Multiscale convolutional and recurrent neural network for quality prediction of continuous casting slabs

Quality prediction in the continuous casting process is of great significance to the quality improvement of casting slabs. Due to the uncertainty and nonlinear relationship between the quality of continuous casting slabs (CCSs) and various factors, reliable prediction of CCS quality poses a challenge to the steel industry. However, traditional prediction models based on domain knowledge and expertise are difficult to adapt to the changes in multiple operating conditions and raw materials from various enterprises. To meet the challenge, we propose a framework with a multiscale convolutional and recurrent neural network (MCRNN) for reliable CCS quality prediction. The proposed framework outperforms conventional time series classification methods with better feature representation since the input is transformed at different scales and frequencies, which captures both long-term trends and short-term changes in time series. Moreover, we generate different category distributions based on the random undersampling (RUS) method to mitigate the impact of the skewed data distribution due to the natural imbalance of continuous casting data. The experimental results and comprehensive comparison with the state-of-the-art methods show the superiority of the proposed MCRNN framework, which has not only satisfactory prediction performance but also good potential to improve continuous casting process understanding and CCS quality.