Abnormity detection and fault diagnosis algorithm of gas turbine based on sensor associated network

Abstract

The invention provides an abnormity detection and fault diagnosis algorithm of a gas turbine based on sensor associated network and relates to the technical field of gas turbine fault diagnosis. The diagnosis algorithm comprises following steps: step 1. signal processing; step 2: evaluating the correlation between any two sensor test points in a pretreated test point set; step 3. hierarchically clustering an obtained gas turbine sensor associated network model; step 4. evaluating the structure distribution of the residual matrix corresponding to the smallest granularity sub-class by using the information entropy index; step 5. calculating information entropy of all sub-classes in all layers and calculating super-class information entropy index of sub-classes whose information entropy indexes are transfinite. The abnormity detection and fault diagnosis algorithm of gas turbine based on sensor associated network is used achieving abnormity detection on the complete operation status of large gas turbines, especially suitable for the case where sensor test point information is very rich.

Description

Technical field: [0001] The invention relates to the technical field of gas turbine fault diagnosis, in particular to a gas turbine anomaly detection and fault diagnosis algorithm based on a sensor association network. Background technique: [0002] Complex industrial systems such as large gas turbines have complex structures and functions, harsh working environments and changing working conditions, and are fault-prone systems, and are usually composed of multi-level subsystems and auxiliary systems in structure. Under the action of material flow, the transmission process of energy flow and information flow guided by material flow is realized, and the monitoring of its operating status can be realized through hundreds, thousands or even tens of thousands of sensors installed on the structure. When the system fails, the effect of the failure will spread along the direction of information transmission, and cause the status of many sensors to appear abnormal one after another a...

AI Technical Summary

Problems solved by technology

When the system fails, the effect of the failure will spread along the direction of information transmission, and cause the status of many sensors to appear abnormal one after another and alarm

When the source of the fault cannot be confirmed, it is difficult for the operator to formulate a reasonable solution, which leads to further expansion of the fault and threatens production safety

[0003] Traditional fault diagnosis methods based on quantitative models and rules make it difficult to describe the complete state of the system as a whole due to the limitation of knowledge representation capabilities, and are only suitable for solving local fault diagnosis problems.

Images