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

Demeulenaere, Alain; Purwanto, Aji; Ligout, Alban; Hirsch, Charles; Dijkers, Ronal; Visser, F.C.

doi:10.1115/fedsm2005-77487

Cited by 18 publications

(17 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is well known that optimization methods based on gradients techniques are efficient in terms of convergence rate, but do not guarantee to produce the global optimum [4]. On the other hand, genetic algorithms offer the advantage of enhancing the probability of reaching the global optimum, but may require thousands of iterations [11]. Their coupling with a three-dimensional Navier-Stokes solver cannot be considered under the framework of an industrial design process.…”

Section: Initial Runner Designmentioning

confidence: 99%

See 1 more Smart Citation

Optimal design of axial hydro turbine for micro hydropower plants

Derakhshan¹,

Kasaeian²

2012

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Abstract. In our country we have enormous low head potation flows in agricultures and aquacultures with almost fix flow rates that can be used as micro hydro power plants for producing energy. But the main problem is the high capital price per kW. Therefore there is needed to design a simple machine with a good runner for covering the various potential flows. In this paper an axial hydro turbine has designed for some low heads micro potential flow with flow rates ranged from 50 lit/sec to 150 lit/sec and heads ranged from 1 m to 5 m. The initial runner designed using classical methods and then the runner geometry has been optimized by evolutionary optimization algorithms. The final design has been simulated by a commercial flow solver in a various blade positions. The results showed a wide range characteristic curve with a wide range high efficiency.

show abstract

Section: Initial Runner Designmentioning

confidence: 99%

“…Each design iteration starts with the neural network learning. As the design proceeds, the database grows, leading to improvements of the approximate relation and therefore to a better localization of the real optimum [11]. The geometry parameterization is a critical element in the success of any shape optimization method.…”

Section: Initial Runner Designmentioning

confidence: 99%

Optimal design of axial hydro turbine for micro hydropower plants

Derakhshan¹,

Kasaeian²

2012

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Demeulenaere et al [1] investigated an optimization process on centrifugal pumps using Fine/ Design 3D environment of Numeca software and genetic algorithms. They tried to increase efficiency and head and decrease the NPSHr at two different flow rates and finally showed that the new blade geometry should have more curvature in the camber line definition.…”

Section: Introductionmentioning

confidence: 99%

Sensitivity analysis of the effective centrifugal pump parameters using the EFAST method

Safikhani

2017

Scientia Iranica

View full text Add to dashboard Cite

In the present study, the effective parameters of centrifugal pumps are investigated using the EFAST Sensitivity Analysis (SA) method. The SA is performed using GMDH type artificial neural networks (ANN) which are based on validated numerical data of flow field in centrifugal pumps. There are four design variables namely: leading edge angle of blades on hub section (β 1 Hub ), leading edge angle of blades on shroud section (β 1 Shroud ), trailing edge angle of blades (β 2 ), and the stagger angle of blades on mid span (γ mid ) and there are two objective functions namely: efficiency () and the required NPSH of impeller. The results show that among design variables, β 2 has the highest effect on variations of  (46%) and NPSH (45%). Except β 2 , β 1 Hub and γ mid has the highest effect on NPSH (33%) and  (28%) respectively. The effects of all of the design variables on objective functions are shown in the results.

show abstract

“…Optimization of centrifugal pumps is a multi-objective optimization problem rather than a single objective optimization problem that has been considered so far in the literature. Demeulenaere et al (2005) investigated an optimization process on centrifugal pumps using Fine/Design 3D environment of Numeca software and genetic algorithms. They tried to increase efficiency and head rise and decrease the NPSHr at two different flow rates and finally showed that the new blade geometry should have more curvature in the camber line definition.…”

Section: Introductionmentioning

confidence: 99%

Pareto Based Multi-Objective Optimization of Centrifugal Pumps Using CFD, Neural Networks and Genetic Algorithms

Safikhani

Khalkhali

Farajpoor

2011

Engineering Applications of Computational Fluid Mechanics

View full text Add to dashboard Cite

Increase of efficiency () and decrease of the required NPSH simultaneously are important objectives in the design of centrifugal pumps. In the present study, multi-objective optimization of centrifugal pumps is performed in three steps. In the first step,  and NPSHr in a set of centrifugal pumps are numerically investigated using commercial software NUMECA. Two meta-models based on the evolved Group Method of Data Handling (GMDH) type neural networks are obtained. The second step is the modeling of  and NPSHr with respect to geometrical design variables. Finally, using obtained polynomial neural networks, multi-objective genetic algorithms are used for Pareto based optimization of centrifugal pumps considering two conflicting objectives,  and NPSHr. It is shown that some interesting and important relationships as useful optimal design principles involved in the performance of centrifugal pumps can be discovered by Pareto based multi-objective optimization of the obtained polynomial meta-models representing their  and NPSHr characteristics. Such important optimal principles would not have been obtained without the use of both GMDH type neural network modeling and the Pareto optimization approach.

show abstract

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

Cited by 18 publications

References 2 publications

Optimal design of axial hydro turbine for micro hydropower plants

Optimal design of axial hydro turbine for micro hydropower plants

Sensitivity analysis of the effective centrifugal pump parameters using the EFAST method

Pareto Based Multi-Objective Optimization of Centrifugal Pumps Using CFD, Neural Networks and Genetic Algorithms

Contact Info

Product

Resources

About