A system for analyzing the deterioration of the lower guide shoe of a hydraulic turbine

Abstract

The present invention discloses a water turbine lower guide shoe degradation analysis system, which relates to the technical field of water turbine power generation equipment monitoring, and includes: a data access module, which is used for data interface management, metadata configuration and data interface testing; a data cleaning module, which is used for processing the water turbine unit lower guide shoe data from the data access module, including abnormal value detection and processing, missing value detection and processing, format standardization processing, data merging and data deduplication; a state monitoring module, which is used for data monitoring of the data processed by the data cleaning module, and provides degradation prediction and abnormal alarm; a statistical analysis module, which is used for statistical analysis of the data processed by the data cleaning module and the monitoring result data from the state monitoring module, and performs multi-dimensional analysis to display degradation trends, abnormal value records, historical state data, alarm statistics and equipment status. The present invention can improve the accuracy of lower guide shoe degradation detection and trend prediction.

Description

Technical Field

[0001] The invention relates to the technical field of monitoring water turbine power generation equipment, and in particular to a water turbine lower guide shoe degradation analysis system. Background Art

[0002] In a hydro-turbine generator set, the guide bearing is a key component that directly bears the radial mechanical and electromagnetic unbalanced forces of the rotating parts of the unit, and maintains the stable operation of the unit's main shaft within the bearing clearance range. Its state is directly related to the reliability and safety of the unit. Among them, the lower guide bearing is more susceptible to the complex operating environment and long-term operating stress due to its special position and load conditions, and may experience degradation phenomena such as wear, cracks, and deformation. Abnormal changes in the lower guide bearing will not only limit the output of the unit and lead to a decrease in power generation efficiency, but may also cause problems such as increased vibration and unstable operation. In severe cases, it may even lead to a burning accident, endangering the safe operation of the unit. Therefore, real-time monitoring of the lower guide bearing and analysis of its degradation trend are of great significance.

[0003] In the prior art, the detection and trend prediction methods for the operating status of hydro-turbine generator sets usually focus on the overall equipment of the unit, coupling bolts, upper guide bearings, water guide bearings, and shaft vibration as the main analysis objects, focusing on abnormal changes in the global operating status of the equipment and life prediction. For example, the Guangzhao Branch of Guizhou Beipanjiang Electric Power Co., Ltd. announced a prediction and analysis method based on the operation monitoring data of the hydro-turbine unit (CN115423158A), which determines the operating status of the unit equipment and issues graded alarms through data anomaly detection, classification analysis, and trend prediction algorithms. Xi'an Thermal Engineering Research Institute Co., Ltd. proposed a fatigue life prediction model based on diffusion rate (CN115544691A) for obtaining the fatigue extension life of the coupling bolts of axial-flow hydro-turbine generator sets. However, for the monitoring and degradation analysis of the key component of the lower guide bearing, the prior art has the following limitations: the existing methods are mostly oriented to the whole machine equipment or other components, and the identification and analysis of the degradation characteristics of the lower guide bearing are insufficient, making it difficult to provide targeted real-time monitoring and trend prediction. The lower guide bearing monitoring data generated during the operation of the turbine unit is multi-source and complex. The existing technology has failed to comprehensively solve problems such as outliers, missing values, redundant data, etc. in the data, which may affect the accuracy of degradation analysis; the current analysis methods are mostly based on a single indicator and lack multi-dimensional statistical analysis capabilities, making it difficult to comprehensively display and evaluate the degradation trend, historical status, and abnormal distribution of the lower guide bearing. Summary of the invention

[0004] The present invention provides a turbine lower guide shoe degradation analysis system, which can solve the above-mentioned problem.

[0005] In order to solve the above problems, the technical solution adopted by the present invention is as follows:

[0006] The present invention provides a turbine lower guide shoe degradation analysis system, comprising:

[0007] Data access module, used for data interface management, metadata configuration and data interface testing;

[0008] A data cleaning module, used for processing the downstream data of the water turbine unit from the data access module, including abnormal value detection and processing, missing value detection and processing, format standardization processing, data merging and data deduplication;

[0009] A status monitoring module, used to monitor the data processed by the data cleaning module and provide degradation prediction and abnormal alarm;

[0010] The statistical analysis module is used to statistically analyze the data processed by the data cleaning module and the monitoring result data from the status monitoring module, and perform multi-dimensional analysis to display degradation trends, abnormal value records, historical status data, alarm statistics and equipment status.

