Decomposition Of Vibration Signals Research Articles

Identification of fault size of rolling element bearing on outer race from vibration signature analysis

Prognostics deals with the estimation of the remaining useful life (RUL) of machine, which is predicated based on their present condition and their future operating condition. Rolling element bearing failure is one of the commonly explained reason for machine breakdown. At the point when machine is in running condition and fault occur in bearing, it is extremely difficult to identify fault size in bearing. Thus, for safety of machine it is necessary to change bearing before fault size increases to a significant level. Further, the replacement of bearing might be extremely costly and on other hand chances can’t be taken with safety aspects. Therefore, it is necessary to find the RUL of bearing by identifying the spall size of fault from vibration signal. Fault size estimation can be done by decomposition of vibration signal by using discrete wavelet transform and also introducing the autoregressive method, minimum entropy deconvolution and Hilbert transform. The decomposed signal is divided into peak corresponding to the ball enter into the fault and exit from the fault. Experiment conducted for various size of faults present on the 25 mm inner diameter polyamide cage deep groove ball bearing. The minimum size of 0.3 mm is detected in the present work for outer race defect with only radial load. Further, fault size estimation is investigated for 1mm defect present at outer race subjected to both radial and axial load

Enhanced vibration decomposition method based on multisynchrosqueezing transform and analytical mode decomposition

This paper proposes an enhanced vibration decomposition approach based on analytical mode decomposition (AMD) and multisynchrosqueezing transform (MSST). Although AMD-based low-pass filter has been applied for signal decomposition with time-varying cutoff frequencies, these cutoff frequencies are usually manually selected from the wavelet scalogram of the target signal. This process therefore significantly reduces the computational efficiency and could affect the accuracy of using AMD-based low-pass filter for non-stationary signal analysis. To overcome this problem, in this study, MSST with a time-varying cutoff frequency detection algorithm is used to automatically define the time-varying bisecting frequencies for the AMD analysis. Once the time-varying cutoff frequencies are identified, AMD can be used to adaptively decompose the non-stationary signal into individual components. To investigate the effectiveness of the proposed approach, termed as MSST–AMD, for vibration signal decomposition and its application, numerical studies on a non-stationary signal with overlapped frequency components are conducted. To further apply the proposed approach for structural vibration response analysis, a three-story shear-type structure with varying stiffness subjected to earthquake excitations is simulated in this study for instantaneous modal parameter identification. In experimental verifications, the proposed MSST–AMD approach combined with a damage index is further extended to evaluate the damage severity of a structure under earthquake excitations. The results in both numerical simulations and experimental validations demonstrate that the proposed approach is reliable and accurate for non-stationary signal analysis and vibration decomposition, which can be further used for instantaneous modal parameter identification and structural damage detection.

Intelligent Diagnosis Technology of Wind Turbine Drive System based on Neural Network

The seriousness of air pollution appears to be the importance of wind energy as a non-polluting energy source. Today, the use of wind power has become a trend for new countries to develop new energy sources. Wind turbines are the key equipment for converting wind energy into electrical energy, the quality of the state directly affects the efficiency of wind power generation. Therefore, how to effectively diagnose the wind turbine drive system is the guarantee of wind power generation. This paper establishes a fault diagnosis method for wind turbine drive based on vibration characteristics, by wavelet packet decomposition of vibration signals. The feature extraction is carried out and back propagation neural network is used for classification research. Finally, the simulation results show that the recognition rate is over 90%, which verify effectiveness of the proposed method.

Fault severity assessment of rolling bearing based on optimized multi-dictionaries matching pursuit and Lempel–Ziv complexity

For the safe working of rolling bearing, this paper presents a fault severity assessment method through optimized multi-dictionaries matching pursuit (OMMP) and Lempel–Ziv (LZ) complexity. To solve the redundancy problem of over-complete dictionary, the OMMP is proposed by introducing the quantum particle swarm optimization into matching pursuit for best representing the original vibration signal. And then, LZ complexity is calculated as an index of fault severity assessment by reconstructed signal. The performance of assessment method is verified through the measured signals of three bearing tests, and the comparisons with various methods are specifically described. The results indicate that the OMMP method averagely takes the shortest running time for the vibration signal decomposition. The assessment method is able to effectively evaluate different fault sizes of rolling bearing, and has a great applicability to in the condition-based maintenance of rotating machineries.

