Improving Signal-to-Noise Ratio (SNR) for Inchoate Fault Detection based on Principal Component Analysis (PCA)

Moussa Hamadache,Dongik Lee 제어로봇시스템학회 2014 제어로봇시스템학회 국제학술대회 논문집 Vol.2014 No.10

Detection of inchoate fault demands high level of fault classification accuracy under poor signal-to-noise ratio (SNR) which appears in most industrial environment. Vibration signal analysis methods are widely used for bearing fault detection. In order to guarantee improved performance under poor SNR, feature extraction based on statistical parameters which are free from Gaussian noise become inevitable. This paper proposes a feature extraction framework based on principal component analysis (PCA) for improving SNR. Features extracted based on PCA have the tendency to alleviate the impact of non-Gaussian noise. PCA algorithm provides useful time domains analysis for no-stationary signals such as vibration in which spectral contents vary with respect to time. Experimental studies on vibration caused by ball bearing faults show that the proposed algorithm demonstrates the improvements in term of classification accuracy under poor signal-to-noise ratio (SNR).

Wind Turbine Main Bearing Fault Detection via Shaft Speed Signal Analysis under Constant Load

Moussa Hamadache,Dongik Lee 제어로봇시스템학회 2016 제어로봇시스템학회 국제학술대회 논문집 Vol.2016 No.10

Early detection of bearing faults is very critical since they cannot be compensated using analytical methods, such as reconfigurable control. From the surveys of current conditions monitoring (CM) systems, there is a clear tendency towards vibration monitoring of wind turbines (WTs). It is likely that this tendency will continue, however it would be reasonable to assume that other CMs and diagnosis techniques will be incorporated into existing systems, with major innovation in terms of developing signal processing techniques. In particular, the industry is already noting the importance of operational parameters such as load and speed and so techniques may begin to adapt further to the WT environment leading to more reliable CM systems, diagnostics and alarm signals. Therefore, this paper presents a Wind Turbine Main Bearing (WTMB) fault detection method via speed signal analysis under constant load providing a benefit in terms of cost, and space. Since process history-based bearing fault detection has considerable advantages in terms of simplicity and implementation, the presented WTMB fault detection method base on Absolute Value Principal Component Analysis (AVPCA) technique. A set of bearing faults with outer-race, inner-race, and ball/roller failure are evaluated to demonstrate the performance and effectiveness of the proposed method.

Fault Diagnosis of Electronic Throttle System Using Parameter Estimation

Hamadache Moussa,Dongik Lee(이동익) 한국자동차공학회 2011 한국자동차공학회 부문종합 학술대회 Vol.2011 No.5

The use of electronics, intelligent sensors/actuators and microprocessor-based control technology enables online real-time fault detection and diagnosis (FDD) of automobiles. In this paper, a FDD method for electronic throttle system is proposed. The proposed FDD method is based on parameter estimation in closed-loop and a nonlinear model of the electronic throttle system. The nonlinear mathematical model of the electronic throttle system is identified in closed-loop, and then the parameter estimation technique is applied to the closed-loop nonlinear system model for the detection and isolation of faults. The simulation results are presented to investigate the performance and effectiveness of the proposed method.

Residual-based Fault Detection Method: Application to Railway Switch & Crossing (S&C) System

Moussa Hamadache,Saikat Dutta,Ramakrishnan Ambur,Osama Olaby,Edward Stewart,Roger Dixon 제어로봇시스템학회 2019 제어로봇시스템학회 국제학술대회 논문집 Vol.2019 No.10

This paper proposes a model-based fault detection (FD) method with application to railway switch & crossing (S&C) systems. These systems are safety critical assets in the rail network and they daily exposed to harsh working conditions and severe environment, which make them more vulnerable to failures and breakdowns. Therefore, it is critical to implement a condition monitoring (CM) technique to enhance the reliability and the availability of these S&C systems. To-the-end of reducing the scheduled maintenance process and decreasing the possible number of delays and/or accidents. This paper thus, proposes a simple model-based technique, a modified residual-based technique, which can be implemented in the real rail network for FD with application to railway electro-mechanical switch system.

Principal Component Analysis Based Signal-to-noise Ratio Improvement for Inchoate Faulty Signals: Application to Ball Bearing Fault Detection

Moussa Hamadache,이동익 제어·로봇·시스템학회 2017 International Journal of Control, Automation, and Vol.15 No.2

