Edge automatic diagnostic analysis system and method for gas turbines

Abstract

This disclosure proposes an edge-based automatic diagnostic analysis system and method for gas turbines. The edge-based automatic diagnostic analysis system is isolated from a public network and includes a gas turbine data acquisition system, a data storage system, a diagnostic analysis system, and a display unit. Both the gas turbine data acquisition system and the diagnostic analysis system are connected to the data storage system, and both are connected to the display unit. The data storage system stores the gas turbine's operating condition data in a time-series database, where the time-series data is a dataset arranged chronologically. The diagnostic analysis system receives and analyzes the time-series data stored in the data storage system and outputs the analysis results of the diagnostic analysis of the gas turbine's operating condition data. Through this arrangement, the diagnostic analysis of the gas turbine's operating condition data can be automatically and quickly achieved.

Description

Technical Field

[0001] This disclosure relates to an automatic diagnostic analysis system for gas turbines, and more particularly to an automatic edge diagnostic analysis system and method for gas turbines. Background Technology

[0002] Currently, to ensure the security of power plant operation data, this data is generally stored locally and isolated from public network environments. This necessitates manual analysis of daily operation data when diagnosing power plant faults.

[0003] However, this data analysis approach leads to delays and prevents the analysis of long-term power plant operating data. Furthermore, the existing diagnostic analysis process relies heavily on human experience and cannot yield highly professional analytical and diagnostic recommendations. Summary of the Invention

[0004] To overcome the aforementioned deficiencies in the prior art, this disclosure provides an edge-based automatic diagnostic analysis system for gas turbines. This edge-based automatic diagnostic analysis system is isolated from a public network and includes a gas turbine data acquisition system, a data storage system, a diagnostic analysis system, and a display unit. Both the gas turbine data acquisition system and the diagnostic analysis system are connected to the data storage system, and both are connected to the display unit. The gas turbine data acquisition system is used to collect operating condition data of the gas turbine, including operating data and combustion data. The gas turbine data acquisition system includes at least two types of operating data acquisition sensors, a combustion data acquisition sensor, and a local operating system. All the aforementioned operational data acquisition sensors are installed on the gas turbine to detect and acquire the operational data in real time. At least one of the operational data acquisition sensors is connected to the local operating system, which is used to collect and store at least a portion of the operational data. The combustion data acquisition sensor is installed on the gas turbine to detect and acquire the combustion data in real time. The data storage system is used to store the operating condition data of the gas turbine in the form of time-series data in a time-series database, where the time-series data is a dataset arranged in chronological order. The diagnostic analysis system is used to receive and analyze the time-series data stored in the data storage system and output the analysis results of the diagnostic analysis of the operating condition data of the gas turbine. The display unit is used to receive and display the analysis results. Accordingly, the edge automatic diagnostic analysis system for gas turbines can effectively isolate from public networks and can perform rapid diagnostic analysis on the time-series data stored in the data storage system, thereby achieving rapid diagnostic analysis of power plant operation.

[0005] Furthermore, the analysis results include at least a statistical report of the gas turbine's operating status over a preset period, fault detection and prediction of the gas turbine, and the gas turbine's operating performance parameters. This allows staff to quickly access the gas turbine's statistical report of its operating status over a preset period, the fault analysis and prediction, and the operating performance parameters, thus providing guidance for their work.

[0006] Furthermore, the diagnostic analysis system includes a report creation module, which acquires the operating condition data of the gas turbine for a predetermined time period corresponding to the time series database, and generates a preset time period operation status statistical report of the gas turbine based on the gas turbine's operating condition data. The preset time period operation status statistical report includes at least the following time series graphs: one generated from the gas turbine's power change data, another from the gas turbine's temperature change data, a third from the gas turbine's vibration change data, a fourth from the gas turbine's operating efficiency change data, a fifth from the gas turbine's power change data, a sixth from the gas turbine's start-up status change data, a seventh from the gas turbine's running time change data, and a eighth from the gas turbine's real-time performance change data. This allows staff to intuitively understand the changes in power, temperature, vibration, and operating efficiency, which is helpful for daily operation and maintenance work.

