Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
ABSTRAK
Kualitas bergantung pada kehandalan suatu produk, khususnya pada peralatan yang dipakai di industri manufaktur, contohnya boiler. Kehandalan dari boiler dilihat dari performa boiler tersebut. Ketergantungan parameter satu dengan yang lainnya dapat meningkatkan kompleksitas operasi boiler. Meskipun pada boiler dengan beban dibawah rancangan awal. Fenomena ini terjadi akibat pergeseran penentuan kebijakan pada pemilik perusahaan yang memilih untuk membeli boiler dengan beban kerja penuh dimasa yang akan datang, namun digunakan dengan beban rendah saat ini. Dapat dicontohkan dengan perusahaan produsen minuman ringan yang memiliki perencanaan penambahan beban dala dua tahun mendatang, membutuhkan 4 ton uap air/jamnya sedangkan untuk saat ini beban kerja yang dibutuhkan hanya 2 ton uap air/jamnya. Sehinggaefesiensi area dari performa boiler hanya berkisar 15-30 persen. Hal ini membuat resiko yang sangat berpotensi untuk mengalami kegagalan. Dibutuhkan pendeteksi kegagalan untuk mengetahui dan menjaga kehandalan dari performa boiler. Kunci utamanya adalah memonitor hubungan antar parmeter dan mendeteksi kegagalan yang mungkin terjadi. Permasalahan utama adalah banyaknya parameter yang berhubungan, analisa data dapat dilakukan dengan mudah menggunakan Data Mining. Salah satu teknikmenganalisa data bernama Artificial Neural Network ANN dapat mendeteksi kegagalan apabila digabungkan dengan back-propagation. Dengan permodelan dan validasi terlebih dahulu diharapkan dapat mendeteksi kegagalan pada performa boiler.

---

ABSTRACT
Quality depends on equipment rsquo s reliability especially in industrial manufacturing equipment, such as boiler. Boiler rsquo s reliability relies on its performance. It is important to maintain boiler rsquo s performance as designed. Boiler rsquo s performance depends on many parameters, which is related to the operating procedure. Therefore, many parameters correlation could cause lot of complexities in boiler rsquo s operating process. Even in a small load boiler such as boiler in food manufacturing industry. The boiler rsquo s performance efficiency area ranges between 15 30 percent. It has a potential risk to fail, when the range approaches to zero. A fault detection is necessary to get boiler rsquo s performance works as reliable as it designed. The key is to monitor parameters correlation and detect any fault that could happen before it occurs. The problem is, there are lot of parameters correlation could happen in boiler rsquo s operating process that could cause failure. By analyzing many parameters correlation in boiler operation, Data Mining could approach a fault detection easier. The purpose of Data Mining is to monitor boiler performance parameters. An Artificial Neural Network ANN would present a smart fault detection model if it is combined with back propagation, because it will train the program itself and learn which condition should be alarmed. At the end, the proposed model could detect a fault by monitoring boiler rsquo s performance.

Abstrak :
ABSTRAK
Synthesis loop merupakan salah satu sistem kritis di pabrik amoniak. Oleh karena itu, ada urgensi untuk menjaga reliability dan availability pada sistem ini. Sebagian besar peristiwa shutdown di pabrik amoniak terjadi tiba-tiba setelah alarm tercapai. Jadi, perlu ada sistem deteksi dini untuk memastikan masalah anomali ditangkap oleh operator sebelum menyentuh set point alarm. Implementasi algoritma machine learning dalam membuat model deteksi potensi kegagalan telah digunakan di berbagai industri dan objek sebagai penelitian. Algoritma yang digunakan adalah classifier dasar dan ensemble untuk membandingkan algoritma mana yang menghasilkan hasil klasifikasi terbaik. Penelitian ini dapat memberikan ide dan perspektif baru ke dalam industri pabrik amoniak untuk mencegah terjadinya shutdown yang tidak terjadwal dengan memanfaatkan data menggunakan algoritma machine learning.

