Stochastic Global Optimization Methods and Applications to Chemical, Biochemical, Pharmaceutical and Environmental Processes

Description

Stochastic global optimization methods and applications to chemical, biochemical, pharmaceutical and environmental processes presents various algorithms that include the genetic algorithm, simulated annealing, differential evolution, ant colony optimization, tabu search, particle swarm optimization, artificial bee colony optimization, and cuckoo search algorithm. The design and analysis of these algorithms is studied by applying them to solve various base case and complex optimization problems concerning chemical, biochemical, pharmaceutical, and environmental engineering processes. Design and implementation of various classical and advanced optimization strategies to solve a wide variety of optimization problems makes this book beneficial to graduate students, researchers, and practicing engineers working in multiple domains. This book mainly focuses on stochastic, evolutionary, and artificial intelligence optimization algorithms with a special emphasis on their design, analysis, and implementation to solve complex optimization problems and includes a number of real applications concerning chemical, biochemical, pharmaceutical, and environmental engineering processes. Cover......Page 1 Stochastic Global Optimization Methods and Applications to Chemical, Biochemical, Pharmaceutical and Environmental Processe .........Page 2 Copyright......Page 3 About the authors......Page 4 Preface......Page 5 1 - Basic features and concepts of optimization......Page 9 1.2.1 Optimization and its benefits......Page 10 1.2.3 Illustrative examples......Page 11 1.2.4 Essential requisites for optimization......Page 14 1.3.1 Functions in optimization......Page 15 1.3.2 Interpretation of behavior of functions......Page 20 1.3.3 Maxima and minima of functions......Page 23 1.3.4 Region of search for constrained optimization......Page 26 1.4.1 Classification of optimization problems......Page 27 1.4.3 Bottlenecks in optimization......Page 31 1.5 Summary......Page 32 References......Page 33 3 - Numerical search methods for unconstrained optimization problems......Page 34 2.2 Statement of optimization problem......Page 35 2.3 Analytical methods for unconstrained single-variable functions......Page 36 9.2.1 Air pollution—significance of modeling and optimization......Page 254 2.3.2 Sufficient conditions for convexity and concavity of a function......Page 37 2.4 Analytical methods for unconstrained multivariable functions......Page 39 7.3.3 Analysis of results......Page 40 2.5.1 Direct substitution......Page 43 2.5.2 Penalty function approach......Page 45 2.5.3.1 Necessary condition for a basic problem......Page 47 2.5.3.2 Necessary condition for a general problem......Page 49 2.5.3.3 Sufficient conditions for a general problem......Page 50 2.6 Analytical methods for solving multivariable optimization problems with inequality constraints......Page 52 2.6.1 Kuhn–Tucker conditions for problems with inequality constraints......Page 53 2.6.2 Kuhn–Tucker conditions for problems with inequality and equality constraints......Page 55 References......Page 58 3.2 Classification of numerical search methods......Page 61 5.3.1 Genetic algorithm implementation strategy......Page 132 3.3.1 Newton's method......Page 62 3.3.2 Quasi-Newton method......Page 65 3.3.3 Secant method......Page 67 3.4.1 Quadratic interpolation method......Page 70 3.4.2 Cubic interpolation method......Page 74 3.5 Multivariable direct search methods......Page 77 8.4.1 Basic algorithms and essential components for formulation of multiobjective optimization strategy......Page 236 3.5.2 Hooke–Jeeves pattern search method......Page 78 3.5.2.2 Pattern move......Page 79 3.5.3 Powell's conjugate direction method......Page 81 3.5.4 Nelder–Mead simplex method......Page 83 3.6 Multivariable gradient search methods......Page 85 3.6.1 Steepest descent method......Page 86 3.6.2 Multivariable Newton's