Search results

The purpose of this paper is to propose a new fault feature extraction scheme for the rolling element bearing.

The generalized Stockwell transform (GST) and the singular value ratio spectrum (SVRS) methods are combined. A time-frequency distribution measurement criterion named the energy concentration measurement (ECM) is initially used to determine the parameter of the optimal GST method. Then, the optimal GST is applied to conduct a time-frequency transformation for a raw signal. Subsequently, the two-dimensional time-frequency matrix is obtained. Finally, the improved singular value decomposition (SVD) analysis is used to conduct a noise reduction of the time-frequency matrix. The SVRS is proposed to select the effective singular values. Furthermore, the time-domain feature of the impact signal is obtained by taking the inverse GST transform.

The simulated and experimental signals are used to verify the superiority of the proposed method over conventional methods. The obtained results show that the proposed method can effectively extract fault features of the rolling element bearing.

This paper mainly discusses the application of GST and SVRS methods to analyze the weak fault feature extraction problem. The next research direction is to explore the application of the Hilbert Huang transform (HHT) and variational modal decomposition (VMD) in the impact feature extraction of rolling bearing.

In the present study, a new SVRS method is proposed to select the number of effective singular values. This paper proposed an effective way to obtain the fault feature in monitoring of rotating machinery.

This paper aims to propose a new ultrasonic diagnosis method for stainless steel weld defects based on multi-domain feature fusion to solve two problems in the ultrasonic diagnosis of austenitic stainless steel weld defects. These are insufficient feature extraction and subjective dependence of diagnosis model parameters.

To express the richness of the one-dimensional (1D) signal information, the 1D ultrasonic testing signal was derived to the two-dimensional (2D) time-frequency domain. Multi-scale depthwise separable convolution was also designed to optimize the MobileNetV3 network to obtain deep convolution feature information under different receptive fields. At the same time, the time/frequent-domain feature extraction of the defect signals was carried out based on statistical analysis. The defect sensitive features were screened out through visual analysis, and the defect feature set was constructed by cascading fusion with deep convolution feature information. To improve the adaptability and generalization of the diagnostic model, the authors designed and carried out research on the hyperparameter self-optimization of the diagnostic model based on the sparrow search strategy and constructed the optimal hyperparameter combination of the model. Finally, the performance of the ultrasonic diagnosis of stainless steel weld defects was improved comprehensively through the multi-domain feature characterization model of the defect data and diagnosis optimization model.

The experimental results show that the diagnostic accuracy of the lightweight diagnosis model constructed in this paper can reach 96.55% for the five types of stainless steel weld defects, including cracks, porosity, inclusion, lack of fusion and incomplete penetration. These can meet the needs of practical engineering applications.

This method provides a theoretical basis and technical reference for developing and applying intelligent, efficient and accurate ultrasonic defect diagnosis technology.

This study examines the tracking error (TE) of a sample of sector exchange traded funds (ETFs) using spectral techniques.

TE is examined by computing its power spectrum using the wavelet transform. The wavelet transform maps the TE time series from the time domain to the time–frequency domain. Albeit the wavelet transform is a more complicated mathematical tool compared with the Fourier transform, it also has important advantages such as that it allows to analyze non-stationary data and to detect transient behavior.

Results show that changes in the TE of a sample of sector ETFs are captured by the wavelet transform. Moreover, the authors also find that the wavelet coherence function can be used as a measure of TE in the time–frequency domain.

The study shows that the wavelet coherence function can be used as a reliable measure of TE.

Provides an introduction to the field of time‐frequency analysis by reviewing four important and popular used time‐frequency analysis methods with focus on the principles and implementation. The basic idea of time‐frequency analysis is to understand and describe situations where the frequency content of a signal is changing in time. Although time‐frequency analysis had its origin almost 50 years ago, significant advances have occurred in the past 15 years or so. Recently, the time‐frequency representation has received considerable attention as a powerful tool for analysing a variety of signals and systems.

This study aims to include the diagnosis of an old concrete deck steel truss rural road bridge in the damaged and retrofitted state through vibration response signals.

