Wavelet Energy Research Articles

Time-Domain Structural Damage Identification Using Ensemble Bagged Trees and Evolutionary Optimization Algorithms

This paper presents a two-step vibration-based strategy for damage identification of framed structures using ensemble bagged trees known as a well-known supervised machine learning (ML) paradigm in conjunction with evolutionary optimization algorithms. The proposed model incorporates the actual response, wavelet coefficients, and wavelet energy to extract damage-sensitive features from the time-domain of the measured and simulated signals. Unlike available studies in this scope, the key objective of this research is to identify damage with a localization precision down to a single structural member, rather than limiting the evaluation to the group of elements. In order to increase the training performance in contributing to extremely large datasets with numerous class labels, the proposed strategy involves the artificial generation of features. Additionally, a modified genetic algorithm is proposed for fast damage localization. It is deduced that the damage locations are confidently detected within a fast computational time. Subsequently, damage identification is followed by the application of evolutionary optimization algorithms. For comparison purpose, the employment of the water cycle optimization algorithm (WCA) is comparatively investigated with the other three state-of-the-art optimizers, i.e., particle swarm optimization (PSO), imperialist competitive algorithm (ICA), and differential evolution algorithm (DE). The numerical and experimental validation studies evidence satisfactorily reliable identification results with no false detection in dealing with multiple damage scenarios in large-scale and real-world applications. It is concluded that developing the most damage-sensitive features and using the proposed data fusion strategy lead to informative features with a reasonably small size and significantly improve the ML performance.

Diagnosis of a brain stroke using wideband microwave scattering.

This paper presents a new computer-aided microwave monitoring system as a promising, portable and inexpensive tool to detect and localize brain stroke using a bank of a new wavelet-matched filters. The head is exposed to microwave radiation over the band from 1.1 to 3 GHz, and the backscattered signals at a hemi-elliptical array of 16 antenna elements surrounding the head are filtered to analyse the perturbation in the microwave signals from the brain. A novel technique is applied to remove the strong reflection from the air-skull interface as a way to estimate the target response and is compared with different techniques from literature to portray their role in the performance. The study results approve that the intensity and the distribution of wavelet energy and Shannon wavelet entropy in the filtered microwave signal, and the novel tool based on the distance between the wavelet energies at symmetric opposite antennas are promising candidate signatures for computer-aided detection and localization of a stroke.

The Real-time Fault Detection Method of Grounding the Circulating Current of Transmission Cable Based on the Wavelet Energy Spectrum of Module Component

Currently, the existing fault detection methods have problems in that the detection results are not in line with reality and the detection accuracy is too low when detecting the grounding circulation fault of transmission cables. This paper introduces the wavelet energy spectrum of module components to design and study the real-time fault detection method of grounding the circulating current of the transmission cable. In this study, the wavelet-based detection function that meets the requirements of fault detection is selected. On this basis, the traveling wave fault features are extracted by using the wavelet energy spectrum of the module component. Finally, the fault detection signal is decomposed in real-time, and the fault detection is realized according to the practical value of the reconstructed signal. The comparative experiment proves that the new detection method can get the detection result of the grounding current fault of the cable, which is more in line with the actual situation and has very high detection accuracy.

Analysis of Acoustic Emission Signals Processed with Wavelet Transform for Structural Damage Detection in Concrete Beams

Concrete beams are elements used in many civil structures; unfortunately, they can contain cracks that lead to the collapse of the structures if those defects are not detected early enough. In this article, a new method to determine the structural condition of concrete beams subjected to bending is proposed. In general, it is based on the processing of the acoustic emissions (AE) signals, which are generated during the application of a load, by using the mathematical tool called wavelet transform (WT). The sound of the internal energy/crack is recorded as a hit or AE signal event; then, those signals acquired as waveforms are post-processed with the continuous WT (CWT); then, the wavelet energy (WE) is calculated for each hit by using an adequate scale range and the most convenient mother wavelet. Thus, with this method, it is possible to determine the structural condition (healthy or damaged) of concrete beams subjected to bending just by calculating the WE of any hit at any time and, even more, it is possible to define more precisely the stage of the structural condition as a healthy condition, micro-cracks appearance, the manifestation of a principal crack (hit with the highest WE), propagation of the principal crack, and final rupture. This method is experimentally validated in the laboratory, and additionally, ultrasonic pulse velocity tests (UPVT) are performed for some specimens to confirm the change between healthy and damaged conditions. The results are promising in order to apply this effective method in concrete beams of real-life structures.

