Optimization control method for multi-procedure conveyor belt feeding processing station system with flexible sites

Abstract

The invention discloses an optimization control method for multi-procedure conveyor belt feeding processing station system with flexible sites, which is characterized in that: a hierarchical decision making system with switching control and forward-looking cooperative control is constructed in conjunction with the concept of hierarchical control according to the features of a flexible site switching working mode; at first, an intelligent learning algorithm, which is suitable for average and discounted unified performance criteria, is constructed for the switching control of flexible sites using a performance potential theory to realize decision optimization, thus solving the problem of inter-procedure coordination; and secondly, the problem of intra-procedure cooperation is solved for forward-looking control using a multi-agent learning algorithm. According to the invention, the concept of hierarchical control is introduced to contrast a two-layer control system, thus enhancing the processing efficiency of system, improving the inter-procedure equilibrium and increasing the workpiece completion rate of system.

Description

technical field [0001] The invention relates to the field of automatic control, in particular to a layered optimization control method for a multi-process conveyor belt material processing station with a flexible station. Background technique [0002] In the actual production of manufacturing enterprises, there is a kind of production line with production and processing stations as the main body of processing, and the processing stations are processed by conveying workpieces by conveyor belts. Such a system is called Conveyor-serviced production station (CSPS) ). Due to the needs of specialization and scale, the production line often has multiple processes, and one process is composed of multiple CSPS processing stations, which is called a multi-process CSPS system. In the multi-process CSPS system, there are two kinds of CSPS processing stations, which are general stations and flexible stations. Generally, the site is equipped with a buffer warehouse for this process, whi...

AI Technical Summary

Problems solved by technology

[0003] 1. If all sites are considered as a whole (including all general sites and flexible sites), that is, a human agent performs centralized control, and all states of all sites are combined to form a system state, and the actions of each site are combined to form a system action ( The look-ahead distance of the general site, the process selection and the look-ahead distance of the flexible site) will inevitably cause the system state space and action set to be too large, resulting in the "curse of dimensionality" and "difficult modeling" problems. The number and number of processes will increase exponentially

[0004] 2. In the multi-process CSPS system, the distribution of workpiece arrival rates in each process is different, and the number of stations in each process also affects the arrival rate of workpieces in adjacent downstream processes, resulting in incoordination between processes

[0005] 3. The communication ability or perception ability between sites is limited, and generally only the information of the adjacent environment can be observed or perceived

Images