Feature extraction method of rolling bearing based on adaptive divergence matrix linear discriminant analysis

Accurate road surface from a three-dimensional (3D) point cloud depends on various parameters. One crucial parameter is the set of point features. Point features enable classification by capturing characteristics of the surface on which the points are located. These features are calculated based on the closest points surrounding each point. In this study, the K-nearest neighbors algorithm (KNN) was applied to identify these closest points. The KNN algorithm requires only one input, the number of closest points (k). Eight different point features were developed using different k values, and their impact on road surface classification from the 3D point cloud was investigated. It was observed that there is no significant improvement in classification accuracy until a certain k value. However, better classification accuracy was achieved after a certain k value. The effect of different k values was also investigated under different training sample structures and machine learning (ML) algorithms. When training samples were selected from a single location as a large group, similar classification accuracy was obtained across different k values. Conversely, when training samples were chosen from various regions in smaller groups rather than a single large group, improved classification was observed as the k value increased. Additionally, it was noted that five different ML algorithms-random forest, support vector machine, generalized linear model, linear discriminant analysis, and robust linear discriminant analysis-have almost similar performance under different k values. Finally, using the optimum k value, improvements of up to 4.543% and 6.601% in accuracy and quality measures, respectively, were found.

Section: Algorithmsmentioning

confidence: 99%

Different KNN parameters on road surface extraction from UAV-based point cloud under several machine learning algorithms

Biçici

2024

“…In recent years, with the intelligent and refined development of mechanical equipment, the fault diagnosis of rolling bea-ring has gained increasing importance in ensuring the normal operation of machinery. Consequently, various fault diagnosis methods have been studied, among which many are developed for signal processing [1] and feature extraction [2].…”

Section: Introductionmentioning

confidence: 99%

Multi-scale residual neural network with enhanced gated recurrent unit for fault diagnosis of rolling bearing

Liao,

Fu,

Yang

et al. 2024

As the key component of rotating machinery, effective and reliable fault diagnosis of rolling bearing is particularly critical for promoting production safety and economic benefits. The powerful representation learning ability of convolutional neural network (CNN) enables it to effectively extract fault information from vibration signals of rolling bearing. Nevertheless, challenges are faced by CNN in extracting features at multi-scale and capturing temporal features. With regard to this issue, a hybrid deep learning model that incorporates the multi-scale residual neural network (MSRN) with the enhanced gated recurrent unit (EGRU), namely MSRN-EGRU, is proposed in this paper. To begin with, MSRN is designed by introducing multi-scale structure and residual connections into CNN for extracting local features effectively and improving the feature representation of the model. Then, the extracted local features are input into EGRU to further extract temporal features, where EGRU is proposed by improving gated recurrent unit (GRU) structure and embeding scaled exponential liner unit (SELU), which enhances the nonlinear modeling and memory ability. Eventually, the obtained features are processed by α-Dropout and global average pooling (GAP) before being inputted into the softmax layer for fault diagnosis. To validate the effectiveness of the proposed model, three baseline models and two ablation models were employed for comparative experiments with two bearing datasets. The experimental results reveal that the proposed model achieves commendable performance in terms of accuracy, robustness, and convergence for fault diagnosis of rolling bearing.

“…Therefore, incipient fault identification is of great significance in bearing condition monitoring for smart maintenance of turbomachines. In recent decades, data-driven failure recognition methods have been well established for rolling element bearings based on different signals, such as current [1], acoustic [2,3], and vibration [4][5][6][7][8]. The periodic impact attenuation model based on vibration signals is the most commonly used method for rolling bearing fault diagnosis [6,7].…”

Section: Introductionmentioning

confidence: 99%

Bearing fault feature extraction method: stochastic resonance-based negative entropy of square envelope spectrum

Zhao,

Jiang,

Wang

et al. 2024

The early identification of bearing defects has recently attracted increasing attention in the fields of condition monitoring and predictive maintenance because of the critical role of bearings on the reliability and safety of turbomachines. The weak features representing early faults in the vibration signals are often submerged in the environmental noise, which poses a major challenge for the early fault diagnosis of rolling bearings. This study proposes a negative entropy of the square envelope spectrum approach integrated with optimized stochastic resonance-based signal enhancement for accurate early defect detection of rolling element bearings. The proposed method considers the cyclostationarity and impulsivity of the raw signal, as well as its similarity with the enhanced signal, thus reinforcing the characteristic frequency while integrating the regularity of the raw signal to evaluate the stochastic resonance performance. A comparison study with different existing methods using both numerical and experimental data was conducted to illustrate the effectiveness and accuracy of the proposed methodology for early defect detection of rolling element bearings in different locations. The results show that the proposed method improves the fault detection by 3.5 days earlier than other stochastic resonance methods, and produces the best enhancement results for fault detection in the outer race, inner race, and rolling element of bearings, with the increase of characteristic frequency intensity coefficient by 126.3%, 118.1%, and 100.5% compared to traditional envelope signals, respectively.