Discrete Optimization on Unsteady Pressure Fluctuation of a Centrifugal Pump Using ANN and Modified GA

Abstract

Pressure fluctuation due to the rotor-stator interaction in turbomachinery is unavoidable, inducing strong vibration and even shortening the lifecycle. The investigation on optimization method of an industrial centrifugal pump was carried out to reduce the pressure fluctuation intensity. Considering the time-consuming transient calculation of unsteady pressure, a novel optimization strategy was proposed by discretizing design variables and genetic algorithm. Four highly related design parameters were chosen, and 40 transient sample cases were generated and simulated using an automatic simulation program. Furthermore, a modified discrete genetic algorithm (MDGA) was proposed to reduce the optimization cost by unsteady simulation. For the benchmark test, the proposed MDGA showed a great advantage over the original genetic algorithm in terms of searching speed and could deal with the discrete variables effectively. After optimization, an improvement in terms of the performance and stability of the inline pump was achieved.