[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"ssr-repo-dspace000004962":3},{"id":4,"title":5,"authors":6,"files":8,"advisors":53,"authors_detail":54,"advisors_detail":58,"publisher":59,"publish_place":60,"language":61,"type":62,"type_slug":63,"year":64,"department":65,"study_program":66,"keywords":67,"keywords_detail":74,"abstract":87,"abstract_html":88,"url":89},"repo-dspace000004962","Implementing Artificial Intelligence (AI) to Enhance Fault Detection and Diagnosis System Based on Current Consumption of The Broken Motor",[7],"Tiftazani Ainun Na’im",[9,14,17,20,23,26,29,32,35,38,41,44,47,50],{"chapter":10,"requires_login":11,"label":12,"available":13},"abstrak",false,"Abstrak",true,{"chapter":15,"requires_login":11,"label":16,"available":11},"pendahuluan","Pendahuluan",{"chapter":18,"requires_login":11,"label":19,"available":13},"bab1","Bab I",{"chapter":21,"requires_login":11,"label":22,"available":13},"bab2","Bab II",{"chapter":24,"requires_login":13,"label":25,"available":13},"bab3","Bab III",{"chapter":27,"requires_login":13,"label":28,"available":13},"bab4","Bab IV",{"chapter":30,"requires_login":13,"label":31,"available":13},"bab5","Bab V",{"chapter":33,"requires_login":13,"label":34,"available":11},"bab6","Bab VI",{"chapter":36,"requires_login":13,"label":37,"available":11},"bab7","Bab VII",{"chapter":39,"requires_login":11,"label":40,"available":11},"daftar_pustaka","Daftar Pustaka",{"chapter":42,"requires_login":13,"label":43,"available":11},"lampiran","Lampiran",{"chapter":45,"requires_login":13,"label":46,"available":11},"jurnal","Jurnal",{"chapter":48,"requires_login":11,"label":49,"available":13},"open","Akses Terbuka",{"chapter":51,"requires_login":13,"label":52,"available":13},"full","Dokumen Lengkap",[],[55],{"name":7,"nim":56,"slug":57},"2141150103","tiftazani-ainun-naim",[],"Politeknik Negeri Malang","Malang","Inggris","Skripsi (D4)","skripsi-d4",2025,"D-IV SISTEM KELISTRIKAN",null,[68,69,70,71,72,73],"Artificial Intelligence","Broken Bar","Decision Tree","Linear Regression","Induction Motor","Random Forest",[75,77,79,81,83,85],{"name":68,"slug":76},"artificial-intelligence",{"name":69,"slug":78},"broken-bar",{"name":70,"slug":80},"decision-tree",{"name":71,"slug":82},"linear-regression",{"name":72,"slug":84},"induction-motor",{"name":73,"slug":86},"random-forest","The early detection of induction motor faults is critical in industrial electrical systems to prevent severe system failures, minimize operational downtime, and reduce maintenance costs. One of the most common internal faults is a broken rotor bar. This study aims to implement Artificial Intelligence (AI) techniques to detect single and double broken bar faults in three-phase induction motors through current signal analysis. Current data from each phase (R, S, and T) were acquired and processed to extract Peak-to-Peak Current (Ipp) and Root Mean Square Current (Irms) values, which served as input parameters for the AI models. Three machine learning algorithms—Linear Regression, Random Forest, and Decision Tree—were implemented using Python on the Google Colaboratory platform. Evaluation results showed that the Linear Regression model achieved an accuracy of 89.83%, while both Random Forest and Decision Tree achieved 100% accuracy, demonstrating the superior capability of tree-based algorithms in accurately identifying fault patterns without misclassification. Compared to previous studies, this research offers advantages in both parameter comprehensiveness and result accuracy. Therefore, AI-based current signal analysis is proven to be an effective and non-invasive diagnostic method for rotor faults in three-phase induction motors.","\u003Cp>The early detection of induction motor faults is critical in industrial electrical systems to prevent severe system failures, minimize operational downtime, and reduce maintenance costs. One of the most common internal faults is a broken rotor bar. This study aims to implement Artificial Intelligence (AI) techniques to detect single and double broken bar faults in three-phase induction motors through current signal analysis. Current data from each phase (R, S, and T) were acquired and processed to extract Peak-to-Peak Current (Ipp) and Root Mean Square Current (Irms) values, which served as input parameters for the AI models. Three machine learning algorithms—Linear Regression, Random Forest, and Decision Tree—were implemented using Python on the Google Colaboratory platform. Evaluation results showed that the Linear Regression model achieved an accuracy of 89.83%, while both Random Forest and Decision Tree achieved 100% accuracy, demonstrating the superior capability of tree-based algorithms in accurately identifying fault patterns without misclassification. Compared to previous studies, this research offers advantages in both parameter comprehensiveness and result accuracy. Therefore, AI-based current signal analysis is proven to be an effective and non-invasive diagnostic method for rotor faults in three-phase induction motors.\u003C\u002Fp>","https:\u002F\u002Frepository.polinema.ac.id\u002Fcollection\u002Fdetail?id=dspace000004962&year=2025&title=implementing-artificial-intelligence-ai-to-enhance-fault-detection-and-diagnosis-system-based-on-current-consumption-of-the-broken-motor"]