{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T10:39:29Z","timestamp":1769510369412,"version":"3.49.0"},"reference-count":46,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2022,8,18]],"date-time":"2022-08-18T00:00:00Z","timestamp":1660780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100015659","name":"Southern Federal University","doi-asserted-by":"publisher","award":["0852-2020-0019"],"award-info":[{"award-number":["0852-2020-0019"]}],"id":[{"id":"10.13039\/501100015659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>During the steel pipeline installation, special attention is paid to the butt weld control performed by fusion welding. The operation of the currently popular automated X-ray and ultrasonic testing complexes is associated with high resource and monetary costs. In this regard, this work is devoted to the development of alternative and cost-effective means of preliminary quality control of the work performed based on the visual testing method. To achieve this goal, a hardware platform based on a single board Raspberry Pi4 minicomputer and a set of available modules and expansion cards is proposed, and software whose main functionality is implemented based on the systemic application of computer vision algorithms and machine learning methods. The YOLOv5 object detection algorithm and the random forest machine learning model were used as a defect detection and classification system. The mean average precision (mAP) of the trained YOLOv5 algorithm based on extracted weld contours is 86.9%. A copy of YOLOv5 trained on the images of control objects showed a mAP result of 96.8%. Random forest identifying of the defect precursor based on the point clouds of the weld surface achieved a mAP of 87.5%.<\/jats:p>","DOI":"10.3390\/s22166201","type":"journal-article","created":{"date-parts":[[2022,8,18]],"date-time":"2022-08-18T23:28:41Z","timestamp":1660865321000},"page":"6201","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Machine Learning and 3D Reconstruction of Materials Surface for Nondestructive Inspection"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1260-8676","authenticated-orcid":false,"given":"Oleg O.","family":"Kartashov","sequence":"first","affiliation":[{"name":"The Smart Materials Research Institute, Southern Federal University, 178\/24 Sladkova, 344090 Rostov-on-Don, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2922-330X","authenticated-orcid":false,"given":"Andrey V.","family":"Chernov","sequence":"additional","affiliation":[{"name":"The Smart Materials Research Institute, Southern Federal University, 178\/24 Sladkova, 344090 Rostov-on-Don, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7918-453X","authenticated-orcid":false,"given":"Alexander A.","family":"Alexandrov","sequence":"additional","affiliation":[{"name":"The Smart Materials Research Institute, Southern Federal University, 178\/24 Sladkova, 344090 Rostov-on-Don, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dmitry S.","family":"Polyanichenko","sequence":"additional","affiliation":[{"name":"The Smart Materials Research Institute, Southern Federal University, 178\/24 Sladkova, 344090 Rostov-on-Don, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladislav S.","family":"Ierusalimov","sequence":"additional","affiliation":[{"name":"The Smart Materials Research Institute, Southern Federal University, 178\/24 Sladkova, 344090 Rostov-on-Don, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Semyon A.","family":"Petrov","sequence":"additional","affiliation":[{"name":"The Smart Materials Research Institute, Southern Federal University, 178\/24 Sladkova, 344090 Rostov-on-Don, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6167-7942","authenticated-orcid":false,"given":"Maria A.","family":"Butakova","sequence":"additional","affiliation":[{"name":"The Smart Materials Research Institute, Southern Federal University, 178\/24 Sladkova, 344090 Rostov-on-Don, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,8,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"107611","DOI":"10.1016\/j.compchemeng.2021.107611","article-title":"Event-Driven Simulation Method for Fuel Transport in a Mesh-like Pipeline Network","volume":"157","author":"Csontos","year":"2022","journal-title":"Comput. Chem. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Johnstone, R.W. (2015). Transportation Systems and Security Risks. Protecting Transportation, Elsevier.","DOI":"10.1016\/B978-0-12-408101-7.00003-9"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"100025","DOI":"10.1016\/j.nexus.2021.100025","article-title":"Green Strategies in Formulating, Stabilizing and Pipeline Transportation of Coal Water Slurry in the Framework of WATER-ENERGY NEXUS: A State of the Art Review","volume":"4","author":"Das","year":"2021","journal-title":"Energy Nexus"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e06999","DOI":"10.1016\/j.heliyon.2021.e06999","article-title":"Environmental and Socioeconomic Impacts of Pipeline Transport Interdiction in Niger Delta, Nigeria","volume":"7","author":"Umar","year":"2021","journal-title":"Heliyon"},{"key":"ref_5","unstructured":"Murrill, B.J. (2016). Pipeline Transportation of Natural Gas and Crude Oil: Federal and State Regulatory Authority, Library of Congress, Congressional Research Service."