[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-id-113":3,"doc-seo-120382-113":53,"doc-detail-120382-id":124},{"code":4,"msg":5,"data":6},0,"success",[7,13,17,21,25,29,33,37,41,45,49],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},55,"Document","Agama & Spiritualitas",60,"religion-spirituality",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":11,"slug":16},48,"Cerita & Novel","story-novel",{"id":18,"doc_module":4,"doc_module_name":9,"category_name":19,"show_sort_weight":11,"slug":20},56,"Gaya Hidup","lifestyle",{"id":22,"doc_module":4,"doc_module_name":9,"category_name":23,"show_sort_weight":11,"slug":24},51,"Komik","comic",{"id":26,"doc_module":4,"doc_module_name":9,"category_name":27,"show_sort_weight":11,"slug":28},53,"Layanan Kesehatan","healthcare",{"id":30,"doc_module":4,"doc_module_name":9,"category_name":31,"show_sort_weight":11,"slug":32},54,"Penelitian & Laporan","research-report",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":11,"slug":36},49,"Sastra","literature",{"id":38,"doc_module":4,"doc_module_name":9,"category_name":39,"show_sort_weight":11,"slug":40},52,"Teknologi","technology",{"id":42,"doc_module":4,"doc_module_name":9,"category_name":43,"show_sort_weight":11,"slug":44},50,"Ujian","exam",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":47,"show_sort_weight":11,"slug":48},57,"Umum","general",{"id":50,"doc_module":4,"doc_module_name":9,"category_name":51,"show_sort_weight":4,"slug":52},181,"Formulir","formulir",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":117,"head_meta":119,"extra_data":121,"updated_unix":123},113,"id","application-of-machine-learning-for-vibration-based-bearing-condition-monitoring","Penerapan Machine Learning untuk Monitoring Kondisi Bantalan Berbasis Getaran","","Kerusakan bearing merupakan masalah umum yang berkontribusi terhadap 40% kegagalan mesin. Machine learning, bagian dari kecerdasan buatan, membangun model prediktif dari data historis untuk meningkatkan akurasi perkiraan kondisi masa depan. CNN dimanfaatkan karena akurat mengenali pola pada citra. Penelitian menggunakan sistem motor poros dengan kecepatan konstan 3000 dan 4000 rpm, merekam data getaran memakai akselerometer, lalu mengonversi data menjadi spectrogram dan membagi data latih-uji 8:2. Pelatihan CNN menghasilkan akurasi di atas 99% dengan keyakinan prediksi 47,5%.",{"@graph":63,"@context":116},[64,81,103],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,72,75,78],{"item":68,"name":69,"@type":70,"position":71},"https://docshare.wps.com","Home","ListItem",1,{"item":73,"name":9,"@type":70,"position":74},"https://docshare.wps.com/id/document/",2,{"item":76,"name":31,"@type":70,"position":77},"https://docshare.wps.com/id/document/penelitian-laporan/",3,{"item":79,"name":59,"@type":70,"position":80},"https://docshare.wps.com/id/document/application-of-machine-learning-for-vibration-based-bearing-condition-monitoring/120382/",4,{"url":79,"name":59,"@type":82,"image":83,"author":88,"headline":59,"publisher":91,"fileFormat":94,"inLanguage":57,"description":61,"dateModified":95,"datePublished":96,"encodingFormat":94,"isAccessibleForFree":97,"interactionStatistic":98},"DigitalDocument",{"url":84,"@type":85,"width":86,"height":87},"https://docshare.wps.com/thumbnails/application-of-machine-learning-for-vibration-based-bearing-condition-monitoring/120382.png","ImageObject",300,407,{"name":89,"@type":90},"Sage","Person",{"url":68,"name":92,"@type":93},"DocShare","Organization","application/pdf","2026-09-19","2026-08-03",true,{"@type":99,"interactionType":100,"userInteractionCount":102},"InteractionCounter",{"@type":101},"ViewAction",7,{"@type":104,"mainEntity":105},"FAQPage",[106,112],{"name":107,"@type":108,"acceptedAnswer":109},"Bagaimana data dipersiapkan sebelum dilatih dengan CNN?","Question",{"text":110,"@type":111},"Data getaran diubah menjadi citra spectrogram, lalu dibagi menjadi data latih dan data uji dengan perbandingan 8:2 (384 gambar latih dan 96 gambar uji).","Answer",{"name":113,"@type":108,"acceptedAnswer":114},"Seberapa baik performa model yang dihasilkan?",{"text":115,"@type":111},"Model CNN mencapai akurasi di atas 99%, dan hasil prediksi menunjukkan keberhasilan mendeteksi kerusakan bantalan dengan tingkat keyakinan prediksi 