[0011] As a further description of the above technical solution, the data interface management includes displaying key information of the data source interface, including interface name, interface type, IP address, port number, complete interface address, data return format, interface creation time and parameters; when a new data source interface needs to be added, basic information needs to be filled in and interface configuration needs to be performed.

[0012] As a further description of the above technical solution, the metadata configuration includes: converting the data fields connected to the system through the data interface according to the system specifications; treating each added interface as an independent data source, and the system will support searching and selecting these data sources; converting the fields in the data source to meet the requirements of the data cleaning module, including configuring the field name, Chinese description, field type, source field name, source field type and field length; and displaying all fields and data after the metadata configuration is completed.

[0013] As a further description of the above technical solution, in the data interface test, the user needs to provide a request address, select a request method, input request parameters, and perform identity authentication before executing the test request.

[0014] As a further description of the above technical solution, during the execution of the data cleaning module, a target data model needs to be established, and the downstream conduction data of the turbine group that needs to be calculated from the data access module is selected according to the model function.

[0015] As a further description of the above technical solution, during the execution of the data cleaning module, missing value detection is to mark the missing part of the data, and provide a missing value supplement strategy in combination with historical data; missing value processing is to fill the missing data with the mean, median and the method in the prediction model based on the missing value detection results.

[0016] As a further description of the above technical solution, during the execution of the data cleaning module, outlier detection refers to identifying data outliers and outliers, and combining historical data to provide a solution strategy for outlier processing; outlier processing is to process abnormal data based on the outlier detection results.

[0017] As a further description of the above technical solution, the execution process of the status monitoring module includes the following steps:

[0018] S1, loading the turbine model and marking the model components;

[0019] S2. acquiring the data processed by the data cleaning module in real time according to the data interface type of the turbine model;

[0020] S3, judging the data processed by the data cleaning module according to the threshold value, if the value exceeds the normal operation range of the equipment, executing step S4, otherwise executing step S5;

[0021] S4: Issue an abnormal data alarm, display the real-time status, and notify the maintenance personnel to handle the abnormality;

[0022] S5. According to the data processed by the data cleaning module, the degradation trend of the unit is predicted based on the degradation prediction algorithm. If there is an abnormality, jump to step S4, otherwise, real-time status display is performed.

[0023] As a further description of the above technical solution, in step S5, the degradation prediction includes unit dynamic balance degradation prediction, unit axis degradation prediction, adjacent guide shoe degradation prediction and unit cooling degradation prediction.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] 1) Through the linkage of the data access module and the data cleaning module, the problems of abnormal values, missing values, inconsistent formats, etc. that may exist in the downstream data of the turbine unit are comprehensively solved. At the same time, data merging and deduplication functions are provided to ensure the accuracy and consistency of the input data, thereby providing high-quality basic data support for subsequent degradation analysis.

[0026] 2) The status monitoring module in the system combines the operating characteristics of the turbine lower guide shoe to monitor key data changes in real time, identify potential performance degradation trends through degradation prediction models, and issue timely alarms when abnormal situations occur, ensuring the timeliness and accuracy of fault warnings.

[0027] 3) The statistical analysis module can perform multi-dimensional statistical analysis on the operation data and monitoring results of the lower guide bushing, and generate a variety of visual displays such as degradation trend graphs, abnormal value record tables, historical status statistics and alarm status summaries, providing comprehensive and intuitive analysis results for operation and maintenance personnel, which helps to optimize equipment operation and maintenance decisions.

[0028] 4) By constructing a systematic lower guide bearing monitoring and degradation analysis system, the present invention can effectively improve the recognition efficiency of abnormal changes in the lower guide bearing, reduce the risk of serious accidents such as burning bearings, thereby ensuring the safe operation and long life of the hydro-generator set and reducing operation and maintenance costs.

[0029] 5) The modular design structure makes it highly versatile and extensible. The functional modules can be flexibly adjusted according to the specific operating requirements and monitoring conditions of different hydro-generator units, providing efficient degradation analysis services for various types of units.

[0030] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the embodiments of the present invention are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 is a schematic diagram of the structure of the turbine lower guide shoe degradation analysis system described in the embodiment;

[0033] Figure 2 is a flow chart of a data access module in an embodiment;

[0034] Figure 3 is a flow chart of a data cleaning module in an embodiment;

[0035] Figure 4 is a flow chart of the state monitoring module in the embodiment;

[0036] Figure 5 4 is a flow chart of the statistical analysis module in the embodiment. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments.

