Search

Significant water loss caused by pipeline leaks emphasizes the importance of effective pipeline leak detection and localization techniques to minimize water wastage. All of the state-of-the-art approaches use deep learning (DL) for leak detection and cross-correlation for leak localization. The existing methods’ complexity is very high, as they detect and localize the leak using two different architectures. This paper aims to present an independent architecture with a single sensor for detecting and localizing leaks with enhanced performance. The proposed approach combines a novel EMD with an optimal mode selector, an MFCC, and a two-dimensional convolutional neural network (2DCNN). The suggested technique uses acousto-optic sensor data from a real-time water pipeline setup in UTAR, Malaysia. The collected data are noisy, redundant, and a one-dimensional time series. So, the data must be denoised and prepared before being fed to the 2DCNN for detection and localization. The proposed novel EMD with an optimal mode selector denoises the one-dimensional time series data and identifies the desired IMF. The desired IMF is passed to the MFCC and then to 2DCNN to detect and localize the leak. The assessment criteria employed in this study are prediction accuracy, precision, recall, F-score, and R-squared. The existing MFCC helps validate the proposed method’s leak detection-only credibility. This paper also implements EMD variants to show the novel EMD’s importance with the optimal mode selector algorithm. The reliability of the proposed novel EMD with an optimal mode selector, an MFCC, and a 2DCNN is cross-verified with cross-correlation. The findings demonstrate that the novel EMD with an optimal mode selector, an MFCC, and a 2DCNN surpasses the alternative leak detection-only methods and leak detection and localization methods. The proposed leak detection method gives 99.99% accuracy across all the metrics. The proposed leak detection and localization method’s prediction accuracy is 99.54%, precision is 98.92%, recall is 98.86%, F-score is 98.89%, and R-square is 99.09%.

The influence of the control strategy of the power electronic converter obscures the fault characteristics of DC distribution networks. The existence of arc faults over an extended period of time poses a grave threat to the security of power grids and may result in electric shock, fire, and other catastrophes. In recent years, the method of fault localization based on the traveling wave method has been a popular topic of research in the field of DC distribution system protection. In this paper, the fault localization principle of the traveling wave method is described in depth, and the propagation characteristics of the traveling wave of fault current in the online mode network are deduced. We present a method for wave head calibration that combines empirical mode decomposition (EMD) and singular value decomposition (VMD). After the fault-traveling current signal has been subjected to EMD, the first eigenmode function is extracted and subjected to singular value decomposition (SVD). After SVD, the detail component can reflect the singularity of the signal. The point of the maximum value of the detail component signal corresponds to the moment when the faulty traveling wave head reaches the monitoring point. Finally, the DC distribution system is modeled based on the PSCAD/EMTDC simulation environment, and the fault location method is verified. The simulation results show that the method can effectively realize fault localization.

This article presents a hybrid method of structural modal parameter identification, based on improved empirical mode decomposition (EMD) and autoregressive and moving average (ARMA). Special attention is given to some implementation issues, such as the modal mixing, false modes, the judgment of the real intrinsic mode function (IMF) of classical EMD, and the difficulty of fixing the order of ARMA. To resolve the existing defects of EMD, an improved EMD (IEMD) that combines frequency band filtering and cluster analysis is proposed in this paper, where frequency band filtering divides the signal into several narrowband signals before the EMD process, and cluster analysis is used to determine the real IMFs. Euclidean distance is used to cluster the decomposition results, with no need to adjust any indexes or thresholds, and only by means of using the nearest distance to efficiently determine the real IMF. Moreover, IEMD is used as a pre-processing tool for ARMA, to resolve the difficulty of fixing its order. The capabilities of the proposed method were compared and assessed using a numerical simulation and an experimental model. The numerical simulation and experimental results showed that the improved method could resolve the modal mixing and false modal problems in the classical EMD process and could automatically identified the real IMFs, while the proposed IEMD was combined with ARMA to successfully identify the frequency and mode shape of the structure. Additionally, since each IMF is a single component signal, it is easy to determine the order of the ARMA model.

