Exploratory Analysis of Metallurgical Process Data with Neural Networks and Related Methods
Regular price
107.250 KD
inc. VAT
Couldn't load pickup availability
Table of contents
- Cover
- Copyright Pageiv
- Prefacev
- Table of Contentsvii
- CHAPTER 1. INTRODUCTION TO NEURAL NETWORKS1
- 1.1. BACKGROUND1
- 1.2. ARTIFICIAL NEURAL NETWORKS FROM AN ENGINEERING PERSPECTIVE2
- 1.3. BRIEF HISTORY OF NEURAL NETWORKS5
- 1.4. STRUCTURES OF NEURAL NETWORKS6
- 1.5. TRAINING RULES9
- 1.6. NEURAL NETWORK MODELS19
- 1.7. NEURAL NETWORKS AND STATISTICAL MODELS45
- 1.8. APPLICATIONS IN THE PROCESS INDUSTRIES48
- CHAPTER 2. TRAINING OF NEURAL NETWORKS50
- 2.1. GRADIENT DESCENT METHODS50
- 2.2. CONJUGATE GRADIENTS52
- 2.3. NEWTON'S METHOD AND QUASI-NEWTON METHOD54
- 2.4. LEVENBERG-MARQUARDT ALGORITHM56
- 2.5. STOCHASTIC METHODS57
- 2.6 REGULARIZATION AND PRUNING OF NEURAL NETWORK MODELS62
- 2.7 PRUNING ALGORITHMS FOR NEURAL NETWORKS64
- 2.8. CONSTRUCTIVE ALGORITHMS FOR NEURAL NETWORKS65
- CHAPTER 3. LATENT VARIABLE METHODS74
- 3.1. BASICS OF LATENT STRUCTURE ANALYSIS74
- 3.2. PRINCIPAL COMPONENT ANALYSIS75
- 3.3. NONLINEAR APPROACHES TO LATENT VARIABLE EXTRACTION89
- 3.4. PRINCIPAL COMPONENT ANALYSIS WITH NEURAL NETWORKS90
- 3.5. EXAMPLE 2: FEATURE EXTRACTION FROM DIGITISED IMAGES OF INDUSTRIAL FLOTATION FROTHS WITH AUTOASS92
- 3.6. ALTERNATIVE APPROACHES TO NONLINEAR PRINCIPAL COMPONENT ANALYSIS95
- 3.7. EXAMPLE 1: LOW-DIMENSIONAL RECONSTRUCTION OF DATA WITH NONLINEAR PRINCIPAL COMPONENT METHODS99
- 3.8. PARTIAL LEAST SQUARES (PLS) MODELS100
- 3.9. MULTIVARIATE STATISTICAL PROCESS CONTROL102
- CHAPTER 4. REGRESSION MODELS112
- 4.1. THEORETICAL BACKGROUND TO MODEL DEVELOPMENT113
- 4.2. REGRESSION AND CORRELATION114
- 4.3. MULTICOLLINEARITY119
- 4.4. OUTLIERS AND INFLUENTIAL OBSERVATIONS124
- 4.5. ROBUST REGRESSION MODELS130
- 4.6. DUMMY VARIABLE REGRESSION132
- 4.7. RIDGE REGRESSION134
- 4.8. CONTINUUM REGRESSION137
- 4.9. CASE STUDY: CALIBRATION OF AN ON-LINE DIAGNOSTIC MONITORING SYSTEM FOR COMMINUTION IN A LABORAT138
- 4.10. NONLINEAR REGRESSION MODELS146
- 4.11. CASE STUDY 1: MODELLING OF A SIMPLE BIMODAL FUNCTION160
- 4.12. NONLINEAR MODELLING OF CONSUMPTION OF AN ADDITIVE IN A GOLD LEACH PLANT167
- CHAPTER 5. TOPOGRAPHICAL MAPPINGS WITH NEURAL NETWORKS172
- 5.1. BACKGROUND172
- 5.2. OBJECTIVE FUNCTIONS FOR TOPOGRAPHIC MAPS174
- 5.3. MULTIDIMENSIONAL SCALING177
- 5.4. SAMMON PROJECTIONS178
- 5.5. EXAMPLE 1: ARTIFICIALLY GENERATED AND BENCHMARK DATA SETS179
- 5.6. EXAMPLE 2: VISUALIZATION OF FLOTATION DATA FROM A BASE METAL FLOTATION PLANT183
- 5.7. EXAMPLE 3: MONITORING OF A FROTH FLOTATION PLANT188
