Hongrui Cao

Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings

Condition monitoring and fault diagnosis of rolling element bearings timely and accurately is very important to ensure the reliable operation of rotating machinery. In this paper, a multi-fault classification model based on the kernel method of support vector machines (SVM) and wavelet frame, wavelet basis were introduced to construct the kernel function of SVM, and wavelet support vector machine (WSVM) is presented. To seek the optimal parameters of WSVM, particle swarm optimization (PSO) is applied to optimize unknown parameters of WSVM. In this work, the vibration signals measured from rolling element bearings are preprocessed using empirical model decomposition (EMD). Moreover, a distance evaluation technique is performed to remove the redundant and irrelevant information and select the salient features for the classification process. Hence, a relatively new hybrid intelligent fault detection and classification method based on EMD, distance evaluation technique and WSVM with PSO is proposed. This method is validated on a rolling element bearing test bench and then applied to the bearing fault diagnosis for electric locomotives. Compared with the commonly used SVM, the WSVM can achieve a greater accuracy. The results indicated that the proposed method can reliably identify different fault patterns of rolling element bearings based on the vibration signals.

Dynamic Modeling and Vibration Response Simulation for High Speed Rolling Ball Bearings With Localized Surface Defects in Raceways

A dynamic model is developed to investigate vibrations of high speed rolling ball bearings with localized surface defects on raceways. In this model, each bearing component (i.e., inner raceway, outer raceway and rolling ball) has six degrees of freedom (DOFs) to completely describe its dynamic characteristics in three-dimensional space. Gyroscopic moment, centrifugal force, lubrication traction/slip between bearing component are included owing to high speed effects. Moreover, local defects are modeled accurately and completely with consideration of additional deflection due to material absence, changes of Hertzian contact coefficient and changes of contact force directions due to raceway curvature variations. The obtained equations of motion are solved numerically using the fourth order Runge–Kutta–Fehlberg scheme with step-changing criterion. Vibration responses of a defective bearing with localized surface defects are simulated and analyzed in both time domain and frequency domain, and the effectiveness of fault feature extraction techniques is also discussed. An experiment is carried out on an aerospace bearing test rig. By comparing the simulation results with experiments, it is confirmed that the proposed model is capable of predicting vibration responses of defective high speed rolling ball bearings effectively.

A demodulating approach based on local mean decomposition and its applications in mechanical fault diagnosis

Since machinery fault vibration signals are usually multicomponent modulation signals, how to decompose complex signals into a set of mono-components whose instantaneous frequency (IF) has physical sense has become a key issue. Local mean decomposition (LMD) is a new kind of time–frequency analysis approach which can decompose a signal adaptively into a set of product function (PF) components. In this paper, a modulation feature extraction method-based LMD is proposed. The envelope of a PF is the instantaneous amplitude (IA) and the derivative of the unwrapped phase of a purely flat frequency demodulated (FM) signal is the IF. The computed IF and IA are displayed together in the form of time–frequency representation (TFR). Modulation features can be extracted from the spectrum analysis of the IA and IF. In order to make the IF have physical meaning, the phase-unwrapping algorithm and IF processing method of extrema are presented in detail along with a simulation FM signal example. Besides, the dependence of the LMD method on the signal-to-noise ratio (SNR) is also investigated by analyzing synthetic signals which are added with Gaussian noise. As a result, the recommended critical SNRs for PF decomposition and IF extraction are given according to the practical application. Successful fault diagnosis on a rolling bearing and gear of locomotive bogies shows that LMD has better identification capacity for modulation signal processing and is very suitable for failure detection in rotating machinery.

A Non-Probabilistic Metric Derived From Condition Information for Operational Reliability Assessment of Aero-Engines

The aero-engine is the heart of an airplane. Operational reliability assessment that aims to identify the reliability level of the aero-engine in the service phase is of great significance for improving flight safety. Traditionally, reliability assessment is carried out by statistical analysis on large failure samples. Because the operational reliability of a specific aero-engine is an individual problem lacking statistical sample data, traditional reliability assessment methods may be insufficient to assess the operational reliability of an individual aero-engine. The operational states of the aero-engine can be identified by its condition information. Changes in the condition information reflect the performance degradation of the aero-engine. Aiming at the assessment of the operational reliability of individual aero-engines, a novel similarity index (SI) is proposed by analyzing the condition information from the fault-free state, and the current state. A condition subspace is first obtained by kernel principal component analysis (KPCA). Subspace similarity is then represented by subspace angles, i.e., kernel principal angles (KPAs). The cosine function is finally utilized as a mapping function to transform the subspace angles into a similarity index. The index can be used as a non-probabilistic metric for operational reliability assessment. Only the condition information is needed for computation of the similarity index, thus it can be performed conveniently for online assessment. The effectiveness of the proposed method is validated by three case studies regarding the health assessment of aero-engines subjected to system-level and component-level degradation. The positive results demonstrate that the proposed SI is an effective metric for operational reliability assessment of individual aero-engines.

