•A new approach, SKC, is proposed for intelligent diagnosis of rolling elements bearings.•The average kurtosis indicator is also proposed for condition monitoring of bearings.•Data related to ...profoundly variable operational conditions are examined.•Both distributed and localized defects with various severities are studied.
Extensive research has been conducted for intelligent fault diagnosis and prognosis of rolling element bearings, a vital component in every rotating machinery, and many robust and reliable techniques have been developed thus far. The majority of the proposed approaches, however, are established for constant operational conditions and therefore encounter difficulties when working conditions vary, which is common in industrial applications. The reason is that many characteristics of a normal state of a system in one working condition might be similar to the characteristics of a defected one in another working condition. The aim of this paper is to develop a method that can differentiate between different health states of machinery, regardless of load and speed conditions. For this purpose, a newly proposed approach, namely spectral amplitude modulation (SAM), is employed to highlight various components of a signal with different energy levels. Subsequently, the impulsivity of these extracted signals’ envelope spectrum is computed to quantify their cyclostationarity level. These quantities could be further utilized as the input variables of machine learning algorithms for automated and intelligent diagnosis of bearings. In this paper, two methods for data classification, namely support vector machine (SVM) and subspace k-nearest neighbors, are employed. Moreover, the computed impulsiveness of signals contains information about the health state of machinery and therefore could be employed as a health indicator for online condition monitoring of machines. To thoroughly assess the potential of the proposed method for condition monitoring and intelligent diagnosis of machinery in constant and highly variable working conditions, it is implemented on data collected from three distinct test rigs, namely the IMS, PoliTo and FEMTO data sets. The damages on bearings in those experiments have different severity levels, types, and they are located on different components of the bearings. In addition to localized defects, distributed faults, which are advanced and critical stages of defects, are also studied in this research. This type of defect is more difficult to detect and has been largely overlooked due to the fact that the characteristics of its signals are different from localized ones and similar to other modulation sources.
Wavelet analysis, being a popular time-frequency analysis method has been applied in various fields to analyze a wide range of signals covering biological signals, vibration signals, acoustic and ...ultrasonic signals, to name a few. With the capability to provide both time and frequency domains information, wavelet analysis is mainly for time-frequency analysis of signals, signal compression, signal denoising, singularity analysis and features extraction. The main challenge in using wavelet transform is to select the most optimum mother wavelet for the given tasks, as different mother wavelet applied on to the same signal may produces different results. This paper reviews on the mother wavelet selection methods with particular emphasis on the quantitative approaches. A brief description of the proposed new technique to determine the optimum mother wavelet specifically for machinery faults diagnosis is also presented in this paper.
•A new deep learning method is proposed to automatically learn the useful fault features from the raw vibration signals.•A new deep auto-encoder model is constructed for the enhancement of feature ...learning ability.•Locality preserving projection is adopted to fuse the deep features to extract the most representative information.
It is meaningful to automatically learn the valuable features from the raw vibration data and provide accurate fault diagnosis results. In this paper, an enhancement deep feature fusion method is developed for rotating machinery fault diagnosis. Firstly, a new deep auto-encoder is constructed with denoising auto-encoder (DAE) and contractive auto-encoder (CAE) for the enhancement of feature learning ability. Secondly, locality preserving projection (LPP) is adopted to fuse the deep features to further improve the quality of the learned features. Finally, the fusion deep features are fed into softmax to train the intelligent diagnosis model. The developed method is applied to the fault diagnosis of rotor and bearing. The results confirm that the proposed method is more effective and robust compared with the existing methods.
•A deep learning method is proposed to address the data imbalance problem.•Deep generative adversarial networks are designed to generate fake samples.•Fake samples are similar with real machinery ...vibration data.•Experiments validate the proposed method on data augmentation in diagnosis.