method......Page 88 3.6.3 Conjugate gradient method......Page 90 References......Page 92 4 - Stochastic and evolutionary optimization algorithms......Page 94 7.1 Introduction......Page 95 5.2 Examples of numerical functions......Page 96 4.2.3 Genetic algorithm implementation procedure......Page 97 4.2.4 Genetic algorithm pseudocode......Page 99 4.3.1 Historical background......Page 100 4.3.2 Basic principle......Page 101 4.3.3 Simulated annealing implementation procedure......Page 102 4.3.4 Simulated annealing pseudocode......Page 103 4.4.2 Basic principle......Page 104 4.4.3 Differential evolution implementation procedure......Page 105 4.4.5 Advantages and limitations of differential evolution......Page 106 4.5.2 Basic principle......Page 107 4.5.3 Ant colony optimization implementation procedure......Page 108 4.5.5 Advantages and disadvantages ant colony optmization......Page 110 4.6.3 Tabu search implementation procedure......Page 111 4.6.3.1 Neighbors generations and neighborhood search......Page 112 4.6.3.6 Stopping criteria......Page 113 4.6.5 Advantages and disadvantages of tabu search......Page 114 4.7.2 Basic principle......Page 115 4.7.3 Particle swarm optimization implementation procedure......Page 116 4.7.6 Applications of particle swarm optimization......Page 118 4.8.2 Basic principle......Page 119 4.8.3 Artificial bee colony algorithm implementation procedure......Page 120 4.8.4 Pseudocode of artificial bee colony algorithm......Page 121 4.9.1 Historical background......Page 122 4.9.3 Cuckoo search implementation procedure......Page 123 4.9.5 Advantages and limitations of cuckoo search algorithm......Page 125 References......Page 126 5.1 Introduction......Page 131 5.3.2 Optimization results of genetic algorithm......Page 133 5.4.2 Optimization results of simulated annealing......Page 136 5.5.1 Differential evolution implementation strategy......Page 137 7.4.3 Development of response surface models for lipopeptide biosurfactant process......Page 206 7.4.4 RSM-ACO strategy for lipopeptide process optimization......Page 139 5.8.1 Artificial bee colony implementation strategy......Page 144 5.10 Summary......Page 147 References......Page 151 6 - Application of stochastic evolutionary optimization techniques to chemical processes......Page 153 6.1 Introduction......Page 154 6.2.1 Optimal control and its importance in polymerization reactors......Page 155 6.2.3 Multistage dynamic optimization strategy......Page 156 6.2.4 The polymerization process and its mathematical representation......Page 157 6.2.5 Control objectives......Page 161 6.2.6 Multistage dynamic optimization of SAN copolymerization process using DE......Page 162 6.2.7 Analysis of results......Page 163 6.3.2 Multistage dynamic optimization of SAN copolymerization process using tabu search......Page 167 6.4 Optimization of multiloop proportional–integral controller parameters of a reactive distillation column using genetic algorithm......Page 169 6.4.1 The need of evolutionary algorithm for optimization of multiloop controller parameters......Page 170 6.4.3 Controller design using genetic algorithms......Page 172 6.4.3.1 Compositions estimation......Page 173 6.4.3.4 Desired response specifications for controller tuning......Page 174 6.4.3.5 Optimal tuning of controller parameters......Page 176 6.5.1 The need for stochastic optimization methods in design of nonlinear control strategies......Page 178 6.5.2.1 Polynomial ARMA model......Page 180 6.5.3 The process representation......Page 181 6.5.4.1 Optimal control policy computation using genetic algorithm......Page 183 6.5.4.2 Optimal control policy computation using SA......Page 184 6.5.4.2.1 Implementation procedure......Page 185 6.5.5 Analysis of results......Page 186 6.6 Summary......Page 189 References......Page 191 7 - Application of stochastic evolutionary optimization techniques to biochemical processes......Page 199 7.3 Media optimization of Chinese hamster ovary cells production process using differential evolution......Page 201 