Figure 9 - uploaded by Mustefa Jibril
Content may be subject to copyright.
Source publication
Recently, active suspension system will become important to the vehicle industries because of its advantages in improving road managing and ride comfort. This paper offers the development of mathematical modelling and design of a neural network control approach. The paper will begin with a mathematical model designing primarily based at the paramet...
Context in source publication
Context 1
... Simulink model for a bump input road disturbance including the nonlinear active suspension system with NARMA-L2, model reference and predictive controllers is shown in Figure 7 below. The body travel, body acceleration and suspension deflection simulation output is shown in Figure 8, Figure 9 and Figure 10respectively. ...
Similar publications
National Undergraduate Engineering Training Integration Ability Competition is essential in Chinese engineering colleges. Among these items, the carbon-free car competition is popular among college students because of its flexible track, challenging design tasks, and fair judging criteria. In this study, to design a reasonable carbon-free car struc...
Citations
ABSTRAK
Pengaturan kecepatan merupakan salah satu permasalahan yang terjadi pada motor induksi. Motor induksi merupakan motor yang paling umum digunakan didunia industri, bisnis transportasi dan lain-lain. Keunggulan motor induksi ialah memiliki rancangan yang sederhana dan kuat, harganya murah, efisiensi tinggi, power factor cukup baik, dan perawatannya lebih mudah. Pada penelitian ini metode pengaturan kecepatan yang digunakan adalah metode Direct Torque Control (DTC) dimana DTC mampu mengatur fluks dan torsi secara langsung serta dapat dilakukan tanpa menggunakan sensor kecepatan. Adapun kontrol yang digunakan yaitu Jaringan Saraf Tiruan (JST) menggunakan Model Reference Control (MRC). Respon plant mampu beradaptasi terhadap nilai dari kecepatan referensi yang diberikan. Hasil pengujian menunjukkan bahwa kontrol JST mampu mengendalikan motor induksi dengan respon waktu yang cukup baik, hal ini dapat dilihat saat diberi kecepatan referensi sebesar 150 rad/s didapatkan nilai time constan sebesar 0,8693 s, rise time sebesar 1,2917 s, settling time sebesar 1,5536 s, time delay sebesar 0,622 s serta error steady state sebesar 0,9%.
ABSTRACT
Speed regulation was one of the problems that occurred in induction motors. induction motors were the most commonly used motors in industry world, transportation business and others. The advantages of an induction motor were it had a simple and robust design, low cost, high effeciency, good power factor, and easier maintenance. In this study, the speed regulation method used was the Direct Torque Control (DTC) method where DTC was able to regulate flux and torque directly and it can be done without using a speed sensor. The control used was Artificial Neural Networks (ANN) using Model Reference Control (MRC). The plant response was able to adapt to the value of reference speed given. The test results showed that the ANN control was able to control the induction motor with a good response time. It can be seen when it was given a reference speed of 150 rad/s, the time constant value of 0.8693 s, rise time of 1.2917 s, settling time of 1.5536 s, delay time of 0.622 s and error steady state of 0.9%.
In this paper a NARMA L2, model reference and neural network predictive controller is utilized in order to control the output flow rate of the steam in furnace by controlling the steam flow valve. The steam flow control system is basically a feedback control system which is mostly used in cement production industries. The design of the system with the proposed controllers is done with Matlab/Simulink toolbox. The system is designed for the actual steam flow output to track the desired steam that is given to the system as input for two desired steam input signals (step and sine wave). In order to analyze the performance of the system, comparison of the proposed controllers is done by simulating the system for the two reference signals for the system with and without sensor noise disturbance. Finally the comparison results prove the effectiveness of the presented process control system with model reference controller.
In this paper a NARMA L2, model reference and neural network predictive controller is utilized in order to control the output flow rate of the steam in furnace by controlling the steam flow valve. The steam flow control system is basically a feedback control system which is mostly used in cement production industries. The design of the system with the proposed controllers is done with Matlab/Simulink toolbox. The system is designed for the actual steam flow output to track the desired steam that is given to the system as input for two desired steam input signals (step and sine wave). In order to analyze the performance of the system, comparison of the proposed controllers is done by simulating the system for the two reference signals for the system with and without sensor noise disturbance. Finally the comparison results prove the effectiveness of the presented process control system with model reference controller. [Mustefa Jibril, Messay Tadese, Eliyas Alemayehu Tadese. Design and Control of Steam Flow in Cement Production Process using Neural Network Based Controllers. Researcher 2020;12(5):76-84]. ISSN 1553-9865 (print); ISSN 2163-8950 (online). http://www.sciencepub.net/researcher. 9.