[0038] Please refer to Figure 1 The embodiment of the present invention provides a turbine lower guide shoe degradation analysis system, which includes four modules, namely a data access module, a data cleaning module, a status monitoring module and a statistical analysis module.

[0039] 1. Data access module

[0040] The data access module is used for data interface management, metadata configuration and data interface testing, such as Figure 2 As shown, the details are as follows:

[0041] 1) Data interface management

[0042] Displays key information of the data source interface, including interface name, interface type, IP address, port number, complete interface address, data return format, interface creation time, and parameters. When adding a new data source interface, you need to fill in basic information and configure the interface. Basic information includes interface name, interface type, and interface description. To configure the interface is to fill in and configure the interface type, IP address, port number, interface address, return format, and parameter examples.

[0043] 2) Metadata configuration

[0044] Convert the data fields accessed through the data interface according to the system specifications to ensure the uniformity of the data fields;

[0045] Select the data source and treat each added interface as an independent data source. The system will support searching and selecting these data sources.

[0046] Convert the fields in the data source to meet the requirements of the data cleaning module, including configuring the field name, Chinese description, field type, source field name, source field type and field length;

[0047] Data preview, showing all fields and data after metadata configuration is completed.

[0048] 3) Data interface test

[0049] The user needs to provide the request address, select the request method, enter the request parameters, and perform identity authentication, then execute the test request to view the interface status and returned data.

[0050] 2. Data cleaning module

[0051] The data cleaning module is used to process the downstream data of the turbine group from the data access module, including abnormal value detection and processing, missing value detection and processing, format standardization processing, data merging and data deduplication, such as Figure 3 As shown, the details are as follows:

[0052] Step 1: Establish the target data model according to the functions to be implemented, including model name, basic model information, model description, and model picture;

[0053] Step 2: selecting the downstream conduction data of the hydraulic turbine unit that needs to be calculated from the data access module according to the model function;

[0054] Step 3: Integrity check: determine the integrity of the access data. If it is complete, go to step 4; otherwise, go to step 6.

[0055] Step 4: Outlier detection, identifying outliers and outliers, and combining historical data to provide solutions for outlier processing;

[0056] Step 5: Outlier processing: According to the results of outlier detection, the abnormal data is processed according to the solution, such as deletion, replacement, retention, etc., and then jump to step 8;

[0057] Step 6: Missing value detection, marking the missing parts, and providing missing value supplement solutions in combination with historical data;

[0058] Step 7: Missing value processing: According to the missing value supplementation plan, the missing data is filled using the mean, median, and prediction model, and then jumps to step 3, where the prediction formula is:

[0059]

[0060] in, is the missing point value, By calculation and others The continuous product of interpolation between obtains each The weights are calculated and weighted to obtain the deviation of each data point relative to the mean within the specified data range around the point. To calculate the deviation of each point in the interval compared to the median, in order to reduce the impact of outliers, It represents the average value in the data interval, n is usually 20, which represents the total number of data collected in the data interval, and M is the median in the interval. represents the time of the i-th data point in the data set, represents the temperature of the i-th data point in the data set, is the time of the missing point location, represents the time of the jth data point in the data set;

[0061] Step 8: Format standardization: standardize the data format, such as date, time, currency, temperature and other parameters;

[0062] Step 9: Implement data merging and deduplication, identify and delete or merge duplicate data records, and ensure that the data is correct and unique.

[0063] 3. Condition monitoring module

[0064] The status monitoring module is used to monitor the data processed by the data cleaning module and provide degradation prediction and abnormal alarm, such as Figure 4 As shown, the specific steps include:

[0065] S1. Load the turbine model and identify the model components.

[0066] S2. According to the data interface type of the turbine model, the data processed by the data cleaning module is obtained in real time.

[0067] S3. Judging the data processed by the data cleaning module according to the threshold value, if the value exceeds the normal operation range of the equipment, executing step S4, otherwise executing step S5.

[0068] S4. Issue an abnormal data alarm, display the real-time status and notify maintenance personnel to handle the abnormality.

[0069] S5. According to the data processed by the data cleaning module, the degradation trend of the unit is predicted based on the degradation prediction algorithm. If there is an abnormality, jump to step S4, otherwise, real-time status display is performed.

