A method and device for power plant monitoring and abnormal alarm

Abstract

This invention discloses a power plant monitoring and anomaly alarm method and device, belonging to the field of power system operation and maintenance technology. The method includes: collecting real-time operating data of the power plant to be monitored according to preset monitoring parameters; determining a dynamic baseline corresponding to each type of operating data based on historical operating data within a preset historical operating data statistical period; determining whether the type of operating data meets alarm conditions based on the dynamic baseline and a preset anomaly judgment threshold; and outputting alarm information to a preset alarm receiver if the alarm conditions are met. This solution can improve monitoring accuracy.

Description

Technical Field

[0001] This invention relates to the field of power system operation and maintenance technology, and in particular to a power plant monitoring and anomaly alarm method and device. Background Technology

[0002] With the large-scale construction and distributed layout of new energy power plants, the number of power plants has surged and their geographical distribution is scattered. Traditional manual inspection and fixed-point monitoring methods are no longer sufficient to meet operation and maintenance needs. Existing power plant operation monitoring technologies have the following shortcomings: Baseline Staticization: The power plant operation monitoring system uses manually preset fixed thresholds as the judgment criteria. However, as the power plant equipment ages and environmental conditions change, the fixed thresholds are prone to "false judgments" or "missed judgments" and cannot adapt to the dynamic characteristics of the power plant's long-term operation. Low monitoring efficiency: The operation data of multiple power stations need to be manually summarized and compared at regular intervals, which is time-consuming, labor-intensive, and prone to human error, making it difficult to achieve uninterrupted monitoring 24 hours a day; Alarm delay: The discovery of abnormal data relies on manual investigation. The cycle from data anomaly to maintenance personnel receiving notification is long, which can easily lead to the escalation of the fault and increase the operation and maintenance costs and safety risks of the power plant.

[0003] Therefore, there is an urgent need for a technical solution that can monitor the operation data of multiple power plants in real time, accurately detect anomalies, and trigger alarms in a timely manner, so as to improve the automation level and response efficiency of power plant operation and maintenance. Summary of the Invention

[0004] The purpose of this invention is to provide a power plant monitoring and anomaly alarm method, device, and electronic equipment that can solve the problem of strong limitations in the prior art.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: This invention provides a power plant monitoring and anomaly alarm method, wherein the method includes: Real-time operating data of the power station to be monitored is collected according to preset monitoring parameters; the types of real-time operating data include: power generation, inverter temperature, DC bus voltage, and wind turbine speed. For each type of operational data, a dynamic baseline corresponding to that type is determined based on historical operational data within a preset historical operational data statistical period; Based on the dynamic baseline and the preset anomaly detection threshold, determine whether the type of operational data meets the alarm conditions; When the alarm conditions are met, the alarm information is output to the preset alarm receiver.

[0006] Optionally, the preset monitoring parameters include: timed scan time, list of power plants to be monitored, data types to be monitored, historical data statistics period, anomaly judgment threshold, and alarm recipient information.

[0007] Optionally, the step of determining the dynamic baseline corresponding to each type of operational data based on historical operational data within a preset historical operational data statistical period includes: For each type of operational data, obtain the historical operational data of that type within a preset historical operational data statistical period; Calculate the average value of historical running data for this type; A dynamic baseline corresponding to the type is generated based on the average value.

[0008] Optionally, the step of determining whether the type of operational data meets the alarm conditions based on the dynamic baseline and the preset anomaly determination threshold includes: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; If the deviation rate exceeds the preset anomaly determination threshold, the type of operating data is determined to meet the alarm conditions. If the deviation rate does not exceed the preset anomaly determination threshold, it is determined that the type of operating data does not meet the alarm conditions.

[0009] Optionally, the step of determining whether the type of operational data meets the alarm conditions based on the dynamic baseline and the preset anomaly determination threshold includes: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; Determine the trend of change in the operational data of the aforementioned type; If the deviation rate does not exceed the preset anomaly detection threshold, and the trend of change indicates an anomaly risk, Determine that the type of runtime data meets the alarm conditions.

[0010] Optionally, the step of determining whether the type of operational data meets the alarm conditions based on the dynamic baseline and the preset anomaly determination threshold includes: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; If the deviation rate does not exceed the preset anomaly determination threshold, the system combines historical operating data of the same type from other power plants to determine whether there is an anomaly in the operating data of the same type from the power plant to be monitored. If an anomaly is found, determine that the operational data of that type meets the alarm conditions.

[0011] Optionally, the method further includes: Analyze historical operational data for each type of data and establish a dynamic correlation model between the data types. The step of determining the dynamic baseline corresponding to each type of operational data based on historical operational data within a preset historical operational data statistical period includes: For each type of operational data, a dynamic baseline corresponding to that type is determined based on historical operational data within a preset historical operational data statistical period and the dynamic correlation model.

