CN-121980201-A - Gas turbine generator state monitoring method, device, equipment and storage medium

CN121980201ACN 121980201 ACN121980201 ACN 121980201ACN-121980201-A

Abstract

The application provides a method, a device, equipment and a storage medium for monitoring the state of a gas turbine generator, wherein the method comprises the steps of obtaining electrical monitoring data of the gas turbine generator in a current period, carrying out cluster analysis on the electrical monitoring data to obtain the current working condition of the gas turbine generator, obtaining a current health index sequence of the gas turbine generator in the current period based on the current working condition and the data state characteristics of the electrical monitoring data, carrying out prediction based on the current health index sequence to obtain a predicted health index sequence in a future period, and carrying out state monitoring on the gas turbine generator based on the current health index sequence and the predicted health index sequence. By the technical scheme, the accuracy of monitoring the health state of the gas turbine generator can be improved.

Inventors

WANG SHIYUN
SHU GUOGANG
ZHANG LAN
CHEN HONGRUI
WU XIANPING
CHEN TAO

Assignees

中国联合重型燃气轮机技术有限公司

Dates

Publication Date: 20260505
Application Date: 20260408

Claims (10)

1. A method for monitoring the condition of a gas turbine generator, comprising: acquiring electrical monitoring data of a gas turbine generator in a current period; performing cluster analysis on the electrical monitoring data to obtain the current working condition of the gas turbine generator; Acquiring a current health index sequence of the gas turbine generator in a current period based on the current working condition and the data state characteristics of the electrical monitoring data; predicting based on the current health index sequence to obtain a predicted health index sequence in a future period; And monitoring the state of the gas turbine generator based on the current health index sequence and the predicted health index sequence.
2. The method of claim 1, wherein said performing a cluster analysis on said electrical monitoring data to obtain a current operating condition of said gas turbine generator comprises: extracting the characteristics of the electrical monitoring data to obtain working condition characteristic parameters; acquiring a feature vector based on the working condition feature parameters; obtaining the distance between the feature vector and a plurality of preset clustering centers, wherein each clustering center corresponds to one working condition; And acquiring the current working condition based on the distance between the feature vector and each clustering center.
3. The method of claim 1, wherein the obtaining a current health indicator sequence for the gas turbine generator over a current period of time based on the current operating conditions and data status characteristics of the electrical monitoring data comprises: Obtaining target health state evaluation models corresponding to the current working condition from a plurality of candidate health state evaluation models, wherein different candidate health state evaluation models correspond to different working conditions, and each candidate health state evaluation model is obtained by training operation data of the corresponding working condition; Inputting the electrical monitoring data into the target health state evaluation model to obtain an initial health index sequence; acquiring a reconstruction error of the target health state evaluation model; and adjusting the initial health index sequence based on the reconstruction error to obtain the current health index sequence.
4. The method of claim 1, wherein the status monitoring of the gas turbine generator based on the current health indicator sequence and the predicted health indicator sequence comprises: acquiring the statistical characteristics of the current health index sequence; Setting at least one level of early warning threshold based on the statistical features; and carrying out state monitoring on the gas turbine generator based on the predicted health index sequence and the at least one level of early warning threshold value.
5. The method of claim 1, wherein the status monitoring of the gas turbine generator based on the current health indicator sequence and the predicted health indicator sequence comprises: performing risk mapping based on the current health index sequence to obtain a fault risk function; Predicting and obtaining a risk critical time based on the fault risk function and the predicted health index sequence; obtaining a device lifetime prediction value based on the risk critical time; A current state of the gas turbine generator is determined based on the current health index sequence and the equipment life prediction value.
6. The method according to claim 1, wherein the method further comprises: acquiring an abnormal scoring model corresponding to the current working condition; inputting the electrical monitoring data into the anomaly score model to obtain basic anomaly scores at all moments in the current period; carrying out sliding window analysis on the basic anomaly scores of all the moments in the current period to obtain weight values corresponding to all the moments in the current period; Weighting the basic anomaly score based on the weight value to obtain a comprehensive anomaly index of each moment in the current period; and determining the data abnormality time in the current period based on the comprehensive abnormality index.
7. A gas turbine generator condition monitoring device, comprising: The acquisition module is used for acquiring electrical monitoring data of the gas turbine generator in the current period; The first processing module is used for carrying out cluster analysis on the electrical monitoring data to obtain the current working condition of the gas turbine generator; The second processing module is used for acquiring a current health index sequence of the gas turbine generator in a current period based on the current working condition and the data state characteristics of the electrical monitoring data; the third processing module is used for predicting based on the current health index sequence to obtain a predicted health index sequence in a future period; And a fourth processing module for performing status monitoring on the gas turbine generator based on the current health index sequence and the predicted health index sequence.
8. An electronic device comprising a processor and a memory communicatively coupled to the processor; the memory stores computer-executable instructions; The processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1-6.
9. A storage medium having instructions stored therein that, when executed on an electronic device, cause the electronic device to perform the method of any one of claims 1-6.
10. A program product comprising at least one of a program, instructions, characterized in that the at least one of a program, instructions, when executed by an electronic device, implements the steps of the method of any of claims 1-6.