A Frequency-Shift Synchrosqueezing Method for Instantaneous Speed Estimation of Rotating Machinery

Instantaneous speed (IS) measurement is crucial in condition monitoring and real-time control of rotating machinery. Since the direct measurement of instantaneous rotating speed is not always available, the vibration measurement has been used for indirect estimation methods. In this paper, a novel indirect method is proposed to estimate the IS of rotating machinery. First, a frequency-shift synchrosqueezing transform is proposed to process the vibration signal to obtain the time–frequency (TF) representation. Second, the Viterbi algorithm is employed to extract the shifted instantaneous frequency (IF) from the TF representation. Finally, the extracted IF is used to recover the IF of the measured vibration signal. The IS of rotating machinery can be calculated from the estimated IF. The proposed method is validated with both numerical simulations and experiments. The results show that the proposed method could provide much higher frequency resolution, better TF concentration results, and more accurate IF estimation of the considered signal compared with the synchrosqueezing method. Furthermore, the proposed method was confirmed to be less sensitive to noise, especially for high-frequency components. [DOI: 10.1115/1.4029824]

A General Method for the Dynamic Modeling of Ball Bearing–Rotor Systems

A general dynamic modeling method of ball bearing–rotor systems is proposed. Gupta’s bearing model is applied to predict the rigid body motion of the system considering the three-dimensional motions of each part (i.e., outer ring, inner ring, ball, and rotor), lubrication tractions, and bearing clearances. The finite element method is used to model the elastic deformation of the rotor. The dynamic model of the whole ball bearing–rotor system is proposed by integrating the rigid body motion and the elastic vibration of the rotor. An experiment is conducted on a test rig of rotor supported by two angular contact ball bearings. The simulation results are compared with the measured vibration responses to validate the proposed model. Good agreements show the accuracy of the proposed model and its ability to predict the dynamic behavior of ball bearing–rotor systems. Based on the proposed model, vibration responses of a two bearing–rotor system under different bearing clearances were simulated and their characteristics were discussed. The proposed model may provide guidance for structural optimization, fault diagnosis, dynamic balancing, and other applications. [DOI: 10.1115/1.4029312]

Application of support vector machine for equipment reliability forecasting

In information age, reliability of digital manufacturing equipment has a large impact on throughput, productivity and executing predictive maintenance. Accurate reliability forecasts can provide a good assessment of machine performance in order to execute predictive maintenance effectively. This paper investigates a methodology of applying support vector machines (SVMs) to predict reliability in computerized numerical control (CNC) machine tool of digital manufacturing system. SVM is capable to solve nonlinear regression and times series problems lie on conducting the structural risk minimization principle seeking to minimize an upper bound of the generalization error rather than minimize the training error. A real reliability data (for 42 suits) of CNC machine tool were employed as the data set. SVM can be trained to learn the relationship between past historical reliability indices and the corresponding targets, and then future reliability or failures can be predicted. The experimental results demonstrate that the SVM prediction model is a valid potential for predicting system reliability and failures.

A Comparative Study of Information-Based Source Number Estimation Methods and Experimental Validations on Mechanical Systems

This paper investigates one eigenvalue decomposition-based source number estimation method, and three information-based source number estimation methods, namely the Akaike Information Criterion (AIC), Minimum Description Length (MDL) and Bayesian Information Criterion (BIC), and improves BIC as Improved BIC (IBIC) to make it more efficient and easier for calculation. The performances of the abovementioned source number estimation methods are studied comparatively with numerical case studies, which contain a linear superposition case and a both linear superposition and nonlinear modulation mixing case. A test bed with three sound sources is constructed to test the performances of these methods on mechanical systems, and source separation is carried out to validate the effectiveness of the experimental studies. This work can benefit model order selection, complexity analysis of a system, and applications of source separation to mechanical systems for condition monitoring and fault diagnosis purposes.

Finite Element Model Updating of Machine-Tool Spindle Systems

The unknown joint dynamics are the main obstacle that limits the accuracy of the finite element (FE) model of a machine-tool spindle assembly. In this paper, an FE model updating method is proposed to assist industrial engineers in achieving a reliable model that can accurately represent the dynamic characteristics of machine-tool spindle systems. In the proposed FE model updating procedure, the iterative algorithm based on frequency response functions (FRFs) is applied. The joint stiffness parameters are identified through the iteration process, while the FE model is updated simultaneously. The proposed method was applied to update an existing coupled model of a machine-tool spindle system. The experimental results show that the identified joint stiffness parameters are acceptable and the dynamic behavior of the spindle mounted in the machine tool column is predicted reliably.

Stability-based selection of cutting parameters to increase material removal rate in high-speed machining process:

The reasonable selection of cutting parameters is of great significance to improve the productivity in high-speed machining process. In this article, a stability-based selection method of cutting parameters is proposed to increase material removal rate in high-speed machining process. First, the coupled dynamics of the high-speed spindle system and machining process is modeled. Then, the interaction mechanism between the spindle-tool system and the cutting process is investigated. Based on the process stability and surface quality of workpiece, a cutting parameter selection method is proposed from the perspective of machining stability. In order to select reasonable spindle speed and depth of cut, the lower bound of chatter stability lobe diagram and surface finish are taken as constraints, and the maximum material removal rate is set as the target. The proposed method is applied to the machining of the front face of a gearbox cover, which is made of Aluminum-7050. The axial depth of cut and spindle speed are chosen reasonably with the increase in machining efficiency by about 133%.