Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
Peralatan dan komponen di Pembangkit Listrik Tenaga Panas Bumi harus selalu diperhatikan keandalan serta ketersediaannya. Sehingga untuk memenuhi hal tersebut sangat diperlukannya program pemeliharaan atau maintenance. Hot well pump sendiri merupakan salah satu komponen utama yang sangat berpengaruh pada produktivitas sistem pembangkit listrik. Karena itulah reliability dan availability dari mesin sangat berpengaruh untuk sistem pembangkit secara keseluruhan. Peningkatan nilai availability ini dapat dilakukan dengan meningkatkan efektivitas daripada waktu operasi uptime mesin tersebut. Adapun sistem pemeliharaan yang dirasa tepat untuk meningkatkan availability tersebut adalah sistem pemeliharaan prediktif yang didasarkan pada kondisi aktual mesin condition-based maintenance. Dalam sistem ini, pemeliharaan akan dilakukan hanya ketika terdapat tanda-tanda penurunan performa mesin. Untuk itu dilakukan perancangan sebuah model prediksi dengan dengan pendekatan machine learning pada metode Classification Learner untuk mempelajari dan mengklasifikasikan rekaman data operasi mesin dalam jumlah besar dari sensor parameter mesin terkait dan menggunakan MATLAB sebagai perangkat lunak pengolah data. Model ini diharapkan dapat menjadi solusi dalam menentukan jadwal pemeliharaan mesin yang tepat sesuai dengan kondisi aktualnya. ......Equipments and components in the Geothermal Power Plant shall always be noted for its reliability and availability. It is very necessary a good maintenance program. Hot well pump itself is one of the main components that are very influential on the productivity of power generation systems. That is why reliability and availability of that machine is very influential for the overall generating system. The increased availability value can be achieved by increasing the effectiveness of the machine 39 s uptime operation time. The maintenance system that considered appropriate to increase availability is a predictive maintenance system based on the actual condition of the machine condition based maintenance. In this system, maintenance will be held only when there are signs of decreased machine performance. For that purpose, designing a prediction model with machine learning approach in Classification Learner method is used to study and classify the machine operation data record in large quantities from the sensor of that machine parameters and using MATLAB as a data processing software. This model is expected to be a solution in determining the exact machine maintenance schedule of machine in accordance with actual conditions.

Abstrak :
Gas turbin engine akan mengalami degradasi sejalan dengan waktu menjadi perhatian utama perusahaan oil dan gas karena akan berpengaruh terhadap engine reliability, availability, dan maintenance cost.Time based maintenance mengabaikan kondisi performance gas turbin apakah dalam kondisi sehat atau rusak, tetap dilakukan overhaul jika telah tercapai TBO Time Between Overhaul antara 25.000 jam. Kerusakan pada gas turbin sebelum TBO sulit terdeteksi. Performance monitoring mampu mendeteksi degradasi gas turbin sehingga membantu penggunanya untuk beralih dari Time based ke Condition Based Maintenance. Dari pola degradasi gas turbin, dapat ditentukan prediksi sisa umur pakai dengan menggunakan metode regresi dan analisa resiko.

---

Gas turbine will experience performance degradation align with operation time. The degradation of gas turbine performance will be main focus in oil and gas company since its affecting to the reliability, availability, and maintenance cost.Time based maintenance was ignoring gas turbine performance whether it still can be running or it will be failed, gas turbine overhaul is still carried out when running hours reached Time Between Overhaul TBO at 25.000 hours. Gas turbine failure before overhauling schedule is difficult to predict when time based maintenance strategy applied. Performance monitoring can detect gas turbine degradation so that assist oil and gas company as the user to change their maintenance program from Time Based to Condition Based Maintenance.Based on gas turbine performance degradation pattern. It can be determined the remaining useful life of gas turbine prior to overhauling by using regression method and carry out risk analysis.

