Classical and Intelligence Speed Control Techniques for Separately Excited DC Motor (Published)
|Most industrial process that uses DC Motor requires that DC Motor operates at a desired speed depending on the load and this speed should be sustained during the operational process however, a significant deviation from the desired speed trajectory was observed on the speed characteristic of DC Motor when acted upon by a load. This paper is aim at investigating the best controller for controlling the speed of a Separately Excited DC Motor in which four different controllers were deployed; the classical Proportional Integral (PI) Controller, Fuzzy Logic Controller (FLC), Artificial Neural Network (ANN) Based Controller and the Adaptive Neuro Fuzzy Inference System (ANFIS) Based Controller. The PI controller was designed by tuning its parameters in MATLAB Simulink in which the proportional and the integral gains were obtained for the best performance as 100.83 and 1750.45 respectively whereas the ANN and the ANFIS controllers were trained to mimic the desired plant input and output relationship. The FLC was designed to have single input which is the error signal and single output which is the speed using five membership function which give rise to five fuzzy rules based on Mamdani principle. A transient analysis was carried out on individual controllers using a speed reference of 1600 rpm to 2200 rpm in steps size of 200 rpm and it was observed that the ANFIS controller demonstrated a higher level of performance in tracking the input reference with an average percentage overshoot of 18.25%, a settling time of 1.446 seconds and a steady state error of 0.1%.|
Keywords: ANFIS, ANN, DC motor, Fuzzy Logic Controller, NARMAL-L2, PI controller, Speed
Analysis on Deep Learning Performance with Low Complexity (Published)
In this article, presenting deep learning to the LTE-A uplink channel estimation system. This work involved creating two SC-FDMA databases, one for training and one for testing, based on three different channel propagation models. The first part of this work consists in applying artificial neural networks to estimate the channel of the SC-FDMA link. Neural network training is an iterative process consisting of adapting the values (weights and biases) of its parameters. After training, the neural network is tested and implemented in the recipient. The second part of this work addresses the same experiment, but uses deep learning, not traditional neural networks. The simulation results show that deep learning has improved significantly compared to traditional methods for bit error rate and processing speed. The third part of this work is devoted to complexity research. Deep learning has been shown to provide better performance than less complex MMSE estimators.
Keywords: ANN, Artificial Intelligence, LTE-A, SC-FDMA, and portable, channel estimation, communications systems, deep learning, mobile
Application of Expert System for Diagnosing Medical Conditions: A Methodological Review (Published)
Naturally, human diseases should be treated on time; otherwise the patients might die if there is delay in attending to such patient or scarcity of medical practitioners’ or experts. Several attempts have been made through studies to design and built software based medical expert systems for probing and prognosis of several medical conditions using artificial and non-artificial based approaches for patients and medical facilities. This paper represents a comprehensive methodological review of existing medical expert systems used for diagnosis of various diseases based on the increasing demand of expert systems to support the human experts. The study provides a concise evaluation of the various techniques used such as rule-based, fuzzy, artificial neural networks and intelligent hybrid models. The rule-based techniques is not too efficient based on its inability to learn and require powerful search strategies for its knowledge-base; while the fuzzy or ANN models are less efficient when compared to the hybrid models that can give a more accurate results.
Keywords: AI, ANN, Expert System, Fuzzy Logic, Intelligent hybrid model, Rule-based
PREDICTION OF WATER QUALITY OF EUPHRATES RIVER BY USING ARTIFICIAL NEURAL NETWORK MODEL (SPATIAL AND TEMPORAL STUDY) (Published)
Euphrates river is one of the most important rivers in Iraq. The monitoring and assessment of the water quality of this river spatially and temporally are a challenging problem. In this study, Artificial Neural Network model (ANN) model was used for prediction and forecasting the monthly Total Dissolved Solid (TDS) parameter in water. In the ANN model calibration, a computers program of multiple regressions (MLR) is used to obtain a set of coefficients for a linear model .Six sampling stations located along the Euphrates River were chosen. The period of study extended during 1999 and 2013.The input parameters of the ANN model were the flow rates of Euphrates River, the year, the month and the distance of the sampling stations from the upstream of the river. The results indicate that the discharge and distance had the most significant effect on the predicted TDS with a relative importance of (75 %) and (61%) respectively, followed by year and month with a relative importance of (33%) and (4%) respectively. The output was TDS of the water. The forecasting ability of these models is accessed on the basis of correlation coefficient, MAPE and RMSE. Using the connection weights and the threshold levels which obtained from ANN model, the equation of TDS concentration in p.p.m. for Euphrates river can accurately predict the TDS with a correlation coefficient, RMSE and MAPE were 0.928, 319.5 and 21.26% respectively. It is important in water quality management and finding the missing data. The concentration gradient of TDS of Euphrates river reaches between A-Qaim-Fallujah, Fallujah-Hindiyah, Hindiyah-Kufa and Kufa-Nassriyah were 0.0, 0.45, 3.0 and 10.0 p.p.m/Km. Comparison between final result of ANN and Multiple Regression Analysis showed the result in ANN models (RMSE and MAPE) values were less than them in multiple regression model which show higher accuracy of ANN model. So, ANN could explain the variability of the TDS of water in Euphrates river with more efficiency and outperform Statistical technique in forecasting. The advantages of using ANN model are to provide a new alternative to MLR and some other conventional statistical techniques which are often limited by strict assumptions of normality, linearity, variable independence, one pass approximation and dimensionality
Keywords: ANN, Distance, Euphrates River, MLR, Time and Discharge