The purpose of this study is to improve the prediction of container volumes in Busan ports by applying external variables and time-series data decomposition methods to deep learning prediction models. Previous studies on container volume forecasting were based on traditional statistical methodologies, such as ARIMA, SARIMA, and regression. However, these methods do not explain the complexity and variability of data caused by changes in the external environment, such as the global financial crisis and economic fluctuations. Deep learning can explore the inherent patterns of data and analyze the characteristics (time series, external environmental variables, and outliers); hence, the accuracy of deep learning-based volume prediction models is better than that of traditional models. However, this does not include the study of overall trends (upward, steady, or downward). In this study, a novel deep learning prediction model is proposed that combines prediction and trend identification of container volume. The proposed model explores external variables that are related to container volume, combining port volume time-series decomposition with external variables and deep learning-based multivariate long short-term memory (LSTM) prediction. The results indicate that the proposed model performs better than the traditional LSTM model and follows the trend simultaneously.

Induction furnaces are widely used for melting scrapped steel in small foundries and their use has recently become more frequent. The maintenance of induction furnaces is usually based on empirical decisions of the operator and an explosion can occur through operator error. To prevent an explosion, previous studies have utilized statistical models but have been unable to generalize the problem and have achieved a low accuracy. Herein, we propose a data-driven method for induction furnaces by proposing a novel 2D matrix called a sequential feature matrix(s-encoder) and multi-channel convolutional long short-term memory (s-ConLSTM). First, the sensor data and operation data are converted into sequential feature matrices. Then, N-sequential feature matrices are imported into the convolutional LSTM model to predict the residual life of the induction furnace wall. Based on our experimental results, our method outperforms general neural network models and enhances the safe use of induction furnaces.