[0012] This invention also provides a power plant monitoring and anomaly alarm device, wherein the device includes: The data acquisition module is used to collect real-time operating data of the power station to be monitored according to preset monitoring parameters; the types of real-time operating data include: power generation, inverter temperature, DC bus voltage, and wind turbine speed. The baseline determination module is used to determine the dynamic baseline corresponding to each type of operational data based on historical operational data within a preset historical operational data statistical period. The judgment module is used to determine whether the type of running data meets the alarm conditions based on the dynamic baseline and the preset anomaly judgment threshold. The alarm module is used to output alarm information to preset alarm recipients when alarm conditions are met.

[0013] Optionally, the preset monitoring parameters include: timed scan time, list of power plants to be monitored, data types to be monitored, historical data statistics period, anomaly judgment threshold, and alarm recipient information.

[0014] Optionally, the baseline determination module includes: The first submodule is used to obtain historical operation data of the type within a preset historical operation data statistical period for each type of operation data; The second submodule is used to calculate the average value of historical running data of the aforementioned type; The third submodule is used to generate a dynamic baseline corresponding to the type based on the average value.

[0015] Optionally, the determination module is specifically used for: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; If the deviation rate exceeds the preset anomaly determination threshold, the type of operating data is determined to meet the alarm conditions. If the deviation rate does not exceed the preset anomaly determination threshold, it is determined that the type of operating data does not meet the alarm conditions.

[0016] Optionally, the determination module is specifically used for: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; Determine the trend of change in the operational data of the aforementioned type; If the deviation rate does not exceed the preset anomaly detection threshold, and the trend of change indicates an anomaly risk, Determine that the type of runtime data meets the alarm conditions.

[0017] Optionally, the determination module is specifically used for: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; If the deviation rate does not exceed the preset anomaly determination threshold, the system combines historical operating data of the same type from other power plants to determine whether there is an anomaly in the operating data of the same type from the power plant to be monitored. If an anomaly is found, determine that the operational data of that type meets the alarm conditions.

[0018] Optionally, the device further includes: Establish a module to analyze historical operational data of various data types and build a dynamic correlation model between data types; The baseline determination module is specifically used to: determine the dynamic baseline corresponding to each type of operational data based on historical operational data within a preset historical operational data statistical period and the dynamic association model.

[0019] This invention provides an electronic device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the steps of any of the above-described power plant monitoring and anomaly alarm methods.

[0020] This invention provides a readable storage medium storing a program or instructions, which, when executed by a processor, implement the steps of any of the above-described power plant monitoring and anomaly alarm methods.

[0021] The power plant monitoring and anomaly alarm scheme provided in this embodiment of the invention collects real-time operating data of the power plant to be monitored, such as power generation, inverter temperature, DC bus voltage, and wind turbine speed, according to preset monitoring parameters. For each type of operational data, a dynamic baseline corresponding to the type is determined based on historical operational data within a preset historical operational data statistical period. Based on the dynamic baseline and a preset anomaly judgment threshold, it is determined whether the operational data of that type meets the alarm conditions. If the alarm conditions are met, alarm information is output to a preset alarm recipient. Through this solution provided by the embodiments of the present invention, firstly, determining the dynamic baseline corresponding to the type based on historical operational data within a preset historical operational data statistical period enables baseline dynamism, thereby avoiding misjudgments caused by fixed thresholds due to equipment aging or environmental changes, and improving monitoring accuracy; secondly, the entire process from data collection, baseline calculation, anomaly judgment to alarm push is fully automated without manual intervention: enabling unmanned monitoring of multiple power stations and reducing maintenance manpower costs; thirdly, alarms are triggered promptly after anomalies occur, allowing maintenance personnel to quickly locate abnormal power stations and abnormal parameters, shortening fault response time. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating the steps of a power plant monitoring and anomaly alarm method according to an embodiment of this application; Figure 2 This is a structural block diagram illustrating a power plant monitoring and anomaly alarm device according to an embodiment of this application. Detailed Implementation

[0023] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0024] To address the shortcomings of existing power plant operation monitoring technologies, such as static baselines, low monitoring efficiency, and delayed alarms, this application provides a baseline monitoring and anomaly alarm scheme for power plant operation data. This scheme periodically acquires real-time operation data from multiple power plants and, combined with historical operation data from these plants, periodically generates a dynamic baseline based on the average historical data (e.g., daily). The real-time operation data is compared with the corresponding dynamic baseline; if the real-time operation data deviates from the dynamic baseline, it is determined to be an anomaly, automatically triggering an alarm message and pushing alarm information including the anomaly power plant identifier, anomaly parameters, baseline value, and actual value. This scheme achieves automation and dynamism in power plant operation monitoring, specifically enabling dynamic baseline generation, timed automatic scanning of data from multiple power plants, accurate anomaly detection, and real-time email alarms. This improves the timeliness and accuracy of power plant operation and maintenance, reduces manual maintenance costs, and enhances the safety and stability of power plant operation.

