{"title":"基于机器视觉的LNG船用装货臂自动对接系统研究","authors":"Zhicheng Ma, Yonghua Lu, Chuan Huang, Shigong Feng, Jing Chen","doi":"10.1002/rob.22579","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>Liquefied Natural Gas is widely used as a clean energy source in production and daily life. The transfer of LNG between receiving terminals and cargo ships is accomplished using LNG marine loading arms. During the loading and unloading of LNG, the flange position on the LNG ship is typically determined manually, and the connection is controlled manually as well. This method is inefficient, dangerous, and its success rate and accuracy do not meet the demands of modern productivity. Moreover, there is limited research on the automatic docking system of LNG marine loading arm and their docking accuracy is not high. To address the need for automated docking of loading arms, this paper proposes a two-step positioning method, combining coarse positioning and fine positioning. It integrates deep learning, edge detection algorithms, and ellipse fitting algorithms to obtain the image coordinates of the flange center. The motion trajectory of the loading arm's end is planned and automatic docking is achieved through PID control. Through testing at the established experimental site, the system achieves a port recognition accuracy of 99.99%, with the maximum docking error of 7.79 mm and the average error of 5.80 mm, thus validating the feasibility of automatic docking for LNG loading arms.</p>\n </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 7","pages":"3213-3226"},"PeriodicalIF":5.2000,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Research on Automatic Docking System of LNG Marine Loading Arm Based on Machine Vision\",\"authors\":\"Zhicheng Ma, Yonghua Lu, Chuan Huang, Shigong Feng, Jing Chen\",\"doi\":\"10.1002/rob.22579\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n <p>Liquefied Natural Gas is widely used as a clean energy source in production and daily life. The transfer of LNG between receiving terminals and cargo ships is accomplished using LNG marine loading arms. During the loading and unloading of LNG, the flange position on the LNG ship is typically determined manually, and the connection is controlled manually as well. This method is inefficient, dangerous, and its success rate and accuracy do not meet the demands of modern productivity. Moreover, there is limited research on the automatic docking system of LNG marine loading arm and their docking accuracy is not high. To address the need for automated docking of loading arms, this paper proposes a two-step positioning method, combining coarse positioning and fine positioning. It integrates deep learning, edge detection algorithms, and ellipse fitting algorithms to obtain the image coordinates of the flange center. The motion trajectory of the loading arm's end is planned and automatic docking is achieved through PID control. Through testing at the established experimental site, the system achieves a port recognition accuracy of 99.99%, with the maximum docking error of 7.79 mm and the average error of 5.80 mm, thus validating the feasibility of automatic docking for LNG loading arms.</p>\\n </div>\",\"PeriodicalId\":192,\"journal\":{\"name\":\"Journal of Field Robotics\",\"volume\":\"42 7\",\"pages\":\"3213-3226\"},\"PeriodicalIF\":5.2000,\"publicationDate\":\"2025-04-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Field Robotics\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/rob.22579\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ROBOTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Field Robotics","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/rob.22579","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ROBOTICS","Score":null,"Total":0}
Research on Automatic Docking System of LNG Marine Loading Arm Based on Machine Vision
Liquefied Natural Gas is widely used as a clean energy source in production and daily life. The transfer of LNG between receiving terminals and cargo ships is accomplished using LNG marine loading arms. During the loading and unloading of LNG, the flange position on the LNG ship is typically determined manually, and the connection is controlled manually as well. This method is inefficient, dangerous, and its success rate and accuracy do not meet the demands of modern productivity. Moreover, there is limited research on the automatic docking system of LNG marine loading arm and their docking accuracy is not high. To address the need for automated docking of loading arms, this paper proposes a two-step positioning method, combining coarse positioning and fine positioning. It integrates deep learning, edge detection algorithms, and ellipse fitting algorithms to obtain the image coordinates of the flange center. The motion trajectory of the loading arm's end is planned and automatic docking is achieved through PID control. Through testing at the established experimental site, the system achieves a port recognition accuracy of 99.99%, with the maximum docking error of 7.79 mm and the average error of 5.80 mm, thus validating the feasibility of automatic docking for LNG loading arms.
期刊介绍:
The Journal of Field Robotics seeks to promote scholarly publications dealing with the fundamentals of robotics in unstructured and dynamic environments.
The Journal focuses on experimental robotics and encourages publication of work that has both theoretical and practical significance.