Low Speed Rolling Element Bearings Research Articles

Detecting and Learning Unknown Fault States by Automatically Finding the Optimal Number of Clusters for Online Bearing Fault Diagnosis

This paper proposes an online fault diagnosis system for bearings that detect emerging fault modes and then updates the diagnostic system knowledge (DSK) to incorporate information about the newly detected fault modes. New fault modes are detected using k-means clustering along with a new cluster evaluation method, i.e., multivariate probability density function’s cluster distribution factor (MPDFCDF). In this proposed model, a heterogeneous pool of features is constructed from the signal. A hybrid feature selection model is adopted for selecting optimal feature for learning the model with existing fault mode. The proposed online fault diagnosis system detects new fault modes from unknown signals using k-means clustering with the help of proposed MPDFCDF cluster evaluation method. The DSK is updated whenever new fault modes are detected and updated DSK is used to classify faults using the k-nearest neighbor (k-NN) classifier. The proposed model is evaluated using acoustic emission signals acquired from low-speed rolling element bearings with different fault modes and severities under different rotational speeds. Experimental results present that the MPDFCDF cluster evaluation method can detect the optimal number of fault clusters, and the proposed online diagnosis model can detect newly emerged faults and update the DSK effectively, which improves the diagnosis performance in terms of the average classification performance.

LOW SPEED ROLLING BEARING DIAGNOSTICS USING ACOUSTIC EMISSION AND HIGHER ORDER STATISTICS TECHNIQUE

Diagnostics in low speed rolling element bearings is difficult. Not only are normal frequency domain diagnostics methods not appropriate for this application, but the bearing response signals are usually immersed in background noise which make it difficult to detect these faults. Higher order statistics (HOS) techniques have been available for decades but have not been widely applied to machine condition monitoring with the exceptions of skewness and kurtosis. There is however reason to believe that these HOS techniques could play an important role in acoustic emission (AE) based condition monitoring of rolling element bearings at low speeds provided appropriate care is taken. To explore this hypothesis, AE signals at low bearing rotational speeds of 70, 80, 90 and 100 rpm respectively were used in this work for the monitoring of tapered roller bearings. In addition to the well-established statistical parameters such as mean, standard deviation, skewness and kurtosis, higher moments such as hyper flatness are considered in this study. A novel diagnostic method is proposed for fault extraction based on hyperflatness, combined with Kullback-Leibler divergence, and an indicator formula derived with the use of Lempel-Ziv Complexity is given. The Kullback-Leibler divergence is used together with the skewness and hyperflatness to obtain the Kullback-Leibler information Wave (KLW)with which the analysis is performed, and better results obtained as compared to conventional frequency domain analysis.

Time–frequency envelope analysis-based sub-band selection and probabilistic support vector machines for multi-fault diagnosis of low-speed bearings

This paper proposes a highly reliable multi-fault diagnosis scheme for low-speed rolling element bearings using an effective time–frequency envelope analysis and a Bayesian inference based one-against-all support vector machines (probabilistic-OAASVM) classifier. The proposed method first performs a wavelet packet transform based envelope analysis on an acoustic emission signal to select sub-bands of the signal that contain the most intrinsic and pertinent information about the defects. Frequency- and time-domain fault features are extracted only from selected sub-bands for fault classification. Traditional one-against-all SVMs (OAASVM), a widely used multi-class pattern recognition technique, employ an arbitrary combination of a series of binary classifiers yielding overlapped feature spaces, where a data sample can be unclassifiable. To address this limitation, we formulate the feature space of OAASVM as an appropriate Gaussian process prior (GPP) and interpret OAASVM results as a posterior probability estimation procedure using Bayesian inference under this GPP. The efficacy of the proposed probabilistic-OAASVM classifier is verified for low-speed rolling element bearings under various conditions. Experimental results indicate that the proposed method outperforms the state-of-the-art algorithms for multi-fault classification of low-speed bearings, yielding a 4.95–20.67% improvement in the average classification accuracy.

