Supervised Attention-Based Bidirectional Long Short-Term Memory Network for Nonlinear Dynamic Soft Sensor Application

Soft sensors are mathematical methods that describe the dependence of primary variables on secondary variables. A nonlinear characteristic commonly appears in modern industrial process data with increasing complexity and dynamics, which has brought challenges to soft sensor modeling. To solve these issues, a novel supervised attention-based bidirectional long short-term memory (SA-BiLSTM) is first proposed in this paper to handle the nonlinear industrial process modeling with dynamic features. In this SA-BiLSTM model, an attention mechanism is introduced to calculate the correlation between hidden features in each time step, thus avoiding the loss of important information. Furthermore, this approach combines historical quality information and a moving window through a supervised strategy of quality variables. Such manipulation not only extracts and exploits nonlinear dynamic latent information from the process and quality variables but also enhances the model's learning efficiency and overall prediction performance. Finally, two real industrial examples demonstrate the superiority of the proposed method compared to conventional methods.

Automated summary

Soft sensors are mathematical methods that describe the dependence of primary variables on secondary variables. This paper proposes a novel supervised attention-based bidirectional long short-term memory (SA-BiLSTM) model to handle nonlinear industrial process modeling with dynamic features. The SA-BiLSTM model introduces an attention mechanism to calculate the correlation between hidden features in each time step, thus avoiding the loss of important information. Additionally, this approach combines historical quality information and a moving window through a supervised strategy of quality variables to enhance the model's learning efficiency and prediction performance. Two real industrial examples demonstrate the superiority of the proposed method compared to conventional methods.