A Study On Forecasting Sound Velocity Of Seafloor Sediments Based On GA-BP Method

With the development of marine geology and other disciplines as well as the need of marine engineering and marine exploration, the study of acoustic characteristics of seafloor sediments has important practical significance, and has received more and more attention. The sediment is general y considered to be a solid-liquid medium. The physical properties of sediment directly determine sound velocity, which is the physical basis of sound wave propagation. The accurate and uniform model has an important significance for velocity inversion, geoacoustic model establishment, enginee r ing practice.The researchers at home and abroad have carried out a lot of practical investiga t io n on the correlation between the velocity and the physical properties of the sediment. In the seafloor sediments velocity prediction, there exist many problems according to the empirical equations, such as poor accuracy, the narrow scope of application, lack of exact physical meaning. Based on the existing BP neural network, genetic algorit hm(GA) is used to optimize the initial weights and threshold. A seafloor sediment sound velocity forecasting model is established with the relationship of water content, porosity and velocity. Measurement data of study samples from the southern South China Sea are applied. These data are divided into two parts, 120 groups including continent a l shelf, slope, trough samples selected as the training data, the other 6 groups as test data.Experiments show that BP neural network based on GA is superior to the traditional single-parameter, double-parameter sound velocity forecasting empirica l equation, which is recommended for the forecasting sound velocity of seafloor sediments. This GA-BP method has certain scientific basis and broad applicatio n prospects in the future, can provide reference for the establishment of the accurate, uniform model.