},{"key":"ref_6","unstructured":"Petro, P.P. (1975). Study of Plastic vs. Steel Pipe Performance. Gas Dig., 1, Available online: https:\/\/www.osti.gov\/biblio\/7219274."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sotoodeh, K. (2021). Piping and Valve Corrosion Study. A Practical Guide to Piping and Valves for the Oil and Gas Industry, Elsevier.","DOI":"10.1016\/B978-0-12-823796-0.00009-X"},{"key":"ref_8","unstructured":"Annila, L. (2018). Nondestructive Testing of Pipelines, Springer."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Becht, C. (2009). Process Piping: The Complete Guide to ASME B31.3, ASME Press. [3rd ed.].","DOI":"10.1115\/1.802861"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1016\/j.ijpvp.2008.05.001","article-title":"Reliability of Nondestructive Test Techniques in the Inspection of Pipelines Used in the Oil Industry","volume":"85","author":"Carvalho","year":"2008","journal-title":"Int. J. Press. Vessel. Pip."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/0029-1021(69)90013-9","article-title":"Nondestructive Testing of High-Pressure Gas Pipelines","volume":"2","author":"Lumb","year":"1969","journal-title":"Nondestruct. Test."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, B., Liu, F., Liu, C., Li, J., Zhang, B., Zhou, Q., Han, X., and Zhao, Y. (2017, January 7\u20139). An Ultrasonic Nondestructive Testing Method for the Measurement of Weld Width in Laser Welding of Stainless Steel. Proceedings of the AIP Conference Proceedings, Wuhan, China.","DOI":"10.1063\/1.5005284"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ma, Q., Tian, G., Zeng, Y., Li, R., Song, H., Wang, Z., Gao, B., and Zeng, K. (2021). Pipeline In-Line Inspection Method, Instrumentation and Data Management. Sensors, 21.","DOI":"10.3390\/s21113862"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1016\/j.matpr.2019.05.131","article-title":"A Review of Implementation of Artificial Intelligence Systems for Weld Defect Classification","volume":"16","author":"Vishal","year":"2019","journal-title":"Mater. Today Proc."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"180947","DOI":"10.1109\/ACCESS.2019.2959810","article-title":"A Deep Artificial Immune System to Detect Weld Defects in DWDI Radiographic Images of Petroleum Pipes","volume":"7","author":"Fioravanti","year":"2019","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1016\/j.ndteint.2008.05.004","article-title":"Detection of Line Weld Defects Based on Multiple Thresholds and Support Vector Machine","volume":"41","author":"Wang","year":"2008","journal-title":"NDT E Int."},{"key":"ref_17","unstructured":"Cassels, B. (2018). Weld Defect Detection Using Ultrasonic Phased Arrays, University of Central Lancashire."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1574350","DOI":"10.1155\/2020\/1574350","article-title":"Deep Learning Technology for Weld Defects Classification Based on Transfer Learning and Activation Features","volume":"2020","author":"Ajmi","year":"2020","journal-title":"Adv. Mater. Sci. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1237","DOI":"10.1080\/08839514.2021.1975391","article-title":"Deep Learning Based Steel Pipe Weld Defect Detection","volume":"35","author":"Yang","year":"2021","journal-title":"Appl. Artif. Intell."},{"key":"ref_20","unstructured":"Beyerer, J., and Puente Le\u00f3n, F. (2019, January 27). Automatic Detection of Welding Defects Using the Convolutional Neural Network. Proceedings of the Automated Visual Inspection and Machine Vision III, Munich, Germany."},{"key":"ref_21","first-page":"1969","article-title":"A Recognition Algorithm to Detect Pipe Weld Defects","volume":"24","author":"Cui","year":"2017","journal-title":"Teh. Vjesn."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Oh, S., Jung, M., Lim, C., and Shin, S. (2020). Automatic Detection of Welding Defects Using Faster R-CNN. Appl. Sci., 10.","DOI":"10.3390\/app10238629"},{"key":"ref_23","first-page":"IJERTV4IS110556","article-title":"A Review on Analysis, Monitoring and Detection of Weld Defect Products","volume":"V4","author":"Kumar","year":"2015","journal-title":"IJERT"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"012052","DOI":"10.1088\/1742-6596\/1986\/1\/012052","article-title":"Research and Method for In-Line Inspection Technology of Girth Weld in Long-Distance Oil and Gas Pipeline","volume":"1986","author":"Chen","year":"2021","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_25","first-page":"7","article-title":"Analysis of Welding Disabilities on Carbon Steel Pipes with SMAW Reviewed from Radiography Test Results","volume":"14","author":"Gaol","year":"2019","journal-title":"Int. J. Appl. Eng. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1134\/S1054661815040021","article-title":"Classification of Welding Defects in Radiographic Images","volume":"26","author":"Moghaddam","year":"2016","journal-title":"Pattern Recognit. Image Anal."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"95097","DOI":"10.1109\/ACCESS.2021.3093487","article-title":"Transfer Learning with CNN for Classification of Weld Defect","volume":"9","author":"Kumaresan","year":"2021","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1007\/s10921-017-0420-x","article-title":"The Application of Rough Sets Theory to Design of Weld Defect Classifiers","volume":"36","author":"Chady","year":"2017","journal-title":"J. Nondestruct. Eval."