This paper addresses the development of an algorithm that can improve the signal-to-noise ratio (SNR)in inchoate faulty signals. The removal of noise and preservation of fault information components cannot be easilyachieved. Many techniques for SNR improvement in healthy signals rely on frequency bands. Such techniqueshave been proven to be efficient in improving the SRN by filtering out frequency bands (FoFBs). However, thesetechniques cannot reduce noise and preserve fault information when dealing with inchoate faulty signals. Thus, afeature extraction technique based on statistical parameters, which are free from Gaussian noise, is proposed in thispaper. The proposed signal subspace-based approach for SNR improvement in inchoate faulty signals is based on amodified principal component analysis (PCA), in which the optimal subspace is selected via a cumulative percentof variance (CPV) criterion and the test statistic condition of the true information loss, which has the tendencyto alleviate the impact of Gaussian and non-Gaussian noise and provides useful time domain analysis for nonstationarysignals such as vibration, in which spectral contents vary with respect to time. Furthermore, the modifiedPCA algorithm is combined with a low-pass filter (LPF) to achieve an optimum balance between noise reductionefficiency and the conservation of inchoate fault information. The proposed PCA-LPF algorithm is compared withdifferent filters under different noise levels to find the most efficient approach in terms of optimizing the trade-offbetween noise reduction efficiency and precision of inchoate fault information conservation, with the final goalof improving the fault detection capability. Further, the performance of the proposed PCA-LPF algorithm wasdemonstrated with an experimental study on vibration-based ball bearing fault detection.

Principal Components Analysis based Fault Detection and Isolation for Electronic Throttle Control System

Moussa Hamadache,Dongik Lee 제어로봇시스템학회 2012 제어로봇시스템학회 국제학술대회 논문집 Vol.2012 No.10

In this paper, a Principal Component Analysis (PCA) based Fault Detection and Isolation (FDI) method for nonlinear Electronic Throttle Control (ETC) system is presented. The proposed method introduces a novel configuration of PCA bases by computing the absolute value of weights. The fault can be detected if the Sum Square Error (SSE) distance exceeds its pre-defined threshold and the isolation of the detected fault is done under the minimum of the SSE distance. The PCA model is used to detect (offline and/or online) failure in the ETC from the old Normal Operation Condition (NOC) as well as to diagnose the cause of the failure. A set of faults with armature resistance, armature inductance are evaluated to demonstrate the performance and effectiveness of the proposed method.

A positive energy residual (PER) based planetary gear fault detection method under variable speed conditions

Park, Jungho,Hamadache, Moussa,Ha, Jong M.,Kim, Yunhan,Na, Kyumin,Youn, Byeng D. Elsevier 2019 Mechanical systems and signal processing Vol.117 No.-

<P><B>Abstract</B></P> <P>Most existing studies on vibration-based fault detection for planetary gears were developed and tested under constant speed conditions. Recently, some methods were developed to consider the variability of the rotating speed; however, these methods have limitations. Specifically, these methods are applicable only for small fluctuations of speed, or the methods require additional angular information as an input. This paper thus proposes a new method, the <I>positive energy residual</I> (<I>PER</I>) method, for fault detection of planetary gears. PER does not require the assumption of only small fluctuations of speed, nor does it need angular information. The proposed PER algorithm is based on two techniques, the wavelet transform (WT) and the Gaussian process (GP), which are used to remove the variability of the signals while extracting the faulty signals. Further, a fault feature is presented that is able to effectively quantify the characteristics of faulty signals. The performance of the proposed method is demonstrated using two case studies: vibration signals from a simulation model and vibration signals from a real test-bed. A comparison study with other methods, WT and energy residual (ER), is also presented to clarify the performance of the proposed PER algorithm. From the results, we conclude that the proposed PER method is capable of detecting faults of a planetary gear under variable speed conditions, while showing better performance than the two other methods.</P> <P><B>Highlights</B></P> <P> <UL> <LI> A novel method is proposed to detect faults of a planetary gear under variable speed conditions. </LI> <LI> The method can be applied to large fluctuations of speeds, and it does not need angular information. </LI> <LI> The proposed method is validated by the simulation and experiment data. </LI> <LI> The proposed method shows better performance compared to the previous methods. </LI> </UL> </P>

Bearing Fault Effect on Induction Motor Stator Current Modeling based on Torque Variations

Jaehoon Kim,Inseok Yang,Donggil Kim,Moussa Hamadache,Dongik Lee 제어로봇시스템학회 2012 제어로봇시스템학회 국제학술대회 논문집 Vol.2012 No.10

Incipient bearing fault detection and diagnosis in an induction motor are important for prevention of drive failures. Bearing fault leads to torque oscillations which results in phase modulation of stator current. Hence, the bearing fault can be detected by checking through the fault-related frequency at stator current spectrum. In this paper, the general model of the load torque oscillated by bearing fault is developed. A set of simulation results demonstrates the efficiency of the proposed generalization of load torque model.

Lagrange Polynomial 커브 피팅을 이용한 전자식 스로틀 밸브에서 시간지연 및 패킷 손실 보장

강선영(Sun-Young Kang),양인석(Inseok Yang),김지연(Jiyeon Kim),하마다쉬 무사(Hamadache Moussa),이동익(Dong-Ik Lee) 대한전자공학회 2010 대한전자공학회 학술대회 Vol.2010 No.6

This paper proposes a simple algorithm for compensating network delays/packet loss can be occurred in an electronic throttle system. Since the proposed algorithm is based on the Lagrange Polynomial curve fitting, it requires no precise model of the process in which the actuator is driving. The effectiveness of the proposed method is evaluated by a simulation applied to a throttle-by-wire system.