Wavelet decomposition algorithm for machine learning model in wind turbines

The paper considers the wavelet decomposition for machine learning model to solve the problem of analyzing the shape of vibration signals in wind energy turbines. The questions of training and optimization of the parameters of the classmate method are highlighted. The principle of constructing a training sample is described. The algorithm for the instance recognition of circuit elements by vibration signals removed from wind turbines. Thus, the method of recognition of equipment elements based on sparse wavelet decomposition of vibration signals can be used in practical renewable energy. The research results will stimulate of the development of generating facilities based on wind energy with an installed capacity of up to 15 kW will contribute to the stimulation of the development of wind power with a vertical axis in the urban environment.

Advance spectral approach for condition evaluation of rolling element bearings

The Performance of rolling element bearings has a significant influence on reliability and safety in the various engineering fields. While heading toward the condition evaluation of rolling element bearings, the higher dimensionality of feature space became a crucial concern. Thus, to have a check on the hurdles, this paper proposes a novel approach of bearing condition assessment utilizing Local mean decomposition (LMD) and spectral clustering (SC). Spectral Clustering (SC) is an influential tool, which heals the curse of dimensionality and facilitates the model by imparting a systematized structure. SC focuses more on connectivity rather than geometrical vicinity; moreover, the provision of a similarity matrix makes SC more reliable and increases its performance. To enrich the efficiency of SC, a novel decision criterion, PI (Parting Index) aiming the optimal number of clusters based on a new similarity indicator and disorder indicator coined as Synergic Association Index (SAI) and Separation Index (SI) respectively, has been proposed. The work aims to achieve better performance degradation assessment (PDA) by the application of the new SC-PI approach with the following steps; the first step is the decomposition of vibration signal into product functions (PFs) utilizing LMD; the second step involves the extraction of proper fault features; third, the extracted features are classified with the SC-PI method; finally the feature or attribute vectors are endowed to trained model and confidence value (CV) is calculated. The proposed method is validated on two datasets of different fault types. The results so obtained indicates that the SC-PI method easily differentiates the various stages when compared to different assessment techniques i.e. time-domain features, self-organizing map (SOM), k-medoids and Gaussian mixture model (GMM).

Multiple Fault Detection of Rolling Bearing through Ensemble Empirical Mode Decomposition of Vibration Signal

Generally, two or more faults occur simultaneously in the bearings. These Compound Faults (CF) in bearing, are most difficult type of faults to detect, by any data-driven method including machine learning. Hence, it is a primary requirement to decompose the fault vibration signals logically, so that frequencies can be grouped in parts. Empirical Mode Decomposition (EMD) is one of the simplest techniques of decomposition of signals. In this paper we have used Ensemble Empirical Mode Decomposition (EEMD) technique for compound fault detection/identification. Ensembled Empirical Mode Decomposition is found useful, where a white noise helps to detect the bearing frequencies. The graphs show clearly the capability of EEMD to detect the multiple faults in rolling bearings.

Fault Diagnosis of a Rotor and Ball-Bearing System Using DWT Integrated with SVM, GRNN, and Visual Dot Patterns.

In this study, a set of methods for the inspection of a working motor in real time was proposed. The aim was to determine if ball-bearing operation is normal or abnormal and to conduct an inspection in real time. The system consists of motor control and measurement systems. The motor control system provides a set fixed speed, and the measurement system uses an accelerometer to measure the vibration, and the collected signal data are sent to a PC for analysis. This paper gives the details of the decomposition of vibration signals, using discrete wavelet transform (DWT) and computation of the features. It includes the classification of the features after analysis. Two major methods are used for the diagnosis of malfunction, the support vector machines (SVM) and general regression neural networks (GRNN). For visualization and to input the signals for visualization, they were input into a convolutional neural network (CNN) for further classification, as well as for the comparison of performance and results. Unique experimental processes were established with a particular hardware combination, and a comparison with commonly used methods was made. The results can be used for the design of a real-time motor that bears a diagnostic and malfunction warning system. This research establishes its own experimental process, according to the hardware combination and comparison of commonly used methods in research; a design for a real-time diagnosis of motor malfunction, as well as an early warning system, can be built thereupon.

Rationale for the use of vibration signal decomposition as a diagnostic method for rolling bearings of oil pumps

Today, the development of new technologies and their application in the oil industry is a key factor in improving the reliability of technological equipment. A promising method of technical diagnostics, described in the article, is intended to identify such defects and is relevant in the consideration of this issue. The data obtained indicate that it is possible not only to isolate the pulse of interest from the signal of the untreated vibration, but also to identify the type of damage in the early stages.

