Early-stage fault early-warning method for synchronous motor stator

Abstract

The invention discloses an early-stage fault early-warning method for a synchronous motor stator. The method comprises the following steps of: step 1, constructing a Deep Belief Network (DBN) model; step 2, training the DBN model; step 3, normalizing stator side data collected by an SCADA system during actual operation of a motor, inputting the stator side data into the trained DBN model, outputting a change trend graph of a reconstruction error by a network, judging whether the change trend graph of the reconstruction error is above a set threshold of the reconstruction error or not, and if yes, judging that a stator side has a fault, and turning to step 4; if not, judging that the stator side operates normally, and then turning to step 5; step 4, subtracting a reconstruction value of a state parameter from an actually measured value to obtain a residual value of the state parameter, and judging whether the residual value exceeds the set threshold or not; and step 5, ending. The early-stage fault early-warning method for the synchronous motor stator provided by the invention realizes a diagnosis method of a synchronous motor stator fault, and can early warn the stator early fault.

Description

technical field [0001] The invention relates to the technical field of motors, in particular to an early warning method for a stator of a synchronous motor. Background technique [0002] With the development of the economy and society, the demand for electricity has increased sharply. Synchronous motors have made great progress in terms of cooling methods, material quality and manufacturing processes. However, large-capacity motors have complex structures, high prices, and wide-ranging faults. As one of the key components of synchronous motors, the stator is easily affected by environmental factors such as high temperature, humidity, and dust, frequent start-up, speed regulation, and braking, and material factors such as poor heat dissipation, corrosion, aging, stress deformation, and oxidation. malfunction. [0003] In synchronous motors, common stator faults include: inter-turn short circuit of stator winding, interphase short circuit of stator winding, open circuit of st...

AI Technical Summary

Problems solved by technology

[0004] Conventional fault prediction methods are difficult to analyze the interaction of each fault on the system in the case of complex faults, difficult to analyze the complex characteristics of equipment data, and difficult to accurately predict faults in real time. The present invention applies artificial intelligence methods combined with big data analysis to fault prediction Technically, a fault prediction technology based on deep belief network is proposed

Images