Multi-Condition Optimization of Cavitation Performance on a Double-Suction Centrifugal Pump Based on ANN and NSGA-II

Abstract

Double-suction centrifugal pumps form an integral part of power plant systems in maintaining operational stability. However, there has been a common problem of achieving a better cavitation performance over a wider operating range because the traditional approach for impeller design often leads to the design effect not meeting the operational needs at off-design conditions. In addressing the problem, an optimization scheme was designed with the hub and shroud inlet angles of the double-suction impeller to minimize the suction performance at non-design flow conditions. A practical approach that speeds up the cavitation simulation process was applied to solve the experimental design, and a multi-layer feed forward artificial neural network (ANN) was combined with the non-dominated sorting genetic algorithm II to solve the multi-objective problem into three-dimensional (3D) Pareto optimal solutions that meet the optimization objective. At the design point, the suction performance was improved by 6.9%. At non-design flow conditions, the cavitation performance was improved by 3.5% at 1.2Qd overload condition, 4% at 0.8Qd, and 5% at 0.6Qd. Additionally, there was significant reduction in the attached cavity distribution in the impeller and suction domains when the optimized model was compared to the original model at off-design points. Finally, the optimization established a faster method for a three-objective optimization of cavitation performance using ANN and 3D Pareto solutions.

Cavitation Prevention Potential of Hydromechanical Pressure Compensation Independent Metering System with External Active Load

“…It is clear that the pressure P b is related to the variable parameter µ when the head chamber pressure P a is greater than negative atmospheric pressure −P at , and the pressure P b is related to the variable parameter F L when the head chamber pressure P a is less than negative atmospheric pressure −P at . The meter-out pressure P a of retraction working mode can be calculated by the Equations ( 20) and (22), it is clear the pressure P a is related to the variable parameter µ when the rod chamber pressure P b is greater than negative atmospheric pressure −P at , and the pressure P q is related to the variable parameter F L when the rod chamber pressure P b is less than negative atmospheric pressure −P at .…”

“…From the two equations, it is clear that the pressure Pb is a constant when the meter-in pressure Pa is greater than the pressure −Pat, and the pressure Pb is related to the variable parameter FL when the meter-in pressure Pa is less than the pressure −Pat. The meter-out pressure Pa with retraction working mode can be calculated by Equations (20) and (22), it is clear that the pressure Pa is a constant when the meter-in pressure meter-in pressure Pb is greater than the pressure −Pat, and the pressure Pa is related to the variable parameter FL when the meter-in pressure meter-in pressure Pb is less than the pressure −Pat.…”

“…If the rod chamber pressure P b is less than the negative atmospheric pressure −P at , the pressure P b equals −P at , the pressure P a can also be calculated by Equation (22).…”

“…If the pressure falls below the vapor pressure of the fluid, the steam bubble is created, and the bubbles reach regions of higher pressure, it will be generated pressure waves and caused erosion [21]. The cavitation may occur in the pumps, valves, actuators, and pipes of the hydraulic system, and it will result in severe damage to the hydraulic components and the whole hydraulic system [22][23][24][25].…”

Many-Objective Hybrid Optimization Method for Impeller Profile Design of Low Specific Speed Centrifugal Pump in District Energy Systems

“…Hence, it is of great significance to optimize the efficiency and suction capacity of LSSCP for energy saving and promoting sustainability of district energy systems. Among all components in LSSCP, the impeller has the greatest impact on the performance of LSSCP since the energy is generated through it [7,8]. Therefore, the key to optimize the performance of LSSCP is the impeller profile.…”