Generator stator fault monitoring method and device based on strain and sound wave sensing

Abstract

The invention discloses a generator stator fault monitoring method and device based on strain and sound wave sensing. The method comprises: installing a sensing optical cable used for measuring the strain and sound wave signals of a large generator stator; calibrating the length of the sensing optical cable and the three-dimensional coordinate of the generator stator; acquiring strain-sound wave signals generated by various faults of a large generator stator, and constructing a convolutional neural network training model for generator stator fault monitoring; performing generator stator fault monitoring, and updating a fault sample library in combination with a field manual maintenance result; and using the updated fault sample library to retrain the generator stator fault monitoring model, and using the updated generator stator fault monitoring model to perform fault type identification and prediction on the large generator in operation based on the abnormal strain-sound wave signal. According to the invention, the fault monitoring range and precision of the generator stator are expanded, and the fault of the large-scale generator stator can be predicted.

Description

technical field [0001] The invention relates to the technical field of large-scale generator stator fault monitoring, in particular to a method and device for fault monitoring of a generator stator based on strain and acoustic wave sensing. Background technique [0002] Large-scale generators are important equipment in the power industry. Once a large-scale generator fails, it will cause a power outage and even endanger the normal and stable operation of the power system. Moreover, the accident involves a large area, the repair period is long, the cost is high, and the economic loss is huge. Therefore, the safe and reliable operation of large generators has become a key factor in the normal operation of power systems. Since the stator of the generator needs to bear the constantly changing mechanical force, electric field, and heat during operation, it is prone to failures such as deformation of the stator core and partial discharge of the stator bar. The fault monitoring of ...

AI Technical Summary

Problems solved by technology

Moreover, there is no automatic identification algorithm for generator stator faults using optical fiber sensing signals in the above literature, so effective identification and early warning of generator stator faults cannot be carried out.

Images