Time-Varying and Multiresolution Envelope Analysis and Discriminative Feature Analysis for Bearing Fault Diagnosis

This paper presents a reliable fault diagnosis methodology for various single and multiple combined defects of low-speed rolling element bearings. This method temporally partitions an acoustic emission (AE) signal and selects a portion of the signal, which contains intrinsic information about the bearing failures. This paper then performs frequency analysis for the selected time-domain AE signal by using multilevel finite-impulse response filter banks to obtain the most informative subband signals involving abnormal symptoms of the bearing defects. It does this by using a 2-D visualization tool that represents the percentage of the Gaussian-mixture-model-based residual component-to-defect component ratios via time-varying and multiresolution envelope analysis (TVMREA). Then, fault signatures in the time and frequency domains are extracted in the informative subband signals. Since all the extracted fault features may not be equally useful for diagnosis, the proposed genetic algorithm (GA)-based discriminative feature analysis (GADFA) selects the most discriminative subset of fault signatures. In experiments, single and multiple combined bearing defects under various conditions are used to validate the effectiveness of this fault diagnosis scheme using TVMREA and GADFA. Experimental results indicate that this reliable fault diagnosis methodology accurately identifies bearing failure type across a variety of conditions. In addition, GADFA outperforms other state-of-the-art feature analysis techniques, yielding 7.3%–46.6% performance improvements in average classification accuracy.

음향 방출 신호와 히스토그램 모델링을 이용한 유도전동기의 베어링 결함 검출

본 논문에서는 저속으로 회전하는 유도 전동기의 베어링 결함을 검출하기 위해 음향 방출 신호와 히스토그램 모델링을 이용하는 방법을 제안한다. 제안한 방법은 정규화된 결함 신호가 구성하는 히스토그램의 포락선을 모델링하여, 부분 상관 계수와 DET(Distance Evaluation Technique) 기법을 이용하여 결함 유형별 고유한 특징을 추출 및 선택한다. 추출된 특징을 SVR(Support Vector Regression) 분류기의 입력으로 사용하여 베어링의 내륜, 외륜 및 롤러 결함을 분류한다. 최적의 분류 성능을 위해 SVR 커널함수의 매개변수를 0.01에서 1.0까지 변화시키고, 특징 개수는 2에서 150까지 변화시키면서 실험한 결과, 0.64-0.65의 매개변수와 75개의 특징 개수에서 제안한 방법은 약 91%의 분류 성능을 보였고, 또한 기존의 결함 분류 알고리즘보다 높은 분류 성능을 보였다. This paper proposes a fault detection method for low-speed rolling element bearings of an induction motor using acoustic emission signals and histogram modeling. The proposed method performs envelop modeling of the histogram of normalized fault signals. It then extracts and selects significant features of each fault using partial autocorrelation coefficients and distance evaluation technique, respectively. Finally, using the extracted features as inputs, the support vector regression (SVR) classifies bearing's inner, outer, and roller faults. To obtain optimal classification performance, we evaluate the proposed method with varying an adjustable parameter of the Gaussian radial basis function of SVR from 0.01 to 1.0 and the number of features from 2 to 150. Experimental results show that the proposed fault identification method using 0.64-0.65 of the adjustable parameter and 75 features achieves 91% in classification performance and outperforms conventional fault diagnosis methods as well.

Condition monitoring of low speed bearings: A comparative study of the ultrasound technique versus vibration measurements

Bearing failure is often attributed to be one of the major causes of breakdown in industrial rotating machines that operate at high and low speeds. This paper presents results of a comparative experimental study on the application of the ultrasound technique for condition monitoring of low speed rolling element bearings and conventional vibration measurements with seeded faults on inner-race defects. The effectiveness of the ultrasound technique is demonstrated through signal processing techniques; use of statistical parameters derived from the time domain, and enveloped spectra in the frequency domain. The results reveal that the ultrasound technique is more effective in detecting low speed bearings failure than that of the vibration measurement.