Elucidation of ball bearing performance utilizing product functions of vibration signals and locality sensitive discriminant analysis

Dimensionality is a decent term utilized for the dimension-related issues of feature vectors for the condition assessment of bearings. It has been a challenging task while dealing with the characteristic information conservation of the sampled data. Feature vectors with higher dimensions provide an accurate description of the condition, while lower dimension vectors are easy to be classified. These conditions make the dimensionality of feature space a big challenge in the performance evaluation of critical machine parts like bearings. This paper presents a judicious and wise application of a linear approach, locality sensitive discriminant analysis along with the rational use of local mean decomposition in performance degradation assessment. The combination effectively solves the problems of insufficient training samples and large dimensionality of fault features, which imparts excessive noise and causes loss of competent hidden characteristics. In such cases, local structures of feature space are more crucial than the global one. These obstacles can be answered by imparting locality sensitive discriminant analysis as an initial operation. Locality sensitive discriminant analysis is a linear dimensionality reduction tool, which explores the precise projections that amplify the margin between data points and prepare a conservation aid to preserve faulty information of bearings. The steps are followed to achieve the same: decomposition of vibration signal into product functions; calculation of fault features; third, higher dimensionality of the features is reduced with the implementation of locality sensitive discriminant analysis and some prime features are selected with the proposed criterion; the reduced features are further clustered and a trained model of assessment is prepared. Finally, health indicator is calculated from the trained model and test features. The proposed technique is verified on two bearing datasets. The superiority of the technique has been envisaged by comparing the method with different similar assessment methods i.e. time domain features, linear discriminant analysis, and principal component analysis.

Vibration analysis using wavelet transform and fuzzy logic for shaft misalignment

In most of rotating kind of machinery, misalignment is commonly observed defect. Though machines are installed to zero-zero aligned condition in initial stage, in due course of run time operation misalignment get introduced due thermal distortion, asymmetry of forces exerted and inadequate assembly of parts. This paper presents a method of misalignment prediction from output vibration signal which is based on combined DWT (Discrete Wavelet Transform) and Fuzzy Logic approach. DWT helps in multilevel decomposition of vibration signal to understand where and at what instant misalignment occurs. This involves selection of mother wavelet. The FIS (Fuzzy Inference System) is combined with DWT to predict degree of misalignment present. An inclusion of FIS has improved prediction accuracy of Degree of Misalignment (DoM) which has claimed error less than one percent (1 %).

Mechanical Fault Diagnosis of HVCBs Based on Multi-Feature Entropy Fusion and Hybrid Classifier.

As high-voltage circuit breakers (HVCBs) are directly related to the safety and the stability of a power grid, it is of great significance to carry out fault diagnoses of HVCBs. To accurately identify operating states of HVCBs, a novel mechanical fault diagnosis method of HVCBs based on multi-feature entropy fusion (MFEF) and a hybrid classifier is proposed. MFEF involves the decomposition of vibration signals of HVCBs into several intrinsic mode functions using variational mode decomposition (VMD) and the calculation of multi-feature entropy by the integration of three Shannon entropies. Principle component analysis (PCA) is then used to reduce the dimension of the multi-feature entropy to achieve an effective fusion of features for selecting the feature vector. The detection of an unknown fault in HVCBs is achieved using support vector data description (SVDD) trained by normal-state samples and specific fault samples. On this basis, the identification and classification of the known states are realized by the support vector machine (SVM). Three faults (i.e., closing spring force decrease fault, buffer spring invalid fault, opening spring force decrease fault) are simulated on a real SF6 HVCB to test the feasibility of the proposed method. The detection accuracies of the unknown fault are 100%, 87.5%, and 100% respectively when each of the three faults is assumed to be the unknown fault. The comparative experiments show that SVM has no ability to detect the unknown fault, and that one-class support vector machine (OCSVM) has a weaker ability to detect the unknown fault than SVDD. For known-state classification, the adoption of the MFEF method achieved an accuracy of 100%, while the use of a single-feature method only achieved an accuracy of 75%. These results indicate that the proposed method combining MFEF with hybrid classifier is thus more efficient and robust than traditional methods.

