Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model

2615 Ogledov
1747 Prenosov
Izvoz citacije: ABNT
YIN, Aijun ;LU, Juncheng ;DAI, Zongxian ;LI, Jiang ;OUYANG, Qi .
Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model. 
Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 62, n.12, p. 740-750, june 2018. 
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/sl/article/isomap-and-deep-belief-network-based-machine-health-combined-assessment-model/>. Date accessed: 28 mar. 2024. 
doi:http://dx.doi.org/10.5545/sv-jme.2016.3694.
Yin, A., Lu, J., Dai, Z., Li, J., & Ouyang, Q.
(2016).
Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model.
Strojniški vestnik - Journal of Mechanical Engineering, 62(12), 740-750.
doi:http://dx.doi.org/10.5545/sv-jme.2016.3694
@article{sv-jmesv-jme.2016.3694,
	author = {Aijun  Yin and Juncheng  Lu and Zongxian  Dai and Jiang  Li and Qi  Ouyang},
	title = {Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {62},
	number = {12},
	year = {2016},
	keywords = {Isomap; dimensionality reduction; deep belief network (DBN); machine health; combined assessment model (CAM)},
	abstract = {This paper presents a novel combined assessment model (CAM) for machine health assessment, in which 38 original features of the vibration signal were extracted from time domain analysis, frequency domain analysis, and wavelet packet transform (WPT), following which the nonlinear global algorithm Isomap was adopted for dimensionality reduction and extraction of the more representative features. Next, the acquired low-dimensional features array is input into the well trained deep belief network (DBN) model to evaluate the performance status of the bearing. Finally,after the bearing accelerated degradation data from Cincinnati University were investigated for further research, through the comparison experiments with two other popular dimensionality reduction methods (principal component analysis (PCA) and Laplacian Eigenmaps) and two other intelligent assessment algorithms (hidden Markov model (HMM) and back-propagation neural network (BPNN)), the proposed CAM has been proved to be more sensitive to the incipient fault and more effective for the evaluation of bearing performance degradation.},
	issn = {0039-2480},	pages = {740-750},	doi = {10.5545/sv-jme.2016.3694},
	url = {https://www.sv-jme.eu/sl/article/isomap-and-deep-belief-network-based-machine-health-combined-assessment-model/}
}
Yin, A.,Lu, J.,Dai, Z.,Li, J.,Ouyang, Q.
2016 June 62. Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 62:12
%A Yin, Aijun 
%A Lu, Juncheng 
%A Dai, Zongxian 
%A Li, Jiang 
%A Ouyang, Qi 
%D 2016
%T Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model
%B 2016
%9 Isomap; dimensionality reduction; deep belief network (DBN); machine health; combined assessment model (CAM)
%! Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model
%K Isomap; dimensionality reduction; deep belief network (DBN); machine health; combined assessment model (CAM)
%X This paper presents a novel combined assessment model (CAM) for machine health assessment, in which 38 original features of the vibration signal were extracted from time domain analysis, frequency domain analysis, and wavelet packet transform (WPT), following which the nonlinear global algorithm Isomap was adopted for dimensionality reduction and extraction of the more representative features. Next, the acquired low-dimensional features array is input into the well trained deep belief network (DBN) model to evaluate the performance status of the bearing. Finally,after the bearing accelerated degradation data from Cincinnati University were investigated for further research, through the comparison experiments with two other popular dimensionality reduction methods (principal component analysis (PCA) and Laplacian Eigenmaps) and two other intelligent assessment algorithms (hidden Markov model (HMM) and back-propagation neural network (BPNN)), the proposed CAM has been proved to be more sensitive to the incipient fault and more effective for the evaluation of bearing performance degradation.
%U https://www.sv-jme.eu/sl/article/isomap-and-deep-belief-network-based-machine-health-combined-assessment-model/
%0 Journal Article
%R 10.5545/sv-jme.2016.3694
%& 740
%P 11
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 62
%N 12
%@ 0039-2480
%8 2018-06-27
%7 2018-06-27
Yin, Aijun, Juncheng  Lu, Zongxian  Dai, Jiang  Li, & Qi  Ouyang.
"Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model." Strojniški vestnik - Journal of Mechanical Engineering [Online], 62.12 (2016): 740-750. Web.  28 Mar. 2024
TY  - JOUR
AU  - Yin, Aijun 
AU  - Lu, Juncheng 
AU  - Dai, Zongxian 
AU  - Li, Jiang 
AU  - Ouyang, Qi 
PY  - 2016
TI  - Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model
JF  - Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2016.3694
KW  - Isomap; dimensionality reduction; deep belief network (DBN); machine health; combined assessment model (CAM)
N2  - This paper presents a novel combined assessment model (CAM) for machine health assessment, in which 38 original features of the vibration signal were extracted from time domain analysis, frequency domain analysis, and wavelet packet transform (WPT), following which the nonlinear global algorithm Isomap was adopted for dimensionality reduction and extraction of the more representative features. Next, the acquired low-dimensional features array is input into the well trained deep belief network (DBN) model to evaluate the performance status of the bearing. Finally,after the bearing accelerated degradation data from Cincinnati University were investigated for further research, through the comparison experiments with two other popular dimensionality reduction methods (principal component analysis (PCA) and Laplacian Eigenmaps) and two other intelligent assessment algorithms (hidden Markov model (HMM) and back-propagation neural network (BPNN)), the proposed CAM has been proved to be more sensitive to the incipient fault and more effective for the evaluation of bearing performance degradation.
UR  - https://www.sv-jme.eu/sl/article/isomap-and-deep-belief-network-based-machine-health-combined-assessment-model/
@article{{sv-jme}{sv-jme.2016.3694},
	author = {Yin, A., Lu, J., Dai, Z., Li, J., Ouyang, Q.},
	title = {Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {62},
	number = {12},
	year = {2016},
	doi = {10.5545/sv-jme.2016.3694},
	url = {https://www.sv-jme.eu/sl/article/isomap-and-deep-belief-network-based-machine-health-combined-assessment-model/}
}
TY  - JOUR
AU  - Yin, Aijun 
AU  - Lu, Juncheng 
AU  - Dai, Zongxian 
AU  - Li, Jiang 
AU  - Ouyang, Qi 
PY  - 2018/06/27
TI  - Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model
JF  - Strojniški vestnik - Journal of Mechanical Engineering; Vol 62, No 12 (2016): Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2016.3694
KW  - Isomap, dimensionality reduction, deep belief network (DBN), machine health, combined assessment model (CAM)
N2  - This paper presents a novel combined assessment model (CAM) for machine health assessment, in which 38 original features of the vibration signal were extracted from time domain analysis, frequency domain analysis, and wavelet packet transform (WPT), following which the nonlinear global algorithm Isomap was adopted for dimensionality reduction and extraction of the more representative features. Next, the acquired low-dimensional features array is input into the well trained deep belief network (DBN) model to evaluate the performance status of the bearing. Finally,after the bearing accelerated degradation data from Cincinnati University were investigated for further research, through the comparison experiments with two other popular dimensionality reduction methods (principal component analysis (PCA) and Laplacian Eigenmaps) and two other intelligent assessment algorithms (hidden Markov model (HMM) and back-propagation neural network (BPNN)), the proposed CAM has been proved to be more sensitive to the incipient fault and more effective for the evaluation of bearing performance degradation.
UR  - https://www.sv-jme.eu/sl/article/isomap-and-deep-belief-network-based-machine-health-combined-assessment-model/
Yin, Aijun, Lu, Juncheng, Dai, Zongxian, Li, Jiang, AND Ouyang, Qi.
"Isomap and Deep Belief Network-Based Machine Health Combined Assessment Model" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 62 Number 12 (27 June 2018)

