Hydroacoustic System in a Biomimetic Underwater Vehicle to Avoid Collision with Vessels with Low-Speed Propellers in a Controlled Environment

Piskur, Paweł; Szymak, Piotr; Jaskólski, Krzysztof; Flis, L.; Gąsiorowski, Marek

doi:10.3390/s20040968

Cited by 19 publications

(17 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The SGDM updates the network parameters (weights and biases) to minimize the loss function by taking small steps in the direction of the negative gradient of the loss. The additional momentum factor helps to reduce the oscillation, which may appear along the path of steepest descent towards the optimum [11]. The stochastic gradient descent with momentum algorithm uses a single learning rate for all the parameters.…”

Section: Training Methodsmentioning

confidence: 99%

“…Due to the strong attenuation of the electromagnetic wave in water, the passive and active hydroacoustic system and the vision system was used for surrounding environment observation. The hydroacoustic passive system for moving obstacles avoidance was depicted in [11]. An underwater image gathered using a video camera is presented in Figure 1, while the sonograms from the sonar system are depicted in Figure 2.…”

Section: Introductionmentioning

confidence: 99%

“…Applied sensor systems can record environmental information in an image format suitable for deep network analysis. The underwater obstacle avoidance system [11] can be supported after implementing DLNN in the BUV control system. Short prediction time is needed to meet the requirements for vehicle motion control time [17].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Effectiveness of Using a Pretrained Deep Learning Neural Networks for Object Classification in Underwater Video

2020

Self Cite

View full text Add to dashboard Cite

Video image processing and object classification using a Deep Learning Neural Network (DLNN) can significantly increase the autonomy of underwater vehicles. This paper describes the results of a project focused on using DLNN for Object Classification in Underwater Video (OCUV) implemented in a Biomimetic Underwater Vehicle (BUV). The BUV is intended to be used to detect underwater mines, explore shipwrecks or observe the process of corrosion of munitions abandoned on the seabed after World War II. Here, the pretrained DLNNs were used for classification of the following type of objects: fishes, underwater vehicles, divers and obstacles. The results of our research enabled us to estimate the effectiveness of using pretrained DLNNs for classification of different objects under the complex Baltic Sea environment. The Genetic Algorithm (GA) was used to establish tuning parameters of the DLNNs. Three different training methods were compared for AlexNet, then one training method was chosen for fifteen networks and the tests were provided with the description of the final results. The DLNNs were trained on servers with six medium class Graphics Processing Units (GPUs). Finally, the trained DLNN was implemented in the Nvidia JetsonTX2 platform installed on board of the BUV, and one of the network was verified in a real environment.

show abstract

Section: Training Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Effectiveness of Using a Pretrained Deep Learning Neural Networks for Object Classification in Underwater Video

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Biomimetic Underwater Vehicles (BUVs) [8], [11] have become more popular due to their ability to achieve a low hydroacoustic spectrum [10] and high energy efficiency in comparison to Underwater Vehicles (UVs) [13] with conventional rotary propellers. The control algorithm is based on the movement of fish, especially on their undulating propulsion [7].…”

Section: Introductionmentioning

confidence: 99%

Influence of Fin’s Material Capabilities on the Propulsion System of Biomimetic Underwater Vehicle

Piskur

Szymak

Kitowski

et al. 2020

Polish Maritime Research

Self Cite

View full text Add to dashboard Cite

The technology of Autonomous Underwater Vehicles (AUVs) is developing in two main directions focusing on improving autonomy and improving construction, especially driving and power supply systems. The new Biomimetic Underwater Vehicles (BUVs) are equipped with the innovative, energy efficient driving system consisting of artificial fins. Because these driving systems are not well developed yet, there are great possibilities to optimize them, e.g. in the field of materials. The article provides an analysis of the propulsion force of the fin as a function of the characteristics of the material from which it is made. The parameters of different materials were used for the fin design and their comparison. The material used in our research was tested in a laboratory to determine the Young’s modulus. For simplicity, the same fin geometry (the length and the height) was used for each type of fin. The Euler–Bernoulli beam theory was applied for estimation of the fluid–structure interaction. This article presents the laboratory test stand and the results of the experiments. The laboratory water tunnel was equipped with specialized sensors for force measurements and fluid–structure interaction analysis. The fin deflection is mathematically described, and the relationship between fin flexibility and the generated driving force is discussed.

show abstract

“…In recent years, the hydrophone is widely used in the obstacle avoidance of underwater vehicles [ 17 ], marine monitoring [ 18 , 19 ], oil quality diagnosis [ 20 ], marine seismic exploration [ 21 ] and underwater target positioning [ 22 ], etc. Piskur et al [ 17 ] designed a kind of underwater acoustic system based on the hydrophone sensor for biomimetic underwater vehicles to avoid collision, and only two hydrophones were used to successfully avoid obstacles. The sensitivity of the hydrophone and the number of hydrophones in the array play important roles.…”

Section: Introductionmentioning

confidence: 99%

Time-Frequency Distribution Map-Based Convolutional Neural Network (CNN) Model for Underwater Pipeline Leakage Detection Using Acoustic Signals

Xie

Xiao

Liu

et al. 2020

Sensors

View full text Add to dashboard Cite

Detection technology of underwater pipeline leakage plays an important role in the subsea production system. In this paper, a new method based on the acoustic leak signal collected by a hydrophone is proposed to detect pipeline leakage in the subsea production system. Through the pipeline leakage test, it is found that the radiation noise is a continuous spectrum of the medium and high-frequency noise. Both the increase in pipe pressure and the diameter of the leak hole will narrow the spectral structure and shift the spectrum center towards the low frequencies. Under the same condition, the pipe pressure has a greater impact on the noise; every 0.05 MPa increase in the pressure, the radiation sound pressure level increases by 6-7 dB. The time-frequency images were obtained by processing the acoustic signals using the Ensemble Empirical Mode Decomposition (EEMD) and Hilbert–Huang transform (HHT), and fed into a two-layer Convolutional Neural Network (CNN) for leakage detection. The results show that CNN can correctly identify the degree of pipeline leakage. Hence, the proposed method provides a new approach for the detection of pipeline leakage in underwater engineering applications.

show abstract

Hydroacoustic System in a Biomimetic Underwater Vehicle to Avoid Collision with Vessels with Low-Speed Propellers in a Controlled Environment

Cited by 19 publications

References 18 publications

The Effectiveness of Using a Pretrained Deep Learning Neural Networks for Object Classification in Underwater Video

The Effectiveness of Using a Pretrained Deep Learning Neural Networks for Object Classification in Underwater Video

Influence of Fin’s Material Capabilities on the Propulsion System of Biomimetic Underwater Vehicle

Time-Frequency Distribution Map-Based Convolutional Neural Network (CNN) Model for Underwater Pipeline Leakage Detection Using Acoustic Signals

Contact Info

Product

Resources

About