Vorenza, Pebiria (2022) Data Analitik Pada Pengembangan Layer Of Protection Analysis (Lopa) Dan Augmented Analytics System Untuk Mengoptimalkan Safety Integrity Level (SIL) Pada Sistem Pintu Otomatis Kereta Api. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 02411840000031-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
02411840000031-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (5MB) | Request a copy |
Abstract
Menentukan persyaratan khusus safety dari sistem keselamatan merupakan bagian penting dalam memastikan bahwa bahaya dapat dicegah. PT XYZ merupakan perusahaan manufaktur kereta api di Indonesia yang mengikuti standarisasi International Electrotechnical Commission (IEC) untuk menentukan tingkat keamanan produknya berupa sertifikasi Safety Integrity Level (SIL). Dalam memastikan tingkatan safety sesuai standarisasi, maka perlu dilakukan proses validasi hasil testing produk menggunakan perhitungan SIL Assessment. Di sisi lain, pentingnya mempercepat pendeteksian kegagalan produk merupakan hal yang krusial untuk dikembangkan. Tingkat ketangkasan yang tinggi akan mendukung proses akselerasi fungsi keamanan produk. Tugas Akhir ini membahas tentang pentingnya memvalidasi tingkat keamanan dan upaya meningkatkan kecepatan mendeteksi kegagalan produk yang dibatasi pada lingkup objek Door System. Berdasarkan hasil perhitungan nilai SIL Assessment diperoleh SIL 0. Nilai ini lebih kecil dari rata-rata standarisasi minimum yang ditetapkan perusahaan, sehingga perlu dilakukan identifikasi dan evaluasi secara lebih luas pada keseluruhan Safety Instrumented System (SIS) dari Door System. Hal ini bertujuan untuk mendapatkan rekomendasi skenario peningkatan nilai SIL menggunakan metode Layer of Protection Analysis (LOPA). Berdasarkan hasil evaluasi LOPA diperoleh nilai SIL 0 sebanyak tiga impact event, nilai No Risk (NR) sebanyak empat impact event, dan SIL 1 sebanyak tujuh impact event. Pada perhitungan SIL Assessment, nilai SIL menunjukkan nilai kondisi aktual, sedangkan pada LOPA nilai SIL menunjukkan gap antara target pengurangan risiko dengan kondisi aktual, sehingga nilai SIL 0 berarti lapisan pelindung telah mampu mengurangi potensi risiko. Nilai No Risk (NR) berarti lapisan pelindung sangat mampu mereduksi sehingga tidak ada potensi risiko. SIL 1 berarti perlu menaikkan nilai SIL satu tingkat agar dapat mereduksi potensi risiko. Selain itu, upaya peningkatan kecepatan prediksi kegagalan dilakukan dengan membangun algoritma klasifikasi Machine Learning yang dikembangkan secara terintegrasi mulai dari input hingga hasil analisis pada prototype dashboard. Terbentuknya algoritma otomatis dan terintegrasi ini merupakan wujud dari pengembangan Automated Analytics System.
====================================================================================================================================
Determining the specific safety requirements of a safety system is an important part of ensuring that hazards are prevented. PT XYZ is a train manufacturing company in Indonesia that follows the International Electrotechnical Commission (IEC) standard to determine the safety level of its products in the form of Safety Integrity Level (SIL) certification. Ensuring that the safety level is following standardization, it is necessary to validate the product testing results using the SIL Assessment calculation. On the other hand, the importance of accelerating the detection of product failures is a crucial thing to develop. A high level of agility will support the process of accelerating the security function of the product. This article discusses the issue of the importance of validating security levels and increasing the speed of detecting product failures that are limited to the scope of Door System objects. The result of the calculation of the SIL Assessment score is SIL 0. This value is smaller than the minimum standardization average set by the company, so it is necessary to identify and evaluate more broadly the entire SIS Door System. It aims to obtain a scenario recommendation for increasing the SIL value using the Layer of Protection Analysis (LOPA) method. The results of the LOPA evaluation obtained SIL 0 values for three impact events, No Risk (NR) values for four impact events, and SIL 1 for seven impact events. In the SIL Assessment calculation, the SIL value indicates the value of the actual condition, while in LOPA the SIL value indicates the gap between the risk reduction target and the actual condition, so a SIL value of 0 means that the protective layer has been able to reduce the potential risk. The No Risk (NR) value means that the protective layer is very capable of reducing so that there is no potential risk. SIL 1 means that it is necessary to increase the SIL value by one level to able reduce the potential risk. In addition, efforts to increase the speed of failure prediction are carried out by establishing a Machine Learning classification algorithm that is developed in an integrated manner starting from input to analysis results on the dashboard prototype. The formation of this automated and integrated algorithm is a manifestation of the development of the Automated Analytics System.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Automated Analytics System, Layer of Protection Analysis, Machine Learning, Safety Integrity Level Assessment. |
| Subjects: | Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. |
| Divisions: | Faculty of Industrial Technology and Systems Engineering (INDSYS) > Industrial Engineering > 26201-(S1) Undergraduate Thesis |
| Depositing User: | Mr. Marsudiyana - |
| Date Deposited: | 09 Feb 2026 01:14 |
| Last Modified: | 09 Feb 2026 01:14 |
| URI: | http://repository.its.ac.id/id/eprint/132259 |
Actions (login required)
 |
View Item |