This book presents modeling methods and algorithms for data-driven prediction and forecasting of practical industrial process by employing machine learning and statistics methodologies. Related case studies, especially on energy systems in the steel industry are also addressed and analyzed. The case studies in this volume are entirely rooted in both classical data-driven prediction problems and industrial practice requirements. Detailed figures and tables demonstrate the effectiveness and generalization of the methods addressed, and the classifications of the addressed prediction problems come from practical industrial demands, rather than from academic categories. As such, readers will learn the corresponding approaches for resolving their industrial technical problems. Although the contents of this book and its case studies come from the steel industry, these techniques can be also used for other process industries. This book appeals to students, researchers, and professionals withinthe machine learning and data analysis and mining communities.

Auteur
Jun Zhao is currently a Professor with the School of Control Science and Engineering, Dalian University of Technology, China. Chunyang Sheng is currently a lecturer with the School of Electrical Engineering and Automation, Shandong University of Science and Technology, China.

Wei Wang is currently a Professor with the School of Control Science and Engineering, Dalian University of Technology, China.

Contenu
PrefaceCh1 Introduction1.1 Why the prediction is required for industrial process1.2 Introduction to industrial process prediction1.3 Category of industrial process prediction1.4 Common-used techniques for industrial process prediction1.5 Brief summaryCh2 Data preprocessing techniques2.1 Anomaly detection of data2.2 Correction of abnormal data2.3 Methods of packing missing data2.4 Data de-noising techniques2.5 Data fusion methods2.6 DiscussionCh3 Industrial time series prediction3.1 Introduction3.2 Methods of phase space reconstruction3.3 Prediction modeling3.4 Benchmark prediction problems3.5 Cases of industrial applications3.6 DiscussionCh4 Factor-based industrial process prediction 4.1 Introduction4.2 Methods of determining factors4.3 Factor-based single-output model4.4 Factor-based multi-output model4.5 Cases of industrial applications4.6 DiscussionCh5 Industrial Prediction intervals with data uncertainty5.1 Introduction5.2 Common-used techniques for prediction intervals5.3 Prediction intervals with noisy outputs 5.4 Prediction intervals with noisy inputs and outputs 5.5 Time series prediction intervals with missing input5.6 Industrial cases of prediction intervals5.7 DiscussionCh6 Granular computing-based long term prediction intervals6.1 Introduction6.2 Basic theory of granular computing6.3 Techniques of granularity partition6.4 Long-term prediction model6.5 Granular-based prediction intervals6.6 Multi-dimension granular-based long term prediction intervals6.7 DiscussionCh7 Parameters estimation and optimization7.1 Introduction7.2 Gradient-based methods7.3 Evolutionary algorithms7.4 Nonlinear Kalman-filter estimation7.5 Probabilistic methods7.6 Gamma-test based noise estimation7.7 Industrial applications7.8 DiscussionCh8 Parallel computing considerations8.1 Introduction8.2 CUDA-based parallel acceleration8.3 Hadoop-based distributed computation8.4 Other techniques8.5 Industrial applications to parallel computing8.6 Discussion Ch9 Prediction-based scheduling of industrial system9.1 Introduction9.2 Scheduling of blast furnace gas system9.3 Scheduling of coke oven gas system9.4 Scheduling of converter gas system9.5 Scheduling of oxygen system9.6 Predictive scheduling for plant-wide energy system9.7 Discussion