Development of hybrid neural network and current forecasting model based dead reckoning method for accurate prediction of underwater glider position

Qiu, Baochun; Wang, Maofa; Li, H X; Ma, Li; Li, Xiuquan; Zhu, Zefei; Zhou, Fan

doi:10.1016/j.oceaneng.2023.115486

Cited by 7 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where: y(n) is the received signal reduced to the baseband. Based on (11), it is possible to determine the impulse response estimate of the hydroacoustic channel by calculating the modulus as follows [7]:…”

Section: Acoustic Wave Propagation Analysismentioning

confidence: 99%

Модель Синтезу Гідроакустичних Сигналів Із Використанням Нейронних Мереж

Parkhomenko,

Lastivka,

Lastivka

2023

SISIOT

View full text Add to dashboard Cite

Underwater acoustics (also called hydroacoustics), which is associated with the study of the patterns of propagation of sound waves in water, is a driving force in the research and development of systems of hydroacoustic technologies and means of communication, monitoring and detection of surface and underwater objects of biological or artificial origin, study of marine resources and environments, noise measurement, etc. This kind of research requires the analysis of huge amounts of data, revealing non-obvious patterns and creating models for the mathematical description of physical phenomena, such as sound propagation in a medium with random characteristics and radiation from different sources, as well as radiation from sources with different apertures or sound scattering, etc. That is why, in order to create the latest technologies in this area, it is necessary to solve complex specialized problems of a fundamental and applied nature using machine learning algorithms and artificial intelligence. Neural networks are nonlinear systems that allow you to effectively classify data compared to mathematical and statistical methods, which are currently quite widely used. In this paper, the authors propose to use a pre-trained neural network for the analysis and classification of hydroacoustic signals. This procedure for distinguishing acoustic signals has a number of advantages, in particular, individual objects are divided into groups based on information about one or more characteristics inherent in these objects, and on the basis of a training sample of pre-labeled objects. Thus, the proposed model of signal synthesis using neural networks is characterized by increased informativeness of the characteristics of the propagation of hydroacoustic signals, which will have prospects in further practical implementation.

show abstract

Section: Acoustic Wave Propagation Analysismentioning

confidence: 99%

Модель Синтезу Гідроакустичних Сигналів Із Використанням Нейронних Мереж

Parkhomenko,

Lastivka,

Lastivka

2023

SISIOT

View full text Add to dashboard Cite

show abstract

“…Based on the background of maritime search and rescue (SAR), Wu proposed an autonomous coverage path planning algorithm based on deep reinforcement learning for search and rescue of drowning people at sea [13]. Qiu proposes a navigation estimation method based on current prediction models and convolutional neural networks-long short-term memory hybrid neural networks to predict the position of underwater gliders [14]. Wang proposed an underwater three-dimensional path planning algorithm based on adaptive step cuckoo search and particle swarm optimization fusion algorithm [15].…”

Section: Introductionmentioning

confidence: 99%

Comprehensive Rescue Model for Submersible Based on Monte Carlo Analysis and Genetic Algorithm

Zhou,

Chen,

et al. 2024

HSET

View full text Add to dashboard Cite

In recent years, there has been a growing interest in deep-sea exploration activities, yet significant gaps persist in search and rescue methodologies for deep-sea submersibles. This paper introduces a position prediction and search model for deep-sea submersibles, leveraging Monte Carlo analysis and genetic algorithms for optimization. The underwater motion of the submersible is simulated through dynamic system modeling. Monte Carlo analysis is utilized to model the scattering of the submersible within the specified ranges of longitude [10.25, 20.25], latitude [20.00, 36.50], and depth [2500m-4000m]. The analysis reveals a normal distribution of scattering points from the middle to the end. Genetic algorithms are employed to refine search and rescue paths, iterated 1000 times to identify the optimal path spanning from 540.1km to 225.6km. In comparison to complex numerical methods, this model offers ease of programming and implementation while accurately predicting the submersible's position in three-dimensional space. It provides the most efficient search and rescue route, ensuring swift response in the face of improbable communication or mechanical failures.

show abstract