Rotating machinery fault diagnosis method, device, system and readable storage medium

Abstract

The invention discloses a method, device, system and computer-readable storage medium for fault diagnosis of a rotating machine, which includes acquiring a target vibration acceleration information group corresponding to the casing of the rotating machine to be diagnosed, and performing a dimensionless operation on the target vibration acceleration information group. According to each pre-acquired dimensionless index data set corresponding to each known operating state and the target dimensionless index data set, a dimensionless index data set corresponding to each type is established. The initial adjacency graph matrix corresponding to each indicator; each initial adjacency graph matrix is ​​processed to obtain each multi-connected domain adjacency graph matrix whose number of connected domains is equal to the total number of known operating states; The fault diagnosis result corresponding to the rotary machine to be diagnosed can be obtained based on similar results and various known operating states; the present invention can improve the diagnostic accuracy of the rotary machine during use.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of mechanical fault diagnosis, in particular to a method, device, system and computer-readable storage medium for fault diagnosis of rotating machinery. Background technique [0002] Large-scale rotating units are one of the most critical parts of petrochemical units, and are also key components in engineering technology fields such as power engineering, chemical engineering, and metallurgical engineering that determine the lifeline of the national economy. Rotating machinery mainly includes generators, steam turbines, blowers, and large steel rolling mills. These are important equipment for industrial production. Their working conditions will affect the stable operation of machinery and equipment and have a great impact on the subsequent production process. Therefore, it is very urgent to explore and study the intelligent fault diagnosis technology of rotating machinery. [0003] The ...

AI Technical Summary

Problems solved by technology

[0004] At present, the use of dimensionless detectors in the existing technology can detect small changes in the machine and remove the influence of the diplomatic environment, forming a satisfactory diagnostic capability. The coincidence phenomenon, that is to say, there is overlap in the numerical range of the dimensionless index between different fault types. Since the upper and lower bounds of the dimensionless index are needed to obtain the reliability value in the process of evidence fusion, the overlap of intervals will lead to conflicting evidence in the process of evidence fusion. , has a great impact on the diagnostic accuracy, and also greatly deepens the difficulty of fault diagnosis using the dimensionless index method

Images