Intelligent Control Technology and System of on-Demand Irrigation Based on Multiobjective Optimization

Abstract

To solve the problem that the parameters of the multiple-input multiple-output (MIMO) irrigation system are difficult to control accurately, an on-demand irrigation control experimental device was developed. The main input parameters of the device are the opening degree of the main pipe valve, the opening frequency of and the pump station, the opening degree of the branch pipeline valve with the different combinations of different opening degrees. Based on these input parameters, four types of experimental methods were designed, and a total of 1695 groups of experiments were designed. The results show that the different opening degree combinations of the branch electric valve cannot significantly affect the flow of the branch pipeline but also significantly affect the pressure of the main pipeline. The prediction error of the operating frequency of the pump station and the opening degree of the branch valve were regarded as the objective function. Six intelligent prediction models were constructed, which are Back Propagation (BP), support vector regression (SVR) Linear, SVR-RBF, SVR-Poly, random forest (RF) and eXtreme Gradient Boosting (XGBoost), respectively. The results show that the XGBoost is the best model among the six models. For the opening degree of three branch valves, the mean absolute error (MAE) between the predicted value and actual value is less than 3.3%, the mean square deviation (RMSE) between the predicted values and actual values is less than 4.5%, and the R2 of between the predicted values and actual values is greater than 0.990. The control models and system can meet the needs of an on-demand irrigation system.

Keywords

• pressure and flow
• machine learning
• control system
• Raspberry Pi