Juan M. Moreno-Eguilaz

Neural network flux optimization using a model of losses in induction motor drives

This paper focuses on loss minimization in induction motor (IM) drives. In many applications Induction Motor drives work below the nominal torque most of the time. In these circumstances the IM efficiency can be improved lowering the flux. For a given torque, this decreases iron looses and increases copper losses. With appropriate algorithms an optimum point for the flux can be achieved in order to minimize IM total power losses. Using an IM model, a neural network (NN) based approach is used to improve efficiency in a vector control of the induction motor drive. A complex loss model of the motor, including magnetic and thermal deviations of its parameters, is used to estimate losses. Based on this model, the neural network is trained to estimate the optimum rotor flux. Inputs to the NN are torque, speed and rotor resistance of the IM and the output is the rotor flux. Analysis, modeling and simulation results are presented to demonstrate the validity of the proposed method. method.

An induction motor drive including a self-tuning loss-model based efficiency controller

An induction motor drive, including a loss-model based efficiency controller, is presented in this paper. To improve the robustness of the control system, a self-tuning controller has been designed. Thermal effects and saturation are considered by an on-line rotor resistance estimator, and by the estimation of the mutual inductance respectively. Analysis, simulation, and experimental results are presented to demonstrate the validity of the proposed method.

Understanding AC power using the generalized instantaneous reactive power theory: considerations for instrumentation of three-phase electronic converters

A didactic explanation of AC power using the generalized instantaneous power theory is presented in this paper. After a review of this theory, its relationship with the classical AC power definitions is described. In order to understand the presented concepts, two different computer simulations are shown. First, a three-phase balanced circuit is analyzed which contains no harmonics. Second, a three-phase power rectifier is studied with this theory. Fundamental and harmonic power concepts are commented upon in detail. The obtained results are used to understand AC power in electronic equipment for instrumentation and diagnosis purposes of three-phase systems. The final objective of this work is focused on the monitoring and efficiency optimization of three-phase electric drives.

A Neural Network Based Optimal Rotor Flux Estimator for Efficiency Optimization of an Induction Motor Drive

In this paper, a vector-controlled induction motor drive with efficiency optimization using a neural network based approach is presented. On-line estimators for rotor resistance and mutual inductance provide additional inputs for the neural network. Modeling and simulation results are presented to demonstrate the validity of the proposed method

Real-time power measuring and monitoring for an efficient vector-controlled induction motor drive

Efficient variable-speed drives are becoming more and more common in todays industry. With increasing harmonic pollution in the power system, real-time monitoring and analysis of harmonic variation have become important. To evaluate power quantities, it is necessary to consider the presence of harmonics because the drive is fed by a power electronics converter. In this paper, a fully digital algorithm to measure and evaluate main power definitions (active power, fundamental reactive power, fundamental apparent power, apparent power, nonfundamental apparent power, total power factor, displacement power factor, intensity total harmonic distortion, etc.) is presented and applied to an efficient variable-speed vector-controlled 1.5 kW induction motor drive. The system is useful to evaluate efficiency and harmonic pollution at different speed and load conditions. Besides, it allows other power quantities to be used as control variables in the efficiency controller.

A PC-based tool for evaluation of harmonics and power in three-phase power electronic converters

Efficiency and harmonics are important topics in todays electronic designs. Friendly tools for evaluation of power and harmonies are required in factories and laboratories. In this paper, a PC-based tool for evaluation of harmonics and power in three-phase power electronics converters is described. The hardware consists of simple Hall-effect sensors and the software is based on Labview language. Experimental results with a 7.5 kW soft starter for an induction motor are shown.

A Comparative Analysis of Two Neural-Network-Based Estimators for Efficiency Optimization of an Induction Motor Drive

A comparative analysis on vector-controlled induction motor drive with efficiency optimization using a neural-network-based and a model-losses-based approaches as flux estimator is presented in this paper. On-line estimators for rotor, stator resistances, and mutual inductance are included, two different neural networks were trained varying their inputs, and was used the losses-model-based estimator with some estimated and nominal parameters. Modeling and simulation results are presented to confirm the best performance approach

A Self-Tuning Loss-Model Based Efficiency Controller for an Induction Motor Drive

In this paper, a vector-controlled induction motor drive with efficiency optimization using a loss model based approach is presented. To improve the robustness of the control system, a self-tuning controller has been designed. On-line estimators for rotor resistance and magnetizing inductance are included in the controller to improve performance. Analysis, modeling and simulation results are presented to demonstrate the validity of the proposed method.

Neural network based approach for the computation of harmonic power in a real-time microprocessor-based vector control for an induction motor drive

With increasing harmonic pollution in the power system, real-time monitoring and analysis of harmonic variation have become important. A neural networks based approach has been demonstrated to be a very interesting tool for this purpose. However, initial conditions are critical for real-time implementation. A selective harmonic tracking algorithm is proposed to calculate initial conditions for the neural network. In this paper, a fully digital algorithm to measure and evaluate harmonic power using a neural network together with a selective harmonic tracking method is applied to an efficient variable-speed vector-controlled 1.5 kW induction motor drive.

Comparison of differential equation resolution methods in a real-time microprocessor-based vector control system for an induction motor drive

Three different differential equation resolution methods are studied in a real-time microprocessor-based vector control algorithm for an AC motor drive. Both accuracy and computing speed are analysed in these methods. Simulation and experimental results with an Intel 80486 32-bit microprocessor running at 50 MHz are included in this paper. The sophisticated resolution methods show similar accuracy and larger processing times when compared to traditional methods. The length of the variables (single or double) is an important parameter for the performance of the system and the stability of the numerical algorithms.<<ETX>>