[0007] Further, the diagnostic analysis system includes: a fault prediction analysis module, which uses a fault prediction analysis model to perform fault analysis on the time series data of the time series database to obtain and output the fault analysis findings and predictions of the gas turbine; wherein, the fault prediction analysis model includes at least one of the following models: a sensor health diagnosis model, which uses a time series prediction algorithm to predict the acquisition trend of sensor signals and diagnose the health of sensor hardware; a combustion state early warning model, which judges the combustion state of the gas turbine based on the trend prediction of combustion data and recommends combustion optimization parameters; The system includes a burner condition diagnostic model, which assesses burner blockage and degradation by analyzing trends in exhaust temperature at the gas turbine outlet and combustion data collected from sensors related to the burner; a gas turbine emission optimization model, which recommends optimized combustion data based on analysis of gas turbine emission and combustion data to improve emission levels; and a gas turbine vibration early warning model, which determines vibration trends based on vibration data analysis to provide early warnings of potential vibration issues and analyze existing vibration faults. This system facilitates fault prediction and analysis of sensor health, combustion status, burner condition, gas turbine emissions, and gas turbine vibration, enabling timely detection of potential faults and rapid analysis of existing problems.

[0008] Furthermore, the diagnostic analysis system includes a calculation and analysis module, which performs calculations on the time-series data in the time-series database to obtain the operating performance parameters of the gas turbine. This allows staff to promptly understand the operating performance of the gas turbine, facilitating routine maintenance.

[0009] Furthermore, the display unit is also used to receive and display the operating data of the gas turbine in real time. This allows staff to easily view the gas turbine's operating data in real time, facilitating real-time management and monitoring.

[0010] Furthermore, there are at least two local operating systems; these at least two local operating systems are used to collect and store at least a portion of the runtime data, and the data collection frequencies of the at least two local operating systems are different. Accordingly, data with different data collection frequencies can be obtained, thereby facilitating better optimization of the accuracy of data collection and enabling accurate subsequent judgments.

[0011] Furthermore, at least two types of the operational data acquisition sensors include an acceleration sensor for acquiring acceleration data of the gas turbine impeller, a velocity sensor for acquiring velocity data of the gas turbine impeller, an angle sensor for acquiring angle data of the gas turbine, and a vibration sensor for acquiring vibration data of the gas turbine; wherein the acceleration sensor, the velocity sensor, and the angle sensor are all connected to the local operating system, and the vibration sensor is connected to the data storage system. Accordingly, it is convenient to comprehensively acquire the operational data of the gas turbine and to accurately calculate the corresponding power data.

[0012] Furthermore, the combustion data includes temperature data, pressure data, and combustion performance data; the combustion data acquisition sensors are of at least two types, including a temperature sensor for acquiring temperature data of the gas turbine and a pressure sensor for acquiring pressure data of the gas turbine; the gas turbine data acquisition system also includes a combustion data storage and calculation module, which is connected to the data storage system, and at least two types of combustion data acquisition sensors are connected to the combustion data storage and calculation module; wherein, the combustion data storage and calculation module is used to store the temperature data and the pressure data, and calculate the combustion performance data based on the temperature data and the pressure data. Accordingly, it is possible to comprehensively acquire the combustion data of the gas turbine, so as to calculate the corresponding combustion performance data and efficiency data.

[0013] This disclosure also provides an edge-automatic diagnostic analysis method for gas turbines, which utilizes the aforementioned edge-automatic diagnostic analysis system for gas turbines. The method includes the following steps: S10, collecting operating condition data of the gas turbine through at least two types of operational data acquisition sensors, a combustion data acquisition sensor, and a local operating system of the gas turbine data acquisition system. The operating condition data of the gas turbine includes at least the operating data and combustion data of the gas turbine; S20, storing the operating condition data of the gas turbine in the form of time-series data in a time-series database through a data storage system. The time-series data is a dataset arranged in chronological order; S30, receiving and analyzing the time-series database stored in the data storage system through a diagnostic analysis system and outputting the analysis results of the diagnostic analysis of the gas turbine operating condition data; S40, receiving and displaying the analysis results through a display unit. Accordingly, the edge-automatic diagnostic analysis method for gas turbines can quickly perform diagnostic analysis on the time-series data stored in the data storage system, facilitating timely provision of corresponding diagnostic analysis results to personnel.

