Nguyen Trong Du

Hanoi University of Science and Technology · School of mechanical engineering

The present study aims to detect gear cracks early at variable gear speeds from vibration signals measured by a single channel accelerometer. The analysis procedure combines the Order Tracking Method (OTM) and the Order Cepstrum Method (OCM), in which a key-phase reference signal is not required. A suitable approach for gear crack detection in gear...

Machine fault diagnostic techniques by vibration signal analysis have been applied and widely developed in the industry. In recent years, using the least number of measuring devices to simplify the diagnostic process of gear fault has attracted many researchers. Various digital signal analysis methods in the time and frequency domains have been eff...

Bánh răng là một chi tiết cơ bản và có vai trò vô cùng quan trọng trong máy móc và thiết bị. Khi một bánh răng xảy ra hư hỏng dù nhỏ cũng có thể ảnh hưởng cả một dây chuyền sản xuất lớn. Để tránh sự cố nghiêm trọng do hư hỏng bánh răng đột ngột, các phương pháp chẩn đoán hư hỏng dựa trên tín hiệu dao động đã được nhiều nhà nghiên cứu quan tâm. Tron...

Rolling bearings are a part of the machine that must regularly work with incredible intensity in harsh environments. Therefore, rolling bearings are more accessible to damage than other components in devices. Fault detection of rolling bearings is a primary problem of prolonging the working life of the whole machine system. The local defect in the...

Effective signal processing methods are essential for machinery fault diagnosis. Most conventional signal processing methods lack adaptability, thus being unable to extract meaningful diagnostic information. Signal decomposition methods have excellent adaptability and high flexibility in describing arbitrary complicated signals. They can extract ri...

This paper proposes a new procedure for classification of gear faults such as normal gear (NG), chipped gear (CG), broken gear (BG), and synthesis fault (SF) using a multi-layer perceptron neural network (MLP network). Measured vibration signals are processed by the wavelet packet transform (WPT) with the Daubechies wavelet function. The standard d...

Recently, the use of machines working under time varying load and speed is increasing rapidly in modern industry. Fault diagnosis of these technical objects plays an important role but faces great challenges, since vibration signals are mostly non-stationary due to uncertainties affected by the change of speed and load during operation. This study...

Bearings are always working under harsh environment, which makes them easily to failure. Condition monitoring of rolling element bearing is a key issue for maintaining the whole machinery system. Rolling element bearing faults in rotating systems are observed as impulses in the vibration signals, which are usually buried in noise. Many methods of v...

This study attempts to demonstrate the usefulness of an automated diagnostic procedure based on the Ensemble Empirical Mode Decomposition (EEMD) method and the Support Vector Machine (SVM) for gear fault detection and classification in a two-stage helical gearbox. First, the vibration signals measured on the gearbox casing corresponding to three co...

Fault diagnosis for industrial gearboxes has attracted increasing interest in recent years, owing to the need to decrease the downtime and the extent of damages caused by failures. The present study aims to analyze and demonstrate the effectiveness of advanced signal processing methods in time-frequency domain for the detection of gear faults in ge...

Machine condition monitoring and fault diagnosis is subject received the attention of professionals in recent years. In a wide variety of mechanical systems, gearboxes transfer power from a rotating power source to other devices and provide speed and torque conversions. Complex gearbox designs are used in order to maximize efficiency, minimize volu...