Simangunsong, Jou (2026) Analisis Kesiapan Pengguna dan Infrastruktur Dalam Mendukung Penerapan Asset Health And Monitoring System Berbasis Kecerdasan Buatan Studi Kasus: Salah Satu Unit Induk Transmisi Listrik Di Indonesia. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5010221075-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5010221075-Undergraduate_Thesis.pdf - Published Version Restricted to Repository staff only Download (4MB) | Request a copy |
Abstract
Sistem transmisi listrik memiliki peran strategis dalam distribusi energi yang efisien dan andal melalui pengelolaan aset yang optimal pada asset health and monitoring system.
Kondisi eksisting pada salah satu unit induk transmisi listrik di Indonesia masih memanfaatkan asset health and monitoring system berbasis threshold yang rentan terhadap
false alarm dan belum optimal dalam deteksi dini kegagalan aset sehingga penerapan asset health and monitoring system berbasis kecerdasan buatan menjadi penting untuk meningkatkan keandalan sistem. Namun, keberhasilan penerapan teknologi baru tidak hanya bergantung pada kesiapan teknologi, tetapi juga kesiapan pengguna dan infrastruktur.
Penelitian ini bertujuan menganalisis tingkat kesiapan penerapan asset health and monitoring system berbasis kecerdasan buatan melalui kerangka Technology Readiness
Index 2.0 (TRI 2.0) untuk mengukur kesiapan pengguna, K-Means Clustering untuk segmentasi profil kesiapan pengguna, dan kerangka ISO 23247 untuk mengukur kesiapan infrastruktur. Hasil penelitian menunjukkan bahwa dari 121 responden, kesiapan pengguna berada pada kategori tinggi dengan nilai TRI 3.63. Dari analisis K-Means diperoleh tiga
segmentasi profil kesiapan pengguna, yaitu kelompok explorers dengan TRI 4.37 yang dinilai sangat antusias dalam menerapkan teknologi dan tidak memiliki hambatan, kelompok
skeptics dengan TRI 3.57 yang dinilai sudah memiliki motivasi namun disertai hambatan yang signifikan, dan kelompok avoiders dengan TRI 3.03 yang dinilai belum siap
menerapkan teknologi. Dari kesiapan infrastruktur, 22 Functional Entity berada pada level 2 dengan gap rata-rata 2.06 dari target level 4, menunjukkan bahwa infrastruktur belum siap mendukung penerapan asset health and monitoring system berbasis kecerdasan buatan.Berdasarkan hasil tersebut, langkah strategis untuk meningkatkan kesiapan pengguna, diantaranya Explorers didorong menjadi agen perubahan melalui program pelatihan praktis, Avoiders diajak memahami manfaat teknologi yang relevan dengan pekerjaannya, dan Skeptics dilibatkan langsung dalam proses evaluasi dan pengembangan sistem. Dari sisi kesiapan infrastruktur, dilakukan secara bertahap melalui empat tahap yang sesuai dengan arsitektur digital twin ISO 23247, mulai dari penguatan fondasi data, integrasi sistem, pengembangan kapabilitas, serta optimalisasi operasional dan pengambilan keputusan dalam mendukung penerapan asset health and monitoring system berbasis kecerdasan buatan.
===================================================================================================================================
Electric power transmission systems play a strategic role in the efficient and reliable distribution of energy through optimal asset management via an asset health and monitoring
system. The current condition at one of Indonesia’s main power transmission units still relies on a threshold-based asset health and monitoring system, which is prone to false alarms and is not yet optimal for the early detection of asset failures; therefore, the implementation of
an artificial intelligence-based asset health and monitoring system is crucial for improving system reliability. However, the success of implementing new technology depends not only
on technological readiness but also on user readiness and infrastructure. This study aims to analyze the readiness level for implementing an artificial intelligence-based asset health and monitoring system using the Technology Readiness Index 2.0 (TRI 2.0) framework to measure user readiness, K-Means Clustering for segmenting user readiness profiles, and the ISO 23247 framework to measure infrastructure readiness. The results show that out of 121
respondents, user readiness falls into the high category with a TRI score of 3.63. The KMeans analysis yielded three user readiness profile segments, the “explorers” group, with a TRI of 4.37, who are considered highly enthusiastic about adopting the technology and face
no barriers; the “skeptics” group, with a TRI of 3.57, who are considered motivated but face
significant barriers; and the “avoiders” group, with a TRI of 3.03, who are considered not yet ready to adopt the technology. In terms of infrastructure readiness, 22 Functional Entities are at Level 2 with an average gap of 2.06 from the target Level 4, indicating that the infrastructure is not yet ready to support the implementation of an AI-based asset health and
monitoring system. Based on these results, strategic steps to improve user readiness include encouraging “Explorers” to become agents of change through hands-on training programs,
helping “Avoiders” understand the benefits of technology relevant to their work, and directly involving “Skeptics” in the system evaluation and development process. Regarding
infrastructure readiness, improvements will be implemented gradually through four phases aligned with the ISO 23247 digital twin architecture, starting from strengthening data
foundations, system integration, and capability development to optimize operations and decision-making in support of the implementation of an artificial intelligence-based asset
health and monitoring system.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | asset health and monitoring system, kecerdasan buatan, technology readiness, kesiapan pengguna, kesiapan infrastruktur, asset health and monitoring system, artificial intelligence, technology readiness, user readiness, infrastructure readiness |
| Subjects: | T Technology > T Technology (General) > T57.5 Data Processing |
| Divisions: | Faculty of Industrial Technology and Systems Engineering (INDSYS) > Industrial Engineering > 26201-(S1) Undergraduate Thesis |
| Depositing User: | Jou Simangunsong |
| Date Deposited: | 31 Jul 2026 03:30 |
| Last Modified: | 31 Jul 2026 07:38 |
| URI: | http://repository.its.ac.id/id/eprint/140432 |
Actions (login required)
 |
View Item |