考虑劣化因素的HMM在设备状态评估中的应用

Age-dependent hidden Markov model for machinery diagnosis

针对传统的基于隐马尔科夫模型(HMM)的设备评估模型大多假定设备状态间的转移概率不变,忽略了实际运行中设备状态间转移概率会随使用时间的增加而变化的问题,提出一类考虑劣化因素的HMM,通过设计劣化因子来克服传统HMM的不足,并开发了一个双重的期望值最大算法来估算劣化因子和状态初始转移概率矩阵,从而对设备状态进行评估。最后,通过算例验证了模型的可行性和有效性。

The traditional Hidden Markov Model（HMM）usually assumed transition probability unfixed,which ignored the influence on transition probability by increasing usage.For this problem,an age-dependent HMM was proposed to eliminate this disadvantage so as to obtain accurate diagnosis result,in which a double Expectation Maximization（EM）algorithm was developed to estimate the aging factor and initial transition probability matrix.Through a numerical example,the computational results could prove the reliability and effectiveness of this proposed model.