An Approach for HVCB Mechanical Fault Diagnosis Based on a Deep Belief Network and a Transfer Learning Strategy

다국어 초록 (Multilingual Abstract)

Traditional fault diagnosis for a high-voltage circuit breaker (HVCB) encounters the following problems: the fault features extracted by traditional shallow models is of weak expression ability, and the accuracy of fault identification can be affected by the lack of labeled training samples. To overcome these problems, we present a new approach for HVCB mechanical fault diagnosis based on a deep belief network (DBN) and a transfer learning strategy. This approach uses a DBN to achieve the deep mining and adaptive extraction of the inherent features of sample data, and combines the transfer learning method to improve the accuracy of the fault diagnosis model, which uses a large amount of selective auxiliary data to augment the tiny amount of target data learning by adjusting the weight of training samples. The target sample data are obtained by collecting the coil current signal of the HVCB from fault simulation experiments, and the auxiliary sample data are obtained through simulation based on the electromagnetic system mathematical model of the HVCB spring mechanism. The experimental results show that compared with the traditional feature extraction and fault diagnosis method, the DBN approach combined with transfer learning can achieve stronger feature learning and generalization ability

참고문헌 (Reference)

1 Hinton G E, "Training products of experts by minimizing contrastive divergence" 14 (14): 1771-1800, 2002

2 ZHUANG F ZH, "Survey on transfer learning research" 26 (26): 26-39, 2015

3 황돈하, "Support Vector Machine Based Bearing Fault Diagnosis for Induction Motors Using Vibration Signals" 대한전기학회 10 (10): 1558-1565, 2015

4 Shao H, "Rolling bearing fault diagnosis using an optimization deep belief network" 26 (26): 2015

5 SUN Yinshan, "Research on Feature Value Extraction and Fault Recognition of Coil Current Signal in High-voltage Circuit Breaker" 51 (51): 134-139, 2015

6 X. Zhang, "Reliability estimation of high voltage SF6 circuit breakers by statistical analysis on the basis of the field data" 105-113, 2013

7 HINTON G E, "Reducing the dimensionality of data with neural networks" 313 (313): 504-507, 2006

8 Su Z, "Multi-fault diagnosis for rotating machinery based on orthogonal supervised linear local tangent space alignment and least square support vector machine" 157 : 208-222, 2015

9 Jin X, "Motor Bearing Fault Diagnosis Using Trace Ratio Linear Discriminant Analysis" 61 (61): 2441-2451, 2014

10 Forootani, A, "Model-based fault analysis of a high-voltage circuit breaker operating mechanism" 25 (25): 2349-2362, 2016

11 Basu, "Learning Sparse Feature Representations Using Probabilistic Quadtrees and Deep Belief Nets" 45 (45): 855-867, 2017

12 A. Janssen, "International surveys on circuit-breaker reliability data for substation and system studies" 29 (29): 808-814, 2014

13 Sudhir Agrawal, "Improved Mechanical Fault Identification of an Induction Motor Using Teager-Kaiser Energy Operator" 대한전기학회 12 (12): 1955-1962, 2017

14 A. Krizhevsky, "ImageNet classification with deep convolutional neural networks" 25 : 1106-1114, 2012

15 Liu, "High-voltage circuit-breaker fault diagnosis based on mechanical vibration signals" 30 (30): 387-394, 2016

16 Shell J, "Fuzzy transfer learning : methodology and application" 293 : 59-79, 2015

17 Tamilselvan P, "Failure diagnosis using deep belief learning based health state classification" 115 : 124-135, 2013

18 Wei F, "FSFP : Transfer Learning From Long Texts to the Short" 8 (8): 2033-2040, 2014

19 Mei Fei, "Development and Application of Distributed Multilayer On-line Monitoring System for High Voltage Vacuum Circuit Breaker" 대한전기학회 8 (8): 813-823, 2013

20 G. E. Hinton, "Deep neural networks for acoustic modeling in speech recognition : the shared views of four research groups" 29 : 82-97, 2012

21 LI Qing-min, "Converse Analysis Dynamic Characteristics of Operating Electromagnets In High Voltage Circuit Breakers" 24 (24): 127-131, 2004

22 Ali Asghar Razi-Kazemi, "Circuit-Breaker Automated Failure Tracking Based on Coil Current Signature" 29 (29): 283-290, 2014

23 Dai W, "Boosting for transfer learning" 238 (238): 1855-1862, 2007

24 VABN, KANG H, "Bearing defect classification based on individual wavelet local fisher discriminant analysis with particle swarm optimization" 12 (12): 124-135, 2016

25 YANG Zhize, "Application of the Gray Correlation Model in Fault Diagnosis of High-Voltage Circuit Breakers" 39 (39): 1731-1735, 2015

26 AlThobiani F, "An approach to fault diagnosis of reciprocating compressor valves using Teager–Kaiser energy operator and deep belief networks" 41 (41): 4113-4122, 2014

27 Kedong Zhu, "Adaptive fault diagnosis of HVCBs based on P-SVDD and P-KFCM" 240 : 127-136, 2017

28 Mohamed Abdel-rahman, "Acoustic modeling using deep belief networks" 20 (20): 14-22, 2012

29 Pan SJ, "A survey on transfer learning" 22 (22): 1345-1359, 2010

30 Wen-zhun Huang, "A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology" 대한전기학회 12 (12): 363-372, 2017