Artificial intelligence based device failure prediction system

Abstract

The application relates to the technical field of data processing, in particular to a device fault prediction system based on artificial intelligence, which comprises a processor and a memory, and the processor executes the computer program of the memory to realize the following steps: obtaining basic modal numbers according to the entropy and energy of vibration acceleration of a target device at different preset time scales in a current period; adaptively adjusting the basic modal numbers according to the marginal spectrum similarity and mutual information between each adjacent two modal components after the vibration acceleration in the current period is decomposed by using the basic modal numbers, the stability of the center frequency of each modal component at different preset time scales, and the kurtosis and instantaneous frequency of the vibration acceleration in the current period, obtaining adaptive modal numbers, decomposing the vibration acceleration in the current period by using a VMD algorithm according to the adaptive modal numbers, realizing fault prediction of the target device at a future time, and improving the accuracy and reliability of fault prediction.

Images