Showing papers in "Mechanical Systems and Signal Processing in 2007"

TL;DR: This paper presents a survey of machine condition monitoring and fault diagnosis using support vector machine (SVM), and attempts to summarize and review the recent research and developments of SVM in machine condition Monitoring and diagnosis.

TL;DR: This communication describes a fast algorithm for computing the kurtogram over a grid that finely samples the ( f, Δ f ) plane and the efficiency of the algorithm is illustrated on several industrial cases concerned with the detection of incipient transient faults.

TL;DR: In this article, a general summary and review of state-of-the-art and development of vibration-based structural damage detection methods is presented, and the principle of intelligent damage diagnosis and its application prospects in structural damage detecting are introduced.

TL;DR: In this article, the minimum entropy deconvolution (MED) technique was used to enhance the surveillance capability of the spectral kurtosis (SK) by using a spalled inner race bearing.

TL;DR: In this paper, a new scheme for the prediction of a ball bearing's remaining useful life based on self-organizing map (SOM) and back propagation neural network methods is presented.

TL;DR: In this paper, a Hilbert-Huang Transform (HHT) based time domain approach for bearing vibration signature analysis is proposed for bearing bearing vibration analysis and its efficiency is evaluated.

TL;DR: This paper illustrates the use of a Decision Tree that identifies the best features from a given set of samples for the purpose of classification using Proximal Support Vector Machine (PSVM), which has the capability to efficiently classify the faults using statistical features.

TL;DR: The proposed method for fault diagnosis based on empirical mode decomposition (EMD), an improved distance evaluation technique and the combination of multiple adaptive neuro-fuzzy inference systems (ANFISs) show that the multiple ANFIS combination can reliably recognise different fault categories and severities.

TL;DR: In this paper, a new approach to machine health monitoring based on the Approximate Entropy (ApEn) is presented, which is a statistical measure that quantifies the regularity of a time series, such as vibration signals measured from an electrical motor or a rolling bearing.

TL;DR: The proposed method is applied to the fault diagnosis of rolling element bearings, and testing results show that the SVMs ensemble can reliably separate different fault conditions and identify the severity of incipient faults, which has a better classification performance compared to the single SVMs.

TL;DR: In this article, the authors used wavelet analysis and support vector machine (SVM) for multi-fault detection in an electric motor with two rolling bearings, one of them was next to the output shaft and the other one was near the fan and for each of them there is one normal form and three false forms, which make 8 forms for study.

TL;DR: In this paper, the authors proposed the use of the minimum entropy deconvolution (MED) technique to enhance the ability of the existing autoregressive (AR) model based filtering technique to detect localised faults in gears.

TL;DR: In this article, a neural network-based sensor fusion model has been developed for tool condition monitoring (TCM), where features extracted from a number of machining zone signals, namely cutting forces, spindle vibration, spindles current, and sound pressure level have been fused to estimate the average flank wear of the main cutting edge.

TL;DR: In this article, a downscaled 2-layer multi-layer perceptron neural-network-based system with great accuracy was designed to carry out the task of fault detection and identification.

TL;DR: A statistical modelling methodology for performing both diagnosis and prognosis in a unified framework based on segmental hidden semi-Markov models (HSMMs), which can be used to predict the useful remaining life of a system.

TL;DR: In this article, it is shown that non-parametric cyclic spectral estimators can all be derived from a general quadratic form, which yields as particular cases cyclic versions of the smoothed, averaged, and multitaper periodograms.

TL;DR: In this paper, a multi-rate Kalman filtering approach is proposed to solve the problem of problematic integration of accelerometer data that causes lowfrequency noise amplification, and potentially more problematic differentiation of displacement measurements which amplify high-frequency noise.

TL;DR: In this paper, an experimental investigation on spur gears in which natural pitting was allowed to occur was conducted, and it was observed that based on the analysis of root mean square (rms) levels only the acoustic emission technique was more sensitive in detecting and monitoring pitting than either the vibration or spectrometric oil analysis (SOA) techniques.

TL;DR: The capacity dimension, information dimension and correlation dimension are applied to classify various fault types and evaluate various fault conditions of rolling element bearing, and the classification performance of each fractal dimension and their combinations are evaluated by using SVMs.

TL;DR: The result shows that C4.5 and PCA-based diagnosis method has higher accuracy and needs less training time than BPNN.

TL;DR: The present study carries out output-only modal analysis using two blind source separation techniques, namely independent component analysis and second-order blind identification using the concept of virtual source.

TL;DR: In this article, the relation between the vibration modes of mechanical systems and the modes computed through a blind source separation technique called independent component analysis (ICA) was investigated for free and random vibrations of weakly damped systems.

TL;DR: In this article, a sensorless algorithm was proposed for angular resampling of the acceleration signal of a gearbox submitted to limited speed fluctuation. But it requires only the knowledge of an approximate value of the running speed and the number of teeth of the gears.

TL;DR: In this paper, the authors present the integration of two different numerical procedures to identify the mechanism bringing to brake instability and to analyse its dynamics, and the two models are compared and the onset of squeal is predicted both in the frequency domain by the linear model and in the time domain by a nonlinear one.

TL;DR: In this article, an artificial source is used to record differences in times of arrival information from a number of locations, to improve source location in complex geometric structures, and a 5-step description of the process is provided.

TL;DR: In this article, a multiobjective optimisation technique is used to extremise two objective functions simultaneously which overcomes the difficulty of weighing the individual objective function of more objectives in conventional finite element updating procedure.

TL;DR: In this paper, a defect in the outer race of an induction motor ball bearing was detected by using vibration, stator current, acoustic emission and shock pulse (SPM) measurements at different loads.

TL;DR: In this article, an energy operator demodulation approach based on EMD (Empirical Mode Decomposition) is proposed to extract the instantaneous frequencies and amplitudes of the multi-component amplitude-modulated and frequency modulated (AM-FM) signals.

TL;DR: In this paper, a tool wear predictive model by combination of least squares support vector machines (LS-SVM) and principal component analysis (PCA) technique was proposed to extract features from multiple sensory signals acquired from machining processes.

TL;DR: This paper presents the use of decision tree to generate the rules automatically from the feature set and builds and tests a fuzzy classifier, found to be encouraging.