公开(公告)号：US11953023B2

公开(公告)日：2024-04-09

申请号：US17466755

申请日：2021-09-03

Applicant: KOREA INSTITUTE OF INDUSTRIAL TECHNOLOGY

Inventor： Jin Hyuk Kim ,  Sung Kim ,  Sang Bum Ma

IPC: G06F30/27 ,  F04D1/06 ,  F04D7/04 ,  F04D29/22 ,  F04D29/30 ,  F04D29/44 ,  G06F30/17 ,  G06N3/086

CPC classification number: F04D29/445 ,  F04D1/06 ,  F04D7/04 ,  F04D29/225 ,  F04D29/30 ,  G06F30/17 ,  G06F30/27 ,  G06N3/086

Abstract: The present disclosure relates to a two-vane pump for wastewater and a design method of a two-vane pump for wastewater using machine learning, and more particularly, a design method of a two-vane pump using machine learning capable of having efficiency of a target head and performing optimal design for sizes of solids that can pass through and a two-vane pump for wastewater according to the machine learning. According to the present disclosure, there is provided a design method of two-vane pump for wastewater using machine learning, including: a) setting an objective function; b) setting design variables of the impeller and volute for deriving the set objective function and a range of each design variable; c) deriving a plurality of experimental points including values of the design variables within the range of the design variable; d) generating an input value by calculating the value of the objective function through numerical analysis of each of the derived experimental points; e) constructing a surrogate model through machine learning for the input value; and f) deriving an optimal design of the two-vane pump for wastewater from the constructed surrogate model.