[0014] Further, step S30 includes: S31, obtaining the operating condition data of the gas turbine for a predetermined time period corresponding to the time series database through the report creation module of the diagnostic analysis system, and generating a preset time period operation status statistical report of the gas turbine based on the operating condition data of the gas turbine; wherein, the preset time period operation status statistical report includes at least a time series graph generated from the power change data of the gas turbine, a time series graph generated from the temperature change data of the gas turbine, a time series graph generated from the vibration change data of the gas turbine, a time series graph generated from the operating efficiency change data of the gas turbine, a time series graph generated from the power change data of the gas turbine, a time series graph generated from the start-up status change data of the gas turbine, and a time series graph generated from the running time change data of the gas turbine. The system includes: S32, a time series graph generated from the real-time performance change data of the gas turbine; and / or, S33, the fault prediction analysis module of the diagnostic analysis system uses a fault prediction analysis model to perform fault analysis on the time series database to obtain and output the fault detection and prediction of the gas turbine; wherein, the fault analysis and prediction of the gas turbine includes fault analysis and prediction of the gas turbine valves, fault analysis and prediction of the operating data acquisition sensors, fault analysis and prediction of the combustion data acquisition sensors, combustion fault analysis and prediction of the gas turbine, performance degradation analysis and prediction of the gas turbine compressor, and emission fault analysis and prediction of the gas turbine; and / or, S34, the calculation analysis module of the diagnostic analysis system calculates on the time series database to obtain the operating performance parameters of the gas turbine. Based on this, it is convenient to provide staff with statistical reports on the operating status of the gas turbine for a preset period and / or fault analysis detection and prediction and / or operating performance parameters, thereby facilitating the provision of more accurate and professional daily maintenance or repair suggestions to staff. Attached Figure Description

[0015] The accompanying drawings are provided to further illustrate this disclosure and form part of this disclosure. The illustrative embodiments and descriptions of this disclosure are used to explain this disclosure and do not constitute an undue limitation thereof. In the drawings:

[0016] Figure 1 This is a schematic diagram of the edge automatic diagnostic analysis system for gas turbines disclosed herein;

[0017] Figure 2 This is a flowchart illustrating the edge-automatic diagnostic analysis method for gas turbines disclosed herein.

[0018] List of reference numerals in the attached diagram:

[0019] 01. Gas turbine data acquisition system;

[0020] 02. Data storage system;

[0021] 03. Diagnostic Analysis System;

[0022] 04. Display Unit. Detailed Implementation

[0023] The technical solutions in the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0024] In the following detailed description, reference is made to the accompanying drawings, which form a part of this specification, wherein specific embodiments of the present disclosure are illustrated by way of example. With respect to the drawings, directional terms such as “top,” “bottom,” “inner,” “outer,” “upper,” “lower,” “front,” and “rear” are used with reference to the orientation of the drawings described. Since components of embodiments of the present disclosure can be positioned in many different orientations, directional terms are used for illustration only and are not intended to be limiting. It should be understood that other embodiments may be used, and structural or logical changes may be made without departing from the scope of the present disclosure. Therefore, the following detailed description should not be construed as limiting, and the present disclosure is defined by the appended claims.

[0025] Reference Appendix Figure 1This disclosure proposes an edge-based automatic diagnostic analysis system 03 for a gas turbine. The edge-based automatic diagnostic analysis system 03 is isolated from a public network and includes a gas turbine data acquisition system 01, a data storage system 02, a diagnostic analysis system 03, and a display unit 04. Both the gas turbine data acquisition system 01 and the diagnostic analysis system 03 are connected to the data storage system 02, and both are connected to the display unit 04. The gas turbine data acquisition system 01 is used to acquire operating condition data of the gas turbine, including operating data and combustion data. The gas turbine data acquisition system 01 includes at least two types of operating data acquisition sensors, a combustion data acquisition sensor, and a local operating system. The system includes at least two types of operational data acquisition sensors installed on the gas turbine to detect and acquire operational data in real time. At least one operational data acquisition sensor is connected to a local operating system, which collects and stores at least a portion of the operational data. A combustion data acquisition sensor is installed on the gas turbine to detect and acquire combustion data in real time. A data storage system 02 stores the gas turbine's operating condition data in a time-series database, where the time-series data is a dataset arranged chronologically. A diagnostic analysis system 03 receives and analyzes the time-series data stored in the data storage system 02 and outputs the diagnostic analysis results for the gas turbine's operating condition data. A display unit 04 receives and displays the analysis results. Accordingly, the edge-based automatic diagnostic analysis system 03 for gas turbines is effectively isolated from public networks and can automatically perform rapid diagnostic analysis on the time-series data stored in the data storage system 02, enabling rapid diagnostic analysis of power plant operation.