[0070] It should be noted that when the equipment value exceeds the normal operating range or the degradation prediction algorithm calculates that the unit degradation trend is increasing, the system will issue an abnormal data alarm, that is, display an abnormal sign and pop-up window on the corresponding module of the turbine to prompt the management personnel to inspect the equipment. When the system has an abnormal sign and pop-up window, the abnormal alarm can be eliminated after the on-site personnel inspect the equipment. Real-time status display refers to the real-time display of equipment operation information and data, and the display of turbine degradation prediction data.

[0071] In step S5, the degradation prediction includes the unit dynamic balance degradation prediction, the unit axis degradation prediction, the adjacent guide shoe degradation prediction and the unit cooling degradation prediction.

[0072] 1) The prediction formula for unit dynamic balance degradation is:

[0073]

[0074] Among them, DBI1 is the deterioration trend index of the unit dynamic balance, is the unit oil temperature related weight coefficient in the unit dynamic balance analysis and prediction, T is the current unit lower guide bearing temperature, The average temperature of each lower guide tile under rated load for 15 days in the first three months, It is used to calculate the linear velocity of the rotor's center of gravity and measure the severity of the imbalance during the rotor's rotation. M1 is the unit's rotor weight, n1 is the rotor speed, and r is the counterweight correction radius. A spatial rectangular coordinate system is constructed on the unit's frame. The north direction of the frame is its x-direction, and the east direction is its y-direction. is the degradation prediction weight coefficient of the vibration of the unit frame in the x-direction of the spatial rectangular coordinate system, is the vibration of the frame in the x-direction of the spatial rectangular coordinate system, is the average vibration of the frame in the x-direction of the spatial rectangular coordinate system under rated load for 15 days, is the degradation prediction weight coefficient of the vibration of the unit frame in the y direction of the spatial rectangular coordinate system, is the vibration of the frame in the y direction of the spatial rectangular coordinate system, is the average vibration of the frame in the y direction of the spatial rectangular coordinate system under rated load for 15 days, is the degradation prediction weight coefficient of the vibration of the unit frame in the z direction of the spatial rectangular coordinate system, is the vibration of the frame in the z direction of the spatial rectangular coordinate system, is the average vibration of the frame in the z direction of the rectangular coordinate system under rated load for 15 days, is the coolant flow related weight coefficient predicted by the dynamic balance analysis of the unit, L is the current coolant flow, It is the average coolant flow rate under rated load for 15 days.

[0075] 2) The prediction formula for unit axis degradation is:

[0076]

[0077] Among them, DBI2 is the degradation trend index of the unit axis, is the unit oil temperature related weight coefficient in the unit axis degradation analysis and prediction; each lower guide shoe is arranged in a circular manner around the rotor. For any lower guide shoe, the direction of the tangent line passing through its point is defined as direction A, and the direction of the axial line of the center of the circle is defined as direction B; is the degradation prediction weight coefficient of the swing of the lower guide pad in the A direction, X1 is the swing of the lower guide pad in the A direction of the second spatial rectangular coordinate system, is the average swing of the guide bearing in the A direction of the second spatial rectangular coordinate system under rated load for 15 days, is the degradation prediction weight coefficient of the swing of the lower guide pad in the B direction of the second spatial rectangular coordinate system, Y1 is the swing of the lower guide pad in the B direction of the second spatial rectangular coordinate system, is the average swing of the guide bearing in the B direction of the second spatial rectangular coordinate system under rated load for 15 days, It is the weight coefficient related to coolant flow rate for predicting the degradation analysis of the unit axis.

[0078] 3) The adjacent guide tile degradation prediction formula is:

[0079]

[0080] Among them, DBI3 is the degradation trend index of the adjacent lower guide tile, The temperature weight coefficient of the influence of the temperature of the guide shoe on the degradation of the guide shoe in the adjacent guide shoe degradation prediction, is the temperature of the two adjacent lower tiles, is the temperature of the two adjacent lower guide tiles at the next moment, The tolerance temperature for the temperature variation of adjacent guide pads is usually 5 degrees Celsius. It indicates the average temperature of the lower guide tile in the past 15 days from the current time. is the average temperature of the lower guide tile in the past 15 days from the next moment, is the degradation prediction weight coefficient of the swing of the lower guide shoe in the A direction in the adjacent guide shoe degradation prediction, is the degradation prediction weight coefficient of the swing of the lower guide shoe in the B direction, It is the coolant flow related weight coefficient for the prediction of unit axis degradation analysis.

