Zhou / Cen Combustion Optimization Based on Computational Intelligence

1. Auflage 2018
ISBN: 978-981-10-7875-0
Verlag: Springer Nature Singapore
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 291 Seiten

Reihe: Advanced Topics in Science and Technology in China

This book presents the latest findings on the subject of combustion optimization based on computational intelligence. It covers a broad range of topics, including the modeling of coal combustion characteristics based on artificial neural networks and support vector machines. It also describes the optimization of combustion parameters using genetic algorithms or ant colony algorithms, an online coal optimization system, etc. Accordingly, the book offers a unique guide for researchers in the areas of combustion optimization, NOx emission control, energy and power engineering, and chemical engineering.

Professor Hao Zhou received his Ph.D. degree from Zhejiang University in 2004. He is currently Deputy Director of  State Key Laboratory of Clean Energy Utilization at Zhejiang University and Director of the Zhejiang University - University of Leeds joint research center for sustainable energy. His research interests include combustion optimization, low pollutant combustion technology for utility boilers, and neural network and support vector machine modeling methods. He has published over 20 academic papers and filed 7 patents in the areas of combustion pollutants control and combustion optimization since 2000. Professor Kefa Cen is a member of the Chinese Academy of Engineering. He received his Ph.D. degree from Moscow Industrial Technology University and has expertise in clean coal combustion and gasification, poly-generation and comprehensive utilization of energy resources, as well as biomass gasification and bio-oil. He is currently Director of the Institute for Thermal Power Engineering at Zhejiang University and Chairman of the Chinese Society of Power Engineering's International Cooperation & Exchange Committee. He is also Editor-in-Chief of the Journal of Zhejiang University (Engineering Science) and the Journal of Renewable Energy. He has published over 800 academic papers and 15 books.

Autoren/Hrsg.

