Exploratory Analysis of Metallurgical Process Data with Neural Networks and Related Methods (eBook)

C. Aldrich (Autor)

eBook Download: PDF

2002 | 1. Auflage
386 Seiten
Elsevier Science (Verlag)
978-0-08-053146-5 (ISBN)

Infos

This volume is concerned with the analysis and interpretation of multivariate measurements commonly found in the mineral and metallurgical industries, with the emphasis on the use of neural networks.

The book is primarily aimed at the practicing metallurgist or process engineer, and a considerable part of it is of necessity devoted to the basic theory which is introduced as briefly as possible within the large scope of the field. Also, although the book focuses on neural networks, they cannot be divorced from their statistical framework and this is discussed in length. The book is therefore a blend of basic theory and some of the most recent advances in the practical application of neural networks.

Inhalt

Front Cover 1
Exploratory Analysis of Metallurgical Process Data with Neural Networks and Related Methods 4
Copyright Page 5
Preface 6
Table of Contents 8
CHAPTER 1. INTRODUCTION TO NEURAL NETWORKS 18
1.1. BACKGROUND 18
1.2. ARTIFICIAL NEURAL NETWORKS FROM AN ENGINEERING PERSPECTIVE 19
1.3. BRIEF HISTORY OF NEURAL NETWORKS 22
1.4. STRUCTURES OF NEURAL NETWORKS 23
1.5. TRAINING RULES 26
1.6. NEURAL NETWORK MODELS 36
1.7. NEURAL NETWORKS AND STATISTICAL MODELS 62
1.8. APPLICATIONS IN THE PROCESS INDUSTRIES 65
CHAPTER 2. TRAINING OF NEURAL NETWORKS 67
2.1. GRADIENT DESCENT METHODS 67
2.2. CONJUGATE GRADIENTS 69
2.3. NEWTON'S METHOD AND QUASI-NEWTON METHOD 71
2.4. LEVENBERG-MARQUARDT ALGORITHM 73
2.5. STOCHASTIC METHODS 74
2.6 REGULARIZATION AND PRUNING OF NEURAL NETWORK MODELS 79
2.7 PRUNING ALGORITHMS FOR NEURAL NETWORKS 81
2.8. CONSTRUCTIVE ALGORITHMS FOR NEURAL NETWORKS 82
CHAPTER 3. LATENT VARIABLE METHODS 91
3.1. BASICS OF LATENT STRUCTURE ANALYSIS 91
3.2. PRINCIPAL COMPONENT ANALYSIS 92
3.3. NONLINEAR APPROACHES TO LATENT VARIABLE EXTRACTION 106
3.4. PRINCIPAL COMPONENT ANALYSIS WITH NEURAL NETWORKS 107
3.5. EXAMPLE 2: FEATURE EXTRACTION FROM DIGITISED IMAGES OF INDUSTRIAL FLOTATION FROTHS WITH AUTOASSOCIATIVE NEURAL NETWORKS 109
3.6. ALTERNATIVE APPROACHES TO NONLINEAR PRINCIPAL COMPONENT ANALYSIS 112
3.7. EXAMPLE 1: LOW-DIMENSIONAL RECONSTRUCTION OF DATA WITH NONLINEAR PRINCIPAL COMPONENT METHODS 116
3.8. PARTIAL LEAST SQUARES (PLS) MODELS 117
3.9. MULTIVARIATE STATISTICAL PROCESS CONTROL 119
CHAPTER 4. REGRESSION MODELS 129
4.1. THEORETICAL BACKGROUND TO MODEL DEVELOPMENT 130
4.2. REGRESSION AND CORRELATION 131
4.3. MULTICOLLINEARITY 136
4.4. OUTLIERS AND INFLUENTIAL OBSERVATIONS 141
4.5. ROBUST REGRESSION MODELS 147
4.6. DUMMY VARIABLE REGRESSION 149
4.7. RIDGE REGRESSION 151
4.8. CONTINUUM REGRESSION 154
4.9. CASE STUDY: CALIBRATION OF AN ON-LINE DIAGNOSTIC MONITORING SYSTEM FOR COMMINUTION IN A LABORATORY-SCALE BALL MILL 155
4.10. NONLINEAR REGRESSION MODELS 163
4.11. CASE STUDY 1: MODELLING OF A SIMPLE BIMODAL FUNCTION 177
4.12. NONLINEAR MODELLING OF CONSUMPTION OF AN ADDITIVE IN A GOLD LEACH PLANT 184
CHAPTER 5. TOPOGRAPHICAL MAPPINGS WITH NEURAL NETWORKS 189
5.1. BACKGROUND 189
5.2. OBJECTIVE FUNCTIONS FOR TOPOGRAPHIC MAPS 191
