Collaborative Optimization of Complex Energy Systems [[electronic resource] ] : Applications in Iron and Steel Industry / / by Dinghui Wu, Junyan Fan, Shenxin Lu, Jing Wang, Yong Zhu, Hongtao Hu

• Autore: Wu Dinghui
• Pubblicazione: Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2023
• Edizione: 1st ed. 2023.
• Descrizione fisica: 1 online resource (158 pages)
• Disciplina: 696
• Soggetto topico: Electric power production; Mathematical optimization; Industrial engineering; Production engineering; Control engineering; Metals; Building materials; Electric power distribution; Electrical Power Engineering; Optimization; Industrial and Production Engineering; Control and Systems Theory; Steel, Light Metal; Energy Grids and Networks
• Nota di bibliografia: Includes bibliographical references.
• Nota di contenuto: Intro -- Preface -- Contents -- Acronyms -- 1 Introduction -- 1.1 Background and Significance -- 1.1.1 Background -- 1.1.2 Significance -- 1.2 Current Research Status -- 1.2.1 Energy Plan Optimization -- 1.2.2 Prediction Methods and Models -- 1.2.3 Energy Distribution Optimization -- 1.3 Main Content -- References -- 2 Energy System Analysis and Modeling -- 2.1 Mathematical Model of Multi-medium Energy -- 2.2 Energy Analysis -- 2.2.1 By-product Gas -- 2.2.2 Steam -- 2.2.3 Electricity -- 2.3 Energy System Unit Operation Model -- 2.3.1 Model of Energy Conversion Unit -- 2.3.2 Model of Energy Storage Unit -- 2.3.3 Model of Waste Heat Recovery Unit -- 2.4 Energy System Operating Condition Analysis -- 2.4.1 Main Process Working Conditions Analysis -- 2.4.2 Working Condition Analysis of Energy Conversion Equipment -- 2.5 Conclusion -- References -- 3 Energy Efficiency Evaluation and Optimization Methods -- 3.1 Evaluation Index System of Energy Efficiency in Steel Enterprises -- 3.2 Comprehensive Evaluation Method Based on Combination Weighting -- 3.2.1 Determination of Subjective Weight -- 3.2.2 Determination of Objective Weight -- 3.2.3 Determination of Combination Weight -- 3.2.4 Fuzzy Comprehensive Evaluation -- 3.3 Example Analysis -- 3.3.1 Calculation of Index Weight -- 3.3.2 Energy Efficiency Evaluation of Iron and Steel Enterprises -- 3.4 Conclusion -- References -- 4 Energy Planning Optimization of Iron and Steel Enterprises -- 4.1 Energy Planning Optimization Under Ordinary Working Conditions -- 4.1.1 Mathematical Model for Energy Planning Optimization -- 4.1.2 An Improved MOEA/D Optimization Method Based on the Degree of Population Evolution -- 4.1.3 Simulation Analysis -- 4.2 Energy Planning Optimization Under Multiple Working Conditions -- 4.2.1 Multiple Working Conditions Factors -- 4.2.2 Energy System Model. ; 4.2.3 Improvement of Optimization Algorithm -- 4.2.4 Simulation Analysis -- 4.2.5 Optimal Results -- 4.3 Simulation Analysis -- References -- 5 Prediction of Production and Consumption of BFG -- 5.1 Feature Extraction and Weight Distribution of Production and Consumption -- 5.1.1 Statistical Characteristics of Time Series -- 5.1.2 Characteristics of Multi-scale Sample Entropy -- 5.1.3 Feature Weight Allocation on Account of CRITIC -- 5.2 SOM-K-means Double Clustering Algorithm -- 5.2.1 K-means Algorithm -- 5.2.2 SOM Neural Network -- 5.2.3 Clustering Evaluation Index -- 5.2.4 Implementation of SOM-K-means Double Clustering -- 5.3 XGBoost Classification-Regression Prediction Model -- 5.3.1 The Principle of XGBoost Algorithm -- 5.3.2 XGBoost Classification-Regression Prediction -- 5.4 Simulation Example -- 5.4.1 Description of the Data Set -- 5.4.2 Construction of Prediction Model Based on Feature Clustering and XGBoost -- 5.4.3 Analysis of Simulation Results -- 5.5 Conclusion -- References -- 6 Multi-step Holder Level Prediction of Blast Furnace Gas -- 6.1 The Principle of ENN -- 6.1.1 The Structure of ENN -- 6.1.2 Learning Algorithm of ENN -- 6.2 Dual Attention Mechanism -- 6.2.1 Feature Attention Mechanism -- 6.2.2 Time Attention Mechanism -- 6.2.3 Dual Attention ENN Model -- 6.3 Jaya Algorithm and Improved Method -- 6.3.1 Basic Jaya Algorithm -- 6.3.2 Nonlinear Decreasing Strategy of Step Length Factor -- 6.3.3 Reverse Learning Strategy -- 6.3.4 Improved Jaya Algorithm -- 6.4 Jaya Algorithm and Improved Method -- 6.5 Verification of Instance Simulations -- 6.5.1 Simulation Case Settings -- 6.5.2 Analysis of Simulation Results -- 6.5.3 Explanation of the Validity of the Model -- 6.6 Summary -- References -- 7 Distribution of a Complex Energy Medium in Steel Production -- 7.1 Energy Medium Distribution Under Ordinary Working Conditions. ; 7.1.1 Objective Equation and Constraint Condition -- 7.1.2 Energy Optimization with Deep Reinforcement Learning -- 7.1.3 Optimization of Energy Conversion System -- 7.1.4 Analysis of Simulation Experiment -- 7.2 Energy Medium Distribution Under Different Working Conditions -- 7.2.1 Mathematical Model of Energy Scheduling -- 7.2.2 Solution Framework for Multi-condition Energy Scheduling Based on the DRL-IDE Algorithm -- 7.2.3 Construction of Working Condition Set Based on DRL Algorithm -- 7.2.4 Energy Scheduling Solution Based on IDE Algorithm -- 7.2.5 Simulation Experiment Analysis -- 7.3 Conclusion -- References.
• Sommario/riassunto: This book mainly focuses on the multi-media energy prediction technology and optimization methods of iron and steel enterprises. The technical methods adopted include swarm intelligence algorithm, neural network, reinforcement learning, and so on. Energy saving and consumption reduction in iron and steel enterprises have always been a research hotspot in the field of process control. This book considers the multi-media energy balance problem from the perspective of system, studies the energy flow and material flow in iron and steel enterprises, and provides energy optimization methods that can be used for planning, prediction, and scheduling under different production scenes. The main audience of this book is scholars and graduate students in the fields of control theory, applied mathematics, energy optimization, etc.
• Titolo autorizzato: Collaborative optimization of complex energy systems
• ISBN: 981-9945-50-X
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910741158403321
• Lo trovi qui: Univ. Federico II
• Serie: Engineering Applications of Computational Methods, . 2662-3374 ; ; 17