Kamal Medjaher

Bearing Health Monitoring Based on Hilbert–Huang Transform, Support Vector Machine, and Regression

The detection, diagnostic, and prognostic of bearing degradation play a key role in increasing the reliability and safety of electrical machines, especially in key industrial sectors. This paper presents a new approach that combines the Hilbert-Huang transform (HHT), the support vector machine (SVM), and the support vector regression (SVR) for the monitoring of ball bearings. The proposed approach uses the HHT to extract new heath indicators from stationary/nonstationary vibration signals able to tack the degradation of the critical components of bearings. The degradation states are detected by a supervised classification technique called SVM, and the fault diagnostic is given by analyzing the extracted health indicators. The estimation of the remaining useful life is obtained by a one-step time-series prediction based on SVR. A set of experimental data collected from degraded bearings is used to validate the proposed approach. The experimental results show that the use of the HHT, the SVM, and the SVR is a suitable strategy to improve the detection, diagnostic, and prognostic of bearing degradation.

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.

Feature Evaluation for Effective Bearing Prognostics

Rolling element bearing failure is one of the foremost causes of breakdown in rotating machinery. It is not uncommon to replace a defected/used bearing with a new one that has shorter remaining useful life than the defected one. Thus, the prognostics of bearing plays critical role for increased availability and reduced cost. Effective prognostics highly depends on the quality of the extracted features. Diagnostics is basically a classification problem, whereas prognostics is the process of forecasting the future health states. The quality of the features for classification has been studied thoroughly. However, the evaluation of the quality of features for prognostics is a relatively new problem. This article presents an evaluation method for the goodness of the features for prognostics and presents results on bearings run until failure in a laboratory environment. Copyright

Fault prognostic of bearings by using support vector data description

This paper presents a method for fault prognostic of bearings based on Principal Component Analysis (PCA) and Support Vector Data Description (SVDD). The purpose of the paper is to transform the monitoring vibration signals into features that can be used to track the health condition of bearings and to estimate their remaining useful life. PCA is used to reduce the dimensionality of original vibration features by removing the redundant ones. SVDD is a pattern recognition method based on structural risk minimization principles. In this contribution, the SVDD is used to fit the trained data to a hypersphere such that its radius can be used as a health indicator. The proposed method is then applied on real bearing degradation performed on an accelerated life test. The experimental results show that the health indicator reflects the bearings degradation.

Dependability of wireless sensor networks for industrial prognostics and health management

HighlightsState of the art in prognostics and health management.Limitations of prognostic models.Dependability of wireless sensor networks.Challenges of remaining useful life prediction. Maintenance is an important activity in industry. It is performed either to revive a machine/component or to prevent it from breaking down. Different strategies have evolved through time, bringing maintenance to its current state: condition-based and predictive maintenances. This evolution was due to the increasing demand of reliability in industry. The key process of condition-based and predictive maintenances is prognostics and health management, and it is a tool to predict the remaining useful life of engineering assets. Nowadays, plants are required to avoid shutdowns while offering safety and reliability. Nevertheless, planning a maintenance activity requires accurate information about the system/component health state. Such information is usually gathered by means of independent sensor nodes. In this study, we consider the case where the nodes are interconnected and form a wireless sensor network. As far as we know, no research work has considered such a case of study for prognostics. Regarding the importance of data accuracy, a good prognostics requires reliable sources of information. This is why, in this paper, we will first discuss the dependability of wireless sensor networks, and then present a state of the art in prognostic and health management activities.

The ISO 13381-1 standard's failure prognostics process through an example

Industrial failure prognostics can be considered as the key process of any condition-based maintenance solution. However, contrary to fault diagnostics which is a mature research and industrial work, failure prognostics is a new field for which few applications exist. In the last decade, the interest for this activity has led to some open and industrial standards where the main objective is to provide users with a guidelines allowing them to perform failure prognostics for a large class of industrial systems. However, these standards, rightly, do not emphasize on any particular example to illustrate their content. The present paper aims at explaining the process of failure prognostics, presented in the standard ISO 13381-1, through an electromechanical example. The purpose is to help beginner researchers in the field of industrial failure prognostics to assimilate the main tasks of the process proposed by the standard. The prognostics process is chosen because it represents the key task among the rest of topics proposed and published by the standard. Thus, the comprehension of this part is important to develop prognostics methods and algorithms based on the solid recommendations given by the international organization for standardization.

A mixture of Gaussians Hidden Markov Model for failure diagnostic and prognostic

This paper deals with a data-driven diagnostic and prognostic method based on a Mixture of Gaussians Hidden Markov Model. The prognostic process of the proposed method is made in two steps. In the first step, which is performed off-line, the monitoring data provided by sensors are processed to extract features, which are then used to learn different models that capture the time evolution of the degradation and therefore of the systems health state. In the second step, performed on-line, the learned models are exploited to do failure diagnostic and prognostic by estimating the assets current health state, its remaining useful life and the associated confidence degree. The proposed method is tested on a benchmark data related to several bearings and simulation results are given at the end of the paper.

Condition Assessment and Fault Prognostics of Microelectromechanical Systems

Abstract Microelectromechanical systems (MEMS) are used in different applications such as automotive, biomedical, aerospace and communication technologies. They create new functionalities and contribute to miniaturize the systems and reduce their costs. However, the reliability of MEMS is one of their major concerns. They suffer from different failure mechanisms which impact their performance, reduce their lifetime and their availability. It is then necessary to monitor their behavior and assess their health state to take appropriate decision such as control reconfiguration and maintenance. These tasks can be done by using Prognostic and Health Management (PHM) approaches. This paper addresses a condition assessment and fault prognostic method for MEMS. The paper starts with a short review about MEMS and presents some challenges identified and which need to be raised to implement PHM methods. The purpose is to highlight the intrinsic constraints of MEMS from PHM point of view. The proposed method is based on a global model combining both nominal behavior model and degradation model to assess the health state of MEMS and predict their remaining useful life. The method is applied on a microgripper, with different degradation models, to show its effectiveness.

Failure prognostic by using Dynamic Bayesian Networks

this paper presents a procedure for failure prognostic by using Dynamic Bayesian Networks (DBNs). The graphical representation of this tool is particularly well suitable for modeling complex systems, with non homogeneous sources of data and knowledge. Moreover, DBNs allow to deal with uncertainty which is an inherent property to any failure prognostic work, especially regarding the estimation of the Remaining Useful Life (RUL) before a failure. The DBN model can be also used to observe the propagation of the effect of any state of the model on the other remaining states. The proposed procedure is applied on a small industrial system to show its feasibility.

Residual-based failure prognostic in dynamic systems.

Abstract this paper deals with failure prognostic in dynamic systems. The systems remaining useful life is estimated based on residual signals. This supposes the possibility to build a dynamic model of the system by using the bond graph tool, and the existence of a degradation model in order to predict its future health state. The choice of bond graph is motivated by the fact that it is well suited for modeling physical systems where several types of energies are involved. In addition, it allows to generate residuals for fault diagnostic and prognostic. The proposed method is then applied on a simple dynamic model of a hydraulic system to show its feasibility.