کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6458727 | 1361745 | 2017 | 11 صفحه PDF | دانلود رایگان |
- GEP was developed to predict of the emitter hydraulic performance qvar and CVm.
- The GEPwithout L model was better than GEPwithout S model for qvar.
- The GEPwithout S model was better than GEPwithout L model for CVm.
- The predicted non-pressure-compensating emitters' qvar and CVm were more accurate.
- The GEP approach leads to high model predictability.
The different hydraulic measures of emitter flow variation (qvar) and manufacturer's coefficient of variation (CVm) at different operating pressure (P) and water temperature (T) were determined by measuring the discharge of different labyrinth-channel emitters. Gene expression programming (GEP) was used to model and predict qvar and CVm of the labyrinth emitters. The structural parameters of each labyrinth emitter [namely, trapezoidal unit number (N), height (H), and spacing (S), and path width (W) and length (L)] as well as P and T were considered as independent variables. The accuracy of GEP models was evaluated by their coefficient of determination (R2), root-mean-square error (RMSE), overall index of model performance (OI), and mean absolute error (MAE). Results of GEP applications established that L and S were the least important variables affecting qvar and CVm, respectively, while N and H were the most important variables. For qvar, the GEPwithout L model gave higher R2 and OI and lower RMSE and MAE than those of the GEPwithout S model. Conversely, for CVm, R2 and OI of the GEPwithout L model were lower and its RMSE and MAE were higher than the corresponding parameters of the GEPwithout S model. Overall, our results indicated that the performance of the developed GEP models were better at predicting qvar and CVm for non-pressure-compensating emitters than pressure-compensating ones. The GEP approach can be a good tool to predict the hydraulic performance of labyrinth emitters.
Journal: Computers and Electronics in Agriculture - Volume 142, Part A, November 2017, Pages 450-460