Turbine blade fault test system and intelligent fault diagnosis method thereof

Abstract

The invention discloses a turbine blade fault test system and an intelligent fault diagnosis method thereof. The test system comprises a gas supply system, a turbine main body system, a lubricating system and a measurement control system. When the turbine blade fault test system runs, the gas supply system provides a gas source for the turbine main body system, the lubricating system provides a lubricating working medium for the turbine main body system, and the measurement control system is used for controlling the running safety of the whole system and measuring required performance parameters. The turbine blade fault test system is established to achieve accurate measurement of pneumatic parameters and vibration parameters during turbine operation, a large amount of test data of fault blades are obtained, and a fault diagnosis model based on a convolutional neural network and deep transfer learning is established. Pneumatic signals and vibration signals of the fault blades are learned, trained and tested, and are migrated and applied to a real turbine unit, so that a foundation is laid for online fault diagnosis of the turbine blades of a large-scale generator set.

Description

technical field [0001] The invention belongs to the field of turbomachinery, in particular to a turbine blade fault testing system and an intelligent fault diagnosis method thereof. Background technique [0002] In large generating sets, turbomachinery plays an important role in the conversion of heat and power. With the development of society, its operating parameters are getting higher and higher. As the "heart" of turbomachinery, blades work in harsh environments and bear the combined effects of centrifugal loads, thermal loads and aerodynamic loads. Once a failure occurs, it will seriously affect the economy and safety of the entire unit. Therefore, it is necessary to carry out real-time online fault monitoring and diagnosis for turbine blades. In actual operation, the monitoring data of turbine units are generally aerodynamic parameters and vibration parameters, so the fault diagnosis of turbine blades is mainly carried out based on the changes of aerodynamic parameter...

AI Technical Summary

Problems solved by technology

The performance of fault diagnosis based on deep learning methods largely depends on the scale and quality of the data set. Conducting tests on real blades will consume a lot of manpower and material resources and is not practical

Therefore, without a large amount of actual operating data, deep learning methods cannot be promoted and applied.

Images