Underwater sound speed inversion by joint artificial neural network and ray theory

Abstract

Sound speed profiles (SSPs) have a great impact on the accuracy of underwater localization and sonar ranging. In traditional SSP inversion, the sound intensity distribution used in normal mode theory-based matching field processing (MFP) or the multipath signal propagation time adopted in ray theory-based MFP is susceptible to boundary parameter mismatch issues, which reduces the inversion accuracy. Moreover, heuristic algorithms introduced in the MFP require many individuals and iterations to search for the optimal feature representation coefficients after the empirical orthogonal function (EOF) decomposition, which causes extra computational time. In this paper, we propose a two-way interactive signal propagation time measurement method based on an autonomous underwater vehicle (AUV) and a horizontal linear array (HLA), and we apply the propagation time of direct arrival signals for shallow-water SSP inversion to avoid the boundary parameter mismatch. We propose a joint artificial neural network (ANN) and ray theory SSP inversion model to reduce the computational time at the working phase by fitting the nonlinear relationship from the signal propagation time to the SSP, and once the relationship is established, the goal of reducing the computational time can be achieved. To make the ANN better learn the SSP distribution in a target region and ensure a good inversion accuracy, we give an empirical data selection strategy. Then we propose a virtual SSP generation algorithm to help ANN training in the case of under-fitting problems caused by insufficient training data. Simulation results show that our approach can provide a reliable and instantaneous monitoring of shallow-water SSP distribution.

Underwater Sound Speed Field Forecasting Based on the Least Square Support Vector Machine

“…The inversion accuracy of SSF based on the neural network is affected by the acoustic time delay observation and the EOF order selection, and the method requires a large number of historical SSPs as reference samples. Aiming for the SSF construction of small sample, a task-driven meta learning (TDML) framework for constructing SSFs was proposed to achieve model convergence [23]. For deep learning without acoustic time delay observation data, Zhang et al [24] proposed the four-layer piecewise function with nine parameters to describe the sound speed structure of the mixed layer, the main thermocline, and the deep-sea isothermal layer, respectively.…”

Deployment Strategy Analysis for Underwater Geodetic Networks

“…As mentioned earlier, the variety of sound speed causes signal propagation path bending, and sound speed changes are typically described using a layered ray model according to [7,37]. We let the sound speed profile be S = [s 0 , s 1 , .…”

A Stratified Linear Sound Speed Profile Simplification Method for Localization Correction

“…For the stratified linear SSP given by Algorithm 1, the total propagation time and horizontal propagation distance of the signal can be derived as a function of the glancing angle, which are presented in [5] as:…”

“…SSPs are usually measured by a conductance, temperature and depth (CTD) system or a sound velocity profiler (SVP) system [10], and SSPs can also be obtained through inversion methods based on match field processing (MFP) [7], artificial neural networks (ANN) [5], and compressive sensing [3]. The original SSP is a sequence of discrete sound speed points, and if it is directly used for sound waves tracking, the ray theory calculation needs to be conducted between each two adjacent sound speed points, which requires too much time for calculation.…”