YOLOv8을 이용한 실시간 함정 추진기 VCIS 탐지 모델 개발 연구
Development of a real-time VCIS detection model using YOLOv8
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This elementary study was conducted to develop a quantitative real-time vibration-captured infrared spectroscopy (VCIS) detection model. In this s tudy, the deep learning model YOLOv8 was used to t rain cavitations and propellers. Among several models with different neural network sizes, an appropriate model was selected based on accuracy and inference time. Subsequently, cavitation detection was performed using a model trained using model tests and full-ship measurement results. The trained model could accurately detect cavitations and propellers in learned cases and cavitations in unlearned cases. Additionally, it could detect cavitations in full-ship measurements. Furthermore, it could detect the cavitation inception speed. These results demonstrate the feasibility of creating a quantitative VCIS detection model using a deep learning-based computer vision model.
Abstract
This elementary study was conducted to develop a quantitative real-time vibration-captured infrared spectroscopy (VCIS) detection model. In this s tudy, the deep learning model YOLOv8 was used to t rain cavitations and propellers. Among several models with different neural network sizes, an appropriate model was selected based on accuracy and inference time. Subsequently, cavitation detection was performed using a model trained using model tests and full-ship measurement results. The trained model could accurately detect cavitations and propellers in learned cases and cavitations in unlearned cases. Additionally, it could detect cavitations in full-ship measurements. Furthermore, it could detect the cavitation inception speed. These results demonstrate the feasibility of creating a quantitative VCIS detection model using a deep learning-based computer vision model.
참고문헌 (19)
- H. seol, "Improvement of Ship Propeller Cavitation Inception Speed by changing the alignment angle of the inclined shaft support strut", Journal of Defense Quality Society, 4(2), pp.116~123 (2022)
- H. Seol, "Ship Underwater Radiated Noise Reduction Technology", Journal of KSNVE, 32(1), pp.14~18 (2022)
- C. Seo, "Study on effect of air leakage in PRAIRIE system between URN and CIS of propeller", Journal of Defense Quality Society, 5(1), pp.166~172 (2023)
- Lim, Y. -S., "A study on the improvement of cavitation inception speed for controllable pitch propeller in the actual warship", Journal of Advanced Marine Engineering and Technology, 38(9), pp.1170~1174 (2014)
- Ahn, J. W., "Study of the Cavitation Inception Speed(CIS)Improvement Through the Propeller Design and the Stern Appendage Modification", Journal of the Society of Naval Architects of Korea, 60(4), pp.231~239 (2023)
- Han, H. S., "Development of an evaluation method to determine cavitation inception speed with aft hull vibration using kurtosis of the DEMON spectrum", Ocean Engineering, 152, pp.167~180 (2018)
- Lee, T., "Study on estimation of propeller cavitation using computer vision", Journal of the Korean Society of Visualization, 20(3), pp.128~135 (2022)
- Sohan, M., "A review on yolov8 and its advancements", Proceedings of ICDICI 2023, pp.529~545 (2024)
- R. Girshick, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp.580~587 (2014)
- J. Redmon, "You Only Look Once : Unified, Real-Time Object Detection", 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp.779~788 (2016)
- Timur Aliev, "Automatic image processing of cavitation bubbles to analyze the properties of petroleum products", Digital Discovery, 3(6), pp.1101~1107 (2024)
- Park Y-H, "Detection of soybean insect pest and a forecasting platform using deep learning with unmanned ground vehicles", Agronomy, 13(2), pp.1~16 (2023)
- Terven, Juan, "A comprehensive review of yolo architectures in computer vision : From yolov1 to yolov8 and yolo-nas", Machine Learning and Knowledge Extraction, 5(4), pp.1680~1716 (2023)
- S. Kim, "Comparison of YOLOv8 Object Detection Performance for Restaurant Congestion Analysis", Proceedings of KIIT Conference (2024)
- J. Lee, "UAM Autonomous Guidance Control Command Generati on Through Deep-learning-based Aircraft Marshalling Recognition", Journal of Institute of Control, Robotics and Systems, 30(2), pp.86~92 (2024)
- "Ultralytics" (2023)[URL]
- "GitHub" (2024)[URL]
- Park, C., "A validation study of the model test method for propeller cavitation noise prediction", Ocean Engineering, 213, pp.1~10 (2020)
- Seol, H., "Experimental Study on the Cavitation Noise Characteristics of Model Propeller in Uniform Inflow", Transactions of the Korean Society for Noise and Vibration Engineering, 28(6), pp.728~734 (2018)