Tito G. Amaral

Brief paper: Hand movement recognition based on biosignal analysis

This paper proposes a methodology that analyses and classifies the electromyographic (EMG) signals using neural networks to control multifunction prostheses. The control of these prostheses can be made using myoelectric signals taken from surface electrodes. Finger motions discrimination is the key problem in this study. Thus the emphasis, in the proposed work, is put on myoelectric signal processing approaches. The EMG signals classification system was established using the linear neural network. The experimental results show a promising performance in classification of motions based on biosignal patterns.

Power quality disturbances classification using the 3-D space representation and PCA based neuro-fuzzy approach

In this paper a new approach for power quality (PQ) event detection and classification is proposed. This approach is based on an automatic four step algorithm. First the acquired voltage signals are represented in a 3-D space referential. Then principal component analysis is performed. In the third, features are extracted from the obtained eigenvalues of each disturbance waveforms. Finally a neuro-fuzzy based classifier automatically classifies the PQ disturbances. To show the effectiveness of the proposed method several case studies are presented. From the obtained results it is possible to confirm that the proposed approach can effectively classify different PQ disturbances.

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.

Induction motor fault detection and diagnosis using a current state space pattern recognition

In the last few decades the continuous monitoring of complex dynamic systems has become an increasingly important issue across diverse engineering areas. This paper presents a pattern recognition based system that uses visual-based efficient invariants features for continuous monitoring of induction motors. The procedures presented here are based on the image identification of the 3-D current state space patterns that allow the identification of distinct fault types and, furthermore, their corresponding severity. This automatic fault detection system deals with time-variant electric currents and is based on the identification of three-phase stator currents specified patterns. Several simulation and experimental results are also presented in order to verify the effectiveness of the proposed methodology.

Automatic helicopter motion control using fuzzy logic

This paper describes the application of the fuzzy logic control (FLC) theory to control the helicopter flight on two basic flight modes: hovering and forward. Hovering is a formidable stability problem, where helicopter pilots typically train for weeks before managing to do it manually. Hence automating this operation is in itself an impressive achievement. In this work, four FLCs execute control rules that represent the linguistic knowledge used by helicopter pilots and found as verbal description in pilot operating manuals. For each flight mode it is used two FLCs where the outputs corresponds to the pitch angle of longitudinal and lateral cyclic. For the hover flight mode the controllers variable input are the pitch attitude and pitch rate of the fuselage for the first controller and the roll angle and roll rate of fuselage for the second controller to control the side and forward velocity through the pitch angle of lateral and longitudinal cyclic. In the forward flight mode, it is used three variable input for each controller where four of them are the same used in the hover flight mode and it is also used the forward velocity variable in both controllers. Simulation results are presented, showing the effectiveness of the proposed FLCs for both flight modes.

Development of an experimental system for teaching induction motors with fault detection and diagnosis capabilities

The study of fault detection and diagnosis of electrical machines, in particular induction motors, as well as the teaching of their behavior requires practical experience in this field. To provide this experience to the students this paper presents an experimental system that can be used with a standard industrial electrical induction machine. This system is based on only one healthy induction machine that is operated under faulty operating modes. Several fault types such as stator winding faults, bearing faults, or broken bars can be tested. The developed system also allows testing the behavior of the electrical machine for different load types. Several typical loads in which the torque depends of time or speed were implemented. The system is based on computer equipment with a DSPIC, a testing system and an induction machine.

Stator winding fault diagnosis in induction motors using the dq current trajectory mass center

This paper proposes the use of the park transformation mass center applied to the stator currents as a method for diagnosing the occurrence of stator winding faults in induction motor. Induction motor stator currents are first measured and recorded. Then, the park transform is applied to the obtained currents in order to obtain a specific pattern that allows the identification of the stator winding fault. For a healthy motor, a single point in a dq-plane is obtained. However, for an induction motor with some stator winding fault one obtains a circle, in the dq-plane, which is dependent on the fault severity. Accordingly to this relationship a fault severity is reported. In order to show the applicability of the proposed technique, several simulation and experimental results are presented.

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.

Web based teaching of electrical drives using a mechanical load simulator

In this paper a Web based teaching of electrical drives using a mechanical load simulator is presented. The developed system allows testing the behavior of an electrical machine for different load types. Several typical loads in which the torque depends of time or speed are implemented. In this way, using this tool it is possible to study the dynamic behavior of an electrical machine. It is also used to study induction machine fault diagnosis under different load types. The remote laboratory is based on an I/O interface controller and client-server architecture. To implement this system the software package MATLAB was used.

Fault detection of voltage-source inverter using pattern recognition of the 3D current trajectory

Three-phase voltage-source inverter is one of the most widely used power converters. Therefore, the need to insure a continuous and safety operation for this power converter with fault detection technique is a need, more or less, depending on their application. For this power converter several faults can appear. This paper presents a method for the detection and identification of the transistor open circuit fault. The proposed method uses a 3D representation of the inverter three-phase currents. This allows obtaining a specific pattern. Then a pattern recognition approach is used to identify the faulty switch. This approach is based on two steps. First it is obtained the current trajectory mass center. Then it is analyzed the symmetry of the image projection around the mass center. Several simulation results are presented showing the effectiveness of the proposed approach. Experimental results are also presented in order to validate simulation results.