Intelligent workshop combined scheduling control method

Abstract

The invention relates to an intelligent workshop combination scheduling control method, which comprises the following steps: forming a new combined scheduling rule by adopting a tree-shaped structure,and determining composition elements of the combined scheduling rule, including a terminator set and a function set; and mining the combined scheduling rule based on a GP (Genetic Program) algorithm;carrying out genetic operations such as replication, crossover, variation and the like on each generation of GP individuals, and carrying out an evolution process of the GP population; establishing aGP individual evaluation model by adopting a mode based on SBO (Sequence Based Optimization); operating the GP individual evaluation model to obtain the fitness value of each GP individual; judging whether an evolution termination condition is met, if so, ending evolution of the GP population, and outputting a final GP individual, namely a combination scheduling rule obtained through final mining; and if not, continuing to evolve the population. Compared with the prior art, the intelligent workshop combination scheduling control method has the advantages that the production performance of theproduction line is improved, and real-time scheduling along with the change of the working condition of the production line is met.

Description

technical field [0001] The invention relates to the technical field of production automation scheduling, in particular to an intelligent workshop combination scheduling control method. Background technique [0002] With the rapid development of information technology, the manufacturing industry has become the pillar industry of the national economy and the mainstream of the global high-tech industry. Production scheduling is the core content of manufacturing management and the key to improving the core competitiveness of enterprises. The production scheduling problem is a decomposable processing task, under certain constraints (such as process routing, resources, delivery time, etc.), how to allocate the most suitable machine for each process and determine the The processing order of all tasks to be processed before the group is used to optimize the production line's productivity, average processing cycle, delivery rate and other performance indicators. Due to the high com...

AI Technical Summary

Problems solved by technology

The above scheduling methods all use simple heuristic rules as the scheduling policy set. The scheduling rules have the advantages of easy implementation, low time complexity, and timely response to dynamic changes. They are very suitable for solving highly complex dynamic environments such as intelligent workshops. However, the simple scheduling rule only utilizes limited production scheduling process information, and cannot fully describe the state of the production scheduling process, and its optimization performance is often poor

[0005] For the intelligent workshop scheduling problem, the above-mentioned traditional optimization methods are often difficult to meet the requirements of production performance and real-time scheduling at the same time. The intelligent optimization algorithm has a good effect on optimizing the performance indicators, but due to the high time cost of the algorithm solution, it cannot meet the real-time requirements.

Scheduling rules are easy to implement, have low time complexity, and have the ability to respond to dynamic changes in a timely manner. However, traditional simple scheduling rules often only use limited production scheduling process information and cannot fully describe the state of the production scheduling process. , so its optimization performance is often poor

Images