Neural network applications in the selective separation of biological products

Abstract

<span style="font-size:11.0pt;line-height:115%; font-family:" calibri","sans-serif";mso-fareast-font-family:"dejavu="" sans";="" mso-bidi-font-family:mangal;mso-bidi-theme-font:minor-bidi;mso-ansi-language:="" en-us;mso-fareast-language:en-us;mso-bidi-language:ar-sa"="">Neural networks have been applied to adsorptive separation, notably chromatography, and aqueous two-phase separation. Phenomenological models for them are either oversimplified or are too complex for easy design, scale-up and on-line implementation. Adsorptive separations have been described by simple networks with topologies such as 3-2-3 and 4-4-1. Aqueous two-phase separations are more complex. In a study of the recovery of selected proteins from a multi-component solution, a hierarchical network with three subnetworks feeding two hidden layers of neurons was needed. The network was flexible, easier to solve than some phenomenological models, and could be integrated with an expert system for on-line optimisation. The application of neural analysis to product recovery methods is an important component of bioprocess optimisation. The combination of neural networks with expert systems enables the development of integrated systems for optimal design and operation of fermentation-cum-recovery plants.</span>