Gene expression programming approach for modeling the hydraulic performance of labyrinth-channel emitters

摘要: GEP was developed to predict of the emitter hydraulic performance qvar and CVm.The GEPwithout L model better than S for qvar.The predicted non-pressure-compensating emitters CVm were more accurate.The approach leads high predictability. The different measures flow variation (qvar) manufacturers coefficient (CVm) at operating pressure (P) water temperature (T) determined by measuring discharge labyrinth-channel emitters. Gene expression programming (GEP) used labyrinth structural parameters each [namely, trapezoidal unit number (N), height (H), spacing (S), path width (W) length (L)] as well asP T considered independent variables. accuracy models evaluated their determination (R2), root-mean-square error (RMSE), overall index (OI), mean absolute (MAE). Results applications established that least important variables affecting CVm, respectively, while N H most For qvar, gave higher R2 OI lower RMSE MAE those model. Conversely, its corresponding Overall, our results indicated predicting pressure-compensating ones. can be a good tool