Smart Monitoring Chemical Oxygen Demand pada Wastewater Treatment Plant Limbah Greywater Berbasis Artificial Neural Network

Aini, Siti Nurul (2025) Smart Monitoring Chemical Oxygen Demand pada Wastewater Treatment Plant Limbah Greywater Berbasis Artificial Neural Network. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 2042211041-Undergraduate_Thesis.pdf] Text
2042211041-Undergraduate_Thesis.pdf
Restricted to Repository staff only

Download (11MB) | Request a copy

Abstract

Greywater dari aktivitas rumah tangga mengandung kadar Chemical Oxygen Demand (COD) yang tinggi akibat bahan organik dan deterjen, sehingga memerlukan pengolahan sebelum dibuang ke lingkungan. Penelitian ini mengembangkan sistem pemantauan COD berbasis Artificial Neural Network (ANN) menggunakan algoritma backpropagation untuk meningkatkan akurasi prediksi COD. Sistem ini menggunakan sensor pH, Total Dissolved Solids (TDS), Dissolved Oxygen (DO), dan gas ammonia (MQ-135) sebagai input model. Hasil prediksi dibandingkan dengan uji laboratorium untuk menilai akurasi model. Proses filtrasi menggunakan zeolit sand, activated carbon, activated sand, manganese green sand, dan silica sand menunjukkan efektivitas dalam menurunkan polutan. Sesudah filtrasi, nilai pH menurun dari 8.37 menjadi 7.36 (12.06%), TDS turun dari 7 61.30mg/L menjadi 259.42 mg/L (65.92%), dan NH₃ turun dari 2.28 mg/L menjadi 0.56 mg/L (75.44%). Sedangkan, DO meningkat dari 3.62 mg/L menjadi 7.15 mg/L (97.51%). Akurasi ANN dievaluasi dengan membandingkan hasil prediksi dan uji laboratorium, menunjukkan error 9.14% untuk BOD sebelum filtrasi dan 6.63% untuk BOD sesudah filtrasi, serta 4.95% untuk COD sebelum filtrasi dan 9.55% untuk COD sesudah filtrasi. Proses filtrasi menurunkan BOD dari 83.0 mg/L menjadi 19.0 mg/L (77.11%) dan COD dari 201.2 mg/L menjadi 11.0 mg/L (94.53%). Sistem ANN berbasis backpropagation terbukti efektif dalam memprediksi kualitas air greywater dan dapat mendukung pengelolaan air limbah yang lebih efisien dan berkelanjutan.
========================================================================================================================
Greywater from household activities contains high levels of Chemical Oxygen Demand (COD) due to organic matter and detergents, requiring treatment before being discharged into the environment. This study developed a COD monitoring system based on an Artificial Neural Network (ANN) using backpropagation algorithm to improve COD prediction accuracy. The system utilizes pH, Total Dissolved Solids (TDS), Dissolved Oxygen (DO), and ammonia gas (MQ-135) sensors as model inputs. The prediction results were compared with laboratory tests to assess the model's accuracy. The filtration process using zeolite sand, activated carbon, activated sand, manganese green sand, and silica sand demonstrated effectiveness in reducing pollutants. After filtration, the pH value decreased from 8.37 to 7.36 (12.06%), TDS dropped from 761.30 mg/L to 259.42 mg/L (65.92%), and NH₃ decreased from 2.28 mg/L to 0.56 mg/L (75.44%). Meanwhile, DO increased from 3.62 mg/L to 7.15 mg/L (97.51%). The ANN accuracy was evaluated by comparing predictions with laboratory test results, showing an error of 9.14% for BOD before filtration and 6.63% after filtration, as well as 4.95% for COD before filtration and 9.55% after filtration. The filtration process reduced BOD from 83.0 mg/L to 19.0 mg/L (77.11%) and COD from 201.2 mg/L to 11.0 mg/L (94.53%). The backpropagation-based ANN system was proven effective in predicting greywater quality and can support more efficient and sustainable wastewater management.

Item Type: Thesis (Other)
Uncontrolled Keywords: Artificial Neural Network (ANN), Chemical Oxygen Demand (COD), Greywater, Wastewater Treatment Artificial Neural Network (ANN), Greywater, Chemical Oxygen Demand (COD), Greywater, Wastewater Treatment
Subjects: Q Science > QC Physics > QC100.5 Measuring instruments (General)
T Technology > TD Environmental technology. Sanitary engineering > TD430 Water--Purification.
T Technology > TD Environmental technology. Sanitary engineering > TD433 Water treatment plants
T Technology > TD Environmental technology. Sanitary engineering > TD794.5 Recycling (Waste, etc.)
Divisions: Faculty of Vocational > Instrumentation Engineering
Depositing User: Siti Nurul Aini
Date Deposited: 04 Aug 2025 03:59
Last Modified: 04 Aug 2025 03:59
URI: http://repository.its.ac.id/id/eprint/126363

Actions (login required)

View Item View Item