Hydroelectric generating set vibration signal energy feature recognition method

The invention discloses a hydroelectric generating set vibration signal energy feature recognition method, which comprises the following steps: acquiring an original signal, and obtaining an original signal of hydroelectric generating set vibration; deriving a differential signal, and performing differential processing on the collected original signal to obtain the differential signal; carrying out empirical mode decomposition, i.e., performing empirical mode decomposition on the signal, and forming an eigenmode function set by a plurality of obtained eigenmode functions; calculating an energy ratio, the total energy of the signals in the eigenmode function set and the ratio of the energy of each eigenmode function in the total energy; and obtaining the energy characteristic matrix, i.e., combining the signal total energy and the eigenmode function energy proportion into the energy characteristic matrix. According to the method, multiple differential processing is carried out on the original signal, the high-