Temperature Prediction of Once-Through Steam Generator Tubes Based on Neural Network

In the field of industrial engineering, the ability to predict the temperature of tubes in once-through steam generator (OTSG) is a critical concern due to its significant impact on the equipment’s serviceability. This study proposes a novel residual dilated convolution neural network model for accurate temperature prediction in OTSG tubes. By integrating a residual dilated convolution layer, this model effectively captures long-range dependencies in the input data, leading to improved prediction accuracy. The effectiveness of the proposed approach is validated through experiments conducted on real-world data obtained from an operating OTSG. The experimental results demonstrate that the proposed model outperforms existing state-of-the-art approaches in terms of mean squared error, root mean squared error, and mean absolute error. The findings of this study provide evidence that residual dilated convolutional neural networks have considerable potential for accurate temperature prediction in OTSG tubes, thereby ensuring safe and efficient operation.