Incipient Broken Rotor Bar Detection in Induction Motors Using Vibration Signals and the Orthogonal Matching Pursuit Algorithm

A methodology for automatic incipient broken rotor bar detection in induction motors (IMs) is presented. Sparse representations of signals are applied as a diagnosis technique. The novelty of this technique is that it can analyze the frequency spectra from vibration signals even when the differences among signals are small. This representation allows decomposing or reconstructing signals through a trained dictionary that has learned the features of one specific group/class. The main feature of this paper is the use of overcomplete dictionaries trained from sets of signals with faults to be detected. In this way, trained dictionaries perform the decomposition of signals using the orthogonal matching pursuit (OMP) algorithm. The decomposition is evaluated and classified by error-based criteria and a majority decision classifier, allowing the detection of early damage, ranging from 1 mm to one broken bar. The detection is performed by the decomposition of vibration signals from three axes ( ${x}$ , ${y}$ , and ${z}$ ) of IMs under three load conditions (unloaded, half loaded, and three-fourths loaded) and different levels of damage (healthy or 0 mm, 1–9 mm, and one broken bar). These signals are processed by the Fourier transform and the spectrum obtained is evaluated by the OMP algorithm. Finally, the retrieved information is evaluated and the diagnosis is given. All algorithms are developed in MATLAB software and the detection accuracy is higher than 90% for damages as small as 1 mm.

A fault diagnosis method for roller bearing based on empirical wavelet transform decomposition with adaptive empirical mode segmentation

This paper proposes a fault diagnosis method for roller bearings based on the decomposition of vibration signals using the empirical wavelet transform (EWT) with adaptive empirical mode segmentation and the merging of redundant empirical modes. The proposed method employs scale-space histogram segmentation to determine the boundaries of the empirical modes adaptively, which helps to eliminate the effect of noise and obtain meaningful empirical modes that are more reflective of fault characteristics. In addition, the method merges similar empirical modes to rectify the tendency of conventional EWT to overly decompose empirical modes for fault feature extraction. To this end, an effective merging algorithm based on Pearson’s correlation coefficient is developed to divide the empirical modes into groups according to their similarity prior to merging, which avoids a large increase in the amplitude of the signal after merging, and ensures the accuracy of the final result. The performance of the proposed method is first tested using an analytically derived signal. Then, the method is tested using actual vibration signals of roller bearings collected by NASA. The results demonstrate that the proposed method can identify fault information effectively and accurately.

Amplitude-cyclic frequency decomposition of vibration signals for bearing fault diagnosis based on phase editing

Abstract In rotating machine diagnosis different spectral tools are used to analyse vibration signals. Despite the good diagnostic performance such tools are usually refined, computationally complex to implement and require oversight of an expert user. This paper introduces an intuitive and easy to implement method for vibration analysis: amplitude cyclic frequency decomposition. This method firstly separates vibration signals accordingly to their spectral amplitudes and secondly uses the squared envelope spectrum to reveal the presence of cyclostationarity in each amplitude level. The intuitive idea is that in a rotating machine different components contribute vibrations at different amplitudes, for instance defective bearings contribute a very weak signal in contrast to gears. This paper also introduces a new quantity, the decomposition squared envelope spectrum, which enables separation between the components of a rotating machine. The amplitude cyclic frequency decomposition and the decomposition squared envelope spectrum are tested on real word signals, both at stationary and varying speeds, using data from a wind turbine gearbox and an aircraft engine. In addition a benchmark comparison to the spectral correlation method is presented.

A new fault detection strategy using the enhancement ensemble empirical mode decomposition

The vibration signals of mechanical components are non-linear and non-stationary and the feature frequencies of faulty bearings will be difficult extracted. This paper presents a new approach that combines the ensemble empirical mode decomposition (EEMD), the random decrement technique (RDT), and envelope spectrum for the fast detection of faults in bearings. The proposed approach uses the optimized and fast EEMD algorithm to extract intrinsic mode functions (IMFs) from vibration signals able to tack the feature frequency of bearings. If the Impulse response signal of the first IMF is unclear, it is further extracted by the RDT, and the feature frequencies are determined by analyzing the signals using envelope spectrum. The advantages of this method are its computational efficiency, and the strong non-stationary vibration signal decomposition and impulse signal extraction abilities. Numerical simulations and experimental data collected from faulty bearings are used to validate the proposed approach. The results show that the use of the EEMD, the RDT, and the envelope spectrum is a suitable and fast on-line strategy to detect faults of mechanical components.

