[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118033-en":3,"doc-seo-118033-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118033,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Machine learning-assisted anomaly detection for power line components - A case study in Pakistan","Reliable electricity supply depends on the health of overhead power line components, yet defect identification in Pakistan often requires human inspection and can be slow, costly, and labor-intensive. This study uses an unmanned aerial vehicle to collect 10,343 photos and builds automated anomaly detection systems using both supervised and unsupervised machine learning. Support vector machine, random forest, VGG16, and ResNet50 are evaluated for supervised detection, while a convolutional auto-encoder performs unsupervised classification of normal versus abnormal components. VGG16 reaches 99.00% accuracy.","Received: 7 November 2023  Revised: 10 March 2024  Accepted: 17 April 2024  The Journal of Engineering  \nDOI: 10.1049/tje2.12405  \nORIGINAL RESEARCH  \nMachine learning-assisted anomaly detection for power line components: A case study in Pakistan  \nAbdul Basit1  Habib Ullah Manzoor1,2   Muhammad Akram1  Hasan Erteza Gelani1   \nSajjad Hussain2  \n1Department of Electrical Engineering, University of Engineering and Technology, Lahore, Pakistan  \n2James Watt School of Engineering, University of Glasgow, Glasgow, UK  \nCorrespondence  \nHabib Ullah Manzoor, James Watt School of Engineering, University of Glasgow, Glasgow, G12 8QQ, UK.  \n[Email: h.manzoor.1@research.gla.ac.uk](Email: h.manzoor.1@research.gla.ac.uk)  \nAbstract  \nA continuous supply of electricity is necessary to maintain an acceptable standard of life, and the power distribution system’s overhead line components play a crucial role in this matter. In Pakistan, identifying defective parts often necessitates human involvement. An unmanned aerial vehicle was used to gather a collection of 10,343 photos to automate this procedure. Using supervised and unsupervised machine learning methods, a number of automated anomaly detection systems were created. Support vector machine, random forest, VGG16, and ResNet50 were used as supervised machine learning models, and a convolutional auto-encoder was used as the unsupervised machine learning model. VGG16 achieved the best accuracy of 99.00% while random forest achieved the worst accuracy of 72.49% . The convolutional auto-encoder was successful in distinguishing between normal and abnormal components. The aforementioned machine learning models can be put on unmanned aerial vehicles to immediately identify defective parts.  \n1  INTRODUCTION  \nElectricity now plays vital roles in home, economic, and industrial activities, and it has become an essential component of contemporary life. Electricity has been essential to the growth of the world and the digitization of the modern period since its creation in 1887 . An uninterrupted power supply is essential for daily living since interruptions in the electric power supply can cause serious losses for businesses and industrial customers. A lot of research has been carried out to improve power infrastructure and meet the growing energy demand, including efficient energy management systems [1], cost optimization [2], power line optimisation [3], tilt angle optimization of PV modules [4], and renewable energy optimization such as solar cells [5–7] .  \nPower utility firms are accountable for maintaining an efficient power system and reducing commercial and economic losses to guarantee uninterrupted power supply to consumers. Power companies routinely carry out preventive maintenance on their distribution systems, including the replacement of faulty or broken parts, the cutting down of trees  \nAbdul Basit and Habib Ullah Manzoor contributed equally to this work.  \nthat encroach on distribution lines, and the adoption of environmental safety measures. Unexpected problems on wires might still happen despite routine surveys and maintenance. Traditional approaches can be time-consuming, laborious, expensive, and require human supervision when employed for premaintenance surveys or during urgent shutdown patrolling for fault identification [8] .  \nRecently, utility firms have started using cutting-edge techniques for line inspection, such as climbing robots and patrolling with assistance from helicopters. These techniques entail gathering image data from the field, which managers or technical staff then examine to find flaws or deficiencies in the equipment, as mentioned in reference [9] . Due to the requirement for human involvement and the delay in making decisions, these methods are nevertheless time and resource-intensive. Therefore, a trustworthy and effective strategy is required that can address problems faster than the ones that are now in use. Artificial intelligence is influencing changes in the cur","cbCaibulWR9YHOr2","https://ap.wps.com/l/cbCaibulWR9YHOr2","pdf",1745115,1,13,"English","en",105,"# Introduction\n## Motivation and challenges in power line inspection\n# Methodology\n## Data collection with UAV images\n## Supervised and unsupervised anomaly detection models","[{\"question\":\"What is the main goal of the study?\",\"answer\":\"To quickly and accurately identify normal and abnormal power line components using deep learning models trained on aerial image data.\"},{\"question\":\"How was the dataset collected?\",\"answer\":\"An unmanned aerial vehicle collected 10,343 photos of power line components for model training and evaluation.\"},{\"question\":\"Which models were used and what results were reported?\",\"answer\":\"Supervised models included SVM, random forest, VGG16, and ResNet50, while a convolutional auto-encoder was used for unsupervised detection; VGG16 achieved the best accuracy at 99.00%.\"}]","Machine learning-assisted anomaly detection for power line components - A case study in Pakistan | PDF",1785680902,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-assisted-anomaly-detection-for-power-line-components-a-case-study-in-pakistan","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-assisted-anomaly-detection-for-power-line-components-a-case-study-in-pakistan/118033/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-02",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the main goal of the study?","Question",{"text":76,"@type":77},"To quickly and accurately identify normal and abnormal power line components using deep learning models trained on aerial image data.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How was the dataset collected?",{"text":81,"@type":77},"An unmanned aerial vehicle collected 10,343 photos of power line components for model training and evaluation.",{"name":83,"@type":74,"acceptedAnswer":84},"Which models were used and what results were reported?",{"text":85,"@type":77},"Supervised models included SVM, random forest, VGG16, and ResNet50, while a convolutional auto-encoder was used for unsupervised detection; VGG16 achieved the best accuracy at 99.00%.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]