Avtorji

Inštitucije

  • Chongqing University, The State Key Laboratory of Mechanical Transmissions, China 1
  • No.1 Branch of Chongqing Academy of Metrology and Quality Inspection, China 2
  • Chongqing University, College of Automation, China 3

Informacije o papirju

Strojniški vestnik - Journal of Mechanical Engineering 62(2016)12, 740-750
© The Authors, CC-BY 4.0 Int. Change in copyright policy from 2022, Jan 1st.

https://doi.org/10.5545/sv-jme.2016.3694

This paper presents a novel combined assessment model (CAM) for machine health assessment, in which 38 original features of the vibration signal were extracted from time domain analysis, frequency domain analysis, and wavelet packet transform (WPT), following which the nonlinear global algorithm Isomap was adopted for dimensionality reduction and extraction of the more representative features. Next, the acquired low-dimensional features array is input into the well trained deep belief network (DBN) model to evaluate the performance status of the bearing. Finally,after the bearing accelerated degradation data from Cincinnati University were investigated for further research, through the comparison experiments with two other popular dimensionality reduction methods (principal component analysis (PCA) and Laplacian Eigenmaps) and two other intelligent assessment algorithms (hidden Markov model (HMM) and back-propagation neural network (BPNN)), the proposed CAM has been proved to be more sensitive to the incipient fault and more effective for the evaluation of bearing performance degradation.

Isomap; dimensionality reduction; deep belief network (DBN); machine health; combined assessment model (CAM)