Introducing Non-Hierarchical RSM and MIGA for Performance Prediction and Optimization of a Centrifugal Pump under the Nominal Condition

In order to improve the operation performance of the multi-stage double-suction centrifugal pump and reduce the internal energy loss of the pump, this paper proposes a single-objective optimization design method based on the non-hierarchical response surface methodology (RSM) and the multi-island genetic algorithm (MIGA). Nine parameters, such as the blade outlet width and blade wrap angle, were used as design variables, and the optimization objective was efficiency under design conditions. In total, 149 sets of valid data were obtained under the Latin hypercube sampling method (LHS), the corresponding thresholds were set for efficiency and head, and 99 sets of valid data were obtained. A cross-validation analysis of the sieved data was carried out based on non-hierarchical RSM, global optimization of the efficiency was carried out using MIGA, and numerical verification was carried out via CFD. The research results show that compared with hierarchical RSM, non-hierarchical RSM can approximate the nonlinear relationship between the objective function and the design variables with higher accuracy, and the model fitting R2 value was 0.919. The efficiency was improved by 3.717% after optimization. The overall prewhirl of the impeller inlet after optimization decreased, the internal speed of the volute significantly improved, the large-area vortex at the volute and the outlet pipe was eliminated, the impact loss at the volute separating tongue disappeared, and the overall hydraulic performance of the pump was improved. The total entropy output value of the optimized pump was reduced by 4.79 (W/K), mainly concentrated on the reduction in the entropy output value of the double volute, and the overall energy dissipation of the pump was reduced.

[1]  M. Shojaeefard,et al.  Experimental and numerical optimization of a centrifugal pump volute and its effect on head and hydraulic efficiency at the best efficiency point , 2022, Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science.

[2]  Zuchao Zhu,et al.  An Energy Consumption Improvement Method for Centrifugal Pump Based on Bionic Optimization of Blade Trailing Edge , 2022, SSRN Electronic Journal.

[3]  J. Ran,et al.  Multi-objective parameter optimization of turbine impeller based on RBF neural network and NSGA-II genetic algorithm , 2021, Energy Reports.

[4]  Hai-Tao Liu,et al.  Parameter optimization of bidirectional re-entrant auxetic honeycomb metamaterial based on genetic algorithm , 2021, Composite Structures.

[5]  Thomas Olofsson,et al.  Application of Regression and ANN Models for Heat Pumps with Field Measurements , 2021, Energies.

[6]  K. Alawadhi,et al.  Design and Optimization of a Centrifugal Pump for Slurry Transport Using the Response Surface Method , 2021, Machines.

[7]  He Huang,et al.  Flow field analysis of multi-stage middle-open centrifugal pump inter-stage flow passage , 2020, E3S Web of Conferences.

[8]  Xueping Gao,et al.  Parameter analysis and performance optimization for the vertical pipe intake-outlet of a pumped hydro energy storage station , 2020 .

[9]  Wenjie Wang,et al.  Artificial Neural Networks Approach for a Multi-Objective Cavitation Optimization Design in a Double-Suction Centrifugal Pump , 2019, Processes.

[10]  Jianping Yuan,et al.  Flow loss analysis of a two-stage axially split centrifugal pump with double inlet under different channel designs , 2019, Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science.

[11]  Jie Chen,et al.  Kriging-assisted design optimization of the impeller geometry for an automotive torque converter , 2018 .

[12]  Peng Yang,et al.  Application of response surface methodology and desirability approach to investigate and optimize the jet pump in a thermoacoustic Stirling heat engine , 2017 .

[13]  S. Yuan,et al.  Effect of Baffles in Between Stages on Performance and Flow Characteristics of a Two-Stage Split Case Centrifugal Pump , 2017 .

[14]  Fabio Polonara,et al.  Assessment of the Energy Performance of an Air Source Heat Pump by Response Surface Methodology , 2017 .

[15]  Chun Jie Wang,et al.  A Monte Carlo simulation based inverse propagation method for stochastic model updating , 2015 .

[16]  Peng Wang,et al.  Multi-objective optimization of a mixed-flow pump impeller using modified NSGA-II algorithm , 2015 .

[17]  M. Nataraj,et al.  Analyzing pump impeller for performance evaluation using RSM and CFD , 2014 .

[18]  Tan Lei,et al.  Development of a pump-turbine runner based on multiobjective optimization , 2014 .

[19]  Svetlana Ibrić,et al.  Combined Application of Experimental Design and Artificial Neural Networks in Modeling and Characterization of Spray Drying Drug: Cyclodextrin Complexes , 2014 .

[20]  Chris Lacor,et al.  Optimization of the cyclone separator geometry for minimum pressure drop using mathematical models and CFD simulations , 2010 .

[21]  Lu Deng,et al.  Bridge Model Updating Using Response Surface Method and Genetic Algorithm , 2010 .

[22]  Richard DeLoach,et al.  The Role of Hierarchy in Response Surface Modeling of Wind Tunnel Data , 2010 .

[23]  Koji Koyamada,et al.  Interactive hierarchical RSM applied to parameter optimization of photonic crystal nanocavities , 2009, 2009 IEEE 13th International Symposium on Consumer Electronics.

[24]  Behrooz Keshtegar,et al.  Reliability analysis of pumping station for sewage network using hybrid neural networks - genetic algorithm and method of moment , 2021 .

[25]  Ryozo Ooka,et al.  Study on optimum design method for pleasant outdoor thermal environment using genetic algorithms (GA) and coupled simulation of convection, radiation and conduction , 2008 .