RAFLI, MUHAMMAD (2026) RANCANG BANGUN SISTEM KONTROL BERBASIS IOT PADA HIDROPONIK NFT UNTUK TANAMAN SELADA MENGGUNAKAN LOGIKA FUZZY MAMDANI TIPE-2. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
Cover.pdf Download (918kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
Bab 1.pdf Restricted to Registered users only Download (37kB) |
|
|
Text (BAB II)
Bab 2.pdf Restricted to Registered users only Download (547kB) |
|
|
Text (BAB III)
Bab 3.pdf Restricted to Registered users only Download (844kB) |
|
|
Text (BAB IV)
Bab 4.pdf Restricted to Registered users only Download (946kB) |
|
|
Text (BAB V)
Bab 5.pdf Restricted to Registered users only Download (29kB) |
|
|
Text (DAFTAR PUSTAKA)
Daftar Pustaka.pdf Restricted to Registered users only Download (157kB) |
|
|
Text (LAMPIRAN)
Lampiran.pdf Restricted to Registered users only Download (773kB) |
Abstract
Limited agricultural land and the need for precise nutrient management have encouraged hydroponic systems with automated monitoring and correction. This study develops an Internet of Things (IoT)-based Nutrient Film Technique (NFT) control system for lettuce using ESP32 as the processing unit. Its integrative novelty lies in applying interval type-2 Mamdani fuzzy logic with pH, Total Dissolved Solids (TDS), and solution temperature as inputs to generate four pump activation-duration outputs: AB Mix Nutrient A, AB Mix Nutrient B, pH Up, and pH Down. pH and TDS are controlled, while temperature serves as a supporting input. The fuzzy implementation on ESP32 was numerically validated against MATLAB; Node-RED was used for monitoring and Firebase Realtime Database for storage. Evaluation included sensor testing, actuator response, numerical validation of fuzzy outputs, a 60-minute functional stability test, data update intervals, and plant growth observations. Validation covered 27 input-condition combinations with four outputs each, producing 108 output data points. Sixteen plants were observed: eight with fuzzy control and eight without. The results showed pH and TDS sensor accuracies of 97.16% and 99.76%, while the DS18B20 achieved 98.62% agreement with the reference instrument. All 108 fuzzy outputs showed 100% numerical agreement between ESP32 and MATLAB with an average difference of 0 seconds. During functional stability testing, pH changed from 7.86 to 6.21 against a 6.2 reference, while TDS increased from 176.73 ppm to 755.73 ppm against a 750 ppm reference. Data were recorded at an average update interval of 2 seconds. The fuzzy-control group had an average plant height of 5.875 cm and leaf width of 2.7625 cm, compared with 2.000 cm and 1.5375 cm without fuzzy control. The system performed pH and TDS correction as designed, maintained fuzzy implementation consistency on ESP32, and descriptively showed greater plant height and leaf width under fuzzy control without implying causality. Keywords: NFT Hydroponics, Internet of Things, Type-2 Mamdani Fuzzy Logic, pH and TDS Control, Lettuce Cultivation Keterbatasan lahan pertanian dan kebutuhan pengelolaan nutrisi yang presisi mendorong pengembangan hidroponik dengan pemantauan dan koreksi otomatis. Penelitian ini mengembangkan sistem kontrol Nutrient Film Technique (NFT) berbasis Internet of Things (IoT) untuk tanaman selada dengan ESP32 sebagai pusat pemrosesan. Kebaruan integratif penelitian terletak pada penerapan logika fuzzy Mamdani tipe-2 interval dengan input pH, Total Dissolved Solids (TDS), dan suhu larutan untuk menghasilkan empat output durasi aktivasi Pompa Nutrisi AB Mix A, AB Mix B, pH Up, dan pH Down. pH dan TDS dikendalikan, sedangkan suhu menjadi input pendukung. Implementasi fuzzy pada ESP32 divalidasi secara numerik terhadap MATLAB; Node-RED digunakan untuk pemantauan dan Firebase Realtime Database untuk penyimpanan data. Evaluasi meliputi pengujian sensor, respons aktuator, validasi numerik output fuzzy, kestabilan fungsional sistem kontrol selama 60 menit, interval pembaruan data, dan pengamatan pertumbuhan awal. Validasi mencakup 27 kombinasi kondisi input dengan empat output pada setiap kombinasi sehingga diperoleh 108 data output. Sebanyak 16 tanaman diamati, terdiri atas delapan tanaman dengan kontrol fuzzy dan delapan tanaman tanpa kontrol fuzzy. Hasil pengujian menunjukkan akurasi sensor pH 97,16% dan TDS 99,76%, sedangkan DS18B20 memiliki tingkat kesesuaian 98,62% terhadap alat referensi. Seluruh 108 output fuzzy menunjukkan kesesuaian numerik 100% antara ESP32 dan MATLAB dengan rata-rata selisih 0 detik. Pada pengujian kestabilan fungsional sistem, pH berubah dari 7,86 menjadi 6,21 terhadap acuan 6,2, sedangkan TDS meningkat dari 176,73 ppm menjadi 755,73 ppm terhadap acuan 750 ppm. Data tercatat dengan interval pembaruan rata-rata 2 detik. Kelompok kontrol fuzzy memiliki rata-rata tinggi 5,875 cm dan lebar daun 2,7625 cm, sedangkan kelompok tanpa kontrol fuzzy masing-masing 2,000 cm dan 1,5375 cm. Hasil tersebut menunjukkan sistem mampu mengoreksi pH dan TDS sesuai rancangan, mempertahankan konsistensi implementasi fuzzy pada ESP32, serta menunjukkan nilai tinggi dan lebar daun yang lebih besar secara deskriptif pada kelompok kontrol fuzzy tanpa menyatakan hubungan sebab-akibat. Kata Kunci: Hidroponik NFT, Internet of Things, Fuzzy Mamdani Tipe-2, Kontrol pH dan TDS, Tanaman Selada
Actions (login required)
 |
View Item |
