Manual Soft Computing in Industrial Electronics

Free download. Book file PDF easily for everyone and every device. You can download and read online Soft Computing in Industrial Electronics file PDF Book only if you are registered here. And also you can download or read online all Book PDF file that related with Soft Computing in Industrial Electronics book. Happy reading Soft Computing in Industrial Electronics Bookeveryone. Download file Free Book PDF Soft Computing in Industrial Electronics at Complete PDF Library. This Book have some digital formats such us :paperbook, ebook, kindle, epub, fb2 and another formats. Here is The CompletePDF Book Library. It's free to register here to get Book file PDF Soft Computing in Industrial Electronics Pocket Guide.

Then model creates a speed corresponding to the voltage and the estimated torque. For actual working condition, a noise source is added to the model output. By subtracting to the ideal speed, the estimated value of the speed difference is achieved. At the same time, the input and output MFs of the fuzzy structure inside the OTFPID are optimized online with respect to the control error minimization by using the learning mechanism while the PID gains are updated through the robust checking conditions, consequently, improving the control quality.

To improve the control quality, the FGP predictor with online tuning ability of its prediction step size is designed to estimate the motor speed difference in a near future. This estimated speed is finally fed-back to the controller to create the control input and subsequently, performs the close-loop control system.

Soft computing in industrial electronics /

Hence, the proposed method using FPID-based estimator investigates the effectiveness of the purpose estimation technique. Learning mechanism with robust checking conditions was implemented into the OTFPID in order to optimize online its parameters with respect to control error minimization. Meanwhile, the FGP predictor techniques takes part in estimating the system output in near future to optimize the controller parameters in advance and consequently, improve estimation performance.

Juing-Shian Chiou et al. For improving the efficiency and accuracy, PSO reinforcement evolutionary algorithm is employed to adjust the swarm of Q-learning to obtain global optimum solution. By this scheme, reduces the suspension deflection, spring mass acceleration and beating distance between the tire and the ground relative and also improves ride comfort and vehicle stability. Rajani K.

The Official Journal of the World Federation on Soft Computing (WFSC)

Mudi et al. This proposed controller is tested with several high order linear and non-linear dead time processes under both set point change and load disturbance. AZNPIC introduce an online gain updating factor which continuously modifies its proportional and integral gains based only on recent process trend. The performance of the proposed auto-tuner is tested for different nonlinear processes which is described by. ZNPIC provides a very poor performance due to excessively large overshoot and oscillation.

When the process dead-time is increased from 0. In this study third-order linear as well as nonlinear process models are also tested to justify the effectiveness of the proposed scheme. Such a linear system is expressed by the following transfer function.

Applied Soft Computing - Journal - Elsevier

The recurrent nodes in addition to the network increase the network response speed and ensure the network has stable outputs. Network algorithm is working online for obtaining optimal parameters to realize an adaptive system with strong learning ability and good robustness. Muawia A. Magzoub et al. There are two fuzzy controller used as fuzzy frequency controller during accelerate-decelerate stage and fuzzy stator current magnitude controller for steady state stage. After simulation, compared with FOC results faster speed and the large changes can be accommodated in load torque.

The minimization of current losses which contribute to energy efficiency system and efficiency is improved by HFFC. Henceforth, from the exploitation of the two features of field-oriented control, the fuzzy fuzzy controller has been found to be more efficient than scalar controller. Sakuntala Mahapatra et al. Therefore, chose with the use of the Neural Networks and Particle Swarm Optimization for the optimization of this controller in order to control Induction motor speed.

Sharda Patwa [ 14 ] investigated the fuzzy logic controller for controlling induction motor parameters such as starting current, flux, torque, and speed. The results of FLC are also compared the controlling of induction motor same parameters with PI controller. The results showed that FLC has given the better performance than PI controller for controlling the induction motor parameters with improved rise time with less starting current.

Menghal and A. Jaya Laxmi [ 15 ] proposed an adaptive Neuro-fuzzy controller based dynamic performance of induction motor to overcome the problems developed in conventional fuzzy controllers.

A Review on Application of Soft Computing Techniques for Load Shedding in Power Systems

The main problem with conventional FLC is that the parameters associated with the membership functions and rules depend on intuition of the experts. Results show that proposed adaptive neuro-fuzzy controller give better performance like speed-torque characteristics, torque response, speed response, rotor and stator currents compared to conventional and fuzzy controller. Menghal et al.

The most popular supervised learning algorithm i. On comparing neuro controller with FLC model, by adding learning algorithm to the control system will decrease rise time more than expectation and it proves neuro controller has better dynamic performance as compared to FLC and conventional controller. Ahmed J. Fattah and Ikhlas Abdel-Qader [ 17 ] investigated an improved hybrid PID fuzzy controller for performance analysis of speed control induction motor and also compare their performance with conventional PI controller.

They proposed a hybrid controller with vector control to control the speed of induction motor. PowerPoint Slide. Larger image png format Tables index Veiw figure View current table in a new window. With different load conditions, comparison with conventional PI controller, the hybrid controller is increased dynamic performance such as rise time, peak overshoot, settling time and steady state error of induction motor and also to provide good stabilization.

Shamseldin and Adel A. In which, first is conventional controller. The second controller is to use to GA technique to adjust the three cost functions. Finally, third controller hybrid fuzzy PID controller is development. All controllers are tested for speed regulation and speed tracking. Comparing among the controllers, the performance of the three cost function controller is best. Results show that proposed self tuning fuzzy PID controller give better performance compared to other two techniques. This review presents a overall summary on the various implementation techniques of fuzzy systems, neural network, PID-fuzzy system, neuro-fuzzy system, PID controller.

This overview represents the information about Neuro-Fuzzy system and PID Controller focuses on its usability and challenges. This study suggests that the future development of Neuro-Fuzzy PID controllers using different soft computing techniques will improve its flexibility and re-usability of the controller. Introduction 2. Literature Review 3. Conclusion Acknowledgements References. Abstract Aadaptability and self-organization of a system is two key factors, when it comes to how well the system is surviving for the changes to the environment and how these work within the plant.

All Rights Reserved. American Journal of Electrical and Electronic Engineering. Agrawal, L. American Journal of Electrical and Electronic Engineering , 4 2 , Fig ure 1. View all figures. Prev Next. Introduction Conventional proportional-integral-derivative PID controllers are extensively used for industrial automation and process control.

  1. Call for Papers – SOCO ?
  2. Intelligent Robotic Systems for Space Exploration!
  3. Numerical Grid Generation!
  4. For Authors;
  5. Combinatorial Chemistry, Part B;
  6. Fancy Pants!
  7. Applied Soft Computing.

Download as. Veiw figure Figures index. Fig ure 2. Block diagram of Fuzzy logic controller. Fig ure 5.

Soft Computing in Industrial Applications

Comparative result of 2 nd , 3 rd and 5 th order plant. Fig ure 8. Hybrid structure of fuzzy-PID controller. Fig ure Recurrent wavelet neural network PID control system. Fig ure 22 a. Plot of membership function using 2 inputs 3 rules. Comparison of actual and desired output plot.