Recurrent Neural Network for Induction Motor Speed Estimation in Industry Applications

Abstract

Many electronic drivers for the induction motor control are based on sensorless technologies. The proposal of this work is to present an alternative approach of speed estimation, from transient to steady state, using artificial neural networks. The inputs of the network are the RMS voltage, current and speed estimated of the induction motor feedback to the input with a delay of n samples. Simulation results are also presented to validate the proposed approach.

Study of Cable Manufacturing Industry with Special Reference to Ravicab Cables Private Limited at Bidadi, Ramanagara District, Karnataka, India

“…Load variation refers to load which is applied on the three phase induction motor shaft. This load on the shaft varies when diameter of the cable varies [6], [8]. Therefore based on this study, it is found that it is better to replace this Pot operated PID based speed controller by placing fuzzy controller in the outset.…”

“…Three phase induction motor plays a vital role for controlling the various operations in the cable manufacturing industry. Mostly this induction motors are operated under imbalance voltages [1].Moreover the use of energy efficient motors in a plant is low [3], [11].Thus an overview of the efficiencies of present-day induction motors are stated [4], [15].Standard applies to squirrel cage induction motors for various industrial applications are discussed [2], [5], [6].Besides study of different factors earlier to make the selection is needed [7].Alternative approach of speed estimation from transient to steady state is required [8], [14].At the same time sensorless induction motor control for industry applications is need to be emphasized [9], [10].Need of vector controlled induction motor drive is emerged [12], [13].Thus this study deals about the overall operation of the cable industry in the beginning. Then application of various horse power three phase induction motors used in this industry are discussed along with its speed controllers.…”

Recurrent Neural Networks Based Impedance Measurement Technique for Power Electronic Systems

“…Past research has demonstrated the ability of the RNN to learn system dynamics and provide efficient prediction, and it has found application in many areas such as wind speed and power forecasting [12], design of a power system stabilizers [13], induction motor speed estimation [14], and prediction of elephant migration [15].…”

Estimador fuzzy de velocidade para motores de indução trifásicos usando abordagem sensorless

“…O uso da tecnologia sensorless é uma tendência crescente no controle do MIT. Os métodos de controle convencionais, como medida direta de torque e de velocidade da máquina, têm várias desvantagens, além do custo envolvido (GOEDTEL, 2006). Além disso, é uma forma de captura de dados não invasiva, vantagem "sine qua non" quando isto se faz necessário em equipamentos que usam o MIT e são lacrados pelos seus fabricantes, sendo que a violação do mesmo custa em perda de garantia (LU et al, 2006).…”

“…Métodos convencionais de estimação de velocidade (GOEDTEL, 2006) ii) necessidade de resolução de sistemas de equações diferenciais;…”