Machine learning regression algorithms to predict emissions from steam boilers.

Currently, the modeling of complex chemical-physical processes is drastically influencing industrial development. Therefore, the analysis and study of the combustion process of the boilers using machine learning (ML) techniques are vital to increase the efficiency with which this equipment operates and reduce the pollution load they contribute to the environment. This work aims to predict the emissions of CO, CO2, NOx, and the temperature of the exhaust gases of industrial boilers from real data. Different ML algorithms for regression analysis are discussed. The following are input variables: ambient temperature, working pressure, steam production, and the type of fuel used in around 20 industrial boilers. Each boiler's emission data was collected using a TESTO 350 Combustion Gas Analyzer. The modeling, with a machine learning approach using the Gradient Boosting Regression algorithm, showed better performance in the predictions made on the test data, outperforming all other models studied. It was achieved with predicted values showing a mean absolute error of 0.51 and a coefficient of determination of 99.80%. Different regression models (DNN, MLR, RFR, GBR) were compared to select the most optimal. Compared to models based on Linear Regression, the DNN model has better prediction performance. The proposed model provides a new method to predict CO2, CO, NOx emissions, and exhaust gas outlet temperature.

Modeling and control of the hydraulic actuator in a ladle furnace.

The dynamic behavior of the hydraulic actuator in a system for regulating the electrode's position is crucial for the operation of a Ladle Furnace. This work aims to identify, model, and control the hydraulic actuator in the Ladle Furnace of ACINOX Las Tunas. For identifying the system, input signals of Pseudo-Random Binary type and black box models were used. As a result, three models were obtained, two reflecting the process's asymmetric behavior according to the upward or downward movement. The third model approximates the process dynamic behavior around the operating point and includes the uncertainty caused by the weight variation during the electrode wear. The models obtained, with a fit greater than 85%, allow a better understanding of the study case behavior. In addition, these allowed the evaluation of the electrode's weight variation and tuning of several controllers. The optimal one was a novel non-linear PI controller of guaranteed robustness. In future works, the use of a non-linear function could be evaluated to compensate for the asymmetric behavior of the process.