Flood Detection in Steel Tubes Using Guided Wave Energy Leakage.

A study that evaluated the use of ultrasonic-guided waves to detect water in hollow pipes is presented. In this work, a guided wave system employed a 40 kHz piezoelectric (PZT) transmitter and a PZT ultrasound transducer. The transmitter was based on a battery-operated microcontroller, and the receiver was composed of a digital signal processor (DSP) module connected to a PC via a USB for monitoring purposes. The transmitter and receiver were attached, non-intrusively without perfect alignment, to the external wall of a steel tube 1 m × 270 mm × 2 mm in size. Flood detection was performed based on guided wave attenuation due to energy leakage from the internal steel wall of the tube to water. Two approaches were carried out. The former was an off-line signal response based on the wavelet energy entropy analysis of a received pulse; the latter was a real-time hit-and-miss analysis centered on measuring the time-space in-between two transmitted pulses. Experiments performed in the laboratory successfully identified flooded tubes.

Wavelet Spatio-Temporal Change Detection on Multitemporal SAR Images

We introduce the WECS (Wavelet Energies Correlation Screening), an unsupervised method to detect spatio-temporal changes on multitemporal SAR images. The procedure is based on wavelet approximation for the multitemporal images, wavelet energy apportionment, and ultra-high dimensional correlation screening for the wavelet coefficients. We show WECS's performance on simulated multitemporal image data. We also evaluate the proposed method on a time series of 85 Sentinel-1 images of a forest region at the border of Brazil and French Guiana. Comparisons with well-known change detection methods found in the literature highlight the proposal's superiority in terms of change detection accuracy. Additionally, the introduced method has simple architecture and low computational cost.

A FOREST FIRE IDENTIFICATION METHOD FOR UNMANNED AERIAL VEHICLE MONITORING VIDEO IMAGES

An automatic forest fire monitoring system based on UAV (unmanned aerial vehicle) acquired video images was studied in this paper. This novel method was proposed to address current problems in forest fire information monitoring practices such as poor real-time performance and low efficiency. Besides, it aims to realize the dynamic monitoring of forest fires in wild environment. In this paper, a forest fire monitoring method based on active analysis of UAV-acquired video image features is proposed to automatically detect and identify the occurrence of forest fires. The motion detection method based on dense optical flow and background modeling method were used to extract the motion regions for eliminating the influence of image background. By using wavelet energy feature and texture feature, 9 video images acquired by multi-rotor UAV on forest fire monitoring were selected as sample images (8 images for experiment and 1 image for contrast purpose). The mean values and standard deviations of the gray level co-occurrence matrix eigen values (angular second moment, entropy moment and reciprocal differential moment) were calculated as the discriminate basis for identifying forest fires. The experimental results showed that the proposed algorithm can effectively identify the forest fire, which provides a theoretical guarantee for the forest resources protection.

Quality evaluation of organic protective paints using terahertz pulse imaging technology based on wavelet packet energy method

It is particularly important to make quality evaluation for paint spraying process. This work presented an efficient method based on wavelet packet energy for terahertz non-destructive evaluation of organic protective paint. The wavelet packet energy analysis algorithm was summarized. Various coating structures were experimentally investigated using terahertz pulsed imaging system and the relative wavelet energy and the Shannon entropy of the detected signal were calculated as wavelet energy indexes. The proposed algorithm was performed on the evaluation of coating unevenness and the identification of hidden corrosion defect. The results demonstrated that the wavelet energy indexes are sensitive to coating structure change when compared to the terahertz peak-finding method, and it allowed more accurate estimate of micro corrosion defect. Therefore, the proposed approach based on wavelet packet energy could be recommended for quick quality evaluation of organic coating with terahertz non-destructive technology.

