Predicting the Imposed Forces on the Tines and Tractor Fuel Consumption during Subsoiling Operation Using Adaptive Neuro-Fuzzy Inference System (ANFIS)

In this research, the adaptive neuro-fuzzy inference system was used for predicting the imposed forces on the tines and tractor fuel consumption during subsoiling operation. The draft and vertical forces imposed on subsoiling tines and tractor fuel consumption were measured under the effect of tine type (subsoiler and paraplow), tillage depth (30, 40 and 50 cm) and forward speed (1.8, 2.3, 2.9 and 3.5 km/h). The field data were used to create the regression and ANFIS models for predicting the studied parameters; the results obtained from applying two models were compared with each other. The field results showed that all independent variables were effective on the studied parameters. Increase in forward speed and tillage depth resulted increase in draft force, vertical forces, and also fuel consumption. Moreover, from the point of consumption of fuel, the paraplow tine was more profitable than subsoiler tine. The results of ANFIS part showed that draft force, vertical force, and fuel consumption, the membership functions of Gaussmf, Trimf and dsigmf, with the mean square error of 0.0156, 0.0231 and 0.0212 also correlation coefficient of 0.999, 0.989 and 0.991, respectively, were the best models for prediction. ANFIS models were found more accurate than regression models, and it could be possible to calculate the model outlet for a special inlet using ANFIS outlet surfaces.