A fault diagnosis method and system for a generator set operating parameter measurement sensor

Abstract

The invention discloses a fault diagnosis method for a generator set operation parameter measurement sensor, which can be applied to the fault diagnosis method of the generator set operation parameter measurement sensor, including: offline modeling, obtaining auxiliary variables related to the parameters to be measured through mechanism analysis, and for all The auxiliary variables are quantitatively screened according to the degree of dependence, and the main auxiliary variables with strong dependence on the parameters to be measured are obtained; then the model and model coefficients used for online diagnosis are obtained through the PLSR modeling method based on B-spline transformation; Diagnosis, online B-spline transformation of real-time data, by loading the mathematical model between the parameters to be measured and the main auxiliary variables, the predicted value of the parameter Y to be measured is obtained, and the predicted data of the model is compared with the measured data by the "window moving method" The statistical characteristics of the sensor can realize the fault diagnosis of the sensor and identify the fault type of the sensor. The invention also discloses a fault diagnosis system for the measuring sensor of the operating parameters of the generating set.

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 measurement points in the generator set system that require soft measurement or detection of the accuracy of measurement data, and the cost of model storage and maintenance will inevitably affect the practical application of this method

Images