Nugraha, Andhika Adi (2026) Rancang Bangun Sistem Charging Baterai Berbasis Hybrid Double PV-Wind Energi Menggunakan Kontrol ANFIS Tipe 2 untuk Suplai Energi pada Smart Farming System. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5009221028-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5009221028-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (4MB) | Request a copy |
Abstract
Pada penelitian ini dilakukan perancangan sistem charging baterai dengan kontrol cerdas Adaptive Neuro Fuzzy Interference System Tipe 2 (ANFIS T2) yang terhubung dengan baterai bersumber hybrid photovoltaic dan wind turbine untuk suplai kebutuhan smart farming. Panel surya yang digunakan berjenis monocrystalline 315 Wp sebanyak 2 buah yang dirangkai secara paralel. Jenis konverter yang digunakan pada perancangan solar charging system adalah buck converter dengan tegangan input sebesar 29 volt - 36 volt dan tegangan setpoint charging baterai sebesar 14,25 volt. Kontrol yang digunakan adalah ANFIS tipe 2 yang merupakan gabungan antara Fuzzy Logic Tipe 2 (FLC T2) dengan Artificial Neural Network (ANN) untuk training data. Parameter perancangan solar charging controller berupa buck converter memiliki nilai komponen induktor sebesar 330 uH, kapasitor sebesar 940 uF, dan resistor sebesar 100 ohm, dengan hasil error karakterisasi hardware solar charging controller berbanding dengan perhitungan sebesar 1,005%. Parameter ANFIS Tipe 2 diinisialisasikan dengan 5 membership function bentuk kombinasi triangular dan trapezoidal yang kemudian di training dengan data, dimana data yang digunakan untuk training ANFIS tipe 2 sebanyak 660 data error tegangan, delta error tegangan serta data duty cycle PWM. ANFIS tipe 2 menghasilkan nilai error steady state, maximum overshoot, dan settling time yang lebih baik dibanding fuzzy tipe 2 biasa dengan nilai settling time sebesar 0,14 s dan nilai error steady state sebesar 0,15%. Hasil performansi hardware Solar Charging Controller berbasis buck converter dengan menggunakan kontrol ANFIS tipe 2 menghasilkan nilai error sebesar 1,38%. Nilai ini menunjukkan bahwa sistem dapat mengikuti nilai setpoint yang telah diberikan dengan baik dan di bawah target 4%.
===========================================================================================================================
In this study, a battery charging system was designed with an intelligent control Adaptive Neuro Fuzzy Interference System Type 2 (ANFIS T2) connected to a battery sourced from hybrid double photovoltaic and wind turbine to supply smart farming needs. The photovoltaic used is a monocrystalline 315 Wp type, 2 pieces connected in parallel. The type of converter used in the solar charging system design is a buck converter with an input voltage of 29 volts - 36 volts and a battery charging setpoint voltage of 14,25 volts. The control used is ANFIS type 2 which is a combination of Fuzzy Logic Type 2 (FLC T2) with Artificial Neural Network (ANN) for training data. The design parameters of the solar charging controller in the form of a buck converter have an inductor component value of 330 uH, a capacitor of 940 uF, and a resistor of 100 ohms, with the results of the solar charging controller hardware characterization error compared to the calculation of 1.005%. The ANFIS Type 2 parameters are initialized as fuzzy type 2 with 5 membership functions in the form of a combination of triangular and trapezoidal which are then trained with data, where the data used for training ANFIS type 2 are 660 voltage error data and voltage delta error data as well as PWM duty cycle data. ANFIS type 2 produces better steady state error, maximum overshoot, and settling time values than ordinary fuzzy type 2 with a settling time value of 0.14 s and a steady state error value of 0.15%. The results of the Solar Charging Controller hardware performance using ANFIS type 2 control produce an error value of 1.38%. This value indicates that the system can follow the setpoint value that has been given well and below the target of 4%.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Buck Converter, Adaptive Neuro Fuzzy Interference System Type 2, Solar Charging System, Sistem Pengisian Baterai, Battery Charging System |
| Subjects: | T Technology > TJ Mechanical engineering and machinery > TJ217 Adaptive control systems |
| Divisions: | Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis |
| Depositing User: | Andhika Adi Nugraha |
| Date Deposited: | 03 Aug 2026 07:14 |
| Last Modified: | 03 Aug 2026 07:14 |
| URI: | http://repository.its.ac.id/id/eprint/142217 |
Actions (login required)
 |
View Item |