(from left) Fitria Kusumaningrum, Citra Annisaa Nurul Ain, Nuzulul Syaqawati Azzahra

ITS Campus, ITS News – Disposal of industrial waste is often not done correctly, causing the hazardous substances from waste to pollute the environment and impact human health. Seeing this, three students of Institut Teknologi Sepuluh Nopember (ITS) designed an artificial intelligence (AI) to make an efficient and environmentally friendly waste treatment for the oil and gas industry.

They are Fitria Kusumaningrum, Citra Annisaa Nurul Ain, Nuzulul Syaqawati Azzahra, members of a team called UCiFi. They are undergraduate students of the Physics Engineering Department, Faculty of Industrial Technology and Systems Engineering (FTI-RS) ITS. They innovated Artificial Intelligence in the form of Artificial Neural Network (ANN) to predict the accuracy of Chemical Oxygen Demand (COD) levels contained in oil and gas industrial waste.

As the team leader, Nuzulul Syaqawati Azzahra said the waste produced by the oil and gas industry was in the form of produced water. The results of these oil exploration activities contain pollutants, including H2S (Hydrogen Sulfide), oils and fats, NH3 (Ammonium), and COD. “The pollutant level exceeds the quality standard, so it must be reduced first before flowing back into nature,” said the girl who is often called Ulul.

One of the team members, Fitria Kusumaningrum, explained that one way to reduce pollutant levels is to use a polishing unit. The input data for this polishing unit is in the form of high COD levels and several other parameters such as pH, temperature, NO3, PO3, MLSS, TSS, and SVM. “After processing the data in the black box polishing unit, a lower COD level will be obtained,” she added.

The ITS UCIFi team is presenting accuracy comparison data among AI models

To predict the COD levels, according to Fitria, an appropriate predictor is needed, namely ANN. But, she also said that optimization techniques need to be applied to support minimal COD results in addition to the ANN model as a predictor. One of the most widely used optimization techniques is the Genetic Algorithm (GA) optimization technique.

Ulul and his team believe that using ANN + GA has better prediction accuracy than other AI models such as ANFIS. “Although ANN and ANFIS both have a lot of data input capabilities, ANN has a hidden layer so that data prediction will be much more accurate,” he explained.

The ITS UCIFi team is presenting their innovations to facilitate more efficient and environmentally friendly waste treatment

When asked about the obstacles, Fitria revealed that her team did not understand the information processing technique using ANN+GA, so they needed more time to understand it. “However, with tenacity and cooperation between team members, we were able to complete the paper that we will compete in,” she said.

The hard work of the UCIFi team has succeeded in producing proud achievements. The paper, entitled Artificial Intelligent in Oil and Gas Wastewater Treatment, successfully led the team guided by Totok Ruki Biyanto ST MT PhD as the second winner in the Petrolida Paper Competition 2021. In this competition held by the Society for Petroleum Engineer ITS Student Chapter (SPE ITS SC), the UCiFi team outperformed the papers from nine other teams.

The ITS UCIFi team won second place in the Petrolida Paper Competition 2021

In the future, Fitria hopes that the UCIFi team can continue to be united and work together to participate in other paper competitions. “By utilizing artificial intelligence for waste treatment, we hope that this innovation can be a breakthrough to improve the performance of waste treatment in the oil and gas industry,” she concluded hopefully. (HUMAS ITS)

Reporter: Tyara Novia Andhin