Dynamic threshold based three-dimensional (3D) quantitative set health evaluation method

Abstract

The invention aims at providing a dynamic threshold based 3D quantitative set health evaluation method. According to the technical scheme, the method comprises the steps that a comprehensive 3D evaluation system based on set components, component associated physical attributes and corresponding measuring points is constructed according to the actual situation of a set; different weights of the different components are set according to the importance of the components to the unit, and different weights of the different physical attributes are set according to the importance of the physical attributes to associated components; fixed thresholds of component associated physical attribute parameters are determined; and a mean value [mu]ijk and a variance value [sigma] of normal distribution ofa large amount of xijk data is calculated according to physical attribute data xijk acquired by a kth measurement point according to the jth physical attribute of the ith component within a unit operation time t, and a dynamic threshold range of the kth measurement point according to the [mu] ijk and the [sigma] is determined. The method is suitable for quantitative evaluation of the running stateof the set.

Description

technical field [0001] The invention relates to a three-dimensional health quantitative evaluation method of a unit based on a dynamic threshold. Applicable to the quantitative evaluation method of the operating state of the unit. Background technique [0002] At present, the industry generally adopts the method of state division for the evaluation of the operating state of large-scale generating sets, and divides them into three types: normal state, abnormal state and fault state. For the two states of abnormality and failure, two fixed thresholds are often preset. When the real-time value of a certain parameter sensor exceeds the corresponding fixed preset threshold, it is determined which state the sensor parameter is in. [0003] The problem with this judgment method at present is that the evaluation threshold is fixed, often an industry standard value, which cannot correctly reflect the specific conditions of the equipment parameters under specific working conditions, ...

AI Technical Summary

Problems solved by technology

[0003] The problem with this judgment method at present is that the evaluation threshold is fixed, which is often an industry standard value, which cannot correctly reflect the specific conditions of the equipment parameters under specific working conditions, and does not consider the correlation of characteristic parameters. When the two parameters are positively correlated , although none of them exceed the standard, but one is getting bigger and the other is getting smaller, which also proves that the equipment is in an abnormal state; at the same time, when the unit is in an abnormal or faulty state, it is impossible to know the specific severity of the state. It is only a qualitative judgment, and cannot reach a quantitative level

Images