Morlet Wavelet Coefficients Research Articles

The Fault Diagnosis based on Deep Long Short-Term Memory Model from the Vibration Signals in the Computer Numerical Control Machines

Rotating machines have become indispensable in every field of life. Because of people's commitment to machines, the machine's faults have devastating consequences. Fault analysis of devices is common in the industry. Studies in the literature mostly work on simple models. These simple models become inefficient as data complexity increases. In this paper, three types of faults are detected in the drill bit of the CNC (Computer Numerical Control) machine. Deep LSTM (Long Short-Term Memory)-based classification model has been proposed for fault diagnosis of CNC machines. Different structures can be combined to obtain higher accuracy rates. The proposed method consists of two stages: (I) the feature extraction including time, frequency domain, and Morlet wavelet coefficients information from vibration signals from CNC machines, (II) the classification of fault types using deep LSTM model based on the extracted features. LSTM structures having two layers, three layers, four layers, and five layers have been proposed and then compared with each other with respect to the classification accuracy of fault diagnosis. The highest accuracy rate obtained in this study was 99.53%. It can be seen that deep LSTM gives outstanding results in the structures with sequential data input and the proposed system gives promising results in the field of fault analysis of machines.

Condition monitoring of bevel gear box using Morlet wavelet coefficients and naïve Bayes classifier

A naive Bayes classifier is used for classifying the faults of a gear box. The rotating equipment like gear box has enough scope for condition monitoring its conditions as it plays a significant role as a prime mover in many engineering applications. This paper discusses about the extraction of Morlet wavelet coefficients from the vibration signal for different conditions of the gear box under investigation, and application of naive Bayes classifier for its condition monitoring and diagnostics. In this paper fault diagnostics of spur bevel gear box is treated as a pattern classification problem. The major steps in pattern classification are feature extraction, and classification. This work investigates the usefulness of statistical features of Morlet wavelet coefficients and naive Bayes for classification. The results show that the developed method can reliably diagnose different conditions of the gear box and the algorithm can be applied for online applications of supervised machine learning.

Condition monitoring of bevel gear box using Morlet wavelet coefficients and naïve Bayes classifier

A naïve Bayes classifier is used for classifying the faults of a gear box. The rotating equipment like gear box has enough scope for condition monitoring its conditions as it plays a significant role as a prime mover in many engineering applications. This paper discusses about the extraction of Morlet wavelet coefficients from the vibration signal for different conditions of the gear box under investigation, and application of naïve Bayes classifier for its condition monitoring and diagnostics. In this paper fault diagnostics of spur bevel gear box is treated as a pattern classification problem. The major steps in pattern classification are feature extraction, and classification. This work investigates the usefulness of statistical features of Morlet wavelet coefficients and naïve Bayes for classification. The results show that the developed method can reliably diagnose different conditions of the gear box and the algorithm can be applied for online applications of supervised machine learning.

Coherence spectra of rotational and translational components of mining induced seismic events

Classical Russian S-5-S pendulum seismometer was modified for recording of the rotational components of ground motion. This seismometer was used for monitoring of mining induced seismic events in the Karviná region (Czech Republic). Together, three translational components of ground vibration velocity and one rotational component of ground vibration velocity around the vertical axis were recorded. Elaborated mining induced seismic events with epicentral distances up to 9 km were recorded in Doubrava locality, where the exploitation of black coal is still active. Numerical study of measured component attributes of mining induced seismic events is presented in this paper, namely squared Morlet wavelet coefficients and squared coherence spectrum between rotational and translational components. Squared Morlet wavelet coefficients enable to analyse time-and-frequency structure of elaborated signal, e.g. dynamics of the onset, evolution and disappearance of typical periods of the harmonic peaks, etc. Spectral measure of coherence was applied here for investigation of synchronization effects in 2-dimensional time series of translational and rotational components.

The Morlet and Daubechies Wavelet Transforms for Fatigue Strain Signal Analysis

This paper presents the convenient wavelet family for the fatigue strain signal analysis based on the wavelet coefficients. This study involves the Morlet and Daubechies wavelet coefficients using both the Continuous and Discrete Wavelet Transforms, respectively. The signals were collected from a front lower suspension arm of a passenger car by placing strain gauges at the highest stress locations. The car was driven over public road surfaces, i. e. pavé, highway and UKM roads. In conclusion, the Daubechies wavelet was the convenient wavelet family for the analysis. It was because the wavelet gave the higher wavelet coefficient values indicating that the resemblance between the wavelet and the signals was stronger, closer and more similar.