47,5%.","https://schema.org",{"og:url":79,"og:type":118,"og:title":59,"og:site_name":92,"og:description":61},"article",{"robots":120,"canonical":79},"index,follow",{"doc_id":122,"site_id":56},120382,1785729749,{"code":4,"msg":5,"data":125},{"doc_id":122,"user_id":126,"nickname":89,"user_avatar":127,"doc_module":4,"category_id":30,"category_name":31,"doc_title":59,"doc_description":61,"doc_content":128,"file_id":129,"file_url":130,"file_type":131,"file_size":132,"view_count":102,"is_deleted":4,"is_public":71,"is_downloadable":71,"audit_status":71,"page_count":77,"language":133,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":134,"faqs":135,"seo_title":136,"seo_description":61,"update_tm":123,"read_time":137},549768702563,"https://ap-avatar.wpscdn.com/avatar/8000c4aa63b76e948b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786536092046926083","TUGAS AKHIR  \nPENERAPAN MACHINE LEARNING UNTUK MONITORING KONDISI BANTALAN BERBASIS  \nGETARAN  \nOleh:  \nMUHAMMAD KHALISH  \nNIM. 1810912014  \nPembimbing:  \nProf. Dr. Eng. Meifal Rusli  \nHendery Dahlan, Ph.D  \nDEPARTEMEN TEKNIK MESIN FAKULTAS TEKNIK UNIVERSITAS ANDALAS PADANG  \nABSTRACT  \nBearing damage is common issue and contributes to 40% of machine failure. Machine learning is a subset of artificial intelligence that enables computers to build predictive models based on past data, improving accuracy in forecasting future conditions. Convolutional Neural Network (CNN) is widely used for classification due to their high accuracy in recognizing image patterns among machine learning algorithms. Early detection of machine damage, reducing maintenance costs and time becomes possible by employing machine learning. In this study, a simple shaft motor system operates with the assumption of a stable speed at 3000 rpm and 4000 rpm. Both normal and damaged stated bearings are installed alternately and vibration data is recorded using an accelerometer. Then, the data is stored and uploaded to Google Drive for processing using Google Colaboratory. After that, the data is converted into spectrogram images and splitted into training data and testing data with a ratio of 8:2 where the training data and testing data amount to 384 images and 96 images respectively. Then, the data is trained using the CNN method which produces an accuracy above 99%. The prediction results show that the model successfully predicted bearing damage with a model confidence level in predicting 47,5%.  \nKeyword: Bearing Defect, Vibration Analysis, Convolutional Neural Network (CNN), Machine Learning, Spectrogram  \nABSTRAK  \nKerusakan bearing merupakan masalah yang umum terjadi dan berkontribusiterhadap 40% dari keseluruhan kegagalan mesin. Machine Learning, bagian darikecerdasan buatan, memungkinkan komputer untuk membangun model prediktifberdasarkan data masa lalu, meningkatkan akurasi dalam memperkirakan kondisi di masa mendatang. Convolutional Neural Network (CNN) merupakan algoritmayang popular digunakan dengan keakuratannya yang tinggi dalam mengenaligambar diantara algoritma yang lain. Deteksi awal kerusakan mesin, pengurangan biaya dan waktu maintenance dapat dilakukan dengan menerapkan machine learning. Penelitian ini menggunakan sistem motor poros sederhana yang dijalankan dengan asumsi kecepatan putar konstan pada 3000 rpm dan 4000 rpm. Bantalan normal dan bantalan dengan kondisi rusak dipasang pada dudukan secara bergantian dan data getaran direkam menggunakan akselerometer. Data kemudian disimpan dan diunggah ke Google Drive untuk diproses menggunakan Google Colaboratory. Kemudian, data diubah menjadi citra spectrogram dan dibagimenjadi data latih dan data uji dengan perbandingan 8:2 dimana data latih dan data uji berjumlah masing-masing 384 gambar dan 96 gambar. Data tersebut kemudian dilatih menggunakan metode CNN yang menghasilkan akurasi diatas 99% . Hasilprediksi menunjukan model berhasil memprediksi kerusakan bantalan dengantingkat keyakinan model dalam memprediksi 47,5% .  \nKata Kunci: Kerusakan Bantalan, Analisis Getaran, Convolutional Neural Network (CNN), Machine Learning, Spectrogram.","cbCailoFdCXnznnQ","https://ap.wps.com/l/cbCailoFdCXnznnQ","pdf",101341,"Indonesian","# Abstrak\n## Latar Belakang\n## Metode dan Pengumpulan Data\n## Pemrosesan Data\n## Pelatihan CNN dan Hasil\n## Kata Kunci","[{\"question\":\"Bagaimana data dipersiapkan sebelum dilatih dengan CNN?\",\"answer\":\"Data getaran diubah menjadi citra spectrogram, lalu dibagi menjadi data latih dan data uji dengan perbandingan 8:2 (384 gambar latih dan 96 gambar uji).\"},{\"question\":\"Seberapa baik performa model yang dihasilkan?\",\"answer\":\"Model CNN mencapai akurasi di atas 99%, dan hasil prediksi menunjukkan keberhasilan mendeteksi kerusakan bantalan dengan tingkat keyakinan prediksi 47,5%.\"}]","Penerapan Machine Learning untuk Monitoring Kondisi Bantalan Berbasis Getaran | PDF",5]