A prognostic method for Radar transmitter based on DHMM

For the randomness and uncertainty of fault for Radar transmitter, a prognostic method based on discrete Hidden Markov Model (DHMM) is proposed. In the paper, three monitoring parameters of transmitter are collected and a discrete Hidden Markov Model is established. In order to have a fast convergence, The Baum-Welch (B-W) algorithm is used for training of DHMM. Finally, the state probability transition curve and reliability transition curve of the transmitter is acquired, therefore health assessment is achieved. The experimental results show that proposed method is a practical method with accuracy and stability.