Journal of Ocean Engineering and Technology 

About: Journal of Ocean Engineering and Technology is an academic journal published by Korean Society of Ocean Engineers. The journal publishes majorly in the area(s): Hull & Welding. It has an ISSN identifier of 1225-0767. It is also open access. Over the lifetime, 1301 publications have been published receiving 2880 citations. The journal is also known as: Journal of ocean engineering and technology & Journal of Ocean Engineering and Technology.

Vibration-Based Damage Monitoring in Model Plate-Girder Bridges under Uncertain Temperature Conditions

Abstract: A vibration-based damage-monitoring scheme is proposed that would generate an alarm showing the occurrence and location of damage under temperature-induced uncertainty conditions. Experiments on a model plate-girder bridge are described, for which a set of modal parameters was measured under uncertain temperature conditions. A damage-alarming model is formulated to statistically identify the occurrence of damage by recognizing the patterns of damage-driven changes in the natural frequencies of the test structure and by distinguishing temperature-induced off-limits. A damage index method based on the concept of modal strain energy is implemented in the test structure to predict the location of damage. In order to adjust for the temperature-induced changes in the natural frequencies that are used for damage detection, a set of empirical frequency correction formulas is analyzed from the relationship between the temperature and frequency ratio.

Underwater Acoustic Research Trends with Machine Learning: General Background

Abstract: Underwater acoustics that is the study of the phenomenon of underwater wave propagation and its interaction with boundaries, has mainly been applied to the fields of underwater communication, target detection, marine resources, marine environment, and underwater sound sources. Based on the scientific and engineering understanding of acoustic signals/data, recent studies combining traditional and data-driven machine learning methods have shown continuous progress. Machine learning, represented by deep learning, has shown unprecedented success in a variety of fields, owing to big data, graphical processor unit computing, and advances in algorithms. Although machine learning has not yet been implemented in every single field of underwater acoustics, it will be used more actively in the future in line with the ongoing development and overwhelming achievements of this method. To understand the research trends of machine learning applications in underwater acoustics, the general theoretical background of several related machine learning techniques is introduced in this paper. Received 2 March 2020, revised 11 April 2020, accepted 13 April 2020 Corresponding author Youngmin Choo: +82-2-6935-2532, ychoo@sejong.ac.kr c 2020, The Korean Society of Ocean Engineers This is an open access article distributed under the terms of the creative commons attribution non-commercial license (http://creativecommons.org/licenses/by-nc/4.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited. 148 Haesang Yang et al. test set (Bishop, 2006; Murphy, 2012). Here, it is necessary to have a process for extracting features from the training set. Some existing machine learning algorithms require these features to be found through human intervention. However, if deep learning is used, this feature extraction process can be performed automatically, and the model’s accuracy can be improved markedly at the same time (Goodfellow et al., 2016). To use deep learning, big data is required, and the existing machine learning methods may be more appropriate than deep learning when a small number of computations are required in situations where there is insufficient data. Therefore, it can be said that there is a complementary relationship between deep learning and machine learning. Many recent attempts have been made to apply various machine learning techniques, such as deep learning, to each aspect of underwater acoustics. However, due to the nature of the underwater environments, the use of these aggressive and open techniques is challenging because the data acquisition/processing procedure is more constrained than that on land (in the air). Therefore, in the field of underwater acoustics, there is a movement towards combining traditional underwater acoustic research techniques with machine learning and developing them in concert with each other. This paper aims to understand how machine learning is applied to each aspect of underwater acoustics. The next section discusses the theories regarding the definitions, types, and basic concepts of machine learning. 2. Machine Learning Theory 2.1 Definitions, Types, and Basic Concepts of Machine Learning Machine learning is a technology in which a machine (computer) uses data to automatically detect and even predict hidden characteristics or patterns (Bishop, 2006; Murphy, 2012). Therefore, machine learning can be regarded as data-driven, and the system performance is determined by the quality of the data. As such, it is very important to build databases that are quantitatively and qualitatively excellent. Machine learning methods can be generally classified into supervised and unsupervised learning. Supervised learning refers to learning the following mapping from  number of training data input/output pairs     (Murphy, 2012).

Dynamic Analysis of Underwater Tracked Vehicle on Extremely Soft Soil by Using Euler Parameters

Abstract: This paper is concerned with the dynamic analysis of an underwater tracked vehicle, operating on extremely soft soil of the deep-seafloor. The vehicle is assumed as a rigid-body with 6-dof. The orientation of the vehicle is defined by four Euler parameters. To solve the motion equations of the vehicle, the Newmark numerical integrator is used in the incremental-iterative algorithm. The normalization constraint of Euler parameters is satisfied by using of a sequential updating method. The hydrodynamic force and moment are included in the tracked vehicle's dynamics. The hydrodynamic effects on the performance of tracked vehicles are investigated through numerical simulations.

Plasticity and Fracture Behaviors of Marine Structural Steel, Part III: Experimental Study on Failure Strain

Abstract: This is the third of several companion papers dealing with the derivation of material constants for ductile failure criteria under hydrostatic stress. It was observed that the ultimate engineering stresses and elongations at fracture from tensile tests for round specimens with various notch radii tended to increase and decrease, respectively, because of the stress triaxiality. The engineering stress curves from tests are compared with numerical simulation results, and it is proved that the curves from the two approaches very closely coincide. Failure strains are obtained from the equivalent plastic strain histories from numerical simulations at the time when the experimental engineering stress drops suddenly. After introducing the new concept of average stress triaxiality and accumulated average strain energy, the material constants of the Johnson-Cook failure criterion for critical energies of 100%, 50%, and 15% are presented. The experimental results obtained for EH-36 steel were in relatively good agreement with the 100% critical energy, whereas the literature states that aluminum fits with a 15% critical energy. Therefore, it is expected that a unified failure criterion for critical energy, which is available for most kinds of ductile materials, can be provided according to the used materials.