Compound fault prediction of rolling bearing using multimedia data

Singh, Sandip K.; Kumar, Sandeep; Dwivedi, J.P.

doi:10.1007/s11042-017-4419-1

Cited by 26 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ANN consists of one input layer and other output layer with one hidden layer in between. On other hand, in CNN there are convolution layers followed by sub-sampling layers in between the input and output layers [12][13]. The input to the convolution layer is given in form of an image of m ×m ×r size, where r represents the number of channels which is equal to 3 for RGB image.…”

Section: The Basic Concept Of Cnn and Proposed Approachmentioning

confidence: 99%

Data Enhanced Convolution Neural Networks for Wall Following Robot Navigation

Singh*

2019

IJEAT

View full text Add to dashboard Cite

Machine learning has been used for solving the Robot Navigation Task through the wall-following control. The wall-following control involves the movement of the robot in some directed direction maintaining a constant distance from a given wall. The path of the movement of robot is measured by ultrasonic sensors. Many machine learning methods have been used for this problem, as classifiers, but Convolution Neural Networks (CNN) outperforms them all with almost 98% of accuracy. This study compared the performance of five classifiers SVC, MLR, ANN, CNN-1D, and CNN-2D, which play the part of controller in the navigation work. We have used the ultrasonic sensor data to understand the hidden pattern in the navigation work and classified the actions by robot in terms of different motions performed by robot in response to it. The classification reports of CNN-2D and CNN-1D with Artificial Neural Networks (ANN) have also been presented in this paper. The smart Data-Enhancement used in proposed method significantly improves the classification performance of all classifiers, especially CNN.

show abstract

Section: The Basic Concept Of Cnn and Proposed Approachmentioning

confidence: 99%

Data Enhanced Convolution Neural Networks for Wall Following Robot Navigation

Singh*

2019

IJEAT

View full text Add to dashboard Cite

show abstract

“…Accurate failure prediction of rolling bearing before it becomes an accident can be valuable in terms of saving maintenance resources, preventing major failures and ensuring the safety and reliability of rotating machinery. 1 Since the raw vibration signals are collected as long time series data, which contains abundant feature information, it is suitable to be used as samples for fault prediction of rolling bearing. 2 Generally, the fault prediction model is composed of time series prediction and fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Intelligent fault prediction of rolling bearing based on gate recurrent unit and hybrid autoencoder

Che

Wang

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

Accurate fault prediction of rolling bearing can predict the operation condition in advance, which is an important means to ensure the safety and reliability of rotating machinery. Aimed at the data processing of rolling bearing vibration signal with multi-fault and long time series, an intelligent fault prediction model based on gate recurrent unit and hybrid autoencoder is proposed in this paper. Firstly, vibration signals of multi-faults are brought into multi-layer gate recurrent unit model for multi-step and multi-variable time series prediction. Secondly, variational autoencoder is used for data augmentation of fault samples. Thirdly, the augmented fault samples are brought into stacked denoising autoencoder for noise reduction and fault prediction. Finally, fault prediction results of rolling bearing can be achieved on the basis of gate recurrent unit and hybrid autoencoder of variational autoencoder and stacked denoising autoencoder. The bearing datasets of Case Western Reserve University are used to verify the effectiveness of the proposed method. Comparative experiment results show that the proposed fault prediction model has more accurate time series prediction result and higher fault prediction accuracy than other deep learning models. With 98.68% accuracy of fault prediction, the proposed fault prediction model can be taken as an effective tool for intelligent predictive maintenance of rolling bearing.

show abstract

“…When the fault occurs, it will cause other parts to fail concurrently. For example, the bolt looseness fault [23][24][25][26] and the compound fault of different parts of bearing [27][28][29] are common during the operation of mechanical equipment. Different types of fault impacts are superimposed and influenced by each other, coupled with heavy colored noise, which makes it difficult to extract multifrequency fault features.…”

Section: Introductionmentioning

confidence: 99%

Extracting weak multi-frequency signal in heavy colored noise

Yang

Zhang

et al. 2020

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

The extraction of weak multi-frequency signal in the background of heavy colored noise is studied. For the multi-frequency signal which cannot be directly decomposed by ensemble empirical mode decomposition (EEMD), further processing is made in the paper. Based on the normalized autocorrelation analysis and EEMD, a new method of weak multi-frequency signal detection is proposed in the article. Firstly, the adaptive noise reduction of multi-frequency signal with strong colored noise is realized by the normalized autocorrelation analysis. Then, the denoised multi-frequency signal is decomposed by the EEMD method. A series of monochromatic intrinsic mode functions are obtained to representing the characteristics of multi-frequency signal. Finally, two mechanical fault experiments are designed to verify the applicability of the proposed method in the fault diagnosis. The vibration signals with bearing pedestal bolt looseness fault, bearing outer raceway and rolling element compound fault were collected, respectively. The experimental results show that the weak multi-frequency fault features in the vibration signals with heavy colored noise are effectively extracted by the new method. The proposed method has a good application prospect in the field of signal processing.

show abstract

Compound fault prediction of rolling bearing using multimedia data

Cited by 26 publications

References 23 publications

Data Enhanced Convolution Neural Networks for Wall Following Robot Navigation

Data Enhanced Convolution Neural Networks for Wall Following Robot Navigation

Intelligent fault prediction of rolling bearing based on gate recurrent unit and hybrid autoencoder

Extracting weak multi-frequency signal in heavy colored noise

Contact Info

Product

Resources

About