Intelligent factory production job scheduling method and system based on deep reinforcement learning

Abstract

The invention relates to an intelligent factory production job scheduling method based on deep reinforcement learning, and the method comprises the following steps: S1, obtaining processing data of each process of each task on a corresponding machine, and carrying out preprocessing of the data, and forming a training set; S2, constructing a deep reinforcement learning DQN model, wherein the deep reinforcement learning DQN model comprises a DQN deep learning network structure and a DQN reinforcement learning module; S3, training the deep reinforcement learning DQN model to obtain a trained deep reinforcement learning DQN model; and S4, pre-processing to-be-produced task scheduling data, and inputting the pre-processed to-be-produced task scheduling data into the trained deep reinforcement learning DQN model to obtain a scheduling arrangement of a production task process. According to the invention, rapid and efficient scheduling of the current production operation can be realized.

Description

technical field [0001] The invention relates to the field of intelligent factory production scheduling, in particular to a method and system for intelligent factory production job scheduling based on deep reinforcement learning. Background technique [0002] As the core of Industry 4.0, the smart factory aims to build a manufacturing-oriented cyber-physical system. Through the integration of information systems and physical entities, the self-organized production of machines, raw materials, and products in the factory can be realized. Among them, the intelligent scheduling of production operations is to improve the factory. One of the keys to production efficiency and saving production costs. In traditional engineering production job scheduling, scheduling often requires staff to manually select one or several fixed scheduling rules based on past experience, which has high requirements for personnel experience. , and the scheduling quality cannot be guaranteed to be always e...

AI Technical Summary

Problems solved by technology

The heuristic algorithm based on swarm intelligence has strong optimization ability and can explore various possible scheduling schemes, but it usually faces the problem of falling into local optimum, and the scheduling execution time will increase significantly with the increase of the scheduling problem scale. growth of

Images