Shipboard aircraft ship surface guarantee process optimization method based on reinforcement learning

A technology of reinforcement learning and process optimization, applied in design optimization/simulation, geometric CAD, special data processing applications, etc., can solve problems such as relying on manual experience, poor real-time performance, and untimely status update, so as to reduce computing time and meet real-time requirements. The effect of scheduling

Inactive Publication Date: 2021-02-23
NAVAL AVIATION UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The scheduling method based on the "Ouija board" is simple to operate, and the situation of the carrier-based aircraft is clear, but it relies too much on manual experience and has the disadvantages of untimely status update and lack of interactivity. Although the scheduling method optimized by traditional intelligent algorithms can achieve better optimization quality, but has the disadvantage of poor real-time performance

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Shipboard aircraft ship surface guarantee process optimization method based on reinforcement learning
  • Shipboard aircraft ship surface guarantee process optimization method based on reinforcement learning
  • Shipboard aircraft ship surface guarantee process optimization method based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Specifically, a method for optimizing the process of carrier-based aircraft surface support based on reinforcement learning includes the following steps:

[0035] S1. According to the type of carrier-based aircraft to be supported and historical experience support data, determine its support time at each support station

[0036] On the deck, the carrier-based aircraft needs to go through the three stages of inspection and maintenance, refueling, and weapon mounting, and then catapult and take off. From the guarantee stage set F and the guarantee station set M j (j∈F) constitutes a carrier-based aircraft surface support system, and n carrier-based aircraft constitute a set I of carrier-based aircraft to be supported, and use historical support experience data to determine the time t required for carrier-based aircraft to receive support at each support station i,j,l (i∈I,j∈F,l∈M j ). At the same time, in order to make up for the error of empirical data, the transition...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a shipboard aircraft ship surface guarantee process optimization method based on reinforcement learning, and belongs to the technical field of shipboard aircraft ship surface guarantee. The method comprises the following steps: firstly, establishing a guarantee scheduling model according to ship surface guarantee flow characteristics of a shipboard aircraft, and summarizingthe guarantee scheduling model into a hybrid flow shop scheduling problem; then, in combination with a reinforcement learning process, designing corresponding state and action representations in a shipboard aircraft ship surface guarantee process scheduling problem, summarizing the shipboard aircraft ship surface guarantee process into a Markov decision process, and designing a corresponding reward function in reinforcement learning; and finally, performing optimization solution on the scheduling problem by using a reinforcement learning algorithm so as to realize minimization of guarantee completion time. According to the method, on the basis of guaranteeing the optimization quality of the shipboard aircraft ship surface guarantee scheduling process, the real-time performance of the solving process is remarkably improved, and a reasonable solution can be provided for shipboard aircraft ship surface guarantee real-time scheduling.

Description

technical field [0001] The invention belongs to the technical field of carrier-based aircraft surface support, and in particular relates to an optimization method for a carrier-based aircraft surface support process based on reinforcement learning. Background technique [0002] Carrier-based aircraft operations are a cyclical process, including catapult takeoff, mission execution, return and landing, deck maintenance, and catapult takeoff again, and so on. Since the number of carrier-based aircraft carried on an aircraft carrier is limited, ensuring that the above-mentioned cycle is carried out efficiently and orderly is an effective way to give full play to the combat capabilities of carrier-based aircraft. In this process, the carrier-based aircraft safely and quickly completes the ship surface support and ejection take-off is the key to restricting the carrier-based aircraft's ability to dispatch. The support process optimization technology for carrier-based aircraft on ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & AuthorityApplications(China)
IPC IPC(8): G06F30/15G06F30/27
CPCG06F30/15G06F30/27
Inventor张勇
OwnerNAVAL AVIATION UNIV