Rosyida, Ulfa (2020) PERANCANGAN SISTEM PENGENDALIAN PH PADA HIDROPONIK NFT MENGGUNAKAN PID-ANN SELF-TUNING. Other thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
02311640000007_Undergraduate_Thesis.pdf Download (2MB) | Preview |
Abstract
Keunggulan sistem hidroponik NFT (nutrient film tehnique) pada tanaman pakcoy dapat mengatasi permintaan konsumen yang meningkat secara signifikan di pasar internasional. Hal ini membutuhkan kontrol yang lebih baik terhadap faktor iklim dan hama terutama variabel pH (Libia I. Trejo-Téllez, Fernando C. Gómez-Merino, 2012). Tugas akhir ini bertujuan untuk merancang sistem sefl-tuning pengendalian pH menggunakan PID-ANN dan merancang simulasi komputasi dinamika fluida pada aliran plant hidroponik. Self-tuning menggunakan algoritma Levenberg-marquardt karena unggul dalam kekokohan dan karakteritik konvergensinya, sehingga menjadikannya metode standar untuk meminimalisir nilai eror. Hasil respon menunjukkan PID-ANN lebih unggul ditinjau dari error steady state yaitu 0,007% dibanding kontroler PID 1,791%. Nilai ITAE sebagai analisis kuantitatif menunjukkan PID-ANN lebih unggul dengan nilai 188,109 dibanding PID yaitu 217,46. Hasil simulasi CFD menunjukkan input flow yang baik yaitu 0,5 liter/menit ditinjau dari nilai maximum skewness yaitu 0,8 dan distribusi aliran nutrisi pada contour yang dihasilkan.
=========================================================
Advantages of NFT (nutrient film technique) hydroponics system on pakcoy could overcome consumer demand that increase significantly at global market. This condition needed better controller on climate and pest, especially pH (Libia I. Trejo-Téllez, Fernando C. Gómez-Merino, 2012). This final project is designing self-tuning controller system on pH using PID-ANN and designing computational fluid dynamics on streamline of hydroponics plant. Self-tuning uses levenberg-marquardt algorithm because of its robustness and convergence so that become standard method to minimalize error. System response of PID-ANN is the best reviewed by error steady state 0.007% than PID controller 1.791%. The value of ITAE shows that PID-ANN is the best 188,109 than PID controller 217,46. The result of CFD shows that the best flow as input is 0.5 litre/minute reviewed by maximum value of skewness, that’s 0.8 and the distribution of nutrition at the final contour.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Kata Kunci: ANN, NFT, self-tuning, Keywords: ANN, NFT, self-tuning |
| Subjects: | Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) T Technology > T Technology (General) > T57.62 Simulation T Technology > TA Engineering (General). Civil engineering (General) > TA357 Computational fluid dynamics. Fluid Mechanics |
| Divisions: | Faculty of Industrial Technology > Physics Engineering > 30201-(S1) Undergraduate Thesis |
| Depositing User: | Ulfa Rosyida |
| Date Deposited: | 25 Aug 2020 02:49 |
| Last Modified: | 12 Jun 2023 15:30 |
| URI: | http://repository.its.ac.id/id/eprint/81024 |
Actions (login required)
 |
View Item |