---

ABSTRACT
Synthesis loop is one of the critical systems in ammonia plant. Therefore, there is urgency for maintaining the reliability and availability of this system. Most of the shutdown events occur suddenly after the alarm is reached. So, there needs to be an early detection system to ensure anomaly problem captured by the operator before touching the alarm settings. The implementation of machine learning algorithms in making fault detection models has been used in various industries and objects. The algorithm used is the basic and ensemble classifier to compare which algorithms generate the best classification results. This research can provide a new idea and perspective into ammonia plant industry to prevent unscheduled shutdown by utilizing data using machine learning algorithm.

Abstrak :
Perlindungan pada sistem tenaga listrik harus dirancang untuk memenuhi prinsip kehandalan, selektivitas, dan prinsip kestabilan, yang dapat dicapai melalui zonasi dan koordinasi proteksi. Dalam hal deteksi dan koordinasi proteksi gangguan tanah, sistem harus mempertimbangkan alokasi pentanahan dan kesesuaian hubungan, seperti pentanahan solid atau impedansi. Oleh karena itu, pemilihan lokasi dan koneksi pentanahan yang tidak tepat dapat menyebabkan gangguan yang tidak diinginkan dan kegagalan yang bertingkat. Studi ini menyajikan desain korektif untuk deteksi dan koordinasi proteksi gangguan hubung singkat satu fasa ke tanah. Sistem pentanahan dievaluasi dengan menggunakan rangkaian urutan nol untuk memperkirakan gangguan yang dapat terjadi pada sistem. Implementasi dari Standar IEEE 142-2007 digunakan untuk menyediakan sistem yang terhubung secara efektif, yang menghasilkan lokasi dan koneksi yang sesuai untuk pentanahan. Simulasi dilakukan dengan menggunakan perangkat lunak analisis sistem tenaga untuk membandingkan kinerja sebelum dan setelah desain korektif yang diusulkan. Hasilnya menunjukkan bahwa desain yang diusulkan dapat mengoreksi kesalahan operasi proteksi kesalahan tanah. ......Power system protection must be designed to meet the reliability, selectivity, and stability principle, which can be achieved through zoning and coordination. In the case of ground fault protection detection and coordination, the appropriate grounding allocation and connection, i.e. solid or impedance, shall be considered throughout the system. Hence, inaccurate selection for grounding location and connection may lead to undesirable disturbances and cascaded failure. This paper presents a corrective design for ground fault protection detection and coordination in an actual 34.5 kV power system network which has faced several misoperation of the ground fault protection. For this, the system’s grounding is assessed by using zero sequence network and the issues are summarized. The implementation of IEEE 142-2007 Standard is utilized to provide an effectively grounded system, resulting in the suitable location and connection for the grounding. The simulation is carried out by using power system analysis software to compare the performances before and after the proposed corrective design. The results shows that the proposed design can solve the misoperation of the ground fault protection.