- 5.8. EXAMPLE 4: ANALYSIS OF THE LIBERATION OF GOLD WITH MULTI-DIMENSIONALLY SCALED MAPS191
- 5.9. EXAMPLE 5. MONITORING OF METALLURGICAL FURNACES BY USE OF TOPOGRAPHIC PROCESS MAPS195
- CHAPTER 6. CLUSTER ANALYSIS199
- 6.1. SIMILARITY MEASURES199
- 6.2. GROUPING OF DATA204
- 6.3. HIERARCHICAL CLUSTER ANALYSIS206
- 6.4. OPTIMAL PARTITIONING (K-MEANS CLUSTERING)209
- 6.5. SIMPLE EXAMPLES OF HIERARCHICAL AND K-MEANS CLUSTER ANALYSIS209
- 6.6. CLUSTERING OF LARGE DATA SETS213
- 6.7. APPLICATION OF CLUSTER ANALYSIS IN PROCESS ENGINEERING214
- 6.8. CLUSTER ANALYSIS WITH NEURAL NETWORKS215
- CHAPTER 7. EXTRACTION OF RULES FROM DATA WITH NEURAL NETWORKS228
- 7.1. BACKGROUND228
- 7.2. NEUROFUZZY MODELING OF CHEMICAL PROCESS SYSTEMS WITH ELLIPSOIDAL RADIAL BASIS FUNCTION NEURAL N229
- 7.3. EXTRACTION OF RULES WITH THE ARTIFICIAL NEURAL NETWORK DECISION TREE (ANN-DT) ALGORITHM235
- 7.4. THE COMBINATORIAL RULE ASSEMBLER (CORA) ALGORITHM249
- 7.5. SUMMARY259
- CHAPTER 8. INTRODUCTION TO THE MODELLING OF DYNAMIC SYSTEMSCHAPTER262
- 8.1. BACKGROUND262
- 8.2. DELAY COORDINATES264
- 8.3. LAG OR DELAY TIME265
- 8.4. EMBEDDING DIMENSION268
- 8.5. CHARACTERIZATION OF ATTRACTORS270
- 8.6. DETECTION OF NONLINEARITIES275
- 8.7. SINGULAR SPECTRUM ANALYSIS280
- 8.8. RECURSIVE PREDICTION282
- CHAPTER 9. CASE STUDIES: DYNAMIC SYSTEMS ANALYSIS AND MODELLING285
- 9.1. EFFECT OF NOISE ON PERIODIC TIME SERIES285
- 9.2. AUTOCATALYSIS IN A CONTINUOUS STIRRED TANK REACTOR287
- 9.3. EFFECT OF MEASUREMENT AND DYNAMIC NOISE ON THE IDENTIFICATION OF AN AUTOCATALYTIC PROCESS293
- 9.4. IDENTIFICATION OF AN INDUSTRIAL PLATINUM FLOTATION PLANT BY USE OF SINGULAR SPECTRUM ANALYSIS A295
- 9.5. IDENTIFICATION OF A HYDROMETALLURGICAL PROCESS CIRCUIT296
- CHAPTER 10. EMBEDDING OF MULTIVARIATE DYNAMIC PROCESS SYSTEMS299
- 10.1. EMBEDDING OF MULTIVARIATE OBSERVATIONS299
- 10.2. MULTIDIMENSIONAL EMBEDDING METHODOLOGY299
- 10.3 APPLICATION OF THE EMBEDDING METHOD303
- 10.4 MODELLING OF NOx -FORMATION305
- CHAPTER 11. FROM EXPLORATORY DATA ANALYSIS TO DECISION SUPPORT AND PROCESS CONTROL313
- 11.1. BACKGROUND313
- 11.2. ANATOMY OF A KNOWLEDGE-BASED SYSTEM313
- 11.3. DEVELOPMENT OF A DECISION SUPPORT SYSTEM FOR THE DIAGNOSIS OF CORROSION PROBLEMS317
- 11.4. ADVANCED PROCESS CONTROL WITH NEURAL NETWORKS320
- 11.5. SYMBIOTIC ADAPTIVE NEURO-EVOLUTION (SANE)322
- 11.6. CASE STUDY: NEUROCONTROL OF A BALL MILL GRINDING CIRCUIT324
- 11.7. NEUROCONTROLLER DEVELOPMENT AND PERFORMANCE328
- 11.8. CONCLUSIONS332
- REFERENCES333
- INDEX366
- APPENDIX: DATA FILES370
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.