Abstrak :
Industri Minyak Bumi di Indonesia tergantung terhadap trend harga minyak yang berfluktuasi. Harga minyak yang cenderung menurun mengharuskan perusahaan melakukan efisiensi dalam operasinya. Salah satunya fokusnya adalah terhadap sistem pemeliharaan karena investasi pemeliharaan sangat signifikan terutama di industri minyak bumi. Pemilihan strategi pemeliharaan harus mengacu kepada kinerja kehandalan dan ketersediaan, dan juga efektifitas biaya total pemeliharaan. Pemeliharaan berbasis kondisi adalah salah satu strategi yang dipandang mempunyai efektifitas biaya yang tinggi. Penelitian ini mengenai analisis biaya dan manfaat dari strategi pemeliharaan berbasis kondisi pada industri minyak bumi di Indonesia. Beberapa perusahaan melakukan pemeliharaan berbasis kondisi untuk mengoptimalkan interval kegiatan inspeksi dengan mengawasi parameter dari peralatan baik secara manual ataupun pemasangan alat monitor di peralatan tersebut.

---

Crude oil industry depends on the trend of world oil price. The oil price trend has been decreasing in the last five years. As a results, crude oil industry has to minimize their operation cost. Maintenance have significant contribution to operation cost. One focus to minimize operation cost is by maintenance strategy selection. The selection must be based on reliability, availability and total maintenance cost. Condition based maintenance is a maintenance strategy which seen as highly cost effective strategy. The objective of this research is to analyze condition based maintenance implementation on an oil production facility in Indonesia. Finding indicates that condition based maintenance could reduce total maintenance cost up to 60% in ideal condition.

Abstrak :
Pemeliharaan merupakan hal terpenting dalam menjalankan sebuah sistem produksi yang melibatkan aset yang besar, termasuk pada Pembangkit Listrik Tenaga Panas Bumi. Pemeliharaan mesin berbasis kondisi mesin Condition-Based Maintenance dirasa efektif dalam menjaga performa mesin. Kondisi mesin dapat diketahui melalui data operasi yang ada. Salah satu pendekatan yang dapat mempelajari dan mengolah ribuan data operasi yang terekam oleh sensor-sensor parameter keseluruhan data operasi yang ada adalah dengan pendekatan machine learning. Data operasi tersebut kemudian akan dibagi menjadi beberapa kategori yaitu long, medium dan short dengan batasan berupa lama waktu aset tersebut beroperasi. Data tersebut kemudian akan menjalani proses training menggunakan aplikasi Classification Learner pada software MATLAB. Proses ini memungkinkan MATLAB mempelajari hubungan antar parameter, waktu dan kategori yang dibuat hingga menghasilkan sebuah model klasifikasi kondisi mesin. Model tersebut kemudian digunakan untuk memprediksi kondisi turbin terkini yang kemudian dapat diperkirakan berapa lama lagi turbin dapat beroperasi dengan baik sampai turbin membutuhkan kegiatan pemeliharaan kembali. ......Maintenance is the most important thing in running a large production system that is using some machinery such as turbines, pumps and so on. This is also applied for a geothermal power plants that have so many assets to maintain. Condition based maintenance is considered to be the most effective maintenance management to be applied for a big scale industrial company. Machines condition could be known from the machines operation data that is continously recorded by the censors of some parameter. One of the most suitable approach to learn and process the big operation data is machine learning. The operation data will be classified into three categories, there are long category, medium category and short category, which has its limit based on the length of time the machine has been operating. Then, the operation data will be trained using Classification Learner toolbox of MATLAB. This process let MATLAB understands the relationship between each parameter, time and the categories until a classification model of machines condition has been produced. The model later could be used to predict the most recent machines condition so that we can also predict how long the machine could still operate well until it needs to be maintained again.

Abstrak :
ABSTRACT
The joint optimization of condition-based opportunistic maintenance and (0,1)-type spare part inventory policy is investigated for a two-component system. Deterioration state-space partitioning (DSSP) of the observed state and the spare part inventory state is developed to analyze all the possible maintenance requirements of the system and calculate the probabilities of the actual maintenance activities with the restriction of the inventory state, as well as the probabilities of ordering and holding of spare parts. An expression of the stationary law of the joint state and its numeric solution are deduced based on an analysis of all the possible transitions of the joint state during an inspection cycle. Further, an expected long-run cost rate model of the operation of the system under the proposed policy was developed to determine the optimal joint strategy which involved a semi-regenerative process theory. Finally, numerical experiments were performed.