Process synthesis of biodiesel production plant using artificial neural networks as the surrogate models

摘要: Abstract Biodiesel is an attractive biofuel because it can be used directly with the traditional petro diesel engines, either as a substitute or blending component. There are several alternatives that to produce biodiesel. In this work, we developed superstructure optimization model synthesize optimum biodiesel production plant, i.e., one gives minimum net present sink. To reduce computational cost of solving resulting disjunctive programming, surrogate models utilizing artificial neural networks (ANNs), have been replace unit operation, thermodynamics and mixing models. The solution alkali-catalyzed reactor (obtained in five CPU seconds) has total sink about $41 million, which differs less than percent from result obtained by modeling process simulator. However, level accuracy required large amount data train ANNs.