Power equipment fault prediction method based on Weibull distribution and hidden semi-Markov model

Abstract

The present invention belongs to the research field of equipment fault prediction, and relates to an equipment fault prediction method in a power communication network based on the Weibull distribution and the hidden semi-Markov model (HSMM). According to the method provided by the present invention, the actual degradation of power equipment is considered, and the hidden Markov model (HMM) with the excellent condition monitoring and degradation diagnosis and recognition capability is introduced; the equipment failure rate is modeled by using the Weibull distribution; the Taylor series expanding-combining like terms method is used to estimate degradation factors; and a state dwell time probability and a state transition probability matrix of the HSMM is calculated, the actual evolution of the equipment fault can be satisfied, the parameter fitting error can be reduced, and better prediction can be performed on the equipment fault state in the communication network.

Description

technical field [0001] The present invention belongs to the research category of failure prediction, especially relates to the prediction of power equipment failure in communication network, and proposes a multi-state power equipment failure prediction method combining Weibull distribution and hidden semi-Markov model. Background technique [0002] Power equipment is the basic element of the complex structure of the power communication network. As the infrastructure that carries various important services on the power communication network, power equipment plays an important role in the power system. During the long-term operation of power equipment, due to the wear and aging of system components and the influence of the external environment, it will inevitably degrade and eventually fail, which will affect people's normal production and life. [0003] As equipment is gradually developing towards automation, the operation of power equipment is increasingly dependent on equip...

AI Technical Summary

Problems solved by technology

[0020] (1) The traditional HMM assumes that the probability distribution of each state duration is exponential, resulting in a disconnect with the actual fault evolution

[0021] (2) The traditional HSMM assumes that the state transition probability at each moment satisfies invariance and has nothing to do with the state residence time, which is inconsistent with the actual degradation process of the equipment

[0022] (3) The traditional HSMM assumes that the state transition probability at each moment does not change with the duration of each state, which weakens the modeling and prediction capabilities of HSMM

Images