Design and Optimization of an Industrial Pump: Application of Genetic Algorithms and Neural Network

This paper presents an integrated environment FINE^TM/Design3D developed for the optimization of turbomachinery blade shapes. The methodology relies on the interaction between a genetic algorithm, an artificial neural network, a database and user generated objective functions and constraints. The optimization is coupled to the FINE^TM/Turbo environment of NUMECA. The present paper focuses on the application of the multipoint optimization algorithm to the design of an industrial pump. The large range of mass flow over which the pump should operate motivates the use of multipoint optimization. The optimization exercise focuses on the efficiency, the head and the NPSH at two operating conditions characterized by largely different mass flows.