Distribution And Performance Testing Of Key Equipment In Farmland Irrigation Systems

In the process of agricultural irrigation,sensors are generally placed randomly in the field according to experience which result in the wasting of sensors,rising cost and serious waste of water resources under uneven irrigation.So we optimize the location of the sensor to improve this situation;In addition,the motor is the core power equipment of the irrigation system,and ensuring its normal operation is of great significance to the irrigation system.Due to the frequent start of the motor during the irrigation process,poor working conditions and other reasons,the motor bearings often malfunction.If they are not dealt with in time,the motor may be blocked or even burned,which will not only affects the irrigation but also aggravates the economic burden on farmers.Traditional detection methods,such as negative selection algorithm,has low fault detection rates due to the existence of black hole which can not be detected by themselves.Due to the low fault detection rates of motor bearing in irrigation process,we optimize the traditional algorithm in order to improve the fault detection rates.The artificial neural network algorithm(ANN)is used to obtain the soil moisture distribution map of the experimental area.The genetic algorithm(GA)is used to optimize the resetting of the humidity sensor's position and finally determine the optimal placement position of the sensor.The immune clone optimization algorithm is used to optimize the traditional negative selection algorithm,and the effective detector set is extended to improve the bearing fault detection rates.The sensor position optimization can not only save water and reduce the cost but also make irrigation more uniform;The improvement of bearing fault detection rates are of great significance to the normal operation of irrigation system.