Speed estimation for induction motor using neural networks method

This work presents an alternative approach based on neural network method in order to estimate speed of induction motors, using the measurement of primary variables such as voltage and current. Induction motors are very common in many sectors of the industry and assume an important role in the national energy policy. The nowadays methodologies, which are used in diagnosis, condition monitoring and dimensioning of these motors, are based on measure of the speed variable. However, the direct measure of this variable compromises the system control and starting circuit of an electric machinery, reducing its robustness and increasing the implementation costs. Simulation results and experimental data are presented to validate the proposed approach. © 2003-2012 IEEE.

A Comparison of Induction Motor Starting Methods Being Powered by a Diesel-Generator Set

Starting induction motors on isolated or weak systems is a highly dynamic process that can cause motor and load damage as well as electrical network fluctuations. Mechanical damage is associated with the high starting current drawn by a ramping induction motor. In order to compensate the load increase, the voltage of the electrical system decreases. Different starting methods can be applied to the electrical system to reduce these and other starting method issues. The purpose of this thesis is to build accurate and usable simulation models that can aid the designer in making the choice of an appropriate motor starting method. The specific case addressed is the situation where a diesel-generator set is used as the electrical supplied source to the induction motor. The most commonly used starting methods equivalent models are simulated and compared to each other. The main contributions of this thesis is that motor dynamic impedance is continuously calculated and fed back to the generator model to simulate the coupling of the electrical system. The comparative analysis given by the simulations has shown reasonably similar characteristics to other comparative studies. The diesel-generator and induction motor simulations have shown good results, and can adequately demonstrate the dynamics for testing and comparing the starting methods. Further work is suggested to refine the equivalent impedance presented in this thesis.

Speed Neuro-fuzzy Estimator Applied To Sensorless Induction Motor Control

This work proposes the development of an Adaptive Neuro-fuzzy Inference System (ANFIS) estimator applied to speed control in a three-phase induction motor sensorless drive. Usually, ANFIS is used to replace the traditional PI controller in induction motor drives. The evaluation of the estimation capability of the ANFIS in a sensorless drive is one of the contributions of this work. The ANFIS speed estimator is validated in a magnetizing flux oriented control scheme, consisting in one more contribution. As an open-loop estimator, it is applied to moderate performance drives and it is not the proposal of this work to solve the low and zero speed estimation problems. Simulations to evaluate the performance of the estimator considering the vector drive system were done from the Matlab/Simulink(R) software. To determine the benefits of the proposed model, a practical system was implemented using a voltage source inverter (VSI) to drive the motor and the vector control including the ANFIS estimator, which is carried out by the Real Time Toolbox from Matlab/Simulink(R) software and a data acquisition card from National Instruments.

PMU measurement based dynamic load modeling using SVC devices in online environment

Online dynamic load modeling has become possible with the availability of Static Voltage Compensator (SVC) and Phasor Measurement Unit (PMU) devices. The power of the load response to the small random bounded voltage fluctuations caused from SVC can be measured by PMU for modelling purposes. The aim of this paper is to illustrate the capability of identifying an aggregated load model from high voltage substation level in the online environment. The induction motor is used as the main test subject since it contributes the majority of the dynamic loads. A test system representing simple electromechanical generator model serving dynamic loads through the transmission network is used to verify the proposed method. Also, dynamic load with multiple induction motors are modeled to achieve a better realistic load representation.

Study of corrugations in motor bearings

Corrugation formation is investigated in bearing components in squirrelcage induction motors. The study, conducted on site, measured shaft voltage and analysed motor bearing vibrations from 48 motors on nine sites. The on-site frequency data was compared with the measured natural frequency of the motors. Detailed profilometric, optical and SEM studies were carried out on the surface of failed bearings to aid discussion on the formation of corrugations in bearings used in squirrelcage induction motors.

A Low-Cost System for Measurement and Spectral Analysis of Motor Acoustic Noise

Workplace noise has become one of the major issues in industry not only because of workers’ health but also due to safety. Electric motors, particularly, inverter fed induction motors emit objectionably high levels of noise. This has led to the emergence of a research area, concerned with measurement and mitigation of the acoustic noise. This paper presents a lowcost option for measurement and spectral analysis of acoustic noise emitted by electric motors. The system consists of an electret microphone, amplifier and filter. It makes use of the windows sound card and associated software for data acquisition and analysis. The measurement system is calibrated using a professional sound level meter. Acoustic noise measurements are made on an induction motor drive using the proposed system as per relevant international standards. These measurements are seen to match closely with those of a professional meter.

Análisis de metodologías para el control de velocidad de motores asíncronos.

[ES]El objetivo de este trabajo es analizar los diferentes métodos de control de velocidad de motores asíncronos ya que es la maquina eléctrica más importante tanto en la industria como en la vida doméstica. Primero se estudian las ventajas que ofrece este tipo de motor frente a los motores de corriente continua, como el precio o el mantenimiento. Después se estudian las metodologías convencionales. Sin embargo, este tipo de métodos no son utilizados actualmente por lo que se analizaran en profundidad los métodos de control actual: control escalar y control vectorial.