The analysis of the vibration response signals is performed in time and time-frequency domains using statistical features-root mean square, impulse factor, crest factor, kurtosis, peak2peak and Stockwell transform. The proposed methodology uses the Hilbert transform in combination with spectral kurtosis and bandpass filtering technique for obtaining robust outcomes of modal frequencies.

The absence or low amplitude of considered mode shape frequencies is observed both before and after retrofitting of bridge indicates the deficient nodes. The kurtosis feature among all statistical approaches is able to reflect significant variation in the amplitude of different nodes of the bridge. The Stockwell transform showed better resolution of present modal frequencies but due to the yield of additional frequency peaks in the vicinity of the first three analytical modal frequencies no decisive conclusions are achieved. The methodology shows promising outcomes in eliminating noise and visualizing distinct modal frequencies of a steel truss bridge.

The findings of the present study help in analyzing noisy vibration signals obtained from various structures (civil or mechanical) and determine vulnerable locations of the structure using mode shape frequencies.

The literature review gave an insight into few experimental investigations related to the combined application of Hilbert transform with spectral kurtosis and bandpass filtering technique in determining mode frequencies of a steel truss bridge.

The purpose of this paper is to test the applicability and the performance of an approach called logical analysis of data (LAD) on the detection of faults in rotating machinery using vibration signals.

LAD is a supervised learning data mining technique that relies on finding patterns in a binary database to generate decision functions. The hypothesis is that a LAD‐based decision model can be used as an effective tool for automatic detection of faults in rolling element bearings. A novel Multiple Integer Linear Programming approach is used to generate patterns for the LAD decision model. Frequency and time‐based features are extracted from rotor bearing vibration signals and are pre‐processed to be suitable for use with LAD.

The results show good classification accuracy with both time and frequency features.

The diagnostic tool implemented in the form of software in a production or operations maintenance environment can be very helpful to maintenance experts as it reveals the patterns that lead to the diagnosis in interpretable terms which facilitates efforts to understand the reasons behind the components' failure.

The proposed modifications to the LAD‐based decision model which is being tested for the first time in the field of fault detection in rotating machinery lead to improved accuracy results in addition to the added value of result interpretability due to this distinctive property of LAD.

The purpose of this paper is to present a diagnosis technique, for rotor broken bar in double cage induction motor, based on advanced use of wavelet transform analysis. The proposed technique is experimentally validated.

The proposed approach is based on a combined use of frequency sliding and wavelet transform analysis, to isolate the contribution of the rotor fault components issued from vibration signals in a single frequency band.

The proposed technique is reliable for tracking the rotor fault components over time-frequency domain. The quantitative analysis results based on this technique are the proof of its robustness.

The validity of the proposed diagnosis approach is not limited to the analysis under steady-state operating conditions, but also for time-varying conditions where rotor fault components are spread in a wide frequency range.

The developed approach is best suited for automotive or high power traction systems, in which safe-operating and availability are mandatory.

The paper presents a diagnosis technique for rotor broken bar in double cage induction motor base on advanced use of wavelet transform which allows the extraction of the most relevant rotor fault component issued from axial vibration signal and clamping it in a single frequency bandwidth, avoiding confusions with other components and false interpretations.

Rotating machineries are widely used in manufacturing, petroleum, chemical, aircraft, and other industries. To accurately identify the operating conditions of such rotating machineries, this paper aims to propose a fault diagnosis method based on sensitive dimensionless parameters and particle swarm optimization (PSO)–support vector machine (SVM) for reducing the unexpected downtime and economic losses.

A relatively new hybrid intelligent fault classification approach is proposed by integrating multiple dimensionless parameters, the Fisher criterion and PSO–SVM. In terms of data pre-processing, a method based on wavelet packet decomposition (WPD), empirical mode decomposition (EMD) and dimensionless parameters is proposed for the extraction of the vibration signal features. The Fisher criterion is applied to reduce the redundant dimensionless parameters and search for the sensitive dimensionless parameters. Then, PSO is adapted to optimize the penalty parameter and kernel parameter for SVM. Finally, the sensitive dimensionless parameters are classified with the optimized model.