[0026] Specifically, combustion data refers to data related to the combustion of the gas turbine, and includes at least temperature and pressure data. Operating data refers to data related to the actual power operation of the gas turbine, and includes at least acceleration, vibration, angle, and velocity data. Specifically, different data are obtained through detection by different sensors.

[0027] The edge-based automatic diagnostic analysis system 03 for gas turbines provided in this disclosure, through a gas turbine data acquisition system 01, a data storage system 02, a diagnostic analysis system 03, and a display unit 04, can automatically collect, store, diagnose, analyze, and display the operating data of the gas turbine. This enables rapid diagnosis and analysis of local data, providing professional diagnostic analysis for routine maintenance or repair work. Because manual calculations are not required, the analysis process is not slow or inefficient, and there is no significant data delay. Furthermore, since the diagnostic analysis system 03 is isolated from public networks, data security is also guaranteed.

[0028] Specifically, using a time-series database allows for easy import, cleaning, and archiving of all operational data from different customer sites. This time-series database is isolated from the public internet, effectively ensuring data security.

[0029] Specifically, the analysis results include at least a statistical report of the gas turbine's operating status for a preset time period, fault analysis and prediction of the gas turbine, and the gas turbine's operating performance parameters. This setup facilitates comprehensive analysis and monitoring of the gas turbine's daily operation and maintenance by staff, enabling appropriate maintenance or repair work and significantly reducing operational risks.

[0030] Specifically, the diagnostic analysis system 03 includes a report creation module. This module acquires the operating condition data of the gas turbine for a predetermined time period from the time-series database and generates a pre-defined period operating status statistical report based on the gas turbine's operating condition data. This pre-defined period operating status statistical report includes at least the following time-series graphs: one generated from gas turbine power variation data, one generated from gas turbine temperature variation data, one generated from gas turbine vibration variation data, one generated from gas turbine operating efficiency variation data, one generated from gas turbine power variation data, one generated from gas turbine start-up status variation data, one generated from gas turbine running time variation data, and one generated from gas turbine real-time performance variation data. This setup facilitates more comprehensive feedback of the time-series graphs of different gas turbine operating data to staff, allowing them to better understand the changing trends of different operating data during gas turbine operation, thereby providing guidance for maintenance and repair work.

[0031] Specifically, the preset time period in the preset time period operation status statistical report can be set according to the specific needs of the staff. For example, the preset time period can be a week, month, or year. When the preset time period is a month, the corresponding preset time period operation status statistical report is a monthly report. The monthly report includes a time series graph of the monthly gas turbine power change data, a time series graph of the monthly gas turbine temperature change data, a time series graph of the monthly gas turbine vibration change trend, and a time series graph of the monthly gas turbine operating efficiency change data.

[0032] Specifically, power and operating efficiency can be calculated using conventional formulas based on the operating data of the gas turbine collected by the data acquisition system.

[0033] In this embodiment, the diagnostic analysis system 03 includes a fault prediction analysis module. This module uses a fault prediction analysis model to perform fault analysis on time-series data from a time-series database to obtain and output fault analysis findings and predictions for the gas turbine. The fault prediction analysis model includes at least one of the following models: a sensor health diagnostic model, a combustion status early warning model, a burner status diagnostic model, a gas turbine emission optimization model, and a gas turbine vibration early warning model. Using these fault prediction models facilitates fault prediction and analysis of sensor health, combustion status, burner status, gas turbine emissions, and gas turbine vibration, enabling timely detection of potential faults and rapid analysis of existing faults.