Wavelet Package Energy Transmissibility Function and Its Application to Wind Turbine Blade Fault Detection

To harvest wind energy from nature, wind turbines are increasingly installed globally, and the blades are the most essential components within the turbine system. The blades usually suffer from time-varying nonstationary wind loads, and the load information is normally unknown or difficult to collect. This poses significant challenges to the blade assessment and damage detection. Transmissibility function (TF) methods have the potential to address this challenge as they do not require loading information. In this article, a novel wavelet package energy TF (WPETF) method is proposed to increase the high-frequency resolution while maintaining its low sensitivity to noise, and it is further used for wind turbine blade fault detection. Compared with the existing Fourier TF method, the proposed method is immune to the external loading impacts, does not require excitation knowledge, and is robust to noise. Compared with the existing wavelet energy TF method, the novel one uses wavelet package decomposition instead of wavelet decomposition to further increase the high-frequency resolution, which provides richer damage-induced information. The effectiveness of the WPETF method for wind turbine blade condition assessment is first verified numerically, and then on three industrial-scale wind turbine blades with both naturally (uncontrolled) and artificially introduced (controlled) damage. Its advantages over a number of existing methods are also demonstrated.

Portable Electromagnetic Device for Steatotic Liver Detection Using Blind Source Separation and Shannon Wavelet Entropy

Hepatic steatosis is the most common cause of chronic liver disease worldwide. Symmetric placement of sensors is the main challenge of previous electromagnetic hepatic steatosis techniques as they require signals from the left side of the torso as a healthy reference. To tackle this issue, this study proposes an electromagnetic technique to assist in observation and detection of hepatic steatosis only by measuring electromagnetic signals from the right side of the torso where liver is located. The combination of blind source separation and wavelet transform techniques is used for detection. Firstly, the principal component analysis is applied to the time-domain converted electromagnetic signals to sphere the measured data. Secondly, the sphered signals are modelled as a linear mixture of different components and separated utilizing independent component analysis technique. Thirdly, the liver response signal is isolated based on its lowest cross-correlation with the average of input signals. Finally, Shannon wavelet entropy and wavelet energy of the estimated liver signal is evaluated by considering the excitation electromagnetic Gaussian pulse as the mother wavelet. Healthy livers can be differentiated from the steatotic ones based on their higher level of wavelet entropy. The method is validated by realistic numerical models and human measurements. In both scenarios, the wavelet entropy of estimated liver response is significantly lower and distinguishable in steatotic livers. The proposed method can detect HS cases with more than 16% diffused fat. Compared to previous techniques, it requires significantly less scanning time, is independent of antennas symmetrical placement, and is thus more reliable.

A Fast Wavelet-Based Bridge Condition Assessment Approach Using Only Moving Vehicle Measurements

Recently, the ‘drive-by’ or vehicle scanning technique has attracted increasing attention over the last decade for the purpose of bridge health monitoring. The feasibility of this technique has been demonstrated by many field tests. In comparison to conventional bridge SHM, the concept of the drive-by bridge technique shows many advantages in terms of efficiency, economy, convenience, and mobility. It has been verified that wavelet transforms can successfully identify bridge damage and its location using the responses of a moving vehicle. However, the validity of this method is challenged by road roughness. This paper proposes a wavelet-based approach to detect bridge defects using wavelet energy. In addition, a damage index based on component wavelet energy is developed to localize the damage. A numerical simulation is modeled to verify the feasibility of the proposed approach, and the result shows that the proposed approach performs well even when considering road roughness in the vehicle and bridge interaction. Moreover, the effects of road surface profile, vehicle velocity, vehicle mass, noise signal, and different damage severity on the proposed approach are investigated. The proposed approach shows a great potential application in bridge health monitoring using indirect measurements from a moving vehicle.