As two different time–frequency analysis methods, a method based on a combination of WPD and EMD used to extract multiple dimensionless parameters is presented. More vital diagnosis information can be obtained from the vibration signals than by only using a single time–frequency analysis method. Besides, a fault classification approach combining the sensitive dimensionless parameters and PSO-SVM classifier is proposed. The comparative experiment results show that the proposed method has a high classification accuracy and efficiency.

To the best of the authors’ knowledge, very few efforts have been performed for fault classification using multiple dimensionless parameters. In this paper, eighty dimensionless parameters have been studied intensively, which provides a new strategy in fault diagnosis field.

The purpose of this paper is to identify the drivers of residential price as well as the degree co-movement of housing among different states in Malaysia.

This study adopted an advanced econometrics technique: the dynamic autoregressive-distributed lag (DARDL) and – the time-frequency domain approach known as the wavelet coherence test. The DARDL model was applied to identify the cointegrating relationships and the CWT was used to analyze the co-movement and lead–lag relationships among four states’ regional housing prices. The extracted data were mainly on annual basis and comprised macroeconomics and financial factors. Information with regard to residential prices and other variables was extracted from the National Property Information Centre (NAPIC) website, the Central Bank of Malaysia Statistics Report, the Department of Statistics, Malaysia, I-Property.com and the World Bank (WB). The data covered in this study were the pool data from four main states in Malaysia and different categories of residential properties.

The empirical results indicate that there were long-run cointegration relationships between the housing price and capital gain and loss, rental per square feet, disposable income, inflation, number of marriages, deposit rate, risk premium and loan-to-value (LTV) ratio. While the wavelet analysis shows that (1) in the long run, Kuala Lumpur housing price having strong co-movement with Selangor, Penang and Melaka housing prices except for Johor and (2) the lead–lag relationship also postulates Kuala Lumpur housing price having in-phase category with Selangor, Penang and Melaka housing prices except for Johor.

This study offers relevant practical implications. First, the study proposes an active collaboration between the private sector and government support which may help to smooth the pricing issue of residential properties. More low-cost residential projects are needed for focus groups including middle- and low-income earners. Furthermore, the results are expected to provide real estate investor in Malaysia, an improved understanding of the regional housing market price dynamics.

The findings of this study were obtained from various reliable sources; therefore, the results reflected the analysis of price drivers and co-movements. Furthermore, findings from this study lend some support to the argument on the rise of residential prices and offer several policy implications from a practical point of view with regard to the residential market.

This work proposes a tertiary wavelet model based automatic epilepsy classification system using electroencephalogram (EEG) signals.

In this paper, a three-stage system has been proposed for automated classification of epilepsy signals. In the first stage, a tertiary wavelet model uses the orthonormal M-band wavelet transform. This model decomposes EEG signals into three bands of different frequencies. In the second stage, the decomposed EEG signals are analyzed to find novel statistical features. The statistical values of the features are demonstrated using multi-parameters graph comparing normal and epileptic signals. In the last stage, the features are inputted to different conventional classifiers that classify pre-ictal, inter-ictal (epileptic with seizure-free interval) and ictal (seizure) EEG segments.

For the proposed system the performance of five different classifiers, namely, KNN, DT, XGBoost, SVM and RF is evaluated for the University of BONN data set using different performance parameters. It is observed that RF classifier gives the best performance among the above said classifiers, with an average accuracy of 99.47%.

Epilepsy is a neurological condition in which two or more spontaneous seizures occur repeatedly. EEG signals are widely used and it is an important method for detecting epilepsy. EEG signals contain information about the brain's electrical activity. Clinicians manually examine the EEG waveforms to detect epileptic anomalies, which is a time-consuming and error-prone process. An automated epilepsy classification system is proposed in this paper based on combination of signal processing (tertiary wavelet model) and novel features-based classification using the EEG signals.