A Flow Shop Scheduling Method Based on Deep Reinforcement Learning

Abstract

The invention discloses a flow shop scheduling method based on deep reinforcement learning, which takes each workpiece as a node and aggregates the processing time of its process as node information to obtain its embedded representation. Use the pointer network to fit the policy network, use the maximum completion time as a reward, train the policy network and save the parameters. In practical problems, the embedded representation of each artifact is used as the input of the policy network, and the artifact with the highest probability is selected in turn until all artifacts are selected to obtain a complete scheduling sequence. The flow shop scheduling method described in the present invention can obtain near-optimal solutions on small-scale problems, and can obtain better solutions than heuristic algorithms and genetic algorithms on large-scale problems, and can be extended to problems with different numbers of machines and jobs On the one hand, it breaks the limitation that the model needs to be retrained on different problem scales and problem data, and has wider versatility.

Description

technical field [0001] The invention relates to the technical field of flow shop scheduling, in particular to a flow shop scheduling method based on deep reinforcement learning. Background technique [0002] The flow shop scheduling problem is one of the classic combinatorial optimization problems, which is difficult to find the optimal solution and has high computational complexity. In order to increase the productivity of the system, effective and efficient manufacturing and scheduling technology solutions must be used. Many researchers have proposed various algorithms for this problem. The exact algorithm can get the optimal solution, but the solution time is often too long, so it is not suitable for large-scale problems; the NEH heuristic algorithm is a kind of flow shop scheduling algorithm that is widely used at present, and can be used to solve the problem with the minimum processing time (makespan) optimization problem. The heuristic algorithm is difficult to guar...

AI Technical Summary

Problems solved by technology

Using a multi-layer perceptron to fit the policy network in reinforcement learning requires manual design of state features and reward functions, and directly using indicators such as the number of machines and jobs as state features will cause large changes in the input of the network, and it is difficult to expand to different numbers of machines. In terms of the number of tasks and the number of jobs, the model may need to be retrained on different problem scales and problem data, and there are still limitations in versatility

Images