Tian Han

University of Science and Technology Beijing | USTB · School of Mechanical Engineering

The particle damper has been widely used as an efficient passive vibration control device in recent years. The highly non-linear characteristic of the energy dissipation mechanism is essential for our increased understanding of non-obstructive particle damper (NOPD). To connect motion modes of the granular system and energy dissipation, we develope...

Remaining Useful Life (RUL) prediction play a crucial part in bearing maintenance, which directly affects the production efficiency and safety of equipment. Moreover, the accuracy of the prediction model is constrained by the feature extraction process and full life data of bearings. In this paper, the life prediction method of faulty rolling beari...

Generally, the recognition models established by deep learning methods need a large amount of training data. Although normal samples are abundant, fault samples are scarce since while faults seldom occur during most of the operation time. The recognition accuracies of abnormal classes are low for the convolutional neural network with such uneven di...

An induction motor is an integrated electrical device that includes plenty of systems and consequently exhibits a diversity of faults. This chapter proposes a fault identification method based on convolutional neural network (CNN) to overcome the complexity of feature extraction and feature selection, which require much experience and professional...

For small sample data, it is difficult to complete the requirements of training complex models in the field of fault diagnosis. To solve the problem, this paper combines convolutional neural network's excellent feature processing ability with the excellent generalization ability of Support Vector Machine (SVM). The proposed CNN-SVM system is applie...

Convolutional neural networks (CNNs) have been applied to the field of fault diagnosis as one of the most widely used deep learning architectures. Different input modes of CNN for bearing fault identification were analyzed by researchers to improve recognition accuracy, such as time-domain diagram, grayscale diagram, short-time Fourier transform di...

Lane detection is crucial for driver assistance systems. However, road scenes are severely degraded in dense fog, which leads to the loss of robustness of many lane detection methods. For this problem, an end-to-end method combining polarimetric dehazing and lane detection is proposed in this paper. From images with dense fog captured by a vehicle-...

The fault signals of low-speed rolling elements bearing are non-stationary and non-linear, and consequently it is difficult to extract the fault characteristics by the traditional time and frequency domains analysis methods. Furthermore, the vibration signals suffer from severe signal attenuation and noise corruption during the signal transmission...

For the main shaft of wind turbine of certain type, shaft fracture occurs at the variable section of the shaft during early stage of operation. In order to validate the failure analysis, finite element analysis of the main shaft was performed. The analysis results demonstrate that there is a severe stress concentration that leads to the formation o...

As a main transmission composition, planetary gearbox is widely used in wind turbine generation system. Due to the complicated working environment, sun gears, planet gear, ring gear and other key components are prone to failure. Therefore, the researches on the fault features of the planetary gearbox have significance to understand the operation of...

A fault recognition method for rolling element bearings based on Multiscale Dynamic Time Warping (MDTW) is proposed in this paper. After preprocessing using Empirical Mode Decomposition (EMD), CWs are extracted from vibration signals. The normalization of CWs is necessary to eliminate the influence of amplitude variations before using MDTW. Followi...

The screening process of particle flow on an elliptical vibration screen was simulated based on the discrete element method (DEM). The motion characteristics and screening mechanisms of particles on the screen deck were studied. The effects of the vibration parameters, including the vibration amplitude, vibration frequency, vibration direction angl...

An effective fault diagnosis method for induction motors is proposed in this paper to improve the reliability of motors using a combination of entropy feature extraction, mutual information, and support vector machine. Sample entropy and multiscale entropy are used to extract the desired entropy features from motor vibration signals. Sample entropy...

This paper presents an investigation on the cause of severe vibration problem of a coach with four-cylinder engine running at an idle state using vibration and impact hammer modal experiments to obtain the main vibration frequency components and the natural characteristics of the coach. The vibration results indicate that the main vibration compone...

In order to research the leakage mechanism and influence factors of the hydraulic rock drill, the mathematical model of the leakage is established, and combined with the structure and working principle of the hydraulic rock drill, the impact mechanism dynamics simulation model is built by the AMESim software. Through the analysis of the leakage mod...

The main purpose of the numerical simulation that described in this paper is to investigate the damping influence on vortex-induced vibration (VIV) system. By considering different damping ratios, the 1-dof vortex-induced vibration of a rigid cylinder with low mass ratio is investigated numerically by the RANS solver combined with SSTk-omega turbul...

Vortex-induced vibration (VIV) was largely investigated by experiments. However, with the improvements in computing capabilities, the numerical method is becoming more and more popular. This paper reviews the literature on the numerical simulation of VIV and focuses on the advances in the last decade.

According to the lumped mass method, the drive system of rolling mill can be simplified as a three-degree-of-freedom spring-mass model. The nonlinear dynamics equations are established considering nonlinear torsion stiffness of connecting shaft and nonlinear friction force between roller and strip, and Hopf bifurcation and critical parameters are a...

A reasonable finite element model of large rotating steel structure - rotary hearth furnace lower ring is established based on ANSYS. Simulation and analysis of the structure is processed on the lower ring. Stress distribution is achieved while bearing the weight of upper ring as the working condition. Spot stress testing is processed on the rotary...

