A new feature extraction approach based on one dimensional gray level co-occurrence matrices for bearing fault classification

Kaya, Yılmaz; Kuncan, Melih; Kaplan, Kaplan; Mi̇naz, Mehmet Recep; Ertunç, H. Metin

doi:10.1080/0952813x.2020.1735530

Cited by 68 publications

(40 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different graph modeling-based approaches are also frequently proposed and implemented. Some worthy mentions are [7][8][9]20,[37][38][39][40][41].…”

Section: Related Workmentioning

confidence: 99%

CNN-Based Fault Detection for Smart Manufacturing

Neupane¹,

Kim

Seok

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

A smart factory is a highly digitized and networked production facility based on smart manufacturing. A smart manufacturing plant is the result of intelligent systems deployed in the factory. Smart factories have higher production volumes and are prone to machine failures when operating in almost all applications on a daily basis. With the growing concept of smart manufacturing required for Industry 4.0, intelligent methods for detecting and classifying bearing faults have become a subject of scientific research and interest. In this paper, a deep learning-based 1-D convolutional neural network is proposed using the time-sequence bearing data from the Case Western Reserve University (CWRU) bearing database. Four different sets of data are used. The proposed method achieves state-of-the-art accuracy even with a small amount of training data. For the sensitivity analysis of the proposed method, metrics such as precision, recall, and f-measure are determined. Next, we compare the proposed method with a 2-D CNN that uses two-dimensional image illustrations of raw data as input. This method shows the effectiveness of using 1-D CNNs over 2-D CNNs for time-sequence data. The proposed method is computationally inexpensive and outperforms the most complex and computationally intensive algorithms used for bearing fault detection and diagnosis.

show abstract

“…Different graph modeling-based approaches are also frequently proposed and implemented. Some worthy mentions are [7][8][9]20,[37][38][39][40][41].…”

Section: Related Workmentioning

confidence: 99%

CNN-Based Fault Detection for Smart Manufacturing

Neupane¹,

Kim

Seok

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In this study, confusion matrices are constructed for determining the performance metrics of the proposed model. Metrics of accuracy, precision and f-measure were used in this study [31]. They can be expressed as follows: Accuracy = (TP+TN)/(TP+TN+FP+FN).…”

Section: Performance Criteriamentioning

confidence: 99%

Turkish handwriting recognition system using multi-layer perceptron

Kuncan¹,

Vardar²,

Kaplan³

et al. 2020

J. mechatron., artif. intell., eng.

Self Cite

View full text Add to dashboard Cite

Recently, handwriting recognition has found many application areas along with technological advances. Handwriting recognition systems can greatly simplify human life by reading tax returns, forwarding mail, reading bank checks, and so on. On the other hand, these systems can reduce the need for human interaction. Therefore, academic and commercial studies of handwriting characters have recently become an important research topic in pattern recognition. In this study, Turkish handwritten letter recognition system from A to Z was developed in C++ environment by using Artificial Neural Networks (ANNs). After the feature data were extracted, handwriting images were presented to the network, the training process of ANN was completed, and different handwriting images were classified with trained ANN. In this study, MLP (Multi-Layered Perceptron: MLP) type ANN and back-propagation learning algorithm were used. The ANN used has 35 inputs and 23 outputs. In the hidden layer, ANNs with different numbers of artificial neural cells (neurons) were evaluated and the most appropriate neural number ANN was selected. As a result, ANN with 24 neurons was selected in the hidden layer and handwriting images was classified with an accuracy rate of 94.90 %.

show abstract

“…The mechanical disc brake of mine hoist combines mechanical structure with electrical control to realize the important functions of online adjustment of braking positive pressure and adaptive adjustment of braking clearance. 12 In this study, through the analysis of the mechanical structure of the electromechanical disc brake, the control strategy of the braking system is explored. The control system of electromechanical disc brake based on Programmable Logic Controller (PLC) control is proposed, which realizes the braking force feedback control, self-adaptive adjustment of braking clearance and other braking objectives, and further improves the automation degree of mining machinery.…”

Section: Introductionmentioning

confidence: 99%

Design and test of electromechanical disc brake controller for mine hoist

Jin

Wang

2022

Measurement and Control

View full text Add to dashboard Cite

Electromechanical braking technology is an effective way to improve the braking response of mine hoist. Through the analysis of the mine hoist electromechanical mechanical disc brake, a mathematical model including the motor, reducer and thread pair is established. The control process is analyzed in detail, and then the control strategy is obtained. An automatic control system based on linear quadratic regulator and PI controller is proposed. The braking goal of self-adaptive adjustment of braking clearance and on-line adjustment of braking force is realized. Compare the simulation and test results, discuss the performance of the controller. The results of the experiment indicate that the brake gap adjustment time is less than 10 s, stable within 1±0.2 mm, and the steady-state error is less than 2%. The positive pressure of the brake has a linear relationship with the motor voltage, with a slope of 920.4 and an intercept of −1298.88. It can replace the existing hydraulic brakes without the problem of low degree of automation and high pollution, which provides a new way for the control system of electromechanical brake.

show abstract

A new feature extraction approach based on one dimensional gray level co-occurrence matrices for bearing fault classification

Cited by 68 publications

References 20 publications

CNN-Based Fault Detection for Smart Manufacturing

CNN-Based Fault Detection for Smart Manufacturing

Turkish handwriting recognition system using multi-layer perceptron

Design and test of electromechanical disc brake controller for mine hoist

Contact Info

Product

Resources

About