Fault Diagnosis of Rolling Bearing Based on Kernel Independent Component Analysis by Using Mixed Kernel Function

Studies have shown that the type of kernel function and parameters have a very important impact on the performance of the kernel method. Aiming at the requirement of rolling bearing fault diagnosis, this paper presents a mixed kernel function of kernel independent component and studies on the optimization of its kernel parameters. The mixed kernel function is constructed based on the weighted fusion method, and the kernel parameters are optimized by using the genetic algorithm. The improved kernel independent component method is used for fault diagnosis of rolling bearing, and the testing results demonstrate that it is an effective method.

Download Full-text

Kernel Function and Parameters Optimization in KICA for Rolling Bearing Fault Diagnosis

Journal of Networks ◽

10.4304/jnw.8.8.1913-1919 ◽

2013 ◽

Vol 8 (8) ◽

Cited By ~ 6

Author(s):

Lingli Jiang ◽

Bo Zeng ◽

Francis R. Jordan ◽

Anhua Chen

Keyword(s):

Fault Diagnosis ◽

Kernel Function ◽

Rolling Bearing ◽

Parameters Optimization ◽

Bearing Fault ◽

Bearing Fault Diagnosis

Download Full-text

Rolling Bearing Fault Diagnosis Based on Deep Learning and Autoencoder Information Fusion

Symmetry ◽

10.3390/sym14010013 ◽

2021 ◽

Vol 14 (1) ◽

pp. 13

Author(s):

Jianpeng Ma ◽

Chengwei Li ◽

Guangzhu Zhang

Keyword(s):

Deep Learning ◽

Fault Diagnosis ◽

Information Fusion ◽

Rolling Bearing ◽

Fusion Method ◽

Rolling Bearings ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Evolution Analysis ◽

Comparison Results

The multisource information fusion technique is currently one of the common methods for rolling bearing fault diagnosis. However, the current research rarely fuses information from the data of different sensors. At the same time, the dispersion itself in the VAE method has asymmetric characteristics, which can enhance the robustness of the system. Therefore, in this paper, the information fusion method of the variational autoencoder (VAE) and random forest (RF) methods are targeted for subsequent lifetime evolution analysis. This fusion method achieves, for the first time, the simultaneous monitoring of acceleration signals, weak magnetic signals and temperature signals of rolling bearings, thus improving the fault diagnosis capability and laying the foundation for subsequent life evolution analysis and the study of the fault–slip correlation. Drawing on the experimental procedure of the CWRU’s rolling bearing dataset, the proposed VAERF technique was evaluated by conducting inner ring fault diagnosis experiments on the experimental platform of the self-research project. The proposed method exhibits the best performance compared to other point-to-point algorithms, achieving a classification rate of 98.19%. The comparison results further demonstrate that the deep learning fusion of weak magnetic and vibration signals can improve the fault diagnosis of rolling bearings.

Download Full-text

Bearing fault diagnosis based on kernel independent component analysis and antlion optimization

Transactions of the Institute of Measurement and Control ◽

10.1177/01423312211038419 ◽

2021 ◽

pp. 014233122110384

Author(s):

Hong Zhong ◽

Jingxing Liu ◽

Liangmo Wang ◽

Yang Ding ◽

Yahui Qian

Keyword(s):

Fault Diagnosis ◽

Independent Component Analysis ◽

Blind Source Separation ◽

Component Analysis ◽

Independent Component ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Kernel Independent Component Analysis ◽

Antlion Optimization ◽

Source Signals

Fault diagnosis of gearboxes based on vibration signal processing is challenging, as vibration signals collected by acceleration sensors are typically a nonlinear mixture of unknown signals. Furthermore, the number of source signals is usually larger than that of sensors because of the practical limitation on sensor positions. Hence, the fault characterization is actually a nonlinear underdetermined blind source separation (NUBSS) problem. In this paper, a novel NUBSS algorithm based on kernel independent component analysis (KICA) and antlion optimization (ALO) is proposed to address the technical challenge. The mathematical model demonstrates the nonlinear mixing of source signals in the underdetermined cases. Ensemble empirical mode decomposition is used as a preprocessing tool to decompose the observed signals into a set of intrinsic mode functions that suffers from the problem of redundant components. The correlation coefficient is utilized to eliminate the redundant components. An adaptive threshold singular value decomposition method is proposed to estimate the number of source signals. Then a whitening process is carried out to transform the overdetermined blind source separation (BSS) into determined BSS, which can be solved by the KICA method. However, the reasonable selection of parameters in KICA limits its application to some extent. Therefore, ALO and Fisher’s linear discriminant analysis are adopted to further enhance the accuracy of the KICA method. The separation performance of the proposed method is assessed through simulation. The numerical results show that the proposed method can accurately estimate the number of source signals and attains a higher separation quality in tackling nonlinear mixed signals when compared with the existing methods. Finally, the inner ring fault experiment is conducted to preliminarily validate the practicability of the proposed method in bearing fault diagnosis.

Download Full-text

Fault Diagnosis of Rolling Bearing Based on Feature-Level Fusion Method

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.273.260 ◽

2013 ◽

Vol 273 ◽

pp. 260-263

Author(s):

Ling Li Jiang ◽

Hua Kui Yin ◽

Si Wen Tang

Keyword(s):

Fault Diagnosis ◽

Rolling Bearing ◽

Normal Operation ◽

Fusion Method ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Study Results ◽

Feature Level Fusion ◽

Level Fusion

Bearing failure is one of the foremost causes of breakdowns in rotating machinery and such failure can be catastrophic. Fault diagnosis is critical to maintaining the normal operation of the bearings. This paper proposes feature-level fusion method for rolling bearing fault diagnosis. Features are extracted from eight vibration signals to constitute a fusion vector. SVM is used for pattern recognition. The case study results show that the proposed method is useful for rolling bearing fault diagnosis.

Download Full-text

Fault Diagnosis of Rolling Bearing Based on Improved Independent Component Analysis and Cepstrum Theory

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.823.188 ◽

2013 ◽

Vol 823 ◽

pp. 188-192 ◽

Cited By ~ 3

Author(s):

Pei Xin Zhu ◽

Guo Yong Jin ◽

Yu Quan Yan ◽

Si Yang Gao

Keyword(s):

Fault Diagnosis ◽

Independent Component Analysis ◽

Rolling Bearing ◽

Component Analysis ◽

Independent Component ◽

Fixed Point Algorithm ◽

Spectral Kurtosis ◽

Bearing Fault Diagnosis ◽

Cepstrum Analysis ◽

Extraction Scheme

Based on the advantages of independent component analysis (ICA) and cepstrum, this paper adopts a novel feature extraction scheme for rolling bearing fault diagnosis utilizing improved independent component analysis and cepstrum analysis. Firstly, the fast fixed-point algorithm (FastICA) based on negative entropy was used here as the ICA approach to separate the mixed observation signals of rolling bearing vibration. Then, the largest spectral kurtosis value was used to confirm the characteristic separated signal associated with the Rolling bearing faults. Finally, cepstrum analysis was employed to deal with the selected signal to extract the original fault feature. The experimental results show that sensitive fault feature can be extracted prominently after the presented processing, and the proposed diagnostic method is effective for the fault diagnosis of rolling bearing. In addition, the proposed method provides an effective technical means for weak fault diagnosis.

Download Full-text