Artificial Intelligence-based Soft Sensor Model for Sulfur Recovery Units to Predict SO2 Emissions

Abstract

Pollutant emissions from chemical plants are a major concern in the context of environmental safety. A reliable emission forecasting model can provide important information for optimizing the process and improving the environmental performance. In this work, forecasting models are developed for the prediction of SO2 emission from a Sulfur Recovery Unit (SRU). Since SRUs incorporate complex chemical reactions, first-principle models are not suitable to predict emission levels based on a given feed condition. Accordingly, artificial intelligence-based models such as standard machine learning (ML) algorithms, multi-layer perceptron (MLP), long short-term networks (LSTM), one-dimensional convolution (1D-CNN), and CNN-LSTM models were tested, and their performance was evaluated. The input features and hyperparameters of the models were optimized to achieve maximum performance. The performance was evaluated in terms of mean squared error (MSE) and mean absolute percentage Error (MAPE) for 1 hour, 3 hours and 5 hours ahead of forecasting. The reported results show that the CNN-LSTM autoencoder model outperforms other tested models, with its superiority becoming more pronounced as the forecasting horizon increased from 1 hour to 5 hours. For the 5-hour ahead forecasting, the proposed model showed a MAPE advantage of 17.23%, 4.41%, and 2.83%, respectively over the 1D-CNN, Deep LSTM, and single-layer LSTM models in the larger dataset.

Date of Award	7 Dec 2023
Original language	American English
Supervisor	Ali AlHammadi (Supervisor)