[0025] The power plant monitoring and anomaly alarm scheme provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0026] As attached Figure 1As shown, the power plant monitoring and anomaly alarm method of this application embodiment includes the following steps: Step 101: Collect real-time operating data of the power station to be monitored according to the preset monitoring parameters.

[0027] The power plant monitoring and anomaly alarm method provided in this application can be applied to electronic devices, which include a processor and a storage medium. The storage medium stores a computer program for power plant monitoring and anomaly alarm. The processor runs the computer program to execute the power plant monitoring and anomaly alarm method flow.

[0028] The preset monitoring parameters include: scheduled scan time, list of power plants to be monitored, data types to be monitored, historical data statistics period, anomaly detection threshold, and alarm recipient information. In practice, users can flexibly set these preset monitoring parameters according to their needs for flexible monitoring of the power plants. For example, the anomaly detection threshold can be set to ±10% of the baseline value, the historical data statistics period can be set to the last 7 days, last 15 days, or last 30 days, and the alarm method can be email or telephone alerts. A configuration management module can be set up to allow users to preset the monitoring parameters. Real-time operating data types can include, but are not limited to: power generation, inverter temperature, DC bus voltage, and wind turbine speed.

[0029] In practical implementation, a data acquisition module can be set up to collect operational data. This module communicates with the operational data terminals of each power station, automatically acquiring real-time operational data according to a preset "timed scan period," and marking it with the power station ID and data type. A historical data storage module can also be set up to store the collected historical operational data of the power stations. Specifically, a relational database can be used to store all real-time operational data acquired by the data acquisition module, forming historical operational datasets for each power station and data type, and supporting data queries by power station ID, data type, and time range.

[0030] Step 102: For each type of operational data, determine the corresponding dynamic baseline based on historical operational data within the preset historical operational data statistical period.

[0031] In one optional embodiment, the dynamic baseline corresponding to each type of operational data is determined based on historical operational data within a preset historical operational data statistical period, as follows: For each type of operational data, obtain the historical operational data of that type within a preset historical operational data statistical period; calculate the average value of the historical operational data for that type; and generate the corresponding dynamic baseline based on the average value.

[0032] In practical implementation, a baseline calculation module can be set up to calculate the dynamic baseline corresponding to the data type. For example, before the "scheduled scan time" each day, such as 23:30-23:59, the historical operation data of the corresponding power station and data type can be retrieved from the historical data storage module according to the "historical operation data statistics cycle" preset by the configuration management module. The arithmetic mean of this historical dataset is calculated, and this mean is used as the "daily operation baseline" for the corresponding power station and data type, and stored in the baseline database. The "daily operation baseline" is the dynamic baseline.

[0033] In actual implementation, a corresponding dynamic baseline can be generated for each type of data, or a corresponding dynamic baseline can be generated for only some types of data. This application embodiment does not impose specific restrictions on this.

[0034] Step 103: Based on the dynamic baseline and the preset anomaly judgment threshold, determine whether the type of running data meets the alarm conditions.

[0035] In an optional embodiment, the method for determining whether a type of operational data meets the alarm conditions based on a dynamic baseline and a preset anomaly determination threshold can be as follows: determine the deviation rate of the operational data of a type relative to the dynamic baseline; if the deviation rate exceeds the preset anomaly determination threshold, determine that the operational data of that type meets the alarm conditions; if the deviation rate does not exceed the preset anomaly determination threshold, determine that the operational data of that type does not meet the alarm conditions.

[0036] The anomaly detection threshold can be flexibly set by those skilled in the art. In this embodiment, no specific restrictions are imposed. For example, the anomaly detection threshold can be set to 10%, 15%, or 20%.

[0037] In the specific implementation process, an anomaly detection module can be set up to determine whether the alarm conditions are met. After the data acquisition module obtains real-time operating data, the anomaly detection module automatically retrieves the "daily operating baseline" for the corresponding power station and data type from the baseline database, calculates the deviation rate of the real-time data using the formula (real-time data - baseline) / baseline × 100%), and determines that the real-time data is "abnormal data" by exceeding ±10%, and generates an anomaly record containing "power station ID, data type, acquisition time, baseline value, real-time value, and deviation rate".

[0038] In one optional embodiment, the method for determining whether a type of operational data meets the alarm conditions based on a dynamic baseline and a preset anomaly detection threshold can be as follows: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; determine the changing trend of the operational data of the aforementioned type; and determine that the operational data of the aforementioned type meets the alarm conditions if the deviation rate does not exceed the preset anomaly judgment threshold and the changing trend indicates an anomaly risk.

[0039] In this optional embodiment, the system compares real-time data with their respective dynamic baselines. It not only checks for out-of-bounds errors but also analyzes trends. For example, if it detects that the voltage of cluster B decreases at a rate of 0.1V per day for five consecutive cycles during full charge, even if the voltage of cluster B remains within the normal range, the system will trigger an "early performance degradation trend" warning. This method of combining operational data trends with alarm determination allows for earlier warnings, enabling technicians to deploy resources more quickly.

[0040] In an optional embodiment, the method for determining whether the