5.3. MULTIDIMENSIONAL SCALING 194
5.4. SAMMON PROJECTIONS 195
5.5. EXAMPLE 1: ARTIFICIALLY GENERATED AND BENCHMARK DATA SETS 196
5.6. EXAMPLE 2: VISUALIZATION OF FLOTATION DATA FROM A BASE METAL FLOTATION PLANT 200
5.7. EXAMPLE 3: MONITORING OF A FROTH FLOTATION PLANT 205
5.8. EXAMPLE 4: ANALYSIS OF THE LIBERATION OF GOLD WITH MULTI-DIMENSIONALLY SCALED MAPS 208
5.9. EXAMPLE 5. MONITORING OF METALLURGICAL FURNACES BY USE OF TOPOGRAPHIC PROCESS MAPS 212
CHAPTER 6. CLUSTER ANALYSIS 216
6.1. SIMILARITY MEASURES 216
6.2. GROUPING OF DATA 221
6.3. HIERARCHICAL CLUSTER ANALYSIS 223
6.4. OPTIMAL PARTITIONING (K-MEANS CLUSTERING) 226
6.5. SIMPLE EXAMPLES OF HIERARCHICAL AND K-MEANS CLUSTER ANALYSIS 226
6.6. CLUSTERING OF LARGE DATA SETS 230
6.7. APPLICATION OF CLUSTER ANALYSIS IN PROCESS ENGINEERING 231
6.8. CLUSTER ANALYSIS WITH NEURAL NETWORKS 232
CHAPTER 7. EXTRACTION OF RULES FROM DATA WITH NEURAL NETWORKS 245
7.1. BACKGROUND 245
7.2. NEUROFUZZY MODELING OF CHEMICAL PROCESS SYSTEMS WITH ELLIPSOIDAL RADIAL BASIS FUNCTION NEURAL NETWORKS AND GENETIC ALGORITHMS 246
7.3. EXTRACTION OF RULES WITH THE ARTIFICIAL NEURAL NETWORK DECISION TREE (ANN-DT) ALGORITHM 252
7.4. THE COMBINATORIAL RULE ASSEMBLER (CORA) ALGORITHM 266
7.5. SUMMARY 276
CHAPTER 8. INTRODUCTION TO THE MODELLING OF DYNAMIC SYSTEMSCHAPTER 279
8.1. BACKGROUND 279
8.2. DELAY COORDINATES 281
8.3. LAG OR DELAY TIME 282
8.4. EMBEDDING DIMENSION 285
8.5. CHARACTERIZATION OF ATTRACTORS 287
8.6. DETECTION OF NONLINEARITIES 292
8.7. SINGULAR SPECTRUM ANALYSIS 297
8.8. RECURSIVE PREDICTION 299
CHAPTER 9. CASE STUDIES: DYNAMIC SYSTEMS ANALYSIS AND MODELLING 302
9.1. EFFECT OF NOISE ON PERIODIC TIME SERIES 302
9.2. AUTOCATALYSIS IN A CONTINUOUS STIRRED TANK REACTOR 304
9.3. EFFECT OF MEASUREMENT AND DYNAMIC NOISE ON THE IDENTIFICATION OF AN AUTOCATALYTIC PROCESS 310
9.4. IDENTIFICATION OF AN INDUSTRIAL PLATINUM FLOTATION PLANT BY USE OF SINGULAR SPECTRUM ANALYSIS AND DELAY COORDINATES 312
9.5. IDENTIFICATION OF A HYDROMETALLURGICAL PROCESS CIRCUIT 313
CHAPTER 10. EMBEDDING OF MULTIVARIATE DYNAMIC PROCESS SYSTEMS 316
10.1. EMBEDDING OF MULTIVARIATE OBSERVATIONS 316
10.2. MULTIDIMENSIONAL EMBEDDING METHODOLOGY 316
10.3 APPLICATION OF THE EMBEDDING METHOD 320
10.4 MODELLING OF NOx -FORMATION 322
CHAPTER 11. FROM EXPLORATORY DATA ANALYSIS TO DECISION SUPPORT AND PROCESS CONTROL 330
11.1. BACKGROUND 330
11.2. ANATOMY OF A KNOWLEDGE-BASED SYSTEM 330
11.3. DEVELOPMENT OF A DECISION SUPPORT SYSTEM FOR THE DIAGNOSIS OF CORROSION PROBLEMS 334
11.4. ADVANCED PROCESS CONTROL WITH NEURAL NETWORKS 337
11.5. SYMBIOTIC ADAPTIVE NEURO-EVOLUTION (SANE) 339
11.6. CASE STUDY: NEUROCONTROL OF A BALL MILL GRINDING CIRCUIT 341
11.7. NEUROCONTROLLER DEVELOPMENT AND PERFORMANCE 345
11.8. CONCLUSIONS 349
REFERENCES 350
INDEX 383
APPENDIX: DATA FILES 387

Produkt-Details

• Erscheint lt. Verlag: 19.4.2002
• Sprache: englisch
• Themenwelt: Informatik ► Datenbanken ► Data Warehouse / Data Mining
• Themenwelt: Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
• Themenwelt: Naturwissenschaften ► Geowissenschaften ► Geologie
• Themenwelt: Technik
• ISBN-10: 0-08-053146-6 / 0080531466
• ISBN-13: 978-0-08-053146-5 / 9780080531465