Abstract The DC motor drives one of the high performance drives that still in competition in industrial application, because of its high performance, robustness, and its lower cost compared with AC motor drives.Due to its majority applications, the separately excited DC motor driver is studied. In order to improve, three independent controller design using classical proportional - integral – derivative, linear quadratic regulator and artificial neural network are considered.The Performance of these controllers has been verified through simulation based on MATLAB/SIMULINK software tools. According to the obtained simulation results, it is found that, an artificial neural network can achieve a better transient and steady state response in comparing to the other two design method. Consequently, the superiority of ANN controller over conventional proportional - integral – derivative is demonstrated this shows the superiority of artificial neural network controller over conventional and linear quadratic regulator controllers.
.زينب إبراهيم علي (2014)

Abstract Most of the controllers used in industries are of PID type, this is because they have simple structure and their usage is well known among industrial specialists. The tuning of controllers is the crucial issue in the overall control loop design in order to obtain a satisfactory performance response. Over the past decades many tuning techniques were developed to adjust the controller parameters. Most of these techniques have the disadvantages of giving a combination of heavy oscillatory response, large overshoot, and long settling and rise time. This work presents a fuzzy logic-PID scheme, the basic concept behind this scheme is to combine the conventional PID controller with the use of fuzzy logic concept. The PID controller regulates the process, while the fuzzy logic part adjusts the proportional gain of the controller. This scheme will be used to overcome the previous disadvantages and to improve the performance of the conventional controller. The effectiveness of fuzzy logic-PID scheme has been analyzed through computer simulation using MATLAB. The results have been compared with those of Ziegler-Nichols, Chien-Hrones-Reswick, Cohen-Coon, Optimum PID controller and a PID with constant and variable weighting factor. This comparison has shown a considerable improvement in the performance of the transient response for different simulated processes
علي عبدالرحمن بن عاشور (2008)

Technology is all around us and it’s changing rapidly, expanding Internet access has had huge impacts on everyday lives as people do everything on their phones and computers. The widespread growth in the use of digital computers, have an increasing need to be able to communicate with machines in a simpler manner. One of the main tasks that can simplify communication with machines is speech recognition. In this work, we introduce the Arabic speech commands database that contains six Arabic control order words and Arabic spoken digits. The created database is used to analyze and compare the recognition accuracy and performance of three recognition techniques which are, Wavelet Time Scattering feature extraction with Support Vector Machine (SVM) classifier, Wavelet Time Scattering feature extraction with Long Short-Term Memory (LSTM) classifier, and Mel-Frequency Cepstrum Coefficients (MFCC) feature extraction with K-Nearest Neighbor (KNN) classifier. Finally, the experimental results show that the most accurate prediction of the database commands was 98.1250% given by Wavelet Time Scattering feature extraction and LSTM classifier and the fastest training time for the database was 144 minutes given by MFCC and KNN classifier. arabic 5 English 42
Osama A. Alkishriwo, Lina Tarek Benamer(12-2020)