Pengembangan Model Digital Autonomous Maintenance Pada Industri Komponen Otomotif Di Indonesia

Widya, Adi Rusdi (2025) Pengembangan Model Digital Autonomous Maintenance Pada Industri Komponen Otomotif Di Indonesia. Doctoral thesis, Insitut Teknologi Sepuluh Nopember, Surabaya.

Text 7010211011-Dissertation.pdf - Accepted Version Restricted to Repository staff only Download (6MB) | Request a copy

Abstract

Revolusi Industri 4.0 telah mengubah cara kerja manusia, menuntut perusahaan untuk memastikan keandalan dan optimalisasi mesin agar tetap kompetitif. Strategi perawatan yang tepat menjadi penting untuk menjaga performa mesin. Meski Total Productive Maintenance (TPM) telah diterapkan, penerapan autonomous maintenance (AM) masih terkendala pada disiplin dan konsistensi. Penelitian ini bertujuan mengembangkan Digital Autonomous Maintenance (DAM) berbasis teknologi Internet of Things (IoT) dan monitoring real-time untuk meningkatkan efektivitas AM dan mempermudah operator. DAM dirancang melalui identifikasi kebutuhan operasional, pemetaan aktivitas AM yang kritis, serta integrasi sensor, dashboard digital, dan notifikasi otomatis ke dalam alur kerja operator. Sistem ini responsif terhadap kondisi mesin dan perilaku operator, dengan kinerja diukur melalui indikator keandalan dan performa mesin. Metode ini juga mempermudah pengendalian AM agar lebih cepat, tepat, dan aman. Implementasi DAM terbukti secara signifikan meningkatkan efisiensi operasional. Data menunjukkan kenaikan Overall Equipment Effectiveness (OEE) dari 61,1% menjadi 87,0%, atau meningkat 42,4%, melalui peningkatan ketersediaan mesin, performa, dan kualitas produk. Peningkatan ini didorong oleh penurunan kerusakan mendadak dan percepatan respons operator. Dibanding AM tradisional, DAM memberikan manfaat langsung seperti mempercepat inspeksi dan perawatan melalui monitoring real-time dan notifikasi otomatis; mengurangi human error berkat panduan digital dan sensor berbasis data; meningkatkan visibilitas kondisi mesin melalui dashboard yang mudah diakses; serta mempercepat pengambilan keputusan berbasis data. DAM juga memungkinkan perawatan yang lebih proaktif dan prediktif, menekan frekuensi kerusakan mendadak, mengurangi downtime, serta meringankan beban kerja operator. Dengan demikian, DAM tidak hanya meningkatkan efisiensi dan keandalan mesin, tetapi juga meningkatkan kenyamanan dan produktivitas operator. Hasil penelitian ini dapat digunakan sebagai panduan manajerial bagi perusahaan dalam memilih strategi perawatan yang lebih tepat, optimal, dan berbasis teknologi. Penelitian ini memiliki kebaruan pada integrasi AM v konvensional dengan teknologi digital IoT, sensor pintar, dan dashboard interaktif, untuk pemantauan real-time serta pengambilan keputusan berbasis data. Manfaatnya meliputi peningkatan keandalan mesin, efisiensi energi, pengurangan biaya, dan dukungan green manufacturing. Batasan penelitian mencakup kebutuhan infrastruktur IoT, kompatibilitas mesin dengan sensor, kesiapan SDM, kapasitas data, serta lingkup uji terbatas pada industri komponen otomotif di Indonesia.
========================================================================================================================
The Fourth Industrial Revolution has transformed the way people work, compelling companies to ensure machine reliability and optimization to remain competitive. An appropriate maintenance strategy is essential to sustain machine performance. Although Total Productive Maintenance (TPM) has been implemented, the application of Autonomous Maintenance (AM) still faces challenges in discipline and consistency. This study aims to develop a Digital Autonomous Maintenance (DAM) system based on Internet of Things (IoT) technology and real-time monitoring to enhance AM effectiveness and facilitate operator tasks. DAM is designed through operational needs identification, mapping of critical AM activities, and integrating sensors, digital dashboards, and automatic notifications into the operator workflow. The system is responsive to both machine conditions and operator behavior, with performance measured by reliability and machine performance indicators. This method also simplifies AM control, making it faster, more accurate, and safer. Implementation of DAM has been proven to significantly improve operational efficiency. Data show an increase in Overall Equipment Effectiveness (OEE) from 61.1% to 87.0%, representing a 42.4% improvement through enhanced machine availability, performance, and product quality. This improvement is driven by reduced sudden breakdowns and faster operator response. Compared to traditional AM, DAM provides direct benefits such as accelerating inspections and maintenance through real-time monitoring and automatic notifications; reducing human error with digital guidance and data-driven sensors; improving machine condition visibility through easily accessible dashboards; and expediting data-driven decision-making. DAM also enables more proactive and predictive maintenance, minimizing unexpected failures, reducing downtime, and easing operator workload. Consequently, DAM not only increases machine efficiency and reliability but also enhances operator comfort and productivity. The findings of this study can serve as managerial guidance for companies in selecting more accurate, optimal, and technology-based maintenance strategies. The novelty of this research lies in integrating conventional AM with digital IoT technology, smart sensors, and interactive dashboards for real-time monitoring and data-driven viii decision-making. The benefits include improved machine reliability, energy efficiency, cost reduction, and support for green manufacturing. Limitations of this study include IoT infrastructure requirements, machine–sensor compatibility, workforce readiness, data capacity, and testing scope limited to the automotive components industry in Indonesia.

Item Type:	Thesis (Doctoral)
Uncontrolled Keywords:	TPM, AM, DAM, OEE, IoT, Real-Time Monitoring
Subjects:	T Technology > T Technology (General) > T58.6 Management information systems T Technology > TS Manufactures > TS174 Maintainability (Engineering) . Reliability (Engineering)
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Industrial Engineering > 26001-(S3) PhD Thesis
Depositing User:	Adi Rusdi Widya
Date Deposited:	05 Aug 2025 11:31
Last Modified:	05 Aug 2025 11:31
URI:	http://repository.its.ac.id/id/eprint/127613

Actions (login required)

View Item