Zhang X.-H.,Ordnance Engineering College |
Kang J.-S.,Ordnance Engineering College |
Gao C.-M.,68262 Unit |
Cao D.-C.,Ordnance Engineering College |
Teng H.-Z.,68129 Unit
Zhendong yu Chongji/Journal of Vibration and Shock | Year: 2013
A new approach for state recognition and remaining useful life (RUL) prediction based on Mixture of Gaussians Hidden Markov Model (MoG-HMM) was presented. The state number optimization method was established based on cluster validity measures. One can recognize the state through identifying the MoG-HMM that best fits the observations. Then, the RUL prediction method was presented on the recognition base. Finally, the data of a gearbox's full life cycle test was used to demonstrate the proposed methods. The results show that the mean accuracy of prediction is 90.94%.
Teng H.-Z.,Ordnance Engineering College |
Teng H.-Z.,68129 Unit |
Zhao J.-M.,Ordnance Engineering College |
Jia X.-S.,Ordnance Engineering College |
And 2 more authors.
Zhendong yu Chongji/Journal of Vibration and Shock | Year: 2012
Combined with full lifetime test data of gearbox, state recognition based on continuous hidden markov model (CHMM) was studied. The frame of state recognition based on CHMM using original vibration signal was established. Virtues and defects of existing classification methods classifying state in full life cycles were analyzed. State number optimization model was established based on K means and cross validation. Gearbox's operating state was determined by calculating the maximum log-likelihood. The recognition results showed that the proposed method of state recognition based on CHMM using original vibration signals is feasible and effective.
Teng H.,Ordnance Engineering College |
Teng H.,68129 Unit |
Jia X.,Ordnance Engineering College |
Zhao J.,Ordnance Engineering College |
And 3 more authors.
Zhongguo Jixie Gongcheng/China Mechanical Engineering | Year: 2011
HHMM has many advantages for state recognition and more accurately calculates recognition results in the form of probability, in comparison with traditional hidden Markov model(HMM). Model parameters increased exponentially with the increasing equipment state. In view of this, dynamic Bayesian network was introduced, which can effectively reduce the computational complexity and decrease the inference time. Accordingly, HHMM was expressed as dynamic Bayesian network, which identified health status by utilizing vibration signals of pretreatment. In order to avoid the limitations of the current state classifications, the optimization of the condition numbers was proposed, on the basis of combination of K-means algorithm and cross-validation. It also investigated the basic framework for HHMM state recognition and calculation process based on full life test for gearbox, which provides a new way for state recognition of complex equipment.
Liu H.,Shijiazhuang Mechanical Engineering College |
Zhao J.M.,Shijiazhuang Mechanical Engineering College |
Zhao J.S.,Shijiazhuang Mechanical Engineering College |
Zhao J.S.,Tianjin University |
Teng H.Z.,68129 Unit
Applied Mechanics and Materials | Year: 2013
Considering the importance of PM (preventive maintenance) in reliability engineering, the formula is given to calculate spare demand rate for the policies of age replacement policy, minimal maintenance policy and block replacement policy. And average spare demand rate was analyzed for age replacement policy, and an approximate empirical formula with PM interval and parameters of Weibull distribution was given compared to CM(corrective maintenance) and PM. Otherwise, compared to minimal maintenance policy and block replacement policy, the demand rate was analyzed in order to better forecast the spare parts demand. © (2013) Trans Tech Publications, Switzerland.