Print ISSN: 1681-6900

Online ISSN: 2412-0758

Keywords : fuzzy

Prediction Fatigue Life of Aluminum Alloy 7075 T73 Using Neural Networks and Neuro-Fuzzy Models

Mustafa S. Abdullatef; Nazhat . AlRazzaq; Mustafa M. Hasan

Engineering and Technology Journal, 2016, Volume 34, Issue 2, Pages 272-283

In present paper the fatigue life of aluminum alloy 7075 T73 under constant amplitude loading is predicted using ANN and ANFIS models. Many neural networks models are used for this purpose and also different neuro-fuzzy models are built for predict fatigue life.Theclassical power law formula ismost common used to find fatigue behaviors of materials. In present study, two techniques are used to find coefficients of the formula linear and nonlinear regression. Forcomparison the fatigue life curves of soft computing methods are plotted together with two conventionalmethods. The neural network and neuro-fuzzy models give good results compared with two conventional methods. Also it is shown thatneural network model which is trained using Levenberg-Marquardt algorithm is best neural network modelscompared with other NNS models.Also, it is foundANFIS models with input trapezoidal membership function is best performance from other membership function types to predict fatigue life. It can be stated that neuro-fuzzy models are better models than neural network and conventional methods to predict fatigue life of the maintained alloy.

Study and Comparison The Performance of Sensorless Control of PMSM Drive System

Majid K. Al-Khatat; Ghphran Taha Ahmed Abd

Engineering and Technology Journal, 2014, Volume 32, Issue 10, Pages 2528-2547

Field oriented control space vector pulse width modulation (FOC- SVPWM) is one of the effective and modern methods for speed control of Permanent magnet synchronous motor (PMSM). A mathematical model and theoretical analysis of (FOC-SVPWM) driven a PMSM are presented .In this work, a control methods for PMSM using Model reference adaptive system (MRAS) are utilized to compare the performance behavior under conventional PI, Fuzzy PI, and Particle swarm optimization (PSO) control methods.
Extensive simulation results are presented using MATLAB/SIMULINK program which including (SVPWM generation, inverter, PMSM, the reference frame transformation and different PI controllers) as well as the estimation method using MRAS.
This work presents a comparative study to investigate the performance of PMSM based on MRAS when different load conditions are applied to PMSM and under three different controllers: the first controller is the Proportional-Integral (PI) based on classical trial and error method, the second controller is PI controller based on PSO technique for optimal gains tuning and thus improve the performance of the system. The obtained results show that an improvement in motor performance when using PI-PSO compared to classical PI controller. The third controller is Fuzzy-PI with scaling factor (gains) tuned by PSO technique. This method can improve the performance of the system compared with PI-PSO in terms of reducing steady state error, rising time, overshoot and smoother response to make this controller more robust to variation in load other than the rest motor controllers.

Computer Simulation Using Fuzzy LogicModel to Predict Hot Corrosion Kinetics in Molten Salt of Steel-T21 Coated by Simultaneous Yttrium-Doped Aluminizing-Siliconizing Process

Abbas Khammas Hussein

Engineering and Technology Journal, 2013, Volume 31, Issue 11, Pages 2183-2197

The present paper describes fuzzy logic simulation of an experimental study on the behavior of hot corrosion in molten salt (Na2SO4) of steel-T21 coated by simultaneous yttrium-doped aluminizing-siliconizingprocess . Diffusion coating was carried out at 1050oC for 6 hr under Aratmosphere . The weight change measurements made on the coated steel during the cyclic tests are used to determine kinetics of hot corrosion at temperature range (800-1000oC) for 100 hr at 5 hrcycle .X-ray diffraction and optical microscope are used to characterize the oxide phases where the oxide phases that formed on coated system are SiO2 and Al2O3 .The parabolic rate constants (Kp) calculated show that the corrosion rate is minimum at 800oC compared to other temperatures. The experimental results, the fuzzy logic model, and the statistical results showed good correlations.The fuzzy logicmodels are developed using Matlab toolbox functions.

Design of Type-2 Fuzzy Logic Controller for a Simple Furnace System

Saba T. Salim

Engineering and Technology Journal, 2012, Volume 30, Issue 8, Pages 1306-1317

Model uncertainty and robustness have been a central theme in the field of automatic control. Many control techniques are used to reduce the effects of uncertainty which may appear in different forms as disturbances, dynamic delays or as other imperfections in the models used.In this paper a comparison between conventional type -1 fuzzy logic controller and type -2 fuzzy logic controller has done in simulation conditions of a simple temperature control of a furnace system to show the great effect of the new generation of fuzzy logic
controllers to improve the performance of a system with high level of uncertainty.