7.3.1 CHO cell cultivation process and its macroscopic state space model......Page 202 9.3 Process model–based optimization of distillery industry wastewater treating fixed bed anaerobic biofilm reactor using ant c .........Page 255 7.4.1 The lipopeptide biosurfactant process and its culture medium......Page 204 7.4.5 Analysis of results......Page 209 7.5.2 Experimental design and data generation......Page 210 7.5.4 Formulation of multiobjective optimization problem......Page 211 7.5.5 ANN-NSDE strategy for multiobjective optimization of rhamnolipid process......Page 212 7.5.5.2 ANN-NSDE with ε-constraint......Page 213 7.5.6 Analysis of results......Page 216 7.6 ANN-DE strategy for simultaneous optimization of rhamnolipid biosurfactant process......Page 217 8.6 Multiobjective optimization of cytotoxic potency of a marine macroalgae on human carcinoma cell lines using nonsorting gene .........Page 243 7.6.3 ANN model for rhamnolipid process......Page 218 7.6.4 Simultaneous optimization of rhamnolipid biosurfactant process using ANN-DE......Page 219 7.6.4.2 Simultaneous optimization using a distance minimization function......Page 220 9.6.4 Analysis of results......Page 277 7.7 Summary......Page 223 References......Page 224 8 - Application of stochastic evolutionary optimization techniques to pharmaceutical processes......Page 228 8.2 Quantitative model–based pharmaceutical formulation......Page 229 8.3 Simultaneous optimization of pharmaceutical (trapidil) product formulation using radial basis function network methodology......Page 230 8.3.2 Radial basis function network and its automatic configuration......Page 231 8.3.3 Configuring RBFN to trapidil formulation......Page 234 8.3.4 Simultaneous optimization study......Page 235 8.4.2 Configuring RBFN to pharmaceutical formulation......Page 237 8.4.3.2 RBFN-NSDE with ε constraint......Page 238 8.4.4 Analysis of results......Page 240 8.5.2 Response surface model for pharmaceutical formulation......Page 242 8.6.1 Cytotoxic potency of marine macroalgae and necessity for its quantitative treatment......Page 244 8.6.2 Response surface model for evaluating the cytotoxic potency of marine macroalgae on human carcinoma cell lines......Page 245 8.6.4 NSGA-based multiobjective optimization strategy for enhancing cytotoxic potency of marine macroalgae on human carcinoma cel .........Page 246 References......Page 249 9 - Application of stochastic evolutionary optimization techniques to environmental processes......Page 252 9.2 Modeling and optimization of different environmental processes......Page 253 9.3.1 The importance of biofilm reactors in industry wastewater treatment......Page 256 9.3.2 Experimental biofilm reactor and data generation......Page 257 9.3.3 Mathematical and kinetic models......Page 258 9.3.3.1.1 One-dimensional model......Page 259 9.3.3.2.1 Monod model......Page 260 9.3.3.3 Film thickness......Page 261 9.3.5 Ant colony optimization–based inverse modeling of biofilm reactor......Page 262 9.3.5.2 Biofilm reactor with gravel stones......Page 263 9.3.6 Analysis of results......Page 264 9.4 Process model–based optimization of pharmaceutical industry wastewater treating a fixed bed anaerobic biofilm reactor using .........Page 266 9.4.2 Mathematical and kinetic models......Page 267 9.4.4 Analysis of results......Page 268 9.5.2 ACO implementation strategy......Page 270 9.5.3 Analysis of results......Page 271 9.6 Optimal estimation of wastewater treating biofilm reaction kinetics using hybrid mechanistic-neural network rate function m .........Page 272 9.6.1 Configuration of hybrid mechanistic-neural network rate function model......Page 273 9.6.3 Design and implementation of hybrid neural network rate function model for optimal estimation of biofilm reaction kinetics......Page 274 References......Page 279 10 - Conclusions......Page 284 A......Page 286 D......Page 287 F......Page 288 I......Page 289 N......Page 290 P......Page 291 R......Page 292 U......Page 293 W......Page 294 Back Cover......Page 295