Optimizing the aeration performance of a perforated pooled circular stepped cascade aerator using hybrid ANN-PSO technique

• A perforated pooled circular stepped cascade (PPCSC) aerator was developed with maximum aeration efficiency using hybrid ANN-PSO technique. • A 3–6-1 ANN model coupled with particle swarm optimization (PSO) technique was used for optimizing the geometric and dynamic parameters of PPCSC aerator. • The optimized values of the consecutive step width ratio, the ratio of perforation diameter to the bottom-most radius, and the water flow rate were found to be 1.15, 0.0027 and 0.0167 m 3 /s, respectively. • The developed PPCSC aerator showed a 25.79% and 68.89% increase in the SAE as compared to the PCSC and CSC aerators, respectively. Artificial aeration system for aquaculture ponds becomes essential to meet the oxygen requirement posed by the aquatic species. The performance of an aerator is generally measured in terms of standard aeration efficiency (SAE), which is significantly affected by the different geometric and dynamic parameters of the aerator. Therefore, to enhance the aeration performance of an aerator, these parameters need to be optimized. In the present study, a perforated pooled circular stepped cascade (PPCSC) aerator was developed, and the geometric and dynamic parameters of the developed aerator were optimized using the hybrid ANN-PSO technique for maximizing its aeration efficiency. The geometric parameters include consecutive step width ratio ( W i-1 /W i ) and the perforation diameter to the bottom-most radius ratio ( d/R b ), whereas the dynamic parameter includes the water flow rate ( Q ). A 3–6-1 ANN model coupled with particle swarm optimization (PSO) approach was used to obtain the optimum values of geometric and dynamic parameters corresponding to the maximum SAE. The optimal values of the consecutive step width ratio ( W i-1 /W i ), the perforation diameter to the bottom-most radius ratio ( d/R b ), and the water flow rate ( Q ) for maximizing the SAE were found to be 1.15, 0.002 7 and 0.016 7 m 3 /s, respectively. The cross-validation results showed a deviation of 3.07 % between the predicted and experimental SAE values, thus confirming the adequacy of the proposed hybrid ANN-PSO technique.