Pemodelan dan Kontrol Water Level pada Steam Boiler dengan Adaptive Neuro-Fuzzy Inference System (ANFIS)

'Alima, Unsa Azmiya Umi (2026) Pemodelan dan Kontrol Water Level pada Steam Boiler dengan Adaptive Neuro-Fuzzy Inference System (ANFIS). Diploma thesis, Institut Teknologi Sepuluh Nopember.

Text 5009201057-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (4MB) | Request a copy

Abstract

Ketinggian air pada steam boiler perlu dijaga agar tetap dalam batas operasi yang aman. Jika level air yang terlalu rendah, boiler bisa mengalami panas berlebih dan berisiko merusak sistem. Sebaliknya, jika terlalu tinggi dapat menurunkan efisiensi penguapan dan mengganggu kinerja komponen lain. Penelitian ini bertujuan untuk merancang model kontrol level air pada steam boiler menggunakan Adaptive Neuro-Fuzzy Inference System (ANFIS) dan mengetahui kinerja ANFIS dalam menjaga kestabilan level air. Penelitian dilakukan dengan simulasi menggunakan MATLAB/Simulink pada model steam boiler dengan kondisi laju aliran steam konstan di 599,2256 kg/s. Data pelatihan ANFIS diperoleh dari hasil simulasi kontrol PID. ANFIS dirancang dengan dua input, yaitu error dan delta error, serta satu output berupa sinyal kontrol untuk mengatur aktuator turbine feedwater pump atau valve feedwater. Pengujian dilakukan pada dua kondisi, yaitu tanpa noise dan dengan noise pada level transmitter. Hasil pengujian menunjukkan bahwa ANFIS mampu menjaga level air steam boiler agar tetap stabil. Pada kondisi tanpa noise, error steady-state yang dihasilkan sebesar 0,0003, sedangkan pada kondisi dengan noise turun menjadi 0,00004. Nilai RMSE pada kondisi tanpa noise sebesar 0,10986 dan pada kondisi dengan noise sebesar 0,10989. Perbedaan nilai RMSE yang kecil menunjukkan bahwa noise pada level transmitter tidak memberikan pengaruh signifikan terhadap kinerja kontrol. Berdasarkan hasil tersebut, ANFIS dapat digunakan sebagai pengendali level air pada steam boiler dalam kondisi simulasi dengan aliran steam konstan karena mampu menghasilkan respons sistem yang stabil dengan error yang kecil.

===============================================================================================================================

The water level in a steam boiler must be maintained within safe operating limits. A low water level can cause the boiler to overheat and potentially damage the system. Conversely, an excessively high water level can reduce evaporation efficiency and interfere with the performance of other components. The purpose of this research is to design a water level control model of a steam boiler using an Adaptive Neuro-Fuzzy Inference System (ANFIS), and to evaluate the ability of ANFIS in controlling the water level. The research was conducted by MATLAB/Simulink simulations on the steam boiler model with the condition of steam flow that is steady at 599.2256 kg/s.. The training data for ANFIS were obtained from PID control simulation results. The ANFIS model was designed with two inputs, namely error and delta error, and one output in the form of a control signal to regulate the turbine feedwater pump actuator or feedwater valve. The tests were carried out under two conditions, namely without noise and with noise in the level transmitter. The results show that ANFIS can maintain a stable steam boiler water level. Under no-noise conditions, the resulting error steady-state is 0.0003, while under noisy conditions it decreases to 0.00004. The RMSE value under no-noise conditions is 0.10986, and under noisy conditions is 0.10989. The small difference in RMSE values indicates that noise in the level transmitter does not significantly affect the control performance. Based on these results, ANFIS can be used as a water level controller in a steam boiler under constant steam flow simulation conditions because it is able to produce a stable system response with small error.

Item Type:	Thesis (Diploma)
Uncontrolled Keywords:	Adaptive Neuro-Fuzzy Inference System (ANFIS), Intelligent Control, Kontrol Level Air, Steam Boiler
Subjects:	T Technology > TJ Mechanical engineering and machinery T Technology > TJ Mechanical engineering and machinery > TJ212 Control engineering systems. Automatic machinery (General) T Technology > TJ Mechanical engineering and machinery > TJ213 Automatic control. T Technology > TJ Mechanical engineering and machinery > TJ263.5 Boilers (general)
Divisions:	Faculty of Industrial Technology > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User:	Unsa Azmiya Umi Alima
Date Deposited:	01 Aug 2026 01:54
Last Modified:	01 Aug 2026 01:54
URI:	http://repository.its.ac.id/id/eprint/141780

Actions (login required)

View Item