A Dual-Attention Recurrent Neural Network Method for Deep Cone Thickener Underflow Concentration Prediction

• Published in: Sensors (Basel, Switzerland) Vol. 20; no. 5; p. 1260
• Main Authors: Yuan, Zhaolin, Hu, Jinlong, Wu, Di, Ban, Xiaojuan
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI 26.02.2020; MDPI AG
• Subjects: cone thickener; dual-attention; industrial internet of things (iiot); spatio-temporal relationship; time series prediction; dual-attention; Time series prediction; industrial internet of things (IIoT); spatio-temporal relationship; cone thickener
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s20051260

This paper focuses on the time series prediction problem for underflow concentration of deep cone thickener. It is commonly used in the industrial sedimentation process. In this paper, we introduce a dual attention neural network method to model both spatial and temporal features of the data collected from multiple sensors in the thickener to predict underflow concentration. The concentration is the key factor for future mining process. This model includes encoder and decoder. Their function is to capture spatial and temporal importance separately from input data, and output more accurate prediction. We also consider the domain knowledge in modeling process. Several supplementary constructed features are examined to enhance the final prediction accuracy in addition to the raw data from sensors. To test the feasibility and efficiency of this method, we select an industrial case based on Industrial Internet of Things (IIoT). This Tailings Thickener is from FLSmidth with multiple sensors. The comparative results support this method has favorable prediction accuracy, which is more than 10% lower than other time series prediction models in some common error indices. We also try to interpret our method with additional ablation experiments for different features and attention mechanisms. By employing mean absolute error index to evaluate the models, experimental result reports that enhanced features and dual-attention modules reduce error of fitting ~5% and ~11%, respectively.