• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.313-319
• /
• 2023

In this paper, a time series machine learning model, Long Short Term Memory (LSTM), is applied into the bubble flow noise data and the underwater projectile launch noise data to predict missing values of time-series underwater noise data. The former is mixed with bubble noise, flow noise, and fluid-induced interaction noise measured in a pipe and can be classified into three types. The latter is the noise generated when an underwater projectile is ejected from a launch tube and has a characteristic of instantaenous noise. For such types of noise, a data-driven model can be more useful than an analytical model. We constructed an LSTM model with given data and evaluated the model's performance based on the number of hidden units, the number of input sequences, and the decimation factor of signal. It is shown that the optimal LSTM model works well for new data of the same type.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2014.10a
• /
• pp.48-53
• /
• 2014

Rocket, held using the CCA for the mission, a plurality of recording devices, and navigation equipment. In case of a projectile which is entered the water after fired into the air, after performing stages and fairing separated in flight to enter the underwater. It is caused by the explosion of gunpowder mainly, vibration phenomenon of a large transition is induced structurally very, also on entering the water, have a significant shock structurally separated. If shock is transmitted directly to the CCA through the body, it can be caused malfunction of payloads, resulting in failure of the mission of the projectile. In order to ensure the stability against shock, in this paper, Calculating a target resonacne frequency of the CCA, and verified through modal test and analysis. Maximum acceleration position of CCA is checked by SRS analysis. In addition, effectiveness of shock isolation system through shock analysis.

• 한국전산유체공학회:학술대회논문집
• /
• 2004.10a
• /
• pp.25-28
• /
• 2004

The purpose of this paper is to present essential numerical data of FCV(Flow rate Control Valve) which is used in a projectile ejection system for a underwater vehicle. A commercial CFD code is applied to analyze the 3 dimensional viscous compressible flow field within the FCV as four cases of opening rate, 25, 50, 75, and $100\%$. The flow coefficient of each cases are mainly calculated. And other characteristics such as the location of shock wave and total temperature distribution are also determined.