Luciana Cambraia Leite

Field Programmable Gate Array (FPGA) Based Neural Network Implementation of Stator Flux Oriented Vector Control of Induction Motor Drive

In this work, it is proposed the implementation of the SFOVC-ANN using field programmable gate array (FPGA). The proposed scheme assure parallel processing of the ANN, since the circuit design was done in such way that the neurons in the same layer processes the input signals in parallel. The non-linear sigmoidal transfer function is implemented using Spline Interpolation, which guarantees an excellent precision. Initially in the digest, a description of the proposed system is given. Then, the nonlinear neuron implementation strategy is explained. Following this, the FPGA implementation of ANN is described. Finally, simulation and experimental results are given to substantiate the development.

Auto-Associative Neural Network Based Sensor Drift Compensation in Indirect Vector Controlled Drive System

The paper proposes an auto-associative neural network (AANN) based sensor drift compensation in an indirect vector-controlled induction motor drive. The feedback signals from the phase current sensors are given as the AANN input. The AANN then performs the auto-associative mapping of these signals so that its output is an estimate of the sensed signals. Since the AANN exploits the physical and analytical redundancy, whenever a sensor starts to drift, the drift is compensated at the output, and the performance of the drive system is barely affected. The paper describes the drive system, gives a brief overview of the AANN, presents the technical approach, and then gives some performance of the system demonstrating validity of the approach. Although current sensors are considered only in the paper, the same approach can be applied to voltage, speed, torque, flux, or any other type sensor.

Development of an embedded module using FPGA technology and Fuzzy technique

This paper presents the implementation of an integrated module which aims to control, effectively, the flow of a centrifuge, in this stage of sugar production, in which the magma must be centrifuged to give rise to sugar. This module was programmed in FPGA and its techniques of fuzzy control were embedded in the NIOS II processor. The prototype implemented to control the flow of magma a modulating control valve with different angles (0, -45, 45, -90, 90), allowing you to maintain a charge that stabilizes in its current effective. Some signal conditioning circuits were developed to perform the operation of the drive and monitoring of this process. Another contribution is the development of a specific template for fuzzy controllers and can be used in other hardware.

Monitoring and control of the processes involved in the capture and filtering of biogas using FPGA embedded fuzzy logic

This article focuses on the development of an intelligent control platform capable of improving the capture and filtration of biogas with the aim of raising the calorific value of the fuel. The biogas was produced in an upflow anaerobic sludge blanket (UASB) reactor at the sewage treatment plant (STP) located near to the town of Los Angeles, Campo Grande, Mato Grosso do Sul, Brazil. For the purposes of system identification, the concentrations, flow rates and pressures of the gases were continuously monitored before and after the filtering processes. The fuzzy proportional derivative controller described herein was required to sustain maximum biogas flow whilst ensuring that the concentration of oxygen did not exceed a predetermined point (the SetPoint) regardless of the variation in load received by the digester. The controller input was oxygen concentration, and the processed output signal was sent to an inverter responsible for raising or lowering the speed of the compressor used in the capture of the biogas. The controller design was developed using MATLAB software and implemented in a field-programmable gate array (FPGA)-embedded Nios II processor. The embedded control algorithm was validated with the aid of ModelSim software. Electronic circuits were developed to allow the FPGA board and the sensors and actuators to communicate via protocols widely used in the industrial setting. This design factor, taken together with the incorporation of reconfigurable hardware and the facility of changing the rules of the fuzzy controller, afforded maximum flexibility of the control platform for use in other applications.

Evaluation of the Auto-Associative Neural Network Based Sensor Compensation in Drive Systems

The paper performs a deep analysis of the sensor drift compensation in motor drives approach presented in past publications [11-12]. In the past, the auto-associative neural networks (AANN) were found to be effective for this application. However, it is still unclear how much improvement may be obtained compared with other modeling techniques and when it is adequate to be applied. Therefore, the modeling techniques, specially the AANN, are detailed and evaluated using performance metrics. Additional experimental results in a motor drive are provided to show the compensation capability of the AANN. The feedback signals are given as the AANN inputs. The AANN then performs the auto-associative mapping of these signals so that its outputs are estimations of the sensed signals. Since the AANN exploits the physical and analytical redundancy, whenever a sensor starts to drift, the drift is compensated, and the performance of the drive system is barely affected.

Performance Assessment of Generators Groups When Connected to an Inductive Load

This study evaluated the behavior of two types of commercial engine generators groups of 3.5 kVA when submitted to a resistive and inductive load bank. Analyzing the quality parameters from generated power, distortions in the waveform of current and voltage were observed to both generators. All parameters analysed were submitted to principal component analysis (PCA), which showed that total harmonic distortion voltage and reactive power affected negatively the generators operation. Distinctions of two groups were also observed and a similarity was noted between operation to resistive and inductive loads. Furthermore, the statistical analysis showed similarity in behavior of gasoline and diesel generators when subjected to resistive / inductive loads.

CONTROLADOR FUZZY APLICADO EM AR CONDICIONADO AUTOMOTIVO

DOI: 10.14684/intertech.13.2014.252-256 The objective of this paper is to use the tool of fuzzy logic to optimize the use of vehicle air conditioning system (VACS). This system has the function of improving the distribution of air conditioning ventilation for the vehicle´s occupants, as well as reducing fuel consumption through a fuzzy controller developed in a microcontroller. The controller implemented in the dsPIC plate will have temperature sensors, and infrared switch, and pressure switch as input signals. As output signal it will have the control of time of compressor drive in order to maintain a comfortable temperature inside the vehicle, depending on the number of occupants, thus reducing the torque exerted on the engine and increasing the electrical system and generator longevity. The system was simulated in the fuzzy logic toolbox of MATLAB and the results were satisfactory, significantly reducing the compressor´s time of use. Index Terms – Fuzzy logic, control of the air conditioning system, fuel economy, dsPIC.

Pulsating Torque Analysis of PMSM Driven by Dual Mode Inverter Control in Wide Constant Power Speed Range

The scope of this work is the analysis of pulsating torque in Permanent Synchronous Machine (PMSM) driven by Dual Mode Inverter Control (DMIC) in wide Constant Power Speed Range (CPSR). The operation principle of DMIC driving PMSM in a CPSR is briefly described. In the sequence, analytical results of the three-phase currents in the stationary reference frame, as well as the dq currents in the rotating reference frame are given. The pulsating torque resulting of the DMIC strategy is then addressed through Fourier analysis showing the harmonic content of the id and iq currents. With this analysis, is possible to observe how the pulsating torque behaves as speed increases. The results are relevant to help engineers to decide to what application DMIC may be used, and to estimate the pulsating torque effect at speed depending on the load/machine parameters.