results gathered from three-phase induction motors operating with different load conditions and fed under unbalance voltage are provided. Three-phase induction motors (TIMs) are the key elements of electromechanical energy conversion in a variety of productive sectors. Identifying a defect in a running motor, before a failure occurs, can provide greater security in the decision-making processes for machine maintenance, reduced costs and increased machine operation availability. This paper proposes a new approach for identifying faults and improving performance in three-phase induction motors by means of a multi-agent system (MAS) with distinct behavior classifiers. The faults observed are related to faulty bearings, breakages in squirrel-cage rotor bars, and short-circuits between the coils of the stator winding. By analyzing the amplitudes of the current signals in the time domain, experimental results are obtained through the different methods of pattern classification under various sinusoidal power and mechanical load conditions for TIMs. The use of an MAS to classify induction motor faults allows the agents to work in conjunction in order to perform a specific set of tasks and achieve the goals. This technique proved its effectiveness in the evaluated situations with 1 and 2hp motors, providing an alternative tool to traditional methods to identify bearing faults, broken rotor bars and stator short-circuit faults in TIMs.

Bearing fault detection using relative entropy of wavelet components and artificial neural networks

Fault detection in electrical machines have been widely explored by researchers, especially bearing faults that represents about 40% to 60% of the total faults. Since this kind of fault is detectable by particular frequencies at the stator current, it is now a source of investigation. Thus, this work presents a predicability analysis method based on relative entropy measures estimated over reconstructed signals obtained from wavelet-packet decomposition components. The signals were simulated using a real motor current signal with addition of frequency components related to the bearing faults. Using three ANN topologies, these entropy measures are classified in two groups: normal and faulty signals with a high performance rate.

Neural Network-Based Approach for Identification of the Harmonic Content of a Nonlinear Load in a Single-Phase System

In this paper an alternative method based on artificial neural networks is presented to determine harmonic components in the load current of a single-phase electric power system with nonlinear loads, whose parameters can vary so much in reason of the loads characteristic behaviors as because of the human intervention. The first six components in the load current are determined using the information contained in the time-varying waveforms. The effectiveness of this method is verified by using it in a single-phase active power filter with selective compensation of the current drained by an AC controller. The proposed method is compared with the fast Fourier transform.

Neural Approach for Speed Estimation in Induction Motors

The use of sensorless technologies is an increasing tendency on industrial drives for electrical machines. The estimation of electrical and mechanical parameters involved with the electrical machine control is used very frequently in order to avoid measurement of all variables involved in this process. The cost reduction may also be considered in industrial drives, besides the increasing robustness of the system, as an advantage of the use of sensorless technologies. This work proposes the use of artificial neural networks to estimate one of the most important variables in the induction motor control schemes: the speed. Simulation and experimental results are presented to validate the proposed approach.

Neural speed estimator for line-connected induction motor embedded in a digital processor

A robust neural-network-method applied to speed estimation in line-connected three-phase induction motors is presented.A comparative study of single and multiple current sensor applied to speed estimation is presented.Proposed method is validated using simulation and experimental results considering unbalance operation conditions and wide range of load torque.Proposed method is embedded in a digital processor and validated in a test bench. Estimating the electrical and mechanical parameters involved in three-phase induction motors is frequently employed to avoid measuring every variable in the process. Among mechanical parameters, speed is an important variable: it is involved in control, diagnosis, condition monitoring, and can be measured or estimated by sensorless methods. These technologies offer advantages when compared with direct measurement, such as lower cost or more robust systems. This paper proposes the use of artificial neural networks to estimate rotor speed by using current sensors for balanced and unbalanced voltage sources with a wide mechanical load range in a line-connected induction motor. This paper also presents two case analyses: (i) a single current sensor; and (ii) a multiple currents sensors. Simulation and experimental results are presented to validate the proposed approach. A neural speed estimator embedded in a digital processor is also presented.