Limb accelerations during sleep are related to measures of strength, sensation, and spasticity among individuals with spinal cord injury

BackgroundTo evaluate the relationship between measures of neuromuscular impairment and limb accelerations (LA) collected during sleep among individuals with chronic spinal cord injury (SCI) to provide evidence of construct and concurrent validity for LA as a clinically meaningful measure.MethodsThe strength (lower extremity motor score), sensation (summed lower limb light touch scores), and spasticity (categorized lower limb Modified Ashworth Scale) were measured from 40 adults with chronic (≥ 1 year) SCI. Demographics, pain, sleep quality, and other covariate or confounding factors were measured using self-report questionnaires. Each participant then wore ActiGraph GT9X Link accelerometers on their ankles and wrist continuously for 1–5 days to measure LA from movements during sleep. Regression models with built-in feature selection were used to determine the most relevant LA features and the association to each measure of impairment.ResultsLA features were related to measures of impairment with models explaining 69% and 73% of the variance (R²) in strength and sensation, respectively, and correctly classifying 81.6% (F1-score = 0.814) of the participants into spasticity categories. The most commonly selected LA features included measures of power and frequency (frequency domain), movement direction (correlation between axes), consistency between movements (relation to recent movements), and wavelet energy (signal characteristics). Rolling speed (change in angle of inclination) and movement smoothness (median crossings) were uniquely associated with strength. When LA features were included, an increase of 72% and 222% of the variance was explained for strength and sensation scores, respectively, and there was a 34% increase in spasticity classification accuracy compared to models containing only covariate features such as demographics, sleep quality, and pain.ConclusionLA features have shown evidence of having construct and concurrent validity, thus demonstrating that LA are a clinically-relevant measure related to lower limb strength, sensation, and spasticity after SCI. LA may be useful as a more detailed measure of impairment for applications such as clinical prediction models for ambulation.

Quantitative Analysis on the Proportion of Renewable Energy Generation Based on Broadband Feature Extraction

With the massive access of distributed renewable energy sources, many uncertain renewable energy power components have been added to the low-voltage lines in substations in addition to the loads of definite classification. From the perspective of economy and cleanliness, it is necessary to quantitatively analyze the renewable energy share among them and improve the power quality level of users. For the power quality information at low-voltage feeders, this paper proposes a quantitative analysis algorithm based on improved wavelet energy entropy and LSTM neural network. The method is based on wavelet transform, based on sym8 wavelet basis function; it divides the long time sequence into equal-length small time sequences, calculates each feature component obtained from wavelet transform decomposition separately, then borrows the concept of information entropy to find its energy entropy. After obtaining the energy entropy sequence of each feature component, it then borrows the concept of kurtosis to weighted differentiation of each energy entropy sequence to highlight the feature information and finally, uses the LSTM neural network to classify the power quality information of different renewable energy sources to determine to which interval segment they belong. By building a simulation model to simulate the actual data in the field, the percentage of renewable energy can be quantitatively analyzed efficiently and accurately.

Laser ultrasonics and machine learning for automatic defect detection in metallic components

This paper develops an automatic and reliable nondestructive evaluation (NDE) technique that enables quantification of the width and depth of subsurface defects of metallic components simultaneously by using non-contact laser ultrasonic technique and identified machine learning (ML) algorithm. Twenty-two specimens with various subsurface defect dimensions are designed and fabricated for laser ultrasonic experiments, and a total of 220 labeled laser ultrasonic signals are obtained for training and verifying ML models. Twelve features, including four time-domain features (maximum, minimum, peak-to-peak, and |Neg|/Pos value of the laser generated Rayleigh ultrasonic waves) and eight wavelet energy features, are identified and extracted as sensitive feature vectors for establishing the dataset. The principal component analysis (PCA) is implemented as dimensionality reduction method of feature vectors to optimize the recognition algorithm and improve the detection accuracy. Three widely used ML models in NDE, adaptive boosting (Adaboost), extreme gradient boosting (XGBboost), and support vector machine (SVM), combined with the PCA are proposed and compared for detecting both the width and depth of subsurface defects. The PCA-XGBoost achieves the highest recognition rate of 98.48%, and is therefore identified as the most effective approach for analyzing laser-ultrasonic signals. Unlike published reports, the proposed model is trained and evaluated with experimental data covered various classification labels, which is more adaptive and reliable in practical application than the models established using simulated data or limited experimental data. In other applications, as long as sufficient laser ultrasonic data with regards to various defect properties (dimensions, orientations, locations, shapes, etc.) can be acquired, the developed approach can realize accurate detection of corresponding defects.

