To broaden the efficient operating zone and increase the energy efficiency of a multi-stage double-suction centrifugal pump, a multi-component and multi-condition optimization design method involving high-precision performance predictions, a flow loss visualization technique based on entropy production theory, and machine learning is proposed. First, the accuracy of the baseline pump numerical methodology is verified via a grid convergence analysis and experiments. Thereafter, nine design parameters of the impeller and double volute are selected as design variables. Subsequently, 150 designs are created according to the Latin hypercube sampling method (LHS) and numerically simulated using an automatic simulation program. A backpropagation neural network (BPNN) and a multi-objective genetic algorithm (MOGA) are adopted to maximize the efficiency at 0.6Q_d, 1.0Q_d, and 1.2Q_d. Finally, the optimal results are verified via numerical calculations and analyzed. The results indicate that the efficiency of the optimized pump is increased by 2.05%, 3.56%, and 5.36% at 0.6Q_d, 1.0Q_d, and 1.2Q_d, respectively. The comparative analysis of the energy characteristics reveals that the improved performance of the optimized pump can be attributed to the improved matching between the rotor and stator. This research further demonstrates the accuracy and reliability of the optimization method using an artificial neural network (ANN).

Cavitation is one of the most important performance of centrifugal pumps. However, the current optimization works of centrifugal pump are mostly focusing on hydraulic efficiency only, which may result in poor cavitation performance. Therefore, it is necessary to find an appropriate solution to improve cavitation performance with acceptable efficiency. In this paper, to improve the cavitation performance of a centrifugal pump with a vaned diffuser, the influence of impeller geometric parameters on the cavitation of the pump is investigated using the orthogonal design of experiment (DOE) based on computational fluid dynamics. The impeller inlet diameter D₁, inlet incidence angle Δβ, and blade wrap angle φ are selected as the main impeller geometric parameters and the orthogonal experiment of L₉(3*3) is performed. Three-dimensional steady simulations for cavitation are conducted by using constant gas mass fraction model with second-order upwind, and the predicated cavitation performance is validated by laboratory experiment. The optimization results are obtained by the range analysis method to improve cavitation performance without obvious decreasing the efficiency of the centrifugal pump. The internal flow of the pump is analyzed in order to identify the flow behavior that can affect cavitation performance. The results show that D₁ has the greatest influence on the pump cavitation and the final optimized impeller provides better flow distribution at blade leading edge. The final optimized impeller accomplishes better cavitation and hydraulic performance and the NPSHR decreases by 0.63m compared with the original one. The presented work supplies a feasible route in engineering practice to optimize a centrifugal pump impeller for better cavitation performance.

This paper seeks to predict the performance of the side channel pump by considering the influences of different wrapping angles. Firstly, three pump cases 1, 2 and 3 are modeled with wrapping angles 15°, 30° and 45°, respectively. Secondly, different physical parameters comprising exchanged mass flow, pressure and velocity distributions are plotted at the best efficiency point (Q_BEP) to analyze the internal flow characteristics. Since the flow exchange times depend on the size of the wrapping angle, the size of the wrapping angle has significant effects on the pump head performance. Case 1 with the smallest wrapping angle recorded the largest head improvement at all operating conditions compared to case 2 and case 3. Case 1 at Q_BEP attained a head coefficient increase of about 9.8% and 38.6% compared to that of case 2 and case 3, respectively. However, the size of the wrapping angle had a slight effect on the pump efficiency; thus, case 1 still predicted a marginal increase in efficiency compared to case 2 and case 3 at all operating conditions. Lastly, the numerical simulations were validated with experimental data after manufacturing pump case 2.

Double-suction centrifugal pumps are widely used in industrial and agricultural applications since their flow rate is twice that of single-suction pumps with the same impeller diameter. They usually run for longer, which makes them susceptible to cavitation, putting the downstream components at risk. A fast approach to predicting the Net Positive Suction Head required was applied to perform a multi-objective optimization on the double-suction centrifugal pump. An L₃₂ (8⁴) orthogonal array was designed to evaluate 8 geometrical parameters at 4 levels each. A two-layer feedforward neural network and genetic algorithm was applied to solve the multi-objective problem into pareto solutions. The results were validated by numerical simulation and compared to the original design. The suction performance was improved by 7.26%, 3.9%, 4.5% and 3.8% at flow conditions 0.6Q_d, 0.8Q_d, 1.0Q_d and 1.2Q_d respectively. The efficiency increased by 1.53% 1.0Q_d and 1.1% at 0.8Q_d. The streamline on the blade surface was improved and the vapor volume fraction of the optimized impeller was much smaller than that of the original impeller. This study established a fast approach to cavitation optimization and a parametric database for both hub and shroud blade angles for double suction centrifugal pump optimization design.