A mobile robot variable pesticide application intelligent decision-making method and system

Abstract

The invention relates to a mobile robot variable pesticide applying intelligent decision-making method and a system. The mobile robot variable pesticide applying intelligent decision-making system comprises a camera, an ultrasonic sensor, a flow sensor and a computer, the camera is used for sending an acquired greenhouse crop image to the computer through a universal serial bus (USB) interface, the ultrasonic sensor is used for measuring the distance of a sprayed target and sending the information of the distance to the computer, the flow sensor is used for measuring actual sprayed pesticide flow, the computer is connected with the camera, the ultrasonic sensor and the flow sensor, a fuzzy neural network decision-making device is configured in the computer, the fuzzy neural network decision-making device is used for obtaining target area, spraying distance and plant diseases and insect pests grade information, preset pesticide applying amount is calculated according to the obtained target area, spraying distance and plant diseases and insect pests grade information, a control amount is calculated and output according to the preset pesticide applying amount, the actual pesticide applying amount is obtained, the actual pesticide applying amount is compared with the preset pesticide applying amount, and the control amount is adjusted.

Description

technical field [0001] The invention relates to the application of fuzzy neural network, in particular to an intelligent decision-making method and system for mobile robot variable pesticide application for row crops in greenhouses. Background technique [0002] At present, pesticide application mainly adopts extensive methods, and most of the application plans are formulated by operators based on experience, which has a heavy workload and is affected by subjective factors. For a long time, my country's pesticide application technology has remained at the level of large-capacity, large-droplet spraying technology, and the low utilization rate of pesticides can easily lead to poisoning of pesticide applicators, seriously restricting the sustainable development of my country's agricultural production. Therefore, variable pesticide application technology is urgently needed in the process of agricultural production to improve the utilization rate of pesticides and reduce the har...

AI Technical Summary

Problems solved by technology

The invention focuses on product structure design, and does not involve variable decision algorithms

In addition, it can be seen from the domestic patents on variable application that the patents for variable application are all new structural designs of various variable application systems. So far, no relevant literature has proposed an ideal decision-making control method for variable application.

[0005] It can be seen from the above related technologies that the existing research has achieved some results, but there are certain limitations.

The fuzzy decision-making method lacks self-learning ability. In the variable pesticide application decision-making system, the decision-making rules cannot be adjusted online, and there is a certain degree of subjectivity in the selection of the membership function of the input and output of the decision maker. The adaptive ability is limited, and it is difficult to obtain ideal variables. Effect of pesticide application; although the neural network decision-making method has a strong self-learning ability, it cannot make good use of existing empirical knowledge in the process of variable spraying decision-making, and the way of knowledge expression and processing is not easy for operators to understand and use

In addition, the above-mentioned related methods fail to effectively integrate the decision-making information that is beneficial to variable pesticide application, such as the crop area to be sprayed, pests and diseases, and distance information. For autonomous mobile robots that work in greenhouses with strong uncertainties, it is difficult to obtain accurate and efficient , Environmentally friendly pesticide application effect

Images