Zhou, Hao

Cen, Kefa

Inhaltsverzeichnis

1;Preface;6
2;Contents;7
3;About the Authors;11
4;List of Figures;12
5;List of Tables;24
6;1 Introduction;26
6.1;Abstract;26
6.2;1.1 Background;26
6.3;1.2 Coal Combustion;27
6.3.1;1.2.1 General Process of Coal Combustion;27
6.3.2;1.2.2 The Duration of Coal Combustion;27
6.3.3;1.2.3 The Characteristic of Coal Combustion;28
6.4;1.3 Carbon Burnout;29
6.5;1.4 Coal Combustion Optimization;30
6.6;1.5 Outline of the Book;30
6.7;References;31
7;2 The Influence of Combustion Parameters on NOx Emissions and Carbon Burnout;32
7.1;Abstract;32
7.2;2.1 Introduction;32
7.3;2.2 Influence of Combustion Parameters on NOx Emissions;33
7.4;2.3 Influence of Combustion Parameters on Carbon Burnout;38
7.5;References;44
8;3 Modeling Methods for Combustion Characteristics;45
8.1;Abstract;45
8.2;3.1 Introduction;45
8.3;3.2 Experimental Method;46
8.3.1;3.2.1 Experimental Methods of Coal Combustion Characteristics Study;46
8.3.1.1;3.2.1.1 Coal Combustion Characteristics;46
8.3.1.2;3.2.1.2 Experimental Methods;46
8.3.1.3;3.2.1.3 Test System of Coal Combustion;53
8.3.2;3.2.2 Flame Temperature Measurement;57
8.3.3;3.2.3 Flue Gas Analysis;58
8.3.4;3.2.4 Application Examples;62
8.4;3.3 CFD Method;89
8.4.1;3.3.1 Turbulence Model;90
8.4.2;3.3.2 Combustion Model;93
8.4.3;3.3.3 Radiative Heat Transfer Model;94
8.4.4;3.3.4 Discrete Phase Model;94
8.4.5;3.3.5 Reaction Models of Particles;95
8.4.6;3.3.6 Pollutant Formation Model;96
8.4.7;3.3.7 Application Examples;96
8.5;3.4 Computational Intelligence Method;156
8.6;3.5 Summary;166
8.7;References;166
9;4 Neural Network Modeling of Combustion Characteristics;170
9.1;Abstract;170
9.2;4.1 Introduction;170
9.2.1;4.1.1 Structural Model of Neuron;170
9.2.2;4.1.2 MP Model;171
9.3;4.2 Back Propagation Neural Network Method;172
9.3.1;4.2.1 BPNN Algorithm;172
9.3.2;4.2.2 Learning Methods;173
9.4;4.3 General Regression Neural Network Method;174
9.4.1;4.3.1 GRNN Algorithm;175
9.4.2;4.3.2 GRNN Structure;175
9.5;4.4 Comparison of BPNN Method and GRNN Method;176
9.5.1;4.4.1 GRNN Advantages;176
9.5.2;4.4.2 Comparison on Example;176
9.6;4.5 Summary;177
9.7;References;177
10;5 Classification of the Combustion Characteristics based on Support Vector Machine Modeling;178
10.1;Abstract;178
10.2;5.1 The Introduction of Support Vector Machine;178
10.3;5.2 The Principle of Support Vector Machine;180
10.3.1;5.2.1 Support Vector Classification;180
10.3.2;5.2.2 Support Vector Regression;181
10.3.3;5.2.3 Kernel Function;181
10.4;5.3 The Application of Support Vector Machine;182
10.4.1;5.3.1 Coal Identification;182
10.4.2;5.3.2 The Prediction of Ash Fusion Temperature;184
10.4.3;5.3.3 The Prediction of Unburned Carbon in Fly Ash;186
10.4.4;5.3.4 The Prediction of NOx Emission;188
10.5;5.4 Summary;192
10.6;References;192
11;6 Combining Neural Network or Support Vector Machine with Optimization Algorithms to Optimize the Combustion;194
11.1;Abstract;194
11.2;6.1 Introduction of Optimization Algorithms;194
11.2.1;6.1.1 Genetic Algorithms;194
11.2.1.1;6.1.1.1 Introduction to GA;194
11.2.1.2;6.1.1.2 The Description of GA;195
11.2.1.3;6.1.1.3 The Process of GA Approach;195
11.2.2;6.1.2 Ant Colony Algorithms;196
11.2.2.1;6.1.2.1 Introduction to ACO;196
11.2.2.2;6.1.2.2 The Description of ACO;196
11.2.2.3;6.1.2.3 Another Algorithm of ACO;199
11.2.3;6.1.3 Particle Swarm Algorithms;201
11.3;6.2 Combining Neural Network and GA to Optimize the Combustion;203
11.3.1;6.2.1 Experiments;203
11.3.2;6.2.2 Result and Discussions;205
11.3.3;6.2.3 Conclusions;210
11.4;6.3 Combining SVM and Optimization Algorithms to Optimize the Combustion;210
