Bearing fault diagnosis is imperative for the maintenance, reliability, and durability of rotary machines. It can reduce economical losses by eliminating unexpected downtime in industry due to failure Though widely investigated past couple decades, continued advancement still desirable improve upon existing techniques. Vibration acceleration signals collected from machine bearings exhibit nonstationary behavior variable working conditions multiple severities. In current work, a two-layered...

Predicting bearing faults is an essential task in machine health monitoring because bearings are vital components of rotary machines, especially heavy motor machines. Moreover, indicating the degradation level will help factories plan maintenance schedules. With advancements extraction useful information from vibration signals, diagnosis failures by engineers can be gradually replaced automatic detection process. Especially, state-of-the-art methods using deep learning have contributed...

This paper proposes a reliable technique for pipeline leak detection using acoustic emission signals. The signal of contains leak-related information. However, the noise in often obscures information, making traditional features, such as count and peaks, less effective. To obtain first, images were obtained from time series signals continuous wavelet transform. (AE images) scalograms that represent time-frequency scales form an image. carried enough information about leak, had high-energy...

Bearing fault diagnosis is essential in manufacturing systems to avoid problems such as downtime costs. Convolutional neural network (CNN) models have enabled a new generation of intelligent bearing methods for smart owing their capability extract features 2-dimensional (2D) representations, signals represented the time-frequency domain. Nevertheless, cost and time required collect sufficient training data tend result lack imbalance real scenarios. This inevitable consequence leads high...

Condition monitoring is used to track the unavoidable phases of rolling element bearings in an induction motor (IM) ensure reliable operation domestic and industrial machinery. The convolutional neural network (CNN) has been as effective tool recognize classify multiple bearing faults recent times. Due nonlinear nonstationary nature vibration signals, it quite difficult achieve high classification accuracy when directly using original signal input a convolution network. To evaluate fault...

Bearing elements are vital in induction motors; therefore, early fault detection of rolling-element bearings is essential machine health monitoring. With the advantage feature representation techniques time–frequency domain for nonstationary signals and advent convolutional neural networks (CNNs), bearing diagnosis has achieved high accuracy, even at variable rotational speeds. However, required computation memory resources CNN-based methods render it difficult to be compatible with embedded...

This paper proposes a Gaussian mixture model-based (GMM) bearing fault band selection (GMM-WBBS) method for signal processing. The proposed benefits reliable feature extraction using frequency oriented model window series. Selecting exclusively harmonics, it eliminates the interference of normal vibrations in lower frequencies, natural and higher contents that prove to be useful only anomaly detection but do not provide any insight into location. features are extracted from time- frequency-...

Medical image segmentation is an essential and challenging aspect in computer-aided diagnosis also pattern recognition research. This paper proposes a hybrid method for magnetic resonance (MR) segmentation. We first remove impulsive noise inherent MR images by utilizing vector median filter. Subsequently, Otsu thresholding used as initial coarse that finds the homogeneous regions of input image. Finally, enhanced suppressed fuzzy c-means to partition brain into multiple segments, which...

Bearings prevent damage caused by frictional forces between parts supporting the rotation and they keep rotating shafts in their correct position. However, continuity of work under harsh conditions leads to inevitable bearing failure. Thus, methods for fault diagnosis (FD) that can predict categorize type, as well level degradation, are increasingly necessary factories. Owing advent deep neural networks, especially convolutional networks (CNNs), intelligent FD have achieved significantly...

Recent convolutional neural network (CNN) models in image processing can be used as feature-extraction methods to achieve high accuracy well automatic bearing fault diagnosis. The combination of deep learning with appropriate signal representation techniques has proven its efficiency compared traditional algorithms. Vital electrical machines require a strict monitoring system, and the these machines’ systems takes precedence over any other factors. In this paper, we propose new method for...

Bearing is one of the most vital components industrial machinery. The failure bearing causes severe problems in Therefore, continuous monitoring for bearings essential rather than regular manual checking, with requirement accuracy prediction and efficiency. This paper proposes a novel intelligent fault condition diagnosis method focusing on computation efficiency, which an important aspect embedded-based device. In proposed method, acoustic emission signals containing health information are...