一种用于异步电机效率优化的混合搜索方法

针对异步电机效率优化问题,提出了一种混合搜索方法。该方法起始于模糊自适应搜索,然后切换至黄金分割法以获取确定收敛速度。这样的搜索步骤能够降低转矩波动,避免在最优点附近发生振荡。利用一个包含铁损和机械损耗的异步电机模型,对该方法进行了矢量控制下的性能验证。仿真结果验证了该方法的有效性。

异步电机非侵入式效率检测与节能控制

异步电机结构简单、坚固耐用，是主要工业动力设备。异步电机的运行节能问题是工业节能研究的重要内容和热点之一。本文分析了异步电机运行性能，对异步电机的转速和效率检测的非侵入式方法、各种运行方式下的节能控制方法进行了研究，主要贡献有： 对比研究异步电机转速检测的各种方法，采用高分辨率谱估计和混叠采样处理实现了准确的转速检测，给出了转速自动判断方法，为非侵入式效率检测提供了重要的支撑技术。 研究了异步电机的低成本非侵入式效率检测方法，研制了相应的测试装置并进行了相关实验，对检测方法进行精度分析并提出了减小误差的措施。 在非侵入式效率检测的基础上，对于异步电机工频运行、转速开环变频调速和转速闭环转差频率控制变频调速三种运行方式进行了基于效率反馈的节能控制研究。通过专门设计的效率优化模糊控制器实现这三种运行方式下的节能控制，仿真分析表明了所提方法是合理有效的。 针对矢量控制异步电机的效率优化问题，对比分析了模糊搜索和黄金分割法这两种主要效率优化策略的特性，提出了一种混合搜索效率优化方法。这种新方法发挥了前两种寻优策略的互补优势，既保证了收敛的确定性，又降低了对电机输出转矩的影响。仿真分析表明了这种混合搜索方法的可行性。同时，在对输入功率的精确检测条件下，提出了一种全新的效率优化方法，该方法能够在更短时间内实现效率寻优。 探讨了基于无线网络技术的工厂电能管理系统。本文说明了工业无线网络技术的优势，阐述了能够实现系统节能的电能检测与管理技术，如异步电机能效分析模型、异步电机状态监测与预测技术等，分析了基于IEEE802.15.4无线传输协议构建异步电机能效监测系统的可行性。

Impact of Heat Pump Load on Distribution Networks

Heat pumps can provide domestic heating at a cost that is competitive with oil heating in particular. If the electricity supply contains a significant amount of renewable generation, a move from fossil fuel heating to heat pumps can reduce greenhouse gas emissions. The inherent thermal storage of heat pump installations can also provide the electricity supplier with valuable flexibility. The increase in heat pump installations in the UK and Europe in the last few years poses a challenge for low-voltage networks, due to the use of induction motors to drive the pump compressors. The induction motor load tends to depress voltage, especially on starting. The paper includes experimental results, dynamic load modelling, comparison of experimental results and simulation results for various levels of heat pump deployment. The simulations are based on a generic test network designed to capture the main characteristics of UK distribution system practice. The simulations employ DIgSlILENT to facilitate dynamic simulations that focus on starting current, voltage variations, active power, reactive power and switching transients.

Diagnóstico de avarias em motores elétricos

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Mecânica

Aplicação de sistemas multi-classificadores no diagnóstico de falhas em motores de indução trifásicos

Equipment maintenance is the major cost factor in industrial plants, it is very important the development of fault predict techniques. Three-phase induction motors are key electrical equipments used in industrial applications mainly because presents low cost and large robustness, however, it isn t protected from other fault types such as shorted winding and broken bars. Several acquisition ways, processing and signal analysis are applied to improve its diagnosis. More efficient techniques use current sensors and its signature analysis. In this dissertation, starting of these sensors, it is to make signal analysis through Park s vector that provides a good visualization capability. Faults data acquisition is an arduous task; in this way, it is developed a methodology for data base construction. Park s transformer is applied into stationary reference for machine modeling of the machine s differential equations solution. Faults detection needs a detailed analysis of variables and its influences that becomes the diagnosis more complex. The tasks of pattern recognition allow that systems are automatically generated, based in patterns and data concepts, in the majority cases undetectable for specialists, helping decision tasks. Classifiers algorithms with diverse learning paradigms: k-Neighborhood, Neural Networks, Decision Trees and Naïves Bayes are used to patterns recognition of machines faults. Multi-classifier systems are used to improve classification errors. It inspected the algorithms homogeneous: Bagging and Boosting and heterogeneous: Vote, Stacking and Stacking C. Results present the effectiveness of constructed model to faults modeling, such as the possibility of using multi-classifiers algorithm on faults classification

Reconhecimento de padrões de falhas em motores trifásicos utilizando redes neurais

This work presents a diagnosis faults system (rotor, stator, and contamination) of three-phase induction motor through equivalent circuit parameters and using techniques patterns recognition. The technology fault diagnostics in engines are evolving and becoming increasingly important in the field of electrical machinery. The neural networks have the ability to classify non-linear relationships between signals through the patterns identification of signals related. It is carried out induction motor´s simulations through the program Matlab R & Simulink R , and produced some faults from modifications in the equivalent circuit parameters. A system is implemented with multiples classifying neural network two neural networks to receive these results and, after well-trained, to accomplish the identification of fault´s pattern