An Optimal Ensemble Empirical Mode Decomposition Method for Vibration Signal Decomposition

The vibration signal decomposition is a critical step in the assessment of machine health condition. Though ensemble empirical mode decomposition (EEMD) method outperforms fast Fourier transform (FFT), wavelet transform, and empirical mode decomposition (EMD) on nonstationary signal decomposition, there exists a mode mixing problem if the two critical parameters (i.e., the amplitude of added white noise and the number of ensemble trials) are not selected appropriately. A novel EEMD method with optimized two parameters is proposed to solve the mode mixing problem in vibration signal decomposition in this paper. In the proposed optimal EEMD, the initial values of the two critical parameters are selected based on an adaptive algorithm. Then, a multimode search algorithm is explored to optimize the critical two parameters by its good performance in global and local search. The performances of the proposed method are demonstrated by means of a simulated signal, two bearing vibration signals, and a vibration signal in a milling process. The results show that compared with the traditional EEMD method and other improved EEMD method, the proposed optimal EEMD method automatically obtains the appropriate parameters of EEMD and achieves higher decomposition accuracy and faster computational efficiency.

Fault diagnosis of valve clearance in diesel engine based on BP neural network and support vector machine

Based on wavelet packet transformation(WPT), genetic algorithm(GA), back propagation neural network(BPNN)and support vector machine(SVM), a fault diagnosis method of diesel engine valve clearance is presented. With power spectral density analysis, the characteristic frequency related to the engine running conditions can be extracted from vibration signals. The biggest singular values(BSV)of wavelet coefficients and root mean square (RMS)values of vibration in characteristic frequency sub-bands are extracted at the end of third level decomposition of vibration signals, and they are used as input vectors of BPNN or SVM. To avoid being trapped in local minima, GA is adopted. The normal and fault vibration signals measured in different valve clearance conditions are analyzed. BPNN, GA back propagation neural network (GA-BPNN), SVM and GA-SVM are applied to the training and testing for the extraction of different features, and the classification accuracies and training time are compared to determine the optimum fault classifier and feature selection. Experimental results demonstrate that the proposed features and classification algorithms give classification accuracy of 100%.

A data-driven method to enhance vibration signal decomposition for rolling bearing fault analysis

Health condition analysis and diagnostics of rotating machinery requires the capability of properly characterizing the information content of sensor signals in order to detect and identify possible fault features. Time–frequency analysis plays a fundamental role, as it allows determining both the existence and the causes of a fault. The separation of components belonging to different time–frequency scales, either associated to healthy or faulty conditions, represents a challenge that motivates the development of effective methodologies for multi-scale signal decomposition. In this framework, the Empirical Mode Decomposition (EMD) is a flexible tool, thanks to its data-driven and adaptive nature. However, the EMD usually yields an over-decomposition of the original signals into a large number of intrinsic mode functions (IMFs). The selection of most relevant IMFs is a challenging task, and the reference literature lacks automated methods to achieve a synthetic decomposition into few physically meaningful modes by avoiding the generation of spurious or meaningless modes. The paper proposes a novel automated approach aimed at generating a decomposition into a minimal number of relevant modes, called Combined Mode Functions (CMFs), each consisting in a sum of adjacent IMFs that share similar properties. The final number of CMFs is selected in a fully data driven way, leading to an enhanced characterization of the signal content without any information loss. A novel criterion to assess the dissimilarity between adjacent CMFs is proposed, based on probability density functions of frequency spectra. The method is suitable to analyze vibration signals that may be periodically acquired within the operating life of rotating machineries. A rolling element bearing fault analysis based on experimental data is presented to demonstrate the performances of the method and the provided benefits.

Online Condition Monitoring of Bearings to Support Total Productive Maintenance in the Packaging Materials Industry.

The packaging materials industry has already recognized the importance of Total Productive Maintenance as a system of proactive techniques for improving equipment reliability. Bearing faults, which often occur gradually, represent one of the foremost causes of failures in the industry. Therefore, detection of their faults in an early stage is quite important to assure reliable and efficient operation. We present a new automated technique for early fault detection and diagnosis in rolling-element bearings based on vibration signal analysis. Following the wavelet decomposition of vibration signals into a few sub-bands of interest, the standard deviation of obtained wavelet coefficients is extracted as a representative feature. Then, the feature space dimension is optimally reduced to two using scatter matrices. In the reduced two-dimensional feature space the fault detection and diagnosis is carried out by quadratic classifiers. Accuracy of the technique has been tested on four classes of the recorded vibrations signals, i.e., normal, with the fault of inner race, outer race, and ball operation. The overall accuracy of 98.9% has been achieved. The new technique can be used to support maintenance decision-making processes and, thus, to increase reliability and efficiency in the industry by preventing unexpected faulty operation of bearings.