An intelligent power plant fan fault degradation state prediction method based on canonical variable analysis and hidden Markov process

The invention discloses an intelligent power plant fan fault degradation state prediction method based on canonical variable analysis and hidden Markov process. Aiming at the fan of large thermal power unit in intelligent power plant, the method of canonical variable analysis and slow feature analysis is used to extract the features, and the extracted features are used to train the continuous hidden Markov model to predict the fault degradation state of closed-loop control system. At the same time, the method takes into account the temporal correlation and variation speed of the variables in the dynamic regulation process of the closed-loop control system of the large thermal power generating unit when the fan fails, and more accurately predicts the fault degradation state of the closed-loop control system of the large thermal power generating unit in the intelligent power plant. While ensuring the good operation of the blower, the invention also ensures the safe combustion of the furnace of the large thermal