The complex nonlinear dynamics of a rotor-rolling bearing system with crack is built by dynamic simulation software ADAMS. The transverse vibration response and swing response of rotor are studied on the basis of considering both the nonlinear contact force of rolling bearing and the impact of stiffness caused by crack. Furthermore, the influence f...

Using ANSYS to calculate modal of truss structure, which is similar to the bus frame, proposing the effect of different modeling methods on modal results and initial selecting the appropriate modeling method to this new type complex bus frame. The above-mentioned methods are used to create actual bus frame models and obtain the corresponding modal...

Dynamic characteristic of a cracked rotor has been theoretically studied by many researchers. In this paper, the virtual prototype model of the rigidity-supported rotor system with a transverse crack is built by dynamic simulation software ADAMS. Furthermore, the vibration characteristics are studied by time and frequency domain analysis based on v...

Rotor unbalance is the main vibration excitation source of rotating machinery accounting for 60~70% of the total machine fault. In this paper, unbalance fault and dynamic balancing are simulated by the virtual prototyping technology based on the unbalance mechanism and balancing theory. The single-face and double-face dynamic balancing are studied....

One fault diagnosis system is proposed to monitor the fan system condition based on virtual prototyping technology. According to the real fan system structure and its foundation condition, the three-dimensional model is built. Under virtual environment, the components are assembled, and the constraints and driver are added. After validate the model...

This paper investigates the possibilities of applying the random forests algorithm (RF) in machine fault diagnosis, and proposes a hybrid method combined with genetic algorithm to improve the classification accuracy. The proposed method is based on RF, a novel ensemble classifier which builds a number of decision trees to improve the single tree cl...

Purpose – The purpose of this paper is to identify the efficiency of vibration signals for fault diagnosis system of induction motors. Design/methodology/approach – A fault diagnosis system for induction motors using vibration signals is designed based on pattern recognition. Genetic algorithm is used for feature reduction and neural network tuning...

Improvement of recognition rate is ultimate aim for fault diagnosis researchers using pattern recognition techniques. However, the unique recognition method can only recognise a limited classification capability which is insufficient for real-life application. An ongoing strategy is the decision fusion techniques. In order to avoid the shortage of...

This paper studies the application of independent component analysis (ICA) and support vector machines (SVMs) to detect and diagnose of induction motor faults. The ICA is used for feature extraction and data reduction from original features. The principal components analysis is also applied in feature extraction process for comparison with ICA does...

This paper proposes a condition classification system using wavelet transform, feature evaluation and artificial neural networks to detect faulty products on the production line of reciprocating compressors for refrigerators. The stationary features of vibration signals are extracted from statistical cumulants of the discrete wavelet coefficients a...

This paper proposes a fault diagnosis system for induction motor which integrates principal component analysis (PCA), genetic algorithm (GA) and artificial neural network (ANN). Vibration signals and stator current signals are measured as the fault diagnosis media. Many sensors result in many features to ANN. In order to avoid the curse of dimensio...

This paper proposes an online fault diagnosis system for induction motors through the combination of discrete wavelet transform (DWT), feature extraction, genetic algorithm (GA), and neural network (ANN) techniques. The wavelet transform improves the signal-to-noise ratio during a preprocessing. Features are extracted from motor stator current, whi...

In recent years, globalization and fast growth of communication technologies, computer and information technologies have changed the pattern of maintenance. Accordingly, a new maintenance, e-maintenance has emerged and has been gradually replacing the traditional maintenance. In this paper, a new e-maintenance system is proposed that is dependent u...

The purpose of this paper is to present a methodology by which rotating machinery faults can be diagnosed. The proposed method is based on random forests algorithm (RF), a novel assemble classifier which builds a large amount of decision trees to improve on the single tree classifier. Although there are several existed techniques for faults diagnos...

In recent years, globalization and fast growth of Internet technology, artificial intelligence, computer and information technologies have changed the pattern of maintenance. Accordingly, a new maintenance concept, e-maintenance has emerged and has been gradually replacing the traditional maintenance. In this paper, a new e-maintenance system is pr...

In this paper, a condition monitoring and fault diagnosis system for induction motors is proposed by integrating artificial intelligence algorithms: principal component analysis (PCA), genetic algorithm (GA) and an artificial neural network (ANN). As main diagnosis media of fault motor, three-direction vibration signals and three-phase stator curre...

Support vector machines (SVMs) have become one of the most popular approaches to learning from examples and have many potential applications in science and engineering However, their applications in fault diagnosis of rotating machinery are rather limited Most of the published papers focus on some special fault diagnoses This study covers the overa...

In this paper, a new neural network (NN) for fault diagnosis of rotating machinery which synthesises the theory of adaptive resonance theory (ART) and the learning strategy of Kohonen neural network (KNN), is proposed. For NNs, as the new case occurs, the corresponding data should be added to their dataset for learning. However, the ‘off-line’ NNs...

This paper presents a new approach for integrating case-based reasoning (CBR) with an ART-Kohonen neural network (ART-KNN) to enhance fault diagnosis. When solving a new problem, the neural network is used to make hypotheses and to guide the CBR module in the search for a similar previous case that supports one of the hypotheses. The knowledge acqu...