Typical Fragment Kinetic Energy Assessment Based on Acoustic Emission Technology.

Fragment kinetic energy is an important parameter to characterize the damage power of fragments. In this study, an acoustic emission technology-based method to evaluate fragment kinetic energy is proposed. The dynamic response of the fragment impacting an aluminum alloy target plate and the relationship between the initial kinetic energy of the fragment impact and the acoustic emission waveform were theoretically evaluated; the numerical simulation of typical spherical fragments (8 mm diameter) penetrating the aluminum alloy target plate was performed, the wavelet energy of the acoustic emission signal was obtained using wavelet packet theory, and a mathematical model of wavelet energy and fragment kinetic energy was constructed. A fragment kinetic energy test system was established, and a fragment penetration test was performed. The analysis showed that the wavelet energy mathematical models and the fragment kinetic energy exhibited favorable consistency, and the measurement errors of the three experiments were 3%, 3.7%, and 3%. This demonstrates the effectiveness of the typical acoustic emission fragment kinetic energy test methods proposed in this study and establishes a new method for the direct measurement of fragment kinetic energy.

Edge-to-Cloud IIoT for Condition Monitoring in Manufacturing Systems with Ubiquitous Smart Sensors.

The Industrial Internet of Things (IIoT) connects industrial assets to ubiquitous smart sensors and actuators to enhance manufacturing and industrial processes. Data-driven condition monitoring is an essential technology for intelligent manufacturing systems to identify anomalies from malfunctioning equipment, prevent unplanned downtime, and reduce the operation costs by predictive maintenance without interrupting normal machine operations. However, data-driven condition monitoring requires massive data collected from smart sensors to be transmitted to the cloud for further processing, thereby contributing to network congestion and affecting the network performance. Furthermore, unbalanced training data with very few labelled anomalies limit supervised learning models because of the lack of sufficient fault data for the training process in anomaly detection algorithms. To address these issues, we proposed an IIoT-based condition monitoring system with an edge-to-cloud architecture and computed the relative wavelet energy as feature vectors on the edge layer to reduce the network traffic overhead. We also proposed an unsupervised deep long short-term memory (LSTM) network module for anomaly detection. We implemented the proposed IIoT condition monitoring system for a manufacturing machine in a real shop site to evaluate our proposed solution. Our experimental results verify the effectiveness of our approach which can not only reduce the network traffic overhead for the IIoT but also detect anomalies accurately.

Wavelet Energy Evolution Characteristics of Acoustic Emission Signal under True-Triaxial Loading during the Rockburst Test

The rockburst simulation test is conducted by utilizing a mineral-containing marble specimen. The loading condition is set to the three directions, each loading on five surfaces except for a single free surface. The whole test procedure is monitored in real time by using a PCI-II acoustic emission monitoring system and a high-speed camera. According to the test outcomes, rockburst is a process in which energy is rapidly released from the free surface. Rock block and rock plate are buckled and ejected from the free surface and a severe rockburst process is accompanied by spray rock powder. An explosion sound can be heard during the process, which can be analyzed by signal processing techniques. The failure mode of the specimen is a splitting-shearing composite failure, and the free surface becomes a rockburst destruction surface. A V-type rockburst pit is formed in the ejection area. The effective acoustic emission signal of the whole test process is decomposed and reconstructed using five-layer wavelets to produce six frequency band sub-signals. In addition, the wavelet energy and its energy distribution coefficients are assessed for various frequency bands, and the proportion of each dominant frequency band within each period is computed. Finally, it was found that the dominant frequency band is 125~250 kHz, while the suboptimal frequency band is 250~500 kHz. The succeeding features are noticed to be used as predicted features for the rockburst disaster. Namely, acoustic emission signals arise in large numbers and the energy distribution coefficient of the dominant frequency band concentrates above 0.4. The proportion of dominant frequency band appears in continuous valley type and keeps below 80%, while the proportion of suboptimal frequency band appears in continuous peak type and keeps above 20%.