Multicomponent seismic exploration provides more wavefield information for imaging complex subsurface structures and predicting reservoirs. Ground roll is strongly coherent noise in land multicomponent seismic data and exhibits similar features, which are strong energy, low frequency, low velocity and dispersion, in each component. Ground roll attenuation is an important step in seismic data processing. In this study, we utilized multivariate empirical mode decomposition to multicomponent seismic data for attenuating ground roll. By adding extra components containing independent white noise, noise-assisted multivariate empirical mode decomposition is adopted to overcome the mode-mixing effect in standard empirical mode decomposition. This method provides a more robust analysis than the standard empirical mode decomposition EMD method performed separately for each component. Multicomponent seismic data are decomposed into different intrinsic mode functions in frequency scale. According to different frequency scales of seismic reflection wave and ground roll, intrinsic mode functions with low frequency are eliminated to suppress ground roll, and the remaining are reconstructed for seismic reflection waves. Synthetic and field data tests show that the proposed approach performs better than the traditional attenuation method.

The friction and imbalance of components in rotating machines are some of the most recurrent failures that significantly increase vibration levels, thus affecting the reliability of the devices, the shelf life of its elements, and the quality of the product. There are many publications related to the different techniques for the diagnosis of friction and imbalance. In this paper, an alternative and new phase-shift empirical mode decomposition integration (PSEMDI) method is proposed to transform the acceleration into its velocity and displacement in order to construct the phase plane and recurrence plot (RP) and analyze the friction. The focus of PSEMDI and RP is to analyze nonlinear failures in mechanical systems. In machinery fault diagnosis, the main reason for using RP is to solve the integration of acceleration, and this can be achieved by phase-shifting the intrinsic mode function (IMF) with the empirical mode decomposition (EMD). Although the highest IMFs contain some frequencies, most of them have very few; thus, by applying the phase shift identity, the integration can be carried out maintaining the nonlinearities. The proposed method is compared with Simpson’s integration and detrending with the EMD method (here referred to as SDEMDI). The experimental RP results show that the proposed method gives significantly more information about the velocity and displacement spectra and it is more stable and proportional than the SDEMDI method. The results of the proposed integration method are compared with vibration measurements obtained with an interferometer.

In this paper the application of cyclostationary signal processing in conjunction with Ensemble Empirical Mode Decomposition (EEMD) technique, on the fault diagnostics of wind turbine gearboxes is investigated and has been highlighted. It is shown that the EEMD technique together with cyclostationary analysis can be used to detect the damage in complex and non-linear systems such as wind turbine gearbox, where the vibration signals are modulated with carrier frequencies and are superimposed. In these situations when multiple faults alongside noisy environment are present together, the faults are not easily detectable by conventional signal processing techniques such as FFT and RMS.

This paper focuses on reconstruction of dynamic velocity and displacement from seismic acceleration signal. For conventional time-domain approaches or frequency-domain approaches, due to initial values and non-negligible noise in the acceleration signal, drift and deviation in velocity and displacement are inevitable. To deal with this deficiency, this paper develops a Walsh transform and Empirical Mode Decomposition (EMD)-based integral algorithm, or WATEBI in short. In the WATEBI algorithm, the Walsh transform is employed to realize vibration signal reconstruction. Next, the EMD method is used to eliminate the residual in the reconstructed signal. Finally, the trend term in velocity and displacement is removed by linear least-squares fit. This algorithm can be straightforwardly implemented by an ordinary computer. Reconstructed displacements and velocities from vibration of a simulated single-degree-of-freedom system and two-site measured ground motions in earthquakes validated the robustness and adaptiveness of this algorithm. It can be also applied to many other areas, like mechanical engineering and ocean engineering.

Early damage, such as microcrack, occupies most of the fatigue life of materials, and timely detection of early damage and positioning has great engineering and economic value. In this paper, a matrix scanning and positioning imaging method based on a probabilistic algorithm is proposed. Cooperating with the single-mode (S0) lamb wave, the microcrack in the thin plate material can be efficiently positioned. Taking the S0 mode lamb wave as the fundamental wave can effectively reduce the influence of the dispersion effect on the signal analysis. Meanwhile, in order to reduce the noise interference, the signal is reconstructed by empirical mode decomposition (EMD) to achieve the filtering effect. Then, the ABAQUS finite element simulation software is used to compare the positioning results under different locations of microcrack and different arrangements of probe. Finally, the feasibility of the localization algorithm is verified by the RAM-5000 SNAP nonlinear ultrasound system. The experimental results are consistent with the simulation theory, and the microcrack is effectively positioned. This facilitates our timely remedial action or further assessment of the remaining value of the material.