摘要：Eco-friendliness is an important global issue, and the maritime field is no exception. Predicting the composition of exhaust gases emitted by ship engines will be of consequence in this respect. Therefore, in this study, exhaust gas data were collected from the generator engine of a real ship along with engine-related data to predict emission characteristics. This is because installing an emission gas analyzer on a ship has substantial economic burden, and, even if it is installed, the accuracy can be increased by a virtual sensor. Furthermore, data were obtained with and without operating the SCR (often mounted on ships to reduce NOx), which is a crucial facility to satisfy environment regulation. In this study, four types of datasets were created by adding cooling and electrical-related variables to the basic engine dataset to check whether it improves model performance or not; each of these datasets consisted of 15 to 26 variables as inputs. CO2 (%), NOx (ppm), and tEx (°C) were predicted from each dataset using an artificial neural network (ANN) model and a support vector machine (SVM) model with optimal hyperparameters selected by trial and error. The results confirmed that the SVM model performed better on smaller datasets, such as the one used in this study compared to the ANN model. Moreover, the dataset type, DaCE, which had both cooling and electrical-related variables added to the basic engine dataset, yielded the best overall prediction performance. When the performance of the SVM model was measured using the test data of a DaCE on both no-SCR mode and SCR mode, the RMSE (R2) of CO2 was between 0.1137% (0.8119) and 0.0912% (0.8975), the RMSE (R2) of NOx was between 17.1088 ppm (0.9643) and 13.6775 ppm (0.9776), and the RMSE (R2) of tEx was between 4.5839 °C (0.8754) and 1.5688 °C (0.9392).