[0034] Specifically, the sensor health diagnostic model uses a time series prediction algorithm to predict the acquisition trend of sensor signals and diagnose the health of the sensor hardware. Here, "sensor signal acquisition trend" can be understood as including the changing trend of operational data acquired by the operational data acquisition sensor and the changing trend of combustion data acquired by the combustion data acquisition sensor. The diagnostic results of sensor health include inaccurate sensor detection, sensor failure, and disconnected sensor connections, all of which can be predicted based on the sensor's detection data. Specifically, to facilitate better prediction of the health of the same type of sensor, multiple sensors of the same type can be set up to detect the same data.

[0035] Specifically, the combustion state early warning model predicts the combustion state of the gas turbine based on the trend of combustion data and recommends combustion optimization parameters. Alternatively, the model can use time series prediction algorithms to predict the combustion state of the gas turbine based on the trend of combustion data changes, and determine corresponding combustion optimization parameters (corresponding to a better combustion state) based on the gas turbine's operating state. These optimization parameters can then be used to adjust the combustion state to a more optimal condition. The combustion optimization parameters may include the natural gas supply rate and combustion temperature; changing these parameters adjusts the combustion state accordingly.

[0036] Specifically, the burner condition diagnostic model determines the degree of blockage and deterioration of the burner by analyzing trends in the exhaust temperature at the gas turbine outlet and partial combustion data collected by sensors related to the gas turbine burner. "Sensors related to the gas turbine burner" can be understood as sensors installed on the gas turbine to collect partial combustion data; these sensors belong to the category of combustion data acquisition sensors. The burner condition diagnostic model can also make predictions and judgments using time series prediction algorithms, and assess the burner's condition based on the combustion data. Specifically, it predicts and infers the internal condition of the burner by checking whether relevant combustion data such as combustion temperature and combustion pressure are within normal ranges.

[0037] Specifically, the gas turbine emission optimization model analyzes gas turbine emission and combustion data to recommend optimized combustion data, thereby optimizing the gas turbine's emission levels. Gas turbine emission data can be collected by combustion data sensors installed on the gas turbine. This data may include temperature and pressure values ​​of the exhaust gases. The model uses time-series prediction algorithms to predict gas turbine emissions and, based on the predicted emissions and the correlation between emission and combustion data, optimizes the combustion data to obtain optimized combustion data.

[0038] Specifically, the gas turbine vibration early warning model determines the vibration trend of the gas turbine based on the analysis of its vibration data, providing early warning of potential vibration hazards and analyzing existing vibration faults. Vibration data of the gas turbine can be collected by operating data sensors installed on the gas turbine. This vibration data primarily consists of vibration data from the gas turbine bearings, including vibration frequency and / or amplitude. The gas turbine vibration early warning model uses a time series prediction algorithm to predict the vibration data and determines whether the predicted vibration data falls within the normal allowable range. A comparison between the predicted and normal allowable vibration data range determines whether a potential vibration hazard has occurred. Specific data on existing vibration faults are analyzed, and combined with data from an expert rule base regarding existing vibration faults and their corresponding occurrences, to determine the type of vibration fault. Bearing fault types in gas turbines include loose bearing installation and bearing structural damage. The specific fault type can be determined by combining the vibration frequency and amplitude with data from a transition rule base.

[0039] In the aforementioned fault prediction and analysis models, specific data and expert rule bases can be combined to perform fault prediction and diagnostic analysis. Specifically, the expert rule base includes algorithms, empirical data, correlations between different data, and threshold ranges for the data.

[0040] The gas turbine fault analysis and prediction includes fault analysis and prediction of gas turbine valves, operational data acquisition sensors, combustion data acquisition sensors, combustion faults, compressor performance degradation, and emissions. This facilitates timely provision of fault analysis and prediction to personnel, enabling them to provide corresponding feedback and adjustments. This allows for faster maintenance and diagnostics of various gas turbine components, improving work efficiency. Specifically, the fault analysis model used here can be a conventional fault analysis model for gas turbine fault diagnosis, established based on common gas turbine fault scenarios and root causes.

[0041] Specifically, the diagnostic analysis system 03 includes a calculation and analysis module. This module performs calculations on time-series data from the time-series database to obtain the operating performance parameters of the gas turbine. This allows staff to perform daily operation, maintenance, and repair work based on the operating performance parameters of the gas turbine. Specifically, the calculation and analysis module can use conventional calculation formulas or models for the operating performance parameters of the gas turbine for calculation and analysis.

