Putra, Kresna Kartika Surya (2017) Perancangan Kontroler Neural Network PI untuk Sistem Pengaturan Level Dengan Metode Decoupling Pada Plant Coupled Tank. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
2212100066_Undergraduate_Thesis.pdf - Published Version Download (2MB) | Preview |
Abstract
Sistem pengendalian pada industri merupakan faktor yang sangat penting dalam proses produksi. Coupled tank merupakan salah satu sistem yang memiliki peran vital . Sistem nonlinear dari pemodelan coupled tank mempengaruhi kestabilan sistem. Selain itu konfigurasi sistem Multi Input Multi Output membuat variabel yang diatur mengalami kesulitan untuk mengikuti sinyal referensi. Dekopling digunakan untuk mengubah dimana Coupled tank yang bersifat MIMO (Multi Input Multi Output) menjadi SISO (Single Input Single Output) neural network digunakan untuk mencari nilai Kp dan Ki yang optimal berdasarkan hasil simulasi dengan model linier didapatkan nilai Kp 13,0031 dan nilai Ki 0,6013 untuk tangki 1dan untuk H2 didapatkan nilai Kp 13,072 dan Ki sebesar 1,0121, kemudian hasil simulasi dengan model nonlinier didapatkan rata rata error steady state sebesar 0,025% untuk tangki 1 dan untuk tangki 2 sebesar 0,033% , kemudian menghasilkan nilai Kp optimal sebesar 12,983 dan Ki sebesar 0,527 untuk level tangki 1, kemudian untuk level tangki 2 mendapat nilai Kp optimal sebesar 13,071 dan Ki optimal sebesar 1,18
==================================================================================================================
The control system is the important factor in industrial process production. Coupled tank one of the vital subsystem in industry.
Nonlinear systems modeling contained in coupled tanks affect the stability of the system. In addition the system configuration Multi Input Multi Output create a variable that is set a challenge to keep the reference signal. Decoupling is used to set the MIMO configuration and control PI kontroler is used to set the level in the coupled tanks. Neural Network is used to best get the optimal parameter for Kp and Ki, from the simulation we get the parameter of Kp and Ki with the value of Kp=13.0031 and Ki=0,6013 for tank 1 then Kp=13.072 and Ki=1.0121 for tank 2. Simulation result for nonlinear model still has error steady state with value 0.0255% for tank 1 and for tank 2 the value is 0.033%, then the optimal parameter Kp=12.983 and Ki=0.527 for tank 1 then the optimal parameter Kp=13.071 and Ki=1.18 for tank 2
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Uncontrolled Keywords: | neural network pi, coupled tank |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science. EDP Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5102.5 Modulation (Electronics), Demodulation (Electronics) |
| Divisions: | Faculty of Industrial Technology > Electrical Engineering > 20201-(S1) Undergraduate Thesis |
| Depositing User: | KRESNA KARTIKA SURYA PUTRA |
| Date Deposited: | 13 Mar 2017 02:20 |
| Last Modified: | 05 Mar 2019 02:09 |
| URI: | http://repository.its.ac.id/id/eprint/1873 |
Actions (login required)
 |
View Item |