This paper proposes a highly reliable fault diagnosis approach for low-speed bearings. The proposed first extracts wavelet-based features that represent diverse symptoms of multiple bearing defects. most useful are then selected by utilizing genetic algorithm (GA)-based kernel discriminative feature analysis cooperating with one-against-all multicategory support vector machines (OAA MCSVMs). Finally, each machine is individually trained its own includes the features, offering highest...

This paper presents a reliable fault diagnosis methodology for various single and multiple combined defects of low-speed rolling element bearings. method temporally partitions an acoustic emission (AE) signal selects portion the signal, which contains intrinsic information about bearing failures. then performs frequency analysis selected time-domain AE by using multilevel finite-impulse response filter banks to obtain most informative subband signals involving abnormal symptoms defects. It...

In practice, outliers, defined as data points that are distant from the other agglomerated in same class, can seriously degrade diagnostic performance. To reduce performance deterioration caused by outliers data-driven diagnostics, an outlier-insensitive hybrid feature selection (OIHFS) methodology is developed to assess subset quality. addition, a new evaluation metric created ratio of intraclass compactness interclass separability estimated understanding relationship between and outliers....

The demand for online fault diagnosis has recently increased in order to prevent severe unexpected failures machinery. To address this issue, paper first proposes a comprehensive bearing algorithm, which consists of signature extraction through time-frequency analysis and one-against-all multiclass support vector machines make reliable decisions. In addition, acoustic emission (AE) signals sampled at 1 MHz are used the early identification failures. Despite fact that proposed methodology...

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...

This paper proposes an effective envelope analysis-based methodology for machinery condition monitoring and validates its efficacy by identifying bearing failures with 1-s acoustic emission (AE) signals sampled at 1 MHz. The proposed of low-speed bearings consists denoising to improve the signal-noise ratio acquired AE signal employing a soft-thresholding technique adaptively estimated positive negative noise levels analysis detect periodic impacts inherent in defects utilizing 2-D...

This paper proposes a method for the reliable fault detection and classification of induction motors using two-dimensional (2D) texture features multiclass support vector machine (MCSVM). The proposed model first converts time-domain vibration signals to 2D gray images, resulting in patterns (or repetitive patterns), extracts these by generating dominant neighborhood structure (DNS) map. principal component analysis (PCA) is then used purpose dimensionality reduction high-dimensional feature...

This paper proposes an approach for a 2-D representation of Shannon wavelets highly reliable fault diagnosis multiple induction motor defects. Since the wavelet transform is efficient analyzing non-stationary and non-deterministic vibration signals, this utilizes coefficients deduced from mother function with varying dilation translation parameters to create gray-level images. Using resulting images their associated texture characteristics, extracts features by generating global neighborhood...

This paper proposes a fault detection methodology for bearings using envelope analysis with genetic algorithm (GA)-based adaptive filter bank. Although bandpass cooperates early identification of bearing defects, no general consensus has been reached as to which passband is optimal. study explores the impact various passbands specified by GA in terms residual frequency components-to-defect components ratio, evaluates degree defectiveness and finally outputs an optimal reliable detection.

The fact that rolling element bearing faults have an amplitude-modulating effect on their characteristic frequencies calls for sub-band analysis to determine optimal signal contains intrinsic information about faults. In this regard, it is significant accurately assess the presence of a bearing's abnormal symptoms. Hence, abnormality index (BAI) properly quantifies how much presented. Additionally, facilitate real-time based BAI, massively parallel approach introduced, where involves use...

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...

To early identify cylindrical roller bearing failures, this paper proposes a comprehensive fault diagnosis method, which consists of spectral kurtosis analysis for finding the most informative subband signal well representing abnormal symptoms about signature calculation using signal, enhanced distance evaluation technique- (EDET-) based that outputs discriminative features accurate diagnosis, and identification various single multiple-combined defects simplified fuzzy adaptive resonance map...

This paper proposes an efficient four-stage approach that automatically detects fire using video capabilities. In the first stage, approximate median method is used to detect frame regions involving motion. second a fuzzy c-means-based clustering algorithm employed extract candidate of from all movement-containing regions. third gray level co-occurrence matrix texture parameters by tracking red-colored objects in These features are, subsequently, as inputs back-propagation neural network...

Image segmentation is an essential process in image analysis and mainly used for automatic object recognition. Fuzzy c-means (FCM) one of the most common methodologies clustering segmentation. FCM measures Euclidean distance between samples based on assumption that each feature has equal importance. However, real-world problems, features are not considered equally important. To overcome this issue, we present a fuzzy algorithm with spatially weighted information (FCM-SWI) takes into account...

Image segmentation plays a crucial role in numerous biomedical imaging applications, assisting clinicians or health care professionals with diagnosis of various diseases using scientific data. However, its high computational complexities require substantial amount time and have limited their applicability. Research has thus focused on parallel processing models that support image segmentation. In this paper, we present analytical results the design space exploration many-core processors for...