Deep learning (DL) plays a very important role in the fault diagnosis of rotating machinery. To enhance self-learning capacity and improve intelligent accuracy DL for machinery, novel hybrid deep method (NHDLM) based on Extended Convolutional Neural Networks with Wide First-layer Kernels (EWDCNN) long short-term memory (LSTM) is proposed complex environments. First, EWDCNN presented by extending convolution layer WDCNN, which can further automatic feature extraction. The LSTM then changes...

Unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs) have garnered considerable research interest in the fields of 5G 6G wireless communication due to their remarkable flexibility cost-effectiveness. However, inherent openness environments renders these technologies vulnerable eavesdropping. This paper presents a penalty-based successive convex approximation algorithm minorize–maximization optimize transmission beamforming vector, RIS UAV–RIS trajectory. The...

A new method is established to construct the 2-D fault diagnosis representation of multiple bearing defects from 1-D acoustic emission signals. This technique starts by applying envelope analysis extract signal. novel strategy propounded for deployment continuous wavelet transform with damage frequency band information generate defect signature image (DSWI), which describes signal in time-frequency-domain, reduces nonstationary effect signal, shows discriminate pattern visualization...

A case study reveals that energy savings do not always translate to longer smartphone battery life and evaluating any plan must be based on consumption, used.

The high-frequency band, crucial for supporting the 5G/6G system, faces challenges of signal obstruction by obstacles. This is attributed to significant path loss resulting from radio straightness and short distance. To address these challenges, there a growing interest in leveraging non-terrestrial networks (NTNs) reconfigurable intelligent surfaces (RISs), utilizing high-altitude satellites as base stations or terminals. Within three-dimensional NTN vulnerability wireless signals...

Recently, 3D integration has been regarded as one of the most promising techniques due to its abilities reducing global wire lengths and lowering power consumption. However, integrated processors inevitably cause higher density lower thermal conductivity, since closer proximity heat generating dies makes existing hotspots more severe. Without an efficient cooling method inside package, should suffer severe performance degradation by dynamic management well reliability problems. In this...

Gearbox fault diagnosis based on the analysis of vibration signals has been a major research topic for few decades due to advantages characteristics. Such characteristics are used early detection guarantee enhanced safety complex systems and their cost-effective operation. There exist many models that have developed classifying various types in gearboxes. However, classification results conventional degrade when they applied gearbox with multi-level tooth cut gear (MTCG) faults operating...

This study aims at characterizing crack types for reinforced concrete beams through the use of acoustic emission burst (AEB) features. The includes developing a solid assessment indicator (CAI) accompanied by detection method using k-nearest neighbor (k-NN) algorithm that can successfully distinguish among normal condition, micro-cracks, and macro-cracks (fractures) beam test specimens. Reinforced (RC) undergo three-point bending test, from which (AE) signals are recorded further processing....

In this paper, an adaptive Takagi–Sugeno (T–S) fuzzy sliding mode extended autoregressive exogenous input (ARX)–Laguerre proportional integral (PI) observer is proposed. The proposed T–S extended-state ARX–Laguerre PI adaptively improves the reliability, robustness, estimation accuracy, and convergence of fault detection, estimation, identification. For fault-tolerant control in presence uncertainties unknown conditions, technique introduced. surface slope gain significant to improve...

In this paper, we propose a three-stage lightweight framework for centrifugal pump fault diagnosis. First, the vibration signatures are fast transformed using Walsh transform, and spectra obtained. To overcome hefty noise produced by macro-structural vibration, proposed method selects characteristic coefficients of spectrum. second stage, statistical features in time spectrum domain extracted from selected transform. These raw result hybrid high-dimensional space. Not all these help...

In this paper, the short-term load forecast is conducted by utilizing SARIMA model and Holt-Winters including classification use of k-NN algorithm. With embodiment a procedure, it could be possible to provide more accurate data. After using 1-year training set test set, was performed through two models. Although differences in results were minor, measuring their MAPE, shown have better performance forecasting.

In this paper, we propose a highly reliable state monitoring system for induction motors. The proposed utilizes vibration signals to analyze characteristics of the motor and extract features classifying abnormal states from normal ones. To faulty healthy signals, first convert one-dimension into two-dimension gray images utilize relationship between each element its neighboring elements, calculate number significant pixels in these converted images. We then use multiclass support vector...