TCN-LSTM: A Deep Learning-Based Temperature Prediction Model for Rotary Kilns

The inherent complexity of physical and chemical reactions within the rotary kiln poses a challenge for traditional mechanism models in effectively characterizing the dynamic kiln process. To address this issue, we propose a deep learning-based temperature prediction dynamic model to accurately track the temperature changes, with a view to providing model-based support for rotary kilns process control and optimization. Our proposed model combines a temporal convolutional network (TCN) with a long short-term memory (LSTM) network, incorporating a unique feature fusion technique along with a hybrid pooling layer and attention layer. This integration enables the extraction of both global and local features, thereby preserving detailed information efficiently while significantly reducing model complexity. Additionally, these enhancements mitigate the risk of overfitting and enhance the stability and robustness of the model. Experimental results based on the zinc rotary kiln dataset demonstrate that the proposed model exhibits a promising prediction accuracy of the rotary kiln's temperature. It outperforms the state-of-the-art prediction models such as LSTM, Gated Recurrent Unit (GRU) and TCN. In the future, this model can be readily implemented and applied in many industrial areas such as systems modeling, time series forecasting, and predictive maintenance.