Intermittent series direct current arc fault detection in direct current more‐electric engine power systems based on wavelet energy spectra and artificial neural network

The move towards More-Electric Aircraft (MEA) and Engine (MEE) systems has resulted in system integrators exploring the use of Direct Current (DC) for primary power distribution to both reduce energy conversion stages and enable parallelling of non-synchronised engine off-take generation. A prevalent challenge of utilising DC systems is the safe management of arc faults. Arcing imposes a significant threat to aircraft and can result in critical system damage. Series intermittent arc faults in DC systems are particularly challenging to detect due to the lack of a zero current crossing coupled with the intermittency caused by in-flight vibrations. Additionally, several state-of-the-art arc fault detection methodologies fail to address the handling of aircraft system-specific conditions such as dynamic loading and stability requirements. This paper addresses these unique MEA/MEE issues through the proposal of a new generalised real-time arc fault detection methodology (WaSp) based on time–frequency domain-extracted features applied to a feed-forward Artificial Neural Network (ANN). The paper outlines the analysis of arc fault time–frequency domain features. Simulation-based case studies emulating a range of on-board EPS conditions are presented and show the proposed system has the potential for highly accurate and generalised detection performance with fast detection times.

Pressure response using wavelet analysis in the process of hydraulic fracturing: Numerical simulation and field case

Diagnosis of hydraulic fracturing is of great significance for field treatment guidance. The real-time analysis of the pressure curve is helpful to evaluate the hydraulic fracture status, and provide guidance for the adjustment of the fracturing treatment. However, the response pattern of hydraulic fracture propagation and fluid flow in the pressure curve is still unclear and difficult to capture. In this paper, the 2D hydraulic fracturing model was built to investigate the effects of different stress differences, elastic modulus, and variable rate. Simultaneously, the wavelet analysis method was introduced to observe its response characteristics. Taking the peak energy of the wavelet as the standard, the db5 wavelet basis is selected as the optimal wavelet basis and the first decomposition level is the optimal recognition level. There is a positive correlation between the pressure drop value and the wavelet peak energy under different stress difference and elastic modulus. In addition, we compared the pressure drop ratio and the wavelet energy ratio found that the wavelet energy can greatly amplify the impact of pressure fluctuations. Comparing the wavelet energy of pressure and rate can eliminate the influence of rate fluctuation on pressure. Finally, the field treatment curve was decomposed and explained by wavelet analysis, then it is compared with the results of microseismic interpretation for the first time. This paper can provide further reference for the interpretation of hydraulic fracturing curves.

Quantitative Identification of Internal and External Wire Rope Damage Based on VMD-AWT Noise Reduction and PSO-SVM.

As a common load-bearing component, mining wire rope produces different types of damage during a long period of operation, especially in the case of damage inside the wire rope, which cannot be identified by the naked eye, and it is difficult to accurately detect such damage using the present technology. In this study we designed a non-destructive testing device based on leakage magnetism, which can effectively detect the internal defects of wire rope damage, and carried out simulation analysis to lay a theoretical foundation for the subsequent experiments. To address the noise reduction problem in the design process, a variational mode decomposition–adaptive wavelet thresholding noise reduction method is proposed, which can improve the signal-to-noise ratio and also calculate the wavelet energy entropy in the reconstructed signal to construct multi-dimensional feature vectors. For the quantitative identification of system damage, a particle swarm optimization–support vector machine algorithm is proposed. Moreover, based on the signal following the noise reduction step, seven different feature vectors, namely, the waveform area, peak value, peak-valley value, wavelet energy entropy classification, and identification of internal and external damage defects, have been determined. The results show that the device can be used to effectively identify internal damage defects. In addition, the comparative analysis showed that the algorithm can reduce the system noise and effectively identify internal and external damage defects with a certain superiority.