Improving cement production process with data-augmented sequence to sequence-Wasserstein generative adversarial networks model for accurate prediction of f-CaO

This paper proposes a method to address the issue of insufficient capture of temporal dependencies in cement production processes, which is based on a data-augmented Seq2Seq-WGAN (Sequence to Sequence-Wasserstein Generate Adversarial Network) model. Considering the existence of various temporal scales in cement production processes, we use WGAN to generate a large amount of f-CaO label data and employ Seq2Seq to solve the problem of unequal length input–output sequences. We use the unlabeled relevant variable data as the input to the encoder of the Seq2Seq-WGAN model and use the generated labels as the input to the decoder, thus fully exploring the temporal dependency relationships between input and output variables. We use the hidden vector containing the temporal characteristics of cement produced by the encoder as the initial state of the gate recurrent unit in the decoder to achieve accurate prediction of key points and continuous time. The experimental results show that the Seq2Seq-WGAN model can achieve accurate prediction of continuous time series of free calcium and offer direction for subsequent production planning. This method has high practicality and application prospects, and can provide strong support for the production scheduling of the cement industry.