[0042] In this embodiment, the display unit 04 is also used to receive and display the operating data of the gas turbine in real time. This allows staff to easily know the real-time operating status of the gas turbine, thereby facilitating real-time monitoring of its operation.

[0043] Specifically, the display unit 04 can be a dashboard, through which real-time information and analysis results can be displayed to staff, thereby saving staff time in data processing, analysis, graphing and report compilation.

[0044] Specifically, there are at least two local operating systems, each used to collect and store at least a portion of the operational data; wherein the data acquisition frequencies of the at least two local operating systems are different. This facilitates the collection of temperature and pressure data at different acquisition frequencies, thereby obtaining more comprehensive and sufficient operational data and improving the accuracy of data collection.

[0045] Specifically, at least two local operating systems can be WinTS and T3000, respectively, and the operating data of the gas turbine (including speed data, acceleration data, etc.) can be stored in WinTS and T3000.

[0046] Specifically, at least two types of operational data acquisition sensors include an acceleration sensor for collecting acceleration data of the gas turbine impeller, a velocity sensor for collecting velocity data of the gas turbine impeller, an angle sensor for collecting the operating angle of the gas turbine, and a vibration sensor for collecting vibration data of the gas turbine. The acceleration, velocity, and angle sensors are all connected to the local operating system, while the vibration sensor is connected to the data storage system. Thus, acceleration, velocity, and angle data are transmitted to the data storage system via the local operating system, while vibration data is directly transmitted to the data storage system.

[0047] In this disclosure, combustion data includes temperature data, pressure data, and combustion performance data. At least two types of combustion data acquisition sensors are used, including a temperature sensor for acquiring temperature data from the gas turbine and a pressure sensor for acquiring pressure data from the gas turbine. The gas turbine data acquisition system also includes a combustion data storage and calculation module connected to the data storage system, and all at least two types of combustion data acquisition sensors are connected to the combustion data storage and calculation module. The combustion data storage and calculation module stores the temperature and pressure data and calculates the combustion performance data based on the temperature and pressure data. This facilitates more comprehensive acquisition of combustion data and enables better analysis of the gas turbine's combustion performance.

[0048] Reference Appendix Figure 2 This disclosure also proposes an edge automatic diagnostic analysis method for gas turbines, which utilizes the aforementioned edge automatic diagnostic analysis system 03 for gas turbines. The edge automatic diagnostic analysis method for gas turbines includes the following steps: S10, collecting gas turbine operating condition data through at least two types of operating data acquisition sensors, a combustion data sensor, and a local operating system of the gas turbine data acquisition system 01, wherein the gas turbine operating condition data includes at least gas turbine operating data and combustion data; S20, storing the gas turbine operating condition data in the form of time-series data in a time-series database through a data storage system 02, wherein the time-series data is a dataset arranged in chronological order; S30, receiving and analyzing the time-series database stored in the data storage system 02 through the diagnostic analysis system 03 and outputting the analysis results of the diagnostic analysis of the gas turbine operating condition data; S40, receiving and displaying the analysis results through a display unit 04.

[0049] This method facilitates the automatic collection, storage, diagnostic analysis, and result display of gas turbine operating data, enabling staff to quickly obtain relevant professional diagnostic analyses of the gas turbine, and facilitating routine maintenance or repair work, thereby improving the efficiency of diagnostic analysis.

[0050] Specifically, step S30 includes: S31, obtaining the gas turbine operating condition data for a predetermined time period from the time series database through the report creation module of the diagnostic analysis system 03, and generating a preset time period operation status statistical report of the gas turbine based on the gas turbine operating condition data; wherein, the preset time period operation status statistical report includes at least the time series graph generated from the gas turbine power change data, the time series graph generated from the gas turbine temperature change data, the time series graph generated from the gas turbine vibration change data, the time series graph generated from the gas turbine operating efficiency change data, the time series graph generated from the gas turbine power change data, the time series graph generated from the gas turbine start-up status change data, the time series graph generated from the gas turbine running time change data, and the time series graph generated from the gas turbine real-time performance change data.

