Generator set operating parameter measuring sensor fault diagnosis method and system

Abstract

The invention discloses a generator set operating parameter measuring sensor fault diagnosis method. The generator set operating parameter measuring sensor fault diagnosis method can be applied to operating parameter measuring sensor fault diagnosis of generator sets. The method includes the following steps that: offline modeling is performed, auxiliary variables related to a parameter to be measured are obtained through mechanism analysis, and quantitative screening is performed on all the auxiliary variables according to the degree of dependencies, so that main auxiliary variables which have strong dependencies with the parameter to be measured can be obtained; a model for online diagnosis and coefficients of the model are obtained through a B spline transform-based PLSR modeling method; and online diagnosis is performed, and online B spline transformation is performed on real-time data, and the predicted value of the parameter to be measured Y can be obtained through loading the mathematical model between the parameter to be measured and the main auxiliary variables, and statistical characteristics of model predicted data and actually measured data are compared through a window moving method, and therefore, diagnosis on the faults of a sensor and identification of the types of the faults can be realized. The invention also discloses a generator set operating parameter measuring sensor fault diagnosis system.

Description

technical field [0001] The invention relates to fault diagnosis of an operating parameter measurement sensor applied to a generating set, in particular to a fault diagnosis method and system for an operating parameter measuring sensor of a generating set. Background technique [0002] Many measurement sensors in modern large-scale thermal power generation units work in a complex environment of high temperature, high pressure, and corrosion, and are subject to electromagnetic interference. They are more prone to failure than other parts of the system, making it difficult to guarantee the accuracy of measurement data. When the performance of the sensor deteriorates, malfunctions or fails, it will have a serious impact on the subsequent monitoring, control, fault diagnosis and other systems, resulting in misdiagnosis, false alarms, and even immeasurable losses. Therefore, it is of great significance to study how to detect and diagnose sensor faults in time. [0003] The basis ...

AI Technical Summary

Problems solved by technology

However, this method does not actually realize the screening of variables, and the principal components still contain relevant information about variables that are not strongly correlated.

Moreover, there are hundreds of measurem

Images