[0081] 4) The prediction formula for unit cooling degradation is:

[0082]

[0083] Among them, DBI4 is the deterioration trend index of unit cooling, The temperature weight coefficient of the influence of the guide bearing temperature on the guide bearing degradation in the unit cooling degradation prediction, The tolerance temperature for the current temperature change of the lower guide tube, usually 5 degrees Celsius, is the degradation prediction weight coefficient of the swing of the lower guide bush in direction A in the unit cooling degradation prediction, is the degradation prediction weight coefficient of the swing of the lower guide shoe in the B direction, is the coolant flow-related weight coefficient in the unit cooling degradation analysis and prediction, is the current coolant flow rate, is the coolant flow rate at the next moment, Indicates the average flow rate of the unit coolant in the past 15 days from the current time. It is the average flow rate of the unit coolant in the past 15 days from the next moment.

[0084] 4. Statistical analysis module

[0085] like Figure 5 As shown, the statistical analysis module is used to statistically analyze the data processed by the data cleaning module and the monitoring result data from the status monitoring module, and perform multi-dimensional analysis to display degradation trends, abnormal value records, historical status data, alarm statistics and equipment status.

[0086] In this embodiment, the module degradation percentage trend and degradation trend are displayed in a graphical form; according to the data interface, the abnormal value data of each interface is statistically displayed; the historical status data is displayed using a list; all alarm information and alarm reasons are statistically displayed; and the equipment operation status information is statistically displayed.

[0087] The turbine lower guide shoe degradation analysis system described in this embodiment uses free and open source technologies for software development, such as Vue, JavaScript, RabbitMQ, MySql, etc., with low development costs. The PC software is developed using Vue, which is a JavaScript framework with good operating performance and cross-platform capabilities. It has low requirements for the hardware environment of the deployed project and is convenient for project transplantation. The missing value prediction algorithm and the degradation prediction algorithm are used to monitor the equipment status in real time and intelligently predict the degradation trend of the operating status to ensure the healthy operation of the equipment. The system monitors the data of the connected equipment in real time and performs threshold management, and provides intelligent alarm notifications for data that exceeds the normal range, providing support for preventing serious accidents and formulating maintenance plans.

[0088] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A turbine lower guide shoe degradation analysis system, characterized in that: include: Data access module, used for data interface management, metadata configuration and data interface testing; The data cleaning module is used to process the downstream data of the turbine group from the data access module, including abnormal value detection and processing, missing value detection and processing, format standardization processing, data merging and data deduplication; the missing value processing is to fill the missing data with the mean, median and the method in the prediction model according to the missing value detection result, and the prediction formula is: in, is the missing point value, By calculation and others The continuous product of interpolation between obtains each The weights are calculated and weighted to obtain the deviation of each data point relative to the mean within the specified data range around the point. To calculate the deviation of each point in the interval compared to the median, represents the average value in the data interval, n represents the total number of data collected in the data interval, and M is the median within the interval. represents the x value of the i-th data point in the data set, which is the time. Indicates the y value of the i-th data point in the data set, which is the temperature, is the x value of the missing point, Represents the x value of the jth data point in the data set; A state monitoring module is used to monitor the data processed by the data cleaning module and provide degradation prediction and abnormal alarm; the degradation prediction includes unit dynamic balance degradation prediction, unit axis degradation prediction, adjacent guide shoe degradation prediction and unit cooling degradation prediction; The prediction formula for unit dynamic balance degradation is: in, is the unit oil temperature related weight coefficient in the unit dynamic balance analysis and prediction, T is the current unit lower guide bearing temperature, The average temperature of each lower guide tile under rated load for 15 days in the first three months, It is used to calculate the linear velocity of the rotor center of gravity and measure the severity of the imbalance during the rotor rotation process, where M1 is the unit rotor weight, n1 is the rotor speed, and r is the counterweight correction radius. is the degradation prediction weight coefficient of the vibration of the unit frame in the x direction, is the current x-axis frame vibration amount, is the average vibration of the frame in the x-direction under rated load for 15 days, is the degradation prediction weight coefficient of the vibration of the unit frame in the y direction, is the current y-axis frame vibration amount, is the average vibration of the frame in the y direction under rated load for 15 days, is the degradation prediction weight coefficient of the vibration of the unit frame in the z direction, is the current z-axis frame vibration amount, is the average vibration of the z-axis frame under rated load for 15 days, is the coolant flow related weight coefficient predicted by the dynamic balance analysis of the unit, L is the current coolant flow, The average flow rate of coolant under rated load for 15 days; The prediction formula for unit axis degradation is: in, is the unit oil temperature related weight coefficient in the unit axis degradation analysis and prediction, is the degradation prediction weight coefficient of the lower guide pad in the x-direction swing, X1 is the current x-direction downward guide pad swing, is the average swing of the x-down guide bearing under rated load for 15 days, is the degradation prediction weight coefficient of the lower guide pad in the y direction, Y1 is the current y downward guide pad swing, is the average swing of the Y-down guide bearing under rated load for 15 days, The weight coefficient related to coolant flow rate for the unit axis degradation analysis and prediction; The adjacent guide tile degradation prediction formula is: in, is the temperature weight coefficient of the influence of the temperature of the guide shoe on the degradation of the guide shoe in the adjacent guide shoe degradation prediction, is the temperature of the two adjacent lower tiles, is the temperature of the two adjacent lower guide tiles at the next moment, The tolerance temperature for the temperature variation of adjacent guide pads, It indicates the average temperature of the lower guide tile in the past 15 days from the current time. is the average temperature of the lower guide tile in the past 15 days from the next moment, is the degradation prediction weight coefficient of the lower guide pad in the x-direction swing in the adjacent guide pad degradation prediction, is the degradation prediction weight coefficient of the lower guide shoe in the y-direction swing, The weight coefficient related to coolant flow rate for the unit axis degradation analysis and prediction; The prediction formula for unit cooling degradation is: in, The temperature weight coefficient of the influence of the guide bearing temperature on the guide bearing degradation in the prediction of unit cooling degradation, is the current lower guide temperature tolerance temperature, is the degradation prediction weight coefficient of the lower guide bushing in the x-direction swing in the unit cooling degradation prediction, is the degradation prediction weight coefficient of the lower guide shoe in the y-direction swing, is the coolant flow-related weight coefficient in the unit cooling degradation analysis and prediction, is the current coolant flow rate, is the coolant flow rate at the next moment, Indicates the average flow rate of the unit coolant in the past 15 days from the current time. The average flow rate of the unit coolant in the past 15 days from the next moment; The statistical analysis module is used to statistically analyze the data processed by the data cleaning module and the monitoring result data from the status monitoring module, and perform multi-dimensional analysis to display degradation trends, abnormal value records, historical status data, alarm statistics and equipment status.

