Review of speed estimation algorithms for three- phase induction motor.

In the field of evolving industrial automation, there is a growing need for refined sensorless speed estimation techniques for induction drives to cater the demands of various applications. In this paper, the sensorless speed estimation algorithms for induction motor drives are investigated and reviewed detailly for real-time industrial usages. The main objective of this paper is to classify sensorless techniques by highlighting the characteristics, merits and drawbacks of each sensorless speed estimation techniques of induction motor drives. Different techniques like Rotor slot harmonics, Signal Injection, and Machine model based system have the benefits of sensorless motor drives involving lower costs, higher reliability, simpler hardware complication, improved noise immunity, and lesser maintenance requirement. As a result of the advancement of current industrial automation, more improved sensorless estimation techniques are required to meet application demand. The various speed estimation techniques are distinguished based on criteria of steady state error, dynamic behavior, low speed operation, parameter sensitivity, noise sensitivity, complexity and computation time. This comparison allows to opt the best sensorless speed estimation technique for induction motor drive to be implemented based on a specific application. The results of comparison highlight the characteristics of each technique.

MPPT control of a solar pumping system based five-phase impedance source inverter fed induction motor.

This paper presents a control method for a system composed of a photovoltaic (PV) array, five-phase impedance source inverter, five-phase induction motor and centrifugal pump. This method is based on controlling the motor speed to control the pump power as the insolation level or temperature change to attain the maximum power extraction from the PV-array. The motor speed is controlled by using artificial neural network (ANN) which is trained to provide the desired inverter frequency and modulation index at any insolation level and temperature to attain the maximum PV operating power. The data of the neural network are based on the operation of the induction motor at constant air gap flux and perturb and observe method for maximum power point tracking. Simulation results are obtained using MATLAB Simulink to verify the proposed control method.

High gain chopper supplied from PV system to fed synchronous reluctance motor drive for pumping water application.

Power generation for renewable energy sources increased rapidly during last few years. Similarly, the high gain dc-dc boost choppers are taking place of conventional power converters used for photovoltaic (PV) appliances. Researchers are developing different methods in order to provide high voltage gain, low ripple, reduced switch stress, low converter costs, and minimized variations of PV operating points. This study proposes a two-stage converter for a freestanding water pumping motor drive power by solar PV system. According to the proposed system, at first, a high gain (HG) cell and a DC-to-DC boost converter are combined to increase the PV voltage to high levels. Later on, the resulting dc voltage feds a three-phase synchronous reluctance motor drive that operates centrifugal pump load. The perturb and observe approach is utilized to get the maximum power out of the solar PV module. Moreover, indirect field-oriented control is implemented to accomplish smooth starting of synchronous reluctance motor. In order to validate the effectiveness of proposed technique, a MATLAB/Simulink environment-based simulation setup along with an experimental prototype is developed. Additionally, various cases are considered based on different operating conditions and irradiance levels to collect and analyse the results.

Contribution of neural networks in the diagnosis and treatment of cardiac arrhythmia.

Arrhythmia is a dangerous disease in which the heart rhythm varies and it may be very fast or very slow. Rapid heartbeats can lead to shortness of breath, chest pain, and sudden weakness, whereas slow heartbeats can lead to dizziness, problems with concentration, and constant stress. Finding an effective treatment for arrhythmia has become a very important endeavor for researchers and clinicians. In this article, we review the latest methodologies used in arrhythmia diagnosis and treatment. They include the application of five different types of artificial neural networks trained by machine learning and powered by artificial intelligence: convolutional, recurrent, feedforward, radial basis function, and modular neural network. Some of these methodologies are merged to enhance accuracy and efficacy. This review suggests that more research needs to be carried out in merging neural network types for their application in electrocardiogram (ECG).