Zhenchang Xu, Kuirong Liu, Bill Gu, Luchun Yan, X. Pang, K. Gao
{"title":"基于深度学习的管道漏磁检测图像识别模型","authors":"Zhenchang Xu, Kuirong Liu, Bill Gu, Luchun Yan, X. Pang, K. Gao","doi":"10.1515/corrrev-2023-0027","DOIUrl":null,"url":null,"abstract":"Abstract Deep learning algorithm has a wide range of applications and excellent performance in the field of engineering image recognition. At present, the detection and recognition of buried metal pipeline defects still mainly rely on manual work, which is inefficient. In order to realize the intelligent and efficient recognition of pipeline magnetic flux leakage (MFL) inspection images, based on the actual demand of MFL inspection, this paper proposes a new object detection framework based on YOLOv5 and CNN models in deep learning. The framework first uses object detection to classify the targets in MFL images and then inputs the features containing defects into a regression model based on CNN according to the classification results. The framework integrates object detection and image regression model to realize the target classification of MFL pseudo color map and the synchronous recognition of metal loss depth. The results show that the target recognition ability of the model is good, its precision reaches 0.96, and the mean absolute error of the metal loss depth recognition result is 1.14. The framework has more efficient identification ability and adaptability and makes up for the quantification of damage depth, which can be used for further monitoring and maintenance strategies.","PeriodicalId":10721,"journal":{"name":"Corrosion Reviews","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2023-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Image recognition model of pipeline magnetic flux leakage detection based on deep learning\",\"authors\":\"Zhenchang Xu, Kuirong Liu, Bill Gu, Luchun Yan, X. Pang, K. Gao\",\"doi\":\"10.1515/corrrev-2023-0027\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Deep learning algorithm has a wide range of applications and excellent performance in the field of engineering image recognition. At present, the detection and recognition of buried metal pipeline defects still mainly rely on manual work, which is inefficient. In order to realize the intelligent and efficient recognition of pipeline magnetic flux leakage (MFL) inspection images, based on the actual demand of MFL inspection, this paper proposes a new object detection framework based on YOLOv5 and CNN models in deep learning. The framework first uses object detection to classify the targets in MFL images and then inputs the features containing defects into a regression model based on CNN according to the classification results. The framework integrates object detection and image regression model to realize the target classification of MFL pseudo color map and the synchronous recognition of metal loss depth. The results show that the target recognition ability of the model is good, its precision reaches 0.96, and the mean absolute error of the metal loss depth recognition result is 1.14. The framework has more efficient identification ability and adaptability and makes up for the quantification of damage depth, which can be used for further monitoring and maintenance strategies.\",\"PeriodicalId\":10721,\"journal\":{\"name\":\"Corrosion Reviews\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2023-08-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Corrosion Reviews\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.1515/corrrev-2023-0027\",\"RegionNum\":4,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ELECTROCHEMISTRY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Corrosion Reviews","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1515/corrrev-2023-0027","RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ELECTROCHEMISTRY","Score":null,"Total":0}
Image recognition model of pipeline magnetic flux leakage detection based on deep learning
Abstract Deep learning algorithm has a wide range of applications and excellent performance in the field of engineering image recognition. At present, the detection and recognition of buried metal pipeline defects still mainly rely on manual work, which is inefficient. In order to realize the intelligent and efficient recognition of pipeline magnetic flux leakage (MFL) inspection images, based on the actual demand of MFL inspection, this paper proposes a new object detection framework based on YOLOv5 and CNN models in deep learning. The framework first uses object detection to classify the targets in MFL images and then inputs the features containing defects into a regression model based on CNN according to the classification results. The framework integrates object detection and image regression model to realize the target classification of MFL pseudo color map and the synchronous recognition of metal loss depth. The results show that the target recognition ability of the model is good, its precision reaches 0.96, and the mean absolute error of the metal loss depth recognition result is 1.14. The framework has more efficient identification ability and adaptability and makes up for the quantification of damage depth, which can be used for further monitoring and maintenance strategies.
期刊介绍:
Corrosion Reviews is an international bimonthly journal devoted to critical reviews and, to a lesser extent, outstanding original articles that are key to advancing the understanding and application of corrosion science and engineering in the service of society. Papers may be of a theoretical, experimental or practical nature, provided that they make a significant contribution to knowledge in the field.