Said Rechak

Remaining useful life estimation based on nonlinear feature reduction and support vector regression

Abstract Prognostics and health management (PHM) of rotating machines is gaining importance in industry and allows increasing reliability and decreasing machines’ breakdowns. Bearings are one of the most components present in mechanical equipments and one of their most common failures. So, to assess machines’ degradations, fault prognostic of bearings is developed in this paper. The proposed method relies on two steps (an offline step and an online step) to track the health state and predict the remaining useful life (RUL) of the bearings. The offline step is used to learn the degradation models of the bearings whereas the online step uses these models to assess the current health state of the bearings and predict their RUL. During the offline step, vibration signals acquired on the bearings are processed to extract features, which are then exploited to learn models that represent the evolution of the degradations. For this purpose, the isometric feature mapping reduction technique (ISOMAP) and support vector regression (SVR) are used. The method is applied on a laboratory experimental degradations related to bearings. The obtained results show that the method can effectively model the evolution of the degradations and predict the RUL of the bearings.

Health assessment and life prediction of cutting tools based on support vector regression

The integrity of machining tools is important to maintain a high level of surface quality. The wear of the tool can lead to poor surface quality of the workpiece and even to damage of the machine. Furthermore, in some applications such as aeronautics and precision engineering, it is preferable to change the tool earlier rather than to loose the workpiece because of its high price compared to the tool’s one. Thus, to maintain a high quality of the manufactured pieces, it is necessary to assess and predict the level of wear of the cutting tool. This can be done by using condition monitoring and prognostics. The aim is then to estimate and predict the amount of wear and calculate the remaining useful life (RUL) of the cutting tool. This paper presents a method for tool condition assessment and life prediction. The method is based on nonlinear feature reduction and support vector regression. The number of original features extracted from the monitoring signals is first reduced. These features are then used to learn nonlinear regression models to estimate and predict the level of wear. The method is applied on experimental data taken from a set of cuttings and simulation results are given. These results show that the proposed method is suitable for assessing the wear evolution of the cutting tools and predicting their RUL. This information can then be used by the operators to take appropriate maintenance actions.

Étude des transferts de chaleur non linéaires dans les ailettes longitudinales

Abstract This work aims to quantify the effects of non-simplified situations on longitudinal fins efficiency. For this purpose a more realistic model, which has been developed here, is based on variable profile and temperature-dependent thermophysical properties in transient two-dimensional fin with internal non-uniform heat generation. An explicit exponential finite-difference method, conditionally stable, is extended in this study for the discretization of the governing equations. The numerical procedure consists in solving series of nodal temperature distribution according to the type of node, in order to reach the steady-state heat exchange. Then, the numerical simulation is used to present the sensitivity of some parameters on efficiency. Numerical results of interest are illustrated for a direct comparison with the traditional solutions. Extensive numerical experiments were conducted and showed that temperature-dependent heat transfer coefficient and generation lead to a significant reduction of fin-efficiency. The simultaneous effects of parameters for this non-linear problem are not negligible.

On the extraction of rules in the identification of bearing defects in rotating machinery using decision tree

A methodology for the extraction of expert rules in the identification of bearing defects in rotating machinery is presented. Data sets are collected from signals measured by piezoelectric accelerometer fixed on bearings of an experimental set-up. Temporal and frequential analyses are then conducted to determine statistical parameters (crest factor (CF), kurtosis, root mean square) and spectrums (Fast Fourier Transform, envelope spectrum). The decision tree is then constructed by applying C4.5 algorithm on the dataset, and thus expert rules are established. The efficiency and applicability of expert rules over rules resulting from human experiments in rotating machinery maintenance is shown throughout the present study.

Nonlinear Forced Vibrations of Rotating Composite Beams with Internal Combination Resonance

This work deals with forced vibration of nonlinear rotating composite beams with uniform cross-section. Coupling the Galerkin method with the balance harmonic method, the nonlinear intrinsic and geometrical exact equations of motion for anisotropic beams are converted into a static formulation, which is treated with the continuation method; the asymptotic numerical method, where power series expansions and Pade approximants are used to represent the generalized vector of displacement and the frequency. Response curves are obtained and the nonlinearity is studied for various angular speed. Internal resonance flexion-flexion is found and the angular speed effect on the coupling between modes is investigated.

Intelligent prognostics based on empirical mode decomposition and extreme learning machine

Prognostics and Health Management (PHM) for condition monitoring systems have been proposed for predicting faults and estimating the remaining useful life (RUL) of components or subsystem. For gaining importance in industry and decrease possible loss of production due to machine stopping, a new intelligent method for the tool wear condition monitoring based on features extraction by using Empirical Modes Decomposition (EMD) and nonlinear regression by using improved extreme learning machine (IELM). Features extraction from raw sensor data is the essential step for the construction of an effective PHM. The IELM is a technique where the goodness of fit is measured; The idea is based on the computation of a nonlinear regression function in a high dimensional feature space where the input data mapped via a nonlinear function. The results of its application in CNC machining show that this indicator can reflect effectively the performance degradation of cutting tools for milling process. The proposed method is applied on real world RUL estimation and health assessment for a given wear limit based on extracted features.

Bearings Prognostics based on Blind Sources Separation and Robust Correlation Analysis.

Prognostics and Health Management (PHM) for condition monitoring systems have been proposed for predicting faults and estimating the remaining useful life (RUL) of components or subsystem. For gaining importance in industry and decrease possible loss of production due to machine stopping, a new intelligent method for bearing health assessment based on Empirical mode decomposition (EMD) and Blind Source Separation (BSS). EMD is one of the most powerful time-frequency analysis decompose the signal into a set of orthogonal components called intrinsic mode functions (IMFs). BSS method used to separate IMFs of one-dimensional time series into independent time series. The health indicator based on the robust correlation coefcient is proposed based on a weighted average correlation calculated from different combinations of the original data. The correlation coefficients between separated IMFs used to estimate the health of bearing; The correlation coefficient used for comparison between the estimated sources with differents degradation levels. The correlation coefficient values are then fitted to a regression to obtain the model for Remaining Useful Life (RUL) estimation. The method is applied on accelerated degradations bearings called PRONOSTIA. Experimental results show that the proposed method can reflect effectively the performance degradation of bearing.

Dynamic Response of Cracked Plate Subjected to Impact Loading Using the Extended Finite Element Method (X-FEM)

Yet and according to our knowledge, the extended finite element method X-FEM has not been used in the dynamic response of cracked plates subjected to impact loading, subject of this study. From prior knowledge of the impact properties (contact force and central deflection) of a virgin plate, one can quantitatively through the present study predicts the eventual presence of discontinuities in plates by comparison of impact properties of cracked plate to the virgin ones. In the numerical implementation, conventional finite element without any discontinuity is first carried out, then enriched functions are added to nodal displacement field for element nodes containing cracks. Therefore no remeshing of the domain is required, leading to a great gain in time computing. The mathematical model includes both transverse shear deformation and rotatory inertia effects. Based on the above, a self contained computer code named “REDYPLAF”, written in FORTRAN is hence developed. The effects of Crack length and crack position on contact force and on plate deflection are analyzed. The obtained results show that the contact force is divided into three zones. The same fact is also observed for the maximum plate deflection. Another observed fact is related to crack dissymmetry which has a direct effect on the maximum plate deflection.