2. The system according to claim 1, characterized in that The data interface management includes displaying key information of the data source interface, including interface name, interface type, IP address, port number, complete interface address, data return format, interface creation time and parameters; when a new data source interface needs to be added, basic information needs to be filled in and interface configuration needs to be performed.

3. The system according to claim 1, characterized in that The metadata configuration includes: converting the source data fields connected to the system according to the system specifications; treating each added interface as an independent data source, and the system will support searching and selecting these data sources; converting the fields in the data source to meet the requirements of the data cleaning module, including configuring the field name, Chinese description, field type, source field name, source field type and field length; and displaying all fields and data after the metadata configuration is completed.

4. The system according to claim 1, characterized in that In the data interface test, the user needs to provide the request address, select the request method, enter the request parameters, and perform identity authentication before executing the test request.

5. The system according to claim 1, characterized in that During the execution of the data cleaning module, a target data model needs to be established, and the downstream data of the hydraulic turbine unit that needs to be calculated from the data access module is selected according to the model function.

6. The system according to claim 1, characterized in that During the execution of the data cleaning module, missing value detection is to mark the missing part of the data and provide a missing value supplement strategy in combination with historical data; missing value processing is to fill the missing data using the mean, median and the method in the prediction model based on the missing value detection results.

7. The system according to claim 6, characterized in that During the execution of the data cleaning module, outlier detection refers to identifying data outliers and outliers, and combining historical data to provide a solution strategy for outlier processing; outlier processing refers to processing abnormal data based on the outlier detection results.

8. The system according to claim 1, characterized in that The execution process of the state monitoring module includes the following steps: S1, loading the turbine model and marking the model components; S2. acquiring the data processed by the data cleaning module in real time according to the data interface type of the turbine model; S3, judging the data processed by the data cleaning module according to the threshold value, if the value exceeds the normal operation range of the equipment, executing step S4, otherwise executing step S5; S4: Issue an abnormal data alarm, display the real-time status, and notify the maintenance personnel to handle the abnormality; S5. According to the data processed by the data cleaning module, the degradation trend of the unit is predicted based on the degradation prediction algorithm. If there is an abnormality, jump to step S4, otherwise, real-time status display is performed.

Images