Fault Diagnosis of Pump Based on a Hybrid HMM/SVM Model

Xia Yue; Chun Liang Zhang; Jian Li; H.Y. Zhu

doi:10.4028/www.scientific.net/AMR.188.629

Paper Titles

The Establishment of Dynamic Model and Stability Research on High-Speed Precision Hard Turning
p.608

Large NC Machining Fast Knife Mould Based on Image Technology
p.613

Finite Element Simulation of Heavy Cutting Process
p.617

Cutting Parameters Optimization of the Matching of Lengthened Shrink-Fit Holder and Cutter in High Speed Milling
p.622

Fault Diagnosis of Pump Based on a Hybrid HMM/SVM Model
p.629

Study on the Machinability Characteristics of Superalloy K424 during High Speed Turning
p.636

Analysis and Research of the Vibration of the High-Speed Cutting Process
p.642

An Experimental Study on the Impact on Vari-Speed Milling to the Capacity Machine Tool
p.648

Process Information Parameterization of Camshaft Part for Virtual High-Speed Grinding
p.652

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 188Fault Diagnosis of Pump Based on a Hybrid HMM/SVM...

Fault Diagnosis of Pump Based on a Hybrid HMM/SVM Model

Abstract:

A hybrid support vector machine (SVM) and hidden Markov model (HMM) model was introduced into the fault diagnosis of pump. This model had double layers: the first layer used HMM to classify preliminarily in order to get the coverage of possible faults; the second layer utilized this information to activate the corresponding SVMs for improving the recognition accuracy. The structure of this hybrid model was clear and feasible. Especially the model had the potential of large-scale multiclass application in fault diagnosis because of its good scalability. The recognition experiments of 26 statuses on the ZLH600-2 pump showed that the recognition capability of this model was sound in multiclass problems. The recognition rate of one bearing eccentricity increased from SVM’s 84.42% to 89.61% while the average recognition rate of hybrid model reached 95.05%. Although some goals while model constructed did not be fully realized, this model was still very good in practical applications.