Communication adaptive adjustment method and system based on underwater acoustic communication frame blank time slot

CN121966739BActive Publication Date: 2026-05-29JIMEI UNIV

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
JIMEI UNIV
Filing Date
2026-04-02
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing underwater acoustic communication systems struggle to quickly perceive and adapt to changes in sea conditions, and their reliance on external devices or highly complex models results in significant latency, failing to meet real-time communication requirements.

Method used

Environmental noise data is collected using the blank time slots of underwater acoustic communication frames. Feature maps are generated through time-frequency transformation, and environmental state classification is performed using a residual hybrid expert network. Combined with a hard routing selection mechanism, a matching underwater acoustic communication physical layer processing strategy is obtained.

Benefits of technology

It enables millisecond-level real-time environmental perception on underwater nodes with limited computing resources, reduces model complexity, improves the reliability and real-time performance of underwater acoustic communication links, and can quickly and adaptively adjust communication strategies.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121966739B_ABST
    Figure CN121966739B_ABST
Patent Text Reader

Abstract

The application discloses a method and system for adaptive adjustment of communication based on a blank time slot of an underwater acoustic communication frame, comprising the following steps: acquiring an underwater acoustic communication frame, and collecting environmental noise data based on a blank time slot of the underwater acoustic communication frame; performing time-frequency conversion on the environmental noise data to generate a time-frequency feature map; inputting the time-frequency feature map into a residual hybrid expert network, wherein the residual hybrid expert network is trained by using a joint loss function, and the residual hybrid expert network comprises a shared backbone network, a gating network and a plurality of expert networks; extracting a high-dimensional feature vector from the time-frequency feature map through the shared backbone network; inputting the high-dimensional feature vector into the gating network, wherein the gating network outputs a hard routing selection result, and the hard routing selection result is used for indicating that a certain expert network is activated; inputting the high-dimensional feature vector into a corresponding expert network according to the hard routing selection result to obtain an environmental state classification result; acquiring an underwater acoustic communication physical layer processing strategy matched with a communication environment according to the environmental state classification result, and applying the underwater acoustic communication physical layer processing strategy to a current underwater acoustic communication frame.
Need to check novelty before this filing date? Find Prior Art