[0051] Step S30 further includes: S32, using the fault prediction analysis module of the diagnostic analysis system 03 to perform fault analysis on the time series database using a fault prediction analysis model, so as to obtain and output the fault analysis findings and predictions of the gas turbine; wherein, the fault analysis and prediction of the gas turbine includes the fault analysis and prediction of the gas turbine valves, the fault analysis and prediction of the operating data acquisition sensors, the fault analysis and prediction of the combustion data acquisition sensors, the combustion fault analysis and prediction of the gas turbine, the performance degradation analysis and prediction of the gas turbine compressor, and the emission fault analysis and prediction of the gas turbine.

[0052] Step S30 also includes: S33, calculating the time series database using the calculation and analysis module of the diagnostic analysis system 03 to obtain the operating performance parameters of the gas turbine. This method allows staff to quickly obtain statistical reports on the gas turbine's operating status for a preset time period and / or the detection and prediction of gas turbine faults and / or the gas turbine's operating performance parameters, thus enabling staff to comprehensively understand the gas turbine's operating status from different perspectives.

[0053] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Various modifications and variations can be made to this disclosure by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An automatic edge diagnostic analysis system for gas turbines, characterized in that, The edge automatic diagnostic analysis system is isolated from the public network. The edge automatic diagnostic analysis system includes a gas turbine data acquisition system, a data storage system, a diagnostic analysis system, and a display unit. The gas turbine data acquisition system and the diagnostic analysis system are both connected to the data storage system, and the data acquisition system and the diagnostic analysis system are connected to the display unit. The gas turbine data acquisition system is used to collect the operating condition data of the gas turbine. The operating condition data includes the gas turbine's operating data and combustion data. The gas turbine data acquisition system includes at least two types of operating data acquisition sensors, a combustion data acquisition sensor, and a local operating system. At least two types of operating data acquisition sensors are installed on the gas turbine to detect and collect the operating data in real time. At least one type of operating data acquisition sensor is connected to the local operating system, which is used to collect and store at least a portion of the operating data. The combustion data acquisition sensor is installed on the gas turbine to detect and collect the combustion data in real time. The data storage system is used to store the operating condition data of the gas turbine in the form of time series data in a time series database, wherein the time series data is a dataset arranged in chronological order; The diagnostic analysis system is used to receive and analyze the time series data stored in the data storage system and output the analysis results of the diagnostic analysis of the operating condition data of the gas turbine. The display unit is used to receive and display the analysis results. The local operating system is at least two; At least two of the local operating systems have different data acquisition frequencies.

2. The edge automatic diagnostic analysis system for gas turbines according to claim 1, characterized in that, The analysis results include at least the statistical report of the gas turbine's operating status during a preset period, the fault detection and prediction of the gas turbine, and the operating performance parameters of the gas turbine.

3. The edge automatic diagnostic analysis system for gas turbines according to claim 1, characterized in that, The diagnostic analysis system includes: The report creation module is used to obtain the operating condition data of the gas turbine for a predetermined time period corresponding to the time series database, and generate a statistical report of the operating status of the gas turbine for a predetermined time period based on the operating condition data of the gas turbine. The preset time period operation status statistical report includes at least the following time series graphs: power change data of the gas turbine, temperature change data of the gas turbine, vibration change data of the gas turbine, operating efficiency change data of the gas turbine, power change data of the gas turbine, start-up status change data of the gas turbine, running time change data of the gas turbine, and real-time performance change data of the gas turbine.

4. The edge automatic diagnostic analysis system for gas turbines according to claim 1, characterized in that, The diagnostic analysis system includes: The fault prediction and analysis module uses a fault prediction and analysis model to perform fault analysis on the time series data in the time series database, so as to obtain and output the fault analysis findings and predictions of the gas turbine. The fault prediction analysis model includes at least one of the following models: A sensor health diagnostic model is provided, which uses a time series prediction algorithm to predict the acquisition trend of sensor signals and diagnose the health of sensor hardware. A combustion state early warning model, which predicts the combustion state of the gas turbine based on the trend of combustion data and recommends combustion optimization parameters; A burner condition diagnostic model is used to determine the blockage and deterioration of the burner by analyzing the trends of the exhaust temperature at the gas turbine outlet and some combustion data collected by sensors related to the gas turbine burner. A gas turbine emission optimization model, which analyzes the emission and combustion data of the gas turbine and recommends optimized combustion data to optimize the emission level of the gas turbine; A gas turbine vibration early warning model is provided, which determines the vibration trend of the gas turbine based on the analysis of the vibration data of the gas turbine, so as to provide early warning of potential vibration hazards and analyze the vibration faults that occur.