Description

Gas turbine generator state monitoring method, device, equipment and storage medium Technical Field The present application relates to the field of gas turbine generator monitoring technologies, and in particular, to a method, an apparatus, a device, and a storage medium for monitoring a state of a gas turbine generator. Background The gas turbine generator is the core of a gas turbine power generation system, and the operation state of the gas turbine generator directly relates to the safety and the economy of the system. In the related art, the monitoring of the gas turbine generator depends on regular maintenance, fixed threshold alarming and manual experience, and the problems of lag response, high false alarm rate, incapability of early warning and the like exist. Disclosure of Invention The present application aims to solve at least one of the technical problems in the related art to some extent. The application provides a method for monitoring the state of a gas turbine generator, which comprises the steps of obtaining electrical monitoring data of the gas turbine generator in a current period, carrying out cluster analysis on the electrical monitoring data to obtain the current working condition of the gas turbine generator, obtaining a current health index sequence of the gas turbine generator in the current period based on the current working condition and the data state characteristics of the electrical monitoring data, carrying out prediction based on the current health index sequence to obtain a predicted health index sequence in a future period, and carrying out state monitoring on the gas turbine generator based on the current health index sequence and the predicted health index sequence. In one implementation mode, the clustering analysis is performed on the electrical monitoring data to obtain the current working condition of the gas turbine generator, wherein the clustering analysis comprises the steps of extracting characteristics of the electrical monitoring data to obtain working condition characteristic parameters, obtaining characteristic vectors based on the working condition characteristic parameters, obtaining distances between the characteristic vectors and a plurality of preset clustering centers, wherein each clustering center corresponds to one working condition, and obtaining the current working condition based on the distances between the characteristic vectors and each clustering center. In one implementation, the method comprises the steps of obtaining a current health index sequence of the gas turbine generator in a current period based on data state characteristics of the current working condition and the electrical monitoring data, obtaining a target health state evaluation model corresponding to the current working condition from a plurality of candidate health state evaluation models, wherein different candidate health state evaluation models correspond to different working conditions, each candidate health state evaluation model is obtained by training operation data of the corresponding working condition, inputting the electrical monitoring data into the target health state evaluation model to obtain an initial health index sequence, obtaining a reconstruction error of the target health state evaluation model, and adjusting the initial health index sequence based on the reconstruction error to obtain the current health index sequence. In one implementation, the monitoring of the state of the gas turbine generator based on the current health index sequence and the predicted health index sequence includes obtaining statistical features of the current health index sequence, setting at least one level of early warning threshold based on the statistical features, and monitoring the state of the gas turbine generator based on the predicted health index sequence and the at least one level of early warning threshold. In one implementation, the monitoring of the state of the gas turbine generator based on the current health index sequence and the predicted health index sequence includes performing risk mapping based on the current health index sequence to obtain a fault risk function, predicting based on the fault risk function and the predicted health index sequence to obtain a risk critical time, obtaining a device life predicted value based on the risk critical time, and determining the current state of the gas turbine generator based on the current health index sequence and the device life predicted value. In one implementation mode, the method further comprises the steps of obtaining an anomaly score model corresponding to the current working condition, inputting the electrical monitoring data into the anomaly score model to obtain basic anomaly scores of all the moments in the current period, carrying out sliding window analysis on the basic anomaly scores of all the moments in the current period to obtain weight values corresponding to all the moments in the current pe