Scheduling method for flexible job shop

Abstract

The invention provides a scheduling method for a flexible job shop, and belongs to the technical field of dynamic scheduling. The method comprises the following steps: S1, establishing a corresponding mathematical model according to preset processing information in flexible job shop scheduling; S2, establishing a time discrete Markov decision model by taking a time point when the processing of each process is completed as a scheduled decision time point; S3, establishing a corresponding flexible workshop scheduling environment according to the mathematical model and a Markov decision model; and S4, constructing a neural network model according to the number of machines and the number of workpieces, and training the neural network model. According to the method, the flexible workshop scheduling problem is converted into the Markov decision model, and the neural network model is constructed to perform scheduling decision on the flexible workshop, so that the method has high adaptability and real-time performance, a reasonable scheduling scheme can be generated within a second level according to environmental changes, the influence of uncertain disturbance in a workshop environment on the production process is reduced, and the production efficiency of a production line is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of dynamic scheduling, and in particular relates to a scheduling method for a flexible job shop. Background technique [0002] The Flexible Job Shop Scheduling Problem (FJSP) has been applied and developed in many practical industrial fields. FJSP can be considered as an extension of the job shop scheduling problem. In the classic FJSP, there are n workpieces that need to be processed on m machines, and each workpiece needs to go through several processing steps. Each processing step corresponds to a set of machines that can be processed, and one processing step needs to be selected. After the machine is completed, each machine can only process one workpiece at the same time, and each workpiece can only be processed by one machine at the same time, and preemption is usually allowed. [0003] Over the past few decades, many optimization methods have been devised and applied to job shop scheduling problems t...

AI Technical Summary

Problems solved by technology

In most real-world environments, scheduling is a continuous reaction process, in which the occurrence of various unexpected interruptions is usually unavoidable, such as machine failure, absence of production personnel, rush orders, rework for quality problems, changes in delivery dates, and Issues such as order cancellations, and constantly forcing the system to reconsider and modify pre-established schedules

At this time, the traditional method proposed to solve the static scheduling problem cannot be fully utilized, and cannot deal with uncertain events in the actual production process (such as machine failure, change of processing time, etc.)

In addition, researchers currently mainly use mathematical programming (integer programming, dynamic programming, etc.) or various meta-heuristics (genetic algorithm, evolutionary algorithm, various hybrid algorithms, etc.) to solve flexible job shop scheduling problems. For the flexible job shop scheduling problem, the above method takes too long to solve and cannot meet the needs of real-time scheduling in large-scale production

Images