Despite the recent advances of intelligent data-driven fault diagnosis methods on rotating machines, balanced training data for different machine health conditions are assumed in most studies. However, the signals in machine faulty states are usually difficult and expensive to collect, resulting in imbalanced training dataset in most cases. That significantly deteriorates the effectiveness of the existing data-driven approaches. This paper proposes a deep learning-based fault diagnosis method to address the imbalanced data problem by explicitly creating additional training data. Generative adversarial networks are firstly used to learn the mapping between the distributions of noise and real machinery temporal vibration data, and additional realistic fake samples can be generated to balance and further expand the available dataset afterwards. Through experiments on two rotating machinery datasets, it is validated that the data-driven methods can significantly benefit from the data augmentation, and the proposed method offers a promising tool on fault diagnosis with imbalanced training data.
Recently, the food packaging industry has focused on developing an eco-friendly and sustainable food packaging system. This study describes the effect of beeswax on the physical, structural, and ...barrier properties of a polyvinyl alcohol (PVA)/polyacrylic acid (PAA) composite film. The incorporation of beeswax improved the barrier properties against oxygen, water, and oil. However, the addition of a high content of beeswax caused phase separation in the film-forming solution. The destabilization mechanisms such as clarification and creaming formation in the film-forming solution were revealed by turbidimetric analysis. The results of scanning electron microscopy (SEM) and confocal laser scanning microscopy (CLSM) indicates that non-homogeneous structures in the film-forming solution were formed as a function of increased beeswax content due to the agglomeration of beeswax. The mechanical properties of the films were also evaluated to determine the most appropriate content of beeswax. There was a slight decrease in tensile strength and an increase in elongation as beeswax content increased up to 10%. Thus, the PVA/PAA composite film with 10% beeswax was chosen for further applications. In summary, the PVA/PAA composite film developed in this study with 10% beeswax exhibited a significant improvement in barrier properties and has the potential for use in commerce.
Monitoring vibrations in rotating machinery allows effective diagnostics, as abnormal functioning states are related to specific patterns that can be extracted from vibration signals. Extensively ...studied issues concern the different methodologies used for carrying out the main phases (signal measurements, pre-processing and processing, feature selection, and fault diagnosis) of a malfunction automatic diagnosis. In addition, vibration-based condition monitoring has been applied to a number of different mechanical systems or components. In this review, a systematic study of the works related to the topic was carried out. A preliminary phase involved the analysis of the publication distribution, to understand what was the interest in studying the application of the method to the various rotating machineries, to identify the interest in the investigation of the main phases of the diagnostic process, and to identify the techniques mainly used for each single phase of the process. Subsequently, the different techniques of signal processing, feature selection, and diagnosis are analyzed in detail, highlighting their effectiveness as a function of the investigated aspects and of the results obtained in the various studies. The most significant research trends, as well as the main innovations related to the various phases of vibration-based condition monitoring, emerge from the review, and the conclusions provide hints for future ideas.
•EMD manifold is proposed for true mode extraction in machinery fault diagnosis.•Sensitive modes with different noise are fused nonlinearly by manifold learning.•The true mode is adaptively learned ...with the assistance of random noise.•The new method has the merits of mode mixing alleviation and noise removal.•The improved performance is verified in enhanced machinery fault diagnosis.
One challenge of the existing noise-assisted methods for solution of mode mixing problem of empirical mode decomposition (EMD) is that, the decomposed modes contain much residual noise derived from both added and self-contained noise. This paper proposes a new noise-assisted method, called EMD manifold (EMDM), for enhanced fault diagnosis of rotating machines. The major contribution is that the new method nonlinearly and adaptively fuses the fault-related modes containing different noise via a manifold learning algorithm, by which true fault-related transients are preserved, while fault-unrelated components including mode-mixing-induced components and the residual noise derived from both the added and self-contained noise are greatly suppressed. First, the sensitive mode is located among the modes obtained by the EMD method according to a newly proposed criterion. Then, a high-dimensional matrix is constructed of the sensitive modes obtained through a small number of EMD trials on the signals plus noise of different amplitudes. Finally, the manifold learning algorithm is performed on the high-dimensional matrix to extract intrinsic manifold of the fault-related transients. The high-dimensional matrix is repeatedly constructed with random noise added to adjust local data distribution of the matrix for adaptive EMDM feature learning. Experimental studies on gearbox and bearing faults are conducted to validate the proposed method and its enhanced performance over traditional noise-assisted EMD methods.