Abstrak :
Pemeliharaan prediktif pada stasiun pengamatan gempa bumi dan tsunami menjadi sangat penting sebagai kualitas kontrol atau pengendalian mutu. Saat ini penentuan kualitas stasiun pengamatan gempa bumi dan tsunami dilakukan secara pemeliharaan preventif dan pemeliharaan korektif dimana seorang pakar akan melakukan pemeliharaan secara berkala ataupun melakukan pemeliharaan apabila keadaan stasiun pengamatan gempa bumi dan tsunami mengalami kerusakan total. Pada penelitian ini pemeliharaan prediktif dilakukan pada seismometer dua stasiun yang berdekatan dengan menganalisis dalam domain frekuensi. Data yang digunakan adalah sinyal seismik pada rekaman seismometer tiga komponen (North-South, East-West, Z-Vertical) pada jaringan stasiun pengamatan gempa bumi dan tsunami. Rancangan penelitian ini yaitu rekaman sinyal seismik pada dua stasiun diubah dalam domain frekuensi menjadi power spectral density kemudian dilakukan cross spectral density dan mendapatkan nilai koherensi dari cross spectral density. Kemudian nilai tersebut menjadi feature untuk machine learning dan label untuk machine learning diberikan oleh pakar dari Badan Meteorologi Klimatologi dan Geofisika. Evaluasi dengan model machine learning berbasis data koherensi cross spectral density pada fault detection seismometer berdasarkan machine learning yang dipakai adalah random forest dan xgboost dengan memiliki akurasi 0,89 dan 0,91. Selain itu, waktu training untuk permodelan xgboost lebih cepat daripada random forest. ......Predictive maintenance of earthquake and tsunami observation stations is very important for quality control. Currently, the determination of the quality of earthquake and tsunami observation stations is carried out by preventive maintenance and corrective maintenance, where an expert will perform regular maintenance or perform maintenance if the earthquake and tsunami observation station is completely damaged. In this research, predictive maintenance is carried out on the seismometers of two adjacent stations by analyzing in the frequency domain. The data used are seismic signals in three-component seismometer recordings (North-South, East-West, Z-Vertical) in the earthquake and tsunami observation station network. The design of this research is that seismic signal recordings at two stations are converted in the frequency domain into power spectral density, then cross spectral density is carried out and the coherence value of the cross spectral density is obtained. Then the value becomes a feature for machine learning and the label for machine learning is given by experts from the Meteorology Climatology and Geophysics Agency. Evaluation with machine learning models based on cross spectral density coherence data on seismometer fault detection based on machine learning used is random forest and xgboost with an accuracy of 0.89 and 0.91. In addition, the training time for xgboost modeling is faster than random forest.

Abstrak :
This book provides a complete picture of several decision support tools for predictive maintenance. These include embedding early anomaly/fault detection, diagnosis and reasoning, remaining useful life prediction (fault prognostics), quality prediction and self-reaction, as well as optimization, control and self-healing techniques. It shows recent applications of these techniques within various types of industrial (production/utilities/equipment/plants/smart devices, etc.) systems addressing several challenges in Industry 4.0 and different tasks dealing with Big Data Streams, Internet of Things, specific infrastructures and tools, high system dynamics and non-stationary environments . Applications discussed include production and manufacturing systems, renewable energy production and management, maritime systems, power plants and turbines, conditioning systems, compressor valves, induction motors, flight simulators, railway infrastructures, mobile robots, cyber security and Internet of Things. The contributors go beyond state of the art by placing a specific focus on dynamic systems, where it is of utmost importance to update system and maintenance models on the fly to maintain their predictive power.

Abstrak :
This book provides readers with a timely snapshot of the potential offered by and challenges posed by signal processing methods in the field of machine diagnostics and condition monitoring. It gathers contributions to the first Workshop on Signal Processing Applied to Rotating Machinery Diagnostics, held in Setif, Algeria, on April 9-10, 2017, and organized by the Applied Precision Mechanics Laboratory (LMPA) at the Institute of Precision Mechanics, University of Setif, Algeria and the Laboratory of Mechanics, Modeling and Manufacturing (LA2MP) at the National School of Engineers of Sfax. The respective chapters highlight research conducted by the two laboratories on the following main topics: noise and vibration in machines; condition monitoring in non-stationary operations; vibro-acoustic diagnosis of machinery; signal processing and pattern recognition methods; monitoring and diagnostic systems; and dynamic modeling and fault detection.

Abstrak :
The book provides readers with a snapshot of recent research and industrial trends in field of industrial acoustics and vibration. Each chapter, accepted after a rigorous peer-review process, reports on a selected, original piece of work presented and discussed at the Second International Conference on Acoustics and Vibration (ICAV2018), which was organized by the Tunisian Association of Industrial Acoustics and Vibration (ATAVI) and held March 19-21, in Hammamet, Tunisia. The contributions cover advances in both theory and practice in a variety of subfields, such as: smart materials and structures; fluid-structure interaction; structural acoustics as well as computational vibro-acoustics and numerical methods. Further topics include: engines control, noise identification, robust design, flow-induced vibration and many others. This book provides a valuable resource for both academics and professionals dealing with diverse issues in applied mechanics. By combining advanced theories with industrial issues, it is expected to facilitate communication and collaboration between different groups of researchers and technology users.