5. The edge automatic diagnostic analysis system for gas turbines according to claim 1, characterized in that, The diagnostic analysis system includes: The calculation and analysis module is used to perform calculations on the time series data in the time series database to obtain the operating performance parameters of the gas turbine.

6. The edge automatic diagnostic analysis system for gas turbines according to claim 1, characterized in that, At least two of the aforementioned operating data acquisition sensors include an acceleration sensor for acquiring acceleration data of the gas turbine impeller, a velocity sensor for acquiring velocity data of the gas turbine impeller, an angle sensor for acquiring angle data of the gas turbine, and a vibration sensor for acquiring vibration data of the gas turbine; wherein the acceleration sensor, the velocity sensor, and the angle sensor are all connected to the local operating system, and the vibration sensor is connected to the data storage system.

7. The edge automatic diagnostic analysis system for gas turbines according to claim 1, characterized in that, The combustion data includes temperature data, pressure data, and combustion performance data; the combustion data acquisition sensors are of at least two types, including a temperature sensor for acquiring temperature data of the gas turbine and a pressure sensor for acquiring pressure data of the gas turbine; the gas turbine data acquisition system also includes a combustion data storage and calculation module, which is connected to the data storage system, and at least two types of combustion data acquisition sensors are connected to the combustion data storage and calculation module; The combustion data storage and calculation module is used to store the temperature data and the pressure data, and to calculate the combustion performance data based on the temperature data and the pressure data.

8. An automatic edge diagnostic analysis method for gas turbines, utilizing the automatic edge diagnostic analysis system for gas turbines as described in any one of claims 1 to 7, characterized in that, The automatic edge diagnostic analysis method for gas turbines includes the following steps: S10, the operating condition data of the gas turbine is collected through at least two types of operating data acquisition sensors, combustion data acquisition sensors and local operating system of the gas turbine data acquisition system. The operating condition data of the gas turbine includes the operating data and combustion data of the gas turbine. S20, the operating condition data of the gas turbine is stored in a time series database in the form of time series data through a data storage system. The time series data is a dataset arranged in chronological order. S30, the diagnostic analysis system receives and analyzes the time series database stored in the data storage system and outputs the analysis results of the diagnostic analysis of the operating condition data of the gas turbine. S40, the analysis results are received and displayed through the display unit.

9. The automatic edge diagnostic analysis method for gas turbines according to claim 8, characterized in that, Step S30 includes: S31, the report creation module of the diagnostic analysis system obtains the operating condition data of the gas turbine for a predetermined time period corresponding to the time series database, and generates a preset time period operation status statistical report of the gas turbine based on the operating condition data of the gas turbine; wherein, the preset time period operation status statistical report includes at least the following time series graphs: power change data of the gas turbine, temperature change data of the gas turbine, vibration change data of the gas turbine, operating efficiency change data of the gas turbine, power change data of the gas turbine, start-up status change data of the gas turbine, running time change data of the gas turbine, and real-time performance change data of the gas turbine; and / or, S32, the fault prediction analysis module of the diagnostic analysis system uses a fault prediction analysis model to perform fault analysis on the time series database to obtain and output the fault detection and prediction of the gas turbine; wherein, the fault analysis and prediction of the gas turbine includes fault analysis and prediction of the gas turbine valves, fault analysis and prediction of the operating data acquisition sensors, fault analysis and prediction of the combustion data acquisition sensors, combustion fault analysis and prediction of the gas turbine, performance degradation analysis and prediction of the gas turbine compressor, and emission fault analysis and prediction of the gas turbine; and / or, S33, The time series database is calculated by the calculation and analysis module of the diagnostic analysis system to obtain the operating performance parameters of the gas turbine.

Images