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Chang, J., Kang, M., and Park, D. (2022). Low-Power On-Chip Implementation of Enhanced SVM Algorithm for Sensors Fusion-Based Activity Classification in Lightweighted Edge Devices. Electronics, 11.","DOI":"10.3390\/electronics11010139"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Tarek, H., Aly, H., Eisa, S., and Abul-Soud, M. (2022). Optimized Deep Learning Algorithms for Tomato Leaf Disease Detection with Hardware Deployment. Electronics, 11.","DOI":"10.3390\/electronics11010140"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Meivel, S., Indira Devi, K., Muthamil Selvam, T., and Uma Maheswari, S. (2021). Real Time Analysis of Unmask Face Detection in Human Skin Using Tensor Flow Package and IoT Algorithm. Mater. Today Proc., S2214785320405826.","DOI":"10.1016\/j.matpr.2020.12.864"},{"key":"ref_32","unstructured":"Abed, A.M., Gitaffa, S.A., and Issa, A.H. (2021). Robust Geophone String Sensors Fault Detection and Isolation Using Pattern Recognition Techniques Based on Raspberry Pi4. Mater. Today Proc., S2214785321032806."},{"key":"ref_33","first-page":"388","article-title":"SSVEP-EEG Signal Classification Based on Emotiv EPOC BCI and Raspberry Pi","volume":"54","author":"Asanza","year":"2021","journal-title":"IFAC-Pap."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Gaggion, N., Ariel, F., Daric, V., Lambert, \u00c9., Legendre, S., Roul\u00e9, T., Camoirano, A., Milone, D.H., Crespi, M., and Blein, T. (2020). ChronoRoot: High-Throughput Phenotyping by Deep Segmentation Networks Reveals Novel Temporal Parameters of Plant Root System Architecture, Plant Biology.","DOI":"10.1101\/2020.10.27.350553"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.jvcir.2017.12.009","article-title":"Encoder Settings Impact on Intra-Prediction-Based Descriptors for Video Retrieval","volume":"50","author":"Rouhi","year":"2018","journal-title":"J. Vis. Commun. Image Represent."},{"key":"ref_36","first-page":"782","article-title":"Improved Approximated Median Filter Algorithm for Real-Time Computer Vision Applications","volume":"34","author":"Appiah","year":"2020","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref_37","first-page":"1","article-title":"GDXray: The database of X-ray images for nondestructive testing","volume":"4","author":"Mery","year":"2015","journal-title":"J. Nondestruct. Eval."},{"key":"ref_38","unstructured":"Mohamed, E., Shaker, A., El-Sallab, A., and Hadhoud, M. (2021). INSTA-YOLO: Real-Time In-stance Segmentation. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Liao, L., Tang, S., Liao, J., Li, X., Wang, W., Li, Y., and Guo, R. (2022). A Supervoxel-Based Random Forest Method for Robust and Effective Airborne LiDAR Point Cloud Classification. Remote Sens., 14.","DOI":"10.3390\/rs14061516"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"072037","DOI":"10.1088\/1757-899X\/768\/7\/072037","article-title":"An Improved Random Forest Model Applied to Point Cloud Classification","volume":"768","author":"Xue","year":"2020","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"48","DOI":"10.31127\/tuje.669566","article-title":"Classification of UAV Point Clouds by Random Forest Machine Learning Algorithm","volume":"5","author":"Zeybek","year":"2021","journal-title":"Turk. J. Eng."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/978-3-642-19315-6_3","article-title":"Efficient Large-Scale Stereo Matching","volume":"Volume 6492","author":"Kimmel","year":"2011","journal-title":"Computer Vision\u2014ACCV 2010"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.compag.2016.11.022","article-title":"Stereo Vision with Equal Baseline Multiple Camera Set (EBMCS) for Obtaining Depth Maps of Plants","volume":"135","author":"Kaczmarek","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"03005","DOI":"10.1051\/matecconf\/20167503005","article-title":"The Depth Map Construction from a 3D Point Cloud","volume":"75","author":"Chmelar","year":"2016","journal-title":"MATEC Web Conf."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1016\/j.apm.2021.05.014","article-title":"Implicit Reconstructions of Thin Leaf Surfaces from Large, Noisy Point Clouds","volume":"98","author":"Whebell","year":"2021","journal-title":"Appl. Math. Model."},{"key":"ref_46","first-page":"102504","article-title":"LV-GCNN: A Lossless Voxelization Integrated Graph Convolutional Neural Network for Surface Reconstruction from Point Clouds","volume":"103","author":"Wu","year":"2021","journal-title":"Int. J. Appl. Earth Obs. Geoinf."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/16\/6201\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:11:48Z","timestamp":1760141508000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/16\/6201"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,18]]},"references-count":46,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["s22166201"],"URL":"https:\/\/doi.org\/10.3390\/s22166201","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,18]]}}}