Intelligent scheduling method for multi-machine cooperative operation based on NSGA-III and improved ant colony algorithm

Aiming at the problems of over-reliance on traditional manual harvest operation experience and lack of dispatching planning scheme under the environment of insufficient grain trucks in agricultural harvest scenario. A multi-objective combined optimization intelligent scheduling model of harvesters and grain transport vehicles was established to save agricultural machinery resources, and improve the overall efficiency of harvesters and transport vehicles, to meet the constraints of plot location, task number, operation time window, and path planning. The model was solved by an intelligent search algorithm, and an intelligent scheduling method of command multi-machine cooperative operation based on NSGA-III and an improved ant colony algorithm was proposed. When the harvester is full loaded, there is non harvest area on one side of the grain unloading cylinder, there the grain truck can not reach and unload cooperatively. To solve this problem, the prediction method of early unloading point was designed and further improved by determining the workload constraints and time constraints. When solving the model, the reference point setting in NSGA-III can ensure the diversity of the population. And then the ant colony algorithm that sets the detour vertex instead of the grid map is used to solve the optimal command call time and the optimal unloading position, and then the dynamic time window and the local dynamic obstacle avoidance path of the transport machine are divided. Finally, the designed model can output an accurate scheduling planning scheme with deployment information. It can be seen from the simulation test that the scheduling model established, and the solution algorithm designed in this research can obtain many groups of good optimization results. Moreover, it can make the unproductive waiting time of harvester 0, and minimize the transfer distance and number of grain transporters. This method can be combined closely with the practical application of unmanned farms, which lays a theoretical foundation for improving the efficiency of multi-machine cooperative operations.