Hasil Pencarian  ::  Simpan CSV :: Kembali

"ABSTRAKTesis ini membahas kemampuan dan penggunaan tiga metode data mining dalam melakukan rangkaian analisis dan menemukan informasi dari sekumpulan data yang berjumlah besar yaitu data penggukuran condition monitoring dan faktor ekstenal dari suatu engine alat berat dengan tujuan untuk mendapatkan penjadwalan penggantian engine yang lebih optimal. Metode clustering digunakan untuk mengelompokkan data condition monitoring, association rule digunakan untuk menganalisis keterkaitan antar variabel dan analisis time series digunakan untuk memprediksi nilai dari pengukuran condition monitoring. Hasil penelitian menunjukkan metode data mining dapat digunakan untuk melakukan optimasi penjadwalan.

---

ABSTRACTThis thesis discusses the capability and use of three data mining rsquo s methods in perform the sequence of analysis and explore information from large data set, that is condition monitoring data and external factors of the heavy equipment engine in order to get more optimized engine replacement scheduling.Clustering method is used to classify condition monitoring data, association rule is used to analyze the interrelationship between variables and time series analysis is used to predict the value of condition monitoring. The result showed that data mining methods can be used to perform scheduling optimization."

"This book discusses the maintenance aspect of rotating machines, which it addresses through a collection of contributions. Sharing the “hands-on” views of experienced engineers on the aspect of maintenance for rotating machines, it offers a valuable reference guide for practicing engineers in the related industries, providing them a glimpse of some of the most common problems associated with rotating machines and equipment in the field, and helping them achieve maximum performance efficiency and high machine availability."

"Most heavy duty mining electrical drives employ squirrel cage induction motors (SCIMs) which are subjected to various undesirable stresses. Therefore, condition monitoring of the SCIMs is indispensable for achieving production goals with minimum downtime in a fault-free working environment. Because bearing damage is the most frequently occurring fault in SCIMs, an effective fault detection scheme will aid in achieving production targets in an industrial mining scenario. In this regard, the present work intends to propose an effective fault monitoring algorithm, which is immune to supply frequency regulation, for the detection of ball bearing damage in an SCIM. Discrete Wavelet Transform (DWT) is used for the design of the fault detection scheme. Validation of the proposed scheme is done in a LabVIEW based laboratory interface. The complete analysis is carried out in MATLAB/ Simulink using a 5.5 kW, 3-phase, 415 V, 50 Hz SCIM."

"This book describes in detail different types of vibration signals and the signal processing methods, including signal resampling and signal envelope, used for condition monitoring of drivetrains. A special emphasis is placed on wind turbines and on the fact that they work in highly varying operational conditions. The core of the book is devoted to cutting-edge methods used to validate and process vibration data in these conditions. Key case studies, where advanced signal processing methods are used to detect failures of gearboxes and bearings of wind turbines, are described and discussed in detail. Vibration sensors, SCADA (Supervisory Control and Data Acquisition), portable data analyzers and online condition monitoring systems, are also covered. This book offers a timely guide to both researchers and professionals working with wind turbines (but also other machines), and to graduate students willing to extend their knowledge in the field of vibration analysis."

"ABSTRAK

Produktifitas pada alat berat merupakan kinerja terpenting dalam industri konstruksi dan pertambangan, sehingga penerapan proses condition monitoring (CM) menjadi elemen penting dalam menentukan umur penggunaan komponen alat berat. Penentuan umur sisa (remaining useful life, RUL) dari komponen alat berat menjadi sangat penting untuk mendukung dan meningkatkan produktifitas alat berat dimana pendekatan best-practices digunakan dalam proses ini. Untuk mengatasi permasalahan ini, dibutuhkan estimasi RUL dari komponen alat berat dengan pendekatan data-driven menggunakan data mining. Metode yang digunakan pada penelitian ini untuk mengestimasi RUL komponen engine, final drive, dan transmisi alat berat adalah menggunakan Neural Networks (NN) dan Bayesian Networks (BN). Penelitian ini menggunakan data CM berjumlah 20 variabel dan melakukan reduksi dimensi variabel menggunakan principal component analysis (PCA). Hasil dari penelitian yang telah dilakukan didapatkan hasil estimasi terbaik pada komponen engine dan transmisi adalah dengan menggunakan metode NN dengan nilai RMSE model masing-masing sebesar 0,242 dan 0,196, sedangkan metode BN menjadi metode terbaik pada final drive dengan nilai RMSE sebesar 0,211.

---

ABSTRACT

---

Condition monitoring (CM) process is the key element to estimate remaining useful life (RUL) on heavy equipment`s components in the construction and mining industry with an aim to increase productivity. Nowadays, the best-practices approach has been applied to estimating RUL to improve production and performance of heavy equipment. Data mining method with the data-driven approach will be implemented to overcome the issue. Neural Networks (NN) dan Bayesian Networks (BN) method has been applied in this research to estimate RUL on heavy equipment`s engine, final drive, and transmission components. Principal component analysis (PCA) has been applied for dimension reduction of 20 variables from CM data in this research. The results shown estimating RUL on engine and transmission components provide better accuracy with the NN method which RMSE model achieve 0.242 and 0.196, respectively. Furthermore, the BN method provides better accuracy on final drive components with RMSE model achieves on 0.211.

"