Spatiotemporal variability of Alberta's seasonal precipitation, their teleconnection with large-scale climate anomalies and sea surface temperature

Using wavelet analysis, wavelet-based principal component analysis (WPCA), composite analysis and scale-averaged wavelet power (SAWP) of seasonal precipitation, we investigated their spatiotemporal variability, their relationships with seven large-scale climate indices and atmospheric circulation patterns, sea surface temperature (SST) of the Pacific and Atlantic oceans, and the predictability of Alberta's seasonal precipitation. June–August (JJA) precipitation showed statistically significant oscillations at about 16–20 year, while September–November (SON) precipitation at about 4–8 year time scale. Plots showing clusters of annular contour lines for positive and negative Morlet wavelet coefficients, respectively represent cycles of abundant and sparse seasonal precipitation that had occurred over 1900–2011. Wavelet power spectrum plots show that seasonal climate indices and principal component (PC1) of precipitation anomalies exhibited dominant oscillations that appeared and disappeared in an unpredictable manner. Wavelet coherence analysis shows that Alberta's precipitation had been linked more to Nino3, Pacific decadal Oscillation (PDO) and Pacific/North American (PNA) than other climate indices, and in the 8–25 year than inter-annual time scales. Similar results are found from Pearson's correlation between PC1 of band-passed, zero to three seasonal lags, of Alberta's seasonal precipitation and climate anomalies. Aggregate composites of Alberta's December–February (DJF) precipitation showed that the influences of El Nino Southern Oscillation (ENSO), PDO and PNA had been stronger in southern than in northern Alberta. El Nino (La Nina), warm PDO (cool PDO) and high PNA (low PNA) are associated mainly with sparse and abundant DJF precipitation of southern Alberta. Prevalent atmospheric circulation patterns provide physical explanations on the effects of climate anomaly on the DJF precipitation revealed by the composite analysis.

Content based image hashing using companding and gray code

AbstractEasily processing, storing, and propagating of digital images demand efficient and automatic techniques to identify and verify image contents. Image hashing is such a promising technique to represent and authenticate images without changing the content of images. The new robust image feature we use is the Morlet wavelet coefficients at feature points with the k‐largest local total variations in images. The Morlet wavelet coefficients are pseudo randomly permutated such that image hashes have a small collision rate and are difficult to analyze by attackers. The Morlet wavelet coefficients are further quantized using companding technique and binarily coded using Gray code to form the final hash. Experimental results show the effectiveness and robustness of our method. The proposed image hash could have applications in image authentication and video signature. Copyright © 2010 John Wiley & Sons, Ltd.

Fault diagnosis of spur bevel gear box using artificial neural network (ANN), and proximal support vector machine (PSVM)

Vibration signals extracted from rotating parts of machineries carries lot many information with in them about the condition of the operating machine. Further processing of these raw vibration signatures measured at a convenient location of the machine unravels the condition of the component or assembly under study. This paper deals with the effectiveness of wavelet-based features for fault diagnosis of a gear box using artificial neural network (ANN) and proximal support vector machines (PSVM). The statistical feature vectors from Morlet wavelet coefficients are classified using J48 algorithm and the predominant features were fed as input for training and testing ANN and PSVM and their relative efficiency in classifying the faults in the bevel gear box was compared.

A case study on classification of features by fast single-shot multiclass PSVM using Morlet wavelet for fault diagnosis of spur bevel gear box

This paper deals with the application of fast single-shot multiclass proximal support vector machine for fault diagnosis of a gear box consisting of twenty four classes. The condition of an inaccessible gear in an operating machine can be monitored using the vibration signal of the machine measured at some convenient location and further processed to unravel the significance of these signals. The statistical feature vectors from Morlet wavelet coefficients are classified using J48 algorithm and the predominant features were fed as input for training and testing multiclass proximal support vector machine. The efficiency and time consumption in classifying the twenty four classes all-at-once is reported.

A comparative study on classification of features by SVM and PSVM extracted using Morlet wavelet for fault diagnosis of spur bevel gear box

The condition of an inaccessible gear in an operating machine can be monitored using the vibration signal of the machine measured at some convenient location and further processed to unravel the significance of these signals. This paper deals with the effectiveness of wavelet-based features for fault diagnosis using support vector machines (SVM) and proximal support vector machines (PSVM). The statistical feature vectors from Morlet wavelet coefficients are classified using J48 algorithm and the predominant features were fed as input for training and testing SVM and PSVM and their relative efficiency in classifying the faults in the bevel gear box was compared.

A high-significance detection of non-Gaussianity in theWilkinson Microwave Anisotropy Probe1-yr data using directional spherical wavelets

A directional spherical wavelet analysis is performed to examine the Gaussianity of the Wilkinson Microwave Anisotropy Probe (WMAP) 1-yr data. Such an analysis is facilitated by the introduction of a fast directional continuous spherical wavelet transform. The directional nature of the analysis allows us to probe orientated structure in the data. Significant deviations from Gaussianity are detected in the skewness and kurtosis of spherical elliptical Mexican hat and real Morlet wavelet coefficients for both the WMAP and Tegmark, de Oliveira-Costa & Hamilton foreground-removed maps. The previous non-Gaussianity detection made by Vielva et al. using the spherical symmetric Mexican hat wavelet is confirmed, although their detection at the 99.9 per cent significance level is only made at the 95.3 per cent significance level using our most conservative statistical test. Furthermore, deviations from Gaussianity in the skewness of spherical real Morlet wavelet coefficients on a wavelet scale of 550 arcmin (corresponding to an effective global size on the sky of ∼26° and an internal size of ∼3°) at an azimuthal orientation of 72°, are made at the 98.3 per cent significance level, using the same conservative method. The wavelet analysis inherently allows us to localize on the sky those regions that introduce skewness and those that introduce kurtosis. Preliminary noise analysis indicates that these detected deviation regions are not atypical and have average noise dispersion. Further analysis is required to ascertain whether these detected regions correspond to secondary or instrumental effects, or whether in fact the non-Gaussianity detected is due to intrinsic primordial fluctuations in the cosmic microwave background.