Artificial Neural Network Based Rotor Reactance Control

Abstract: Problem: In recent research, rotor reactance control with an external capacitor in the rotor circuit is a way to improve the performance of a wound rotor induction motor (WRIM). The rotor capacitive reactance is adjusted such that the efficiency of the WRIM is maximum for any desired load torque. Dynamic capacitors can be used to control the external capacitance of the rotor if the duty cycle is changed to simulate the capacitance value. In this research, we proposed a new technique for tracking the maximum efficiency point of WRIM's entire work area using artificial neural network (ANN).

Computer-based neural networks are inspired by biology. We call this an artificial neural network or ANN for short. Normally when we say "neural network", what actually means is ANN. Since the function of ANN is exactly the same as the function of biological function, please do not mistakenly think ANN as a kind of simulated brain. No. For example, in a biological neural network (BNN), each neuron is not connected to all other neurons, and in ANN each neuron in the layer is usually connected to each neuron in the next layer . .

If you suck math to learn artificial intelligence - P5 - Deep learning and convolution neural network in simple English!

Neural networks or artificial neural networks (ANN) are very similar to the brain. A "neuron" in a neural network is a simple mathematical function that obtains and organizes information according to the architecture of the data set being provided. The neural network is the brains of your computer, and you can learn faster as you enter more data. You can provide data as a series of algorithms that will give you the best results. Since neural networks can adapt to changing inputs, the network can produce possible results without redesigning output standards.

In this course, you will understand the intuition behind the artificial neural network, apply artificial neural networks to practice, understand the intuition behind the convolution neural network, actually apply the convolution neural network, I understand the background. Intuition, actually the application of recurrent neural network understands the intuition behind the self-organizing map, actually applies self-organizing mapping, understands the intuition behind the Boltzmann machine, and actually the Boltzmann machine Apply and understand the intuition behind the auto encoder

The report defines AI as a deep learning technology based on artificial neural network such as feed forward neural network, recurrent neural network (RNN), convolution neural network (CNN). These algorithms have evolved from the just-started research course to the mature technology used in the real world. Advanced artificial intelligence technologies such as generational confrontation network (GAN) and reinforcement learning are beyond the scope of this report. Of the 19 industries we have surveyed, the potential annual value of AI is between $ 3.5 trillion and $ 5.8 trillion. The greatest impact on the retail industry is expected to be between 0.4 and 0.8 trillion US dollars, followed by tourism (0.3-0.5 trillion dollars), transportation and logistics (0.4-0.5 trillion dollars). Marketing and sales, supply chain management and manufacturing are areas that help AI increase annual sales of enterprises by 1 trillion to 2.6 trillion dollars.