New Approaches to the Identification of Semi-mechanistic Process Models

Abstract

In process engineering, first-principles models derived from dynamic mass, energy and momentum balances are mostly used. When the process is not perfectly known, the unknown parts of the first principles model should be represented by black-box models, e.g. by neural networks. This paper is devoted to the identification and application of such hybrid models. For the identification of the neural network elements of a hybrid model two methods are investigated in this article: back-propagation algorithm and direct optimization. We study three optimization algorithms: Sequential Quadratic Programming, Evolutionary Strategy and Particle Swarm Optimization. The different algorithms are compared in a case study, the baker’s yeast production process.