<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Fault prognosis plays a key role in the framework of Condition-Based Maintenance (CBM). Limited by the inherent disadvantages, most traditional intelligent algorithms perform not very well in fault prognosis of hydraulic pumps. In order to improve the prediction accuracy, a novel methodology for fault prognosis of hydraulic pump based on the bispectrum entropy and the deep belief network is proposed in this paper. Firstly, the bispectrum features of vibration signals are analyzed, and a bispectrum entropy method based on energy distribution is proposed to extract the effective feature for prognostics. Then, the Deep Belief Network (DBN) model based on the Restrict Boltzmann Machine (RBM) is proposed as the prognostics model. For the purpose of accurately predicting the trends and the random fluctuations during the performance degradation of the hydraulic pump, the Quantum Particle Swarm Optimization (QPSO) is introduced to search for the optimal value of initial parameters of the network. Finally, analysis of the hydraulic pump degradation experiment demonstrates that the proposed algorithm has a satisfactory prognostics performance and is feasible to meet the requirements of CBM.</p></abstract>

Fault prognosis plays a key role in the framework of Condition-Based Maintenance (CBM). Limited by the inherent disadvantages, most traditional intelligent algorithms perform not very well in fault prognosis of hydraulic pumps. In order to improve the prediction accuracy, a novel methodology for fault prognosis of hydraulic pump based on the bispectrum entropy and the deep belief network is proposed in this paper. Firstly, the bispectrum features of vibration signals are analyzed, and a bispectrum entropy method based on energy distribution is proposed to extract the effective feature for prognostics. Then, the Deep Belief Network (DBN) model based on the Restrict Boltzmann Machine (RBM) is proposed as the prognostics model. For the purpose of accurately predicting the trends and the random fluctuations during the performance degradation of the hydraulic pump, the Quantum Particle Swarm Optimization (QPSO) is introduced to search for the optimal value of initial parameters of the network. Finally, analysis of the hydraulic pump degradation experiment demonstrates that the proposed algorithm has a satisfactory prognostics performance and is feasible to meet the requirements of CBM.

Fault Prognosis of Hydraulic Pump Based on Bispectrum Entropy and Deep Belief Network

Measurement Science Review

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Fault prognosis plays a key role in the framework of Condition-Based Maintenance (CBM). Limited by the inherent disadvantages, most traditional intelligent...

Fault Prognosis of Hydraulic Pump Based on Bispectrum Entropy and Deep Belief Network

Data publikacji: 07 paź 2019

Zakres stron: 195 - 203

Otrzymano: 06 lut 2019

Przyjęty: 30 sie 2019

DOI: https://doi.org/10.2478/msr-2019-0025

Słowa kluczowe
Fault prognosis, bispectrum entropy, DBN, QPSO, hydraulic pump

© 2019 Hongru Li et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Fault Prognosis of Hydraulic Pump Based on Bispectrum Entropy and Deep Belief Network

Data publikacji: 07 paź 2019

Zakres stron: 195 - 203

Otrzymano: 06 lut 2019

Przyjęty: 30 sie 2019

DOI: https://doi.org/10.2478/msr-2019-0025

Słowa kluczoweFault prognosis, bispectrum entropy, DBN, QPSO, hydraulic pump

© 2019 Hongru Li et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Słowa kluczowe
Fault prognosis, bispectrum entropy, DBN, QPSO, hydraulic pump