I Putu Eka Suartana, . (2023) ESTIMASI KECEPATAN REAKSI ELEKTROLISIS BERDASARKAN ENERGI LISTRIK DARI SUMBER ENERGI TERBARUKAN DENGAN ESTIMATOR EXTREME LEARNING MACHINE. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
Abstrak.pdf Download (62kB) |
|
Text
Awal.pdf Download (646kB) |
|
Text
BAB 1.pdf Download (184kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (918kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (386kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (146kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (134kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (223kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (146kB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (831kB) |
Abstract
Indonesia has enormous potential to develop new and renewable energy (EBT) because it is rich in sustainable natural resources such as water. Water can be used as a driving force for generators from hydropower plants and can also produce hydrogen to be used as a source of heat and electricity. Hydrogen is a source that can replace materials containing hydrocarbons. Rapid technological developments in this era allow machine learning technology to be utilized to estimate the speed of hydrogen production through the water electrolysis process, while also being able to utilize IoT technology to retrieve the required data. The algorithm used to build machine learning models is Extreme Learning Machine because data processing is relatively fast and the results obtained are also accurate. The data needed to build an estimation model, such as light intensity, temperature, humidity, voltage, current, power, and production volume of hydrogen are obtained using telemetry techniques from installed sensors in order to obtain data in real time and accurately. The model development process uses a data division of 30% for test data, 70% for training data and uses a hidden neuron parameter of 40, initializes random weights between -1 to 1, and uses the binary sigmoid activation function so that the RMSE value is 23.29. MAE is 17,061, and R2 is 0,995.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1910511070] [Pembimbing: Didit Widiyanto] [Penguji 1: Yuni Widiastiwi] [Penguji 2: Ati Zaidiah] |
| Uncontrolled Keywords: | Estimation, Extreme Learning Machine, IoT, Hydrogen |
| Subjects: | T Technology > T Technology (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | I Putu Eka Suartana |
| Date Deposited: | 25 Jul 2023 03:53 |
| Last Modified: | 10 Aug 2023 04:25 |
| URI: | http://repository.upnvj.ac.id/id/eprint/25594 |
Actions (login required)
 |
View Item |