Monitoring extremely slow rolling element bearings: part II

The most established technique for monitoring the integrity of rolling element bearings is vibration analysis. However, at extremely slow rotational speeds monitoring the health of rolling element bearings is fraught with difficulty. Part I of this work details difficulties with monitoring rolling element bearings rotating at speeds of less than 2 rpm. Furthermore, it presents a study of the high frequency acoustic emission (AE) technique as a means of monitoring low-speed rolling element bearings. The application of AEs to monitor operational slow-speed bearings with bore diameters of 120 mm is presented. It is concluded that the mechanism of AE generation was the relative movement between bearing elements experiencing loss of mechanical integrity, for example, the rolling/sliding action of a roller on a defective outer race.

Diagnosis of Machinery Fault Status using Transient Vibration Signal Parameters

This paper reports the results of an investigation in which a Prony model based method is developed. The method shows potential for analysing transient vibration signals. An example is included that shows how the procedure was employed to analyse the transient vibration signals created from faulty low speed rolling element bearings. Spectral plots generated by applying the procedure to very short data samples, as well as trending parameters based on these spectral estimations and Prony parameters, are presented. An equation was also derived to quantitatively determine the fault status. It is shown that application of the Prony model based method has the potential to be an effective as well as efficient machine condition monitoring and diagnostic tool where short duration transient vibration signals are being generated.

Monitoring extremely slow rolling element bearings: part I

The most established technique for monitoring the integrity of rolling element bearings is vibration analysis. However, at extremely slow rotational speeds monitoring the health of rolling element bearings is fraught with difficulty. Part I of this work details difficulties with monitoring rolling element bearings rotating at speeds of less than 2 rpm. Furthermore, it presents a study of the high frequency acoustic emission (AE) technique as a means of monitoring low-speed rolling element bearings. The application of AEs to monitor operational slow-speed bearings with bore diameters of 120 mm is presented. It is concluded that the mechanism of AE generation was the relative movement between bearing elements experiencing loss of mechanical integrity, for example, the rolling/sliding action of a roller on a defective outer race.

Fault detection and diagnosis in low speed rolling element bearings using inductive inference classification

An effective procedure for the early detection and objective diagnosis of faults in rolling element bearings is described. The procedure involves the use of an inductive inference theory based classification program called ‘Snob’. The program objectively divides frequency spectra into classes representing different bearing conditions. The estimated description length of each spectrum, which is used for classification, can also be used to detect the early stages of bearing deterioration. The procedure was tested using parametric frequency spectra representing various low speed (60 rpm) rolling element bearing fault conditions. It is shown that the inductive inference theory based spectra classification procedure works well at objectively diagnosing faults in low speed rolling element bearings and allowing early detection of bearing deterioration.

Parametric spectral estimation to detect and diagnose faults in low speed rolling element bearings: Preliminary investigations

The monitoring of low speed bearings (⩽100 rpm) is fraught with difficulties, not the least of which is the impracticality of recording sufficiently long periods of data for appropriate data analysis to be performed. Based on current fast Fourier transform (FFT) techniques, it would be normal to analyse data for several minutes if low frequency bandwidths are being investigated. A parametric model based approach could reduce the data acquisition period to a fraction of the time taken by the FFT technique. This paper presents a brief review of the parametric spectral estimation method, as well as report on some preliminary work that compares the two methods when applied to low speed rolling element bearings.

Fault detection and diagnosis in low speed rolling element bearings Part I: The use of parametric spectra

An effective procedure for vibration condition monitoring of low speed (⩽100 RPM) rolling element bearings is described. The procedure incorporates fault detection using frequency domain trending indices with fault diagnosis using the frequency spectra. By using parametric models to generate frequency spectra, successful fault detection and diagnosis can be achieved from considerably shorter signal lengths than when using conventional procedures. The results presented here follow directly from earlier work done to compare parametric model based frequency spectra with FFT based frequency spectra, when being used to detect and diagnose faults in low speed rolling element bearings.

Fault detection and diagnosis in low speed rolling element bearings Part II: The use of nearest neighbour classification

An effective procedure for automatic fault diagnosis in low speed (⩽100 RPM) rolling element bearings is described. The procedure involves the calculation of a statistical distance measure between vibration signals. The distance measure is then automatically used to distinguish between different fault conditions. A new trending index, based on the statistical distance measure, which may be used for fault detection, is also described.