11.4.1;6.3.1 Modeling NOx Emissions by SVM and ACO with Operating Parameters Optimizing;211
11.4.1.1;6.3.1.1 Experimental Setup and Data Analysis;211
11.4.1.2;6.3.1.2 Results;214
11.4.1.3;6.3.1.3 Prediction Results of ACO–SVR;214
11.4.1.4;6.3.1.4 Prediction Results of Grid SVR;218
11.4.1.5;6.3.1.5 Comparison and Discussion;220
11.4.1.6;6.3.1.6 Conclusions;222
11.4.2;6.3.2 Modeling NOx Emissions by SVM and PSO with Model and Operating Parameters Optimizing;223
11.4.2.1;6.3.2.1 Experimental Setup;223
11.4.2.2;6.3.2.2 Optimization Results for the Boiler Load of 288.45 MW;227
11.4.2.3;6.3.2.3 Comparison with Other Methods;228
11.4.2.4;6.3.2.4 Conclusions;231
11.4.3;6.3.3 Comparison of Optimization Algorithms for Low NOx Combustion;232
11.4.3.1;6.3.3.1 Experimental Setup and NOx Emission Data;232
11.4.3.2;6.3.3.2 Estimation of NOx Emissions by SVR;234
11.4.3.3;6.3.3.3 Selection of Model Parameters;235
11.4.3.4;6.3.3.4 NOx Emissions Prediction Results;236
11.4.3.5;6.3.3.5 Low NOx Emissions by Combining SVR and Optimization Methods;237
11.4.3.6;6.3.3.6 Parameter Settings for Various Algorithms;239
11.4.3.7;6.3.3.7 Performance Comparisons;239
11.4.3.8;6.3.3.8 Convergence Rate;244
11.4.3.9;6.3.3.9 Conclusions;245
11.5;6.4 Multi-objective Optimization of Coal Combustion for Utility Boilers;246
11.5.1;6.4.1 Multi-objective Optimization Algorithm;246
11.5.1.1;6.4.1.1 The Cellular Genetic Algorithm for Multi-objective Optimization (MOCell);246
11.5.1.2;6.4.1.2 AbYSS Algorithm;247
11.5.1.3;6.4.1.3 OMOPSO Algorithm;247
11.5.1.4;6.4.1.4 SPEA2 Algorithm;249
11.5.2;6.4.2 Introduction and Experiment Setup;250
11.5.3;6.4.3 Modeling NOx Emissions and Carbon Burnout;251
11.5.4;6.4.4 Performance Metrics of Pareto Solution;253
11.5.4.1;6.4.4.1 The Ratio of Non-dominated Individuals (RNI);253
11.5.4.2;6.4.4.2 Cover Rate;253
11.5.5;6.4.5 Parameter Settings for Various Algorithms;254
11.5.6;6.4.6 Performance Comparisons;254
11.5.7;6.4.7 Conclusion;258
11.6;6.5 Summary;258
11.7;References;259
12;7 Online Combustion Optimization System;261
12.1;Abstract;261
12.2;7.1 Introduction;262
12.2.1;7.1.1 Data Detection Requirements;262
12.2.2;7.1.2 Quickness and Accuracy Requirements;262
12.2.3;7.1.3 Requirements for Different Optimization Goals;263
12.2.4;7.1.4 Requirements Online Self-Learning;263
12.2.5;7.1.5 Parameter Optimization Limit Requirements;263
12.2.6;7.1.6 Fault Tolerance Requirements;263
12.2.7;7.1.7 Alarm Requirements;264
12.2.8;7.1.8 Compatibility of Off-line Data Processing and Optimizing;264
12.3;7.2 Instruments or Sensors for Online Combustion Optimization System;264
12.4;7.3 Online SVM Algorithm;265
12.4.1;7.3.1 Algorithm Introduction;265
12.4.2;7.3.2 Derivation of the Incremental Relations;268
12.4.3;7.3.3 AOSVR Bookkeeping Procedure;270
12.4.4;7.3.4 Efficiently Updating the R Matrix;271
12.4.5;7.3.5 Initialization of the Incremental Algorithm;272
12.4.6;7.3.6 Decremental Algorithm;273
12.5;7.4 Online Combustion Optimization System;273
12.5.1;7.4.1 Online Monitoring and Alarm Function;273
12.5.2;7.4.2 Online Optimization and Self-Learning Function;274
12.5.3;7.4.3 Off-line Modeling and Optimization Function;275
12.6;7.5 The Application of Online Combustion Optimization System;280
12.6.1;7.5.1 Train and Prediction;280
12.6.2;7.5.2 Test Purpose;283
12.6.3;7.5.3 Test Condition;283
12.6.4;7.5.4 Test Data;283
12.6.5;7.5.5 Result and Analysis;285
12.7;7.6 Summary;285
12.8;Reference;286
13;8 Combustion Optimization Based on Computational Intelligence Applications: Future Prospect;287
13.1;Abstract;287
13.2;References;288
14;Index;290