Continuous-Time Prediction of Industrial Paste Thickener System With Differential ODE-Net  

作　　者：Zhaolin Yuan Xiaorui Li Di Wu Xiaojuan Ban Nai-Qi Wu Hong-Ning Dai Hao Wang 

机构地区：[1]the Beijing Advanced Innovation Center for Materials Genome Engineering,Institute of Artificial Intelligence,Beijing Key Laboratory of Knowledge Engineering for Materials Science,School of Computer and Communication Engineering,University of Science and Technology Beijing [2]the Department of ICT and Natural Science,Norwegian University of Science and Technology [3]IEEE [4]the Institute of Systems Engineering,and Collaborative Laboratory for Intelligent Science and Systems,Macao University of Science and Technology [5]the Department of Computing and Decision Sciences,Lingnan University [6]the Department of Computer Science,Norwegian University of Science and Technology

出　　处：《IEEE/CAA Journal of Automatica Sinica》2022年第4期686-698,共13页自动化学报（英文版）

基　　金：supported by National Key Research and Development Program of China(2019YFC0605300);the National Natural Science Foundation of China(61873299,61902022,61972028);Scientific and Technological Innovation Foundation of Shunde Graduate School,University of Science and Technology Beijing(BK21BF002);Macao Science and Technology Development Fund under Macao Funding Scheme for Key R&D Projects(0025/2019/AKP);Macao Science and Technology Development Fund(0015/2020/AMJ)。

摘　　要：It is crucial to predict the outputs of a thickening system,including the underflow concentration(UC)and mud pressure,for optimal control of the process.The proliferation of industrial sensors and the availability of thickening-system data make this possible.However,the unique properties of thickening systems,such as the non-linearities,long-time delays,partially observed data,and continuous time evolution pose challenges on building data-driven predictive models.To address the above challenges,we establish an integrated,deep-learning,continuous time network structure that consists of a sequential encoder,a state decoder,and a derivative module to learn the deterministic state space model from thickening systems.Using a case study,we examine our methods with a tailing thickener manufactured by the FLSmidth installed with massive sensors and obtain extensive experimental results.The results demonstrate that the proposed continuous-time model with the sequential encoder achieves better prediction performances than the existing discrete-time models and reduces the negative effects from long time delays by extracting features from historical system trajectories.The proposed method also demonstrates outstanding performances for both short and long term prediction tasks with the two proposed derivative types.

关 键 词：Industrial 24 paste thickener ordinary differential equation(ODE)-net recurrent neural network time series prediction 

分 类 号：TD40[矿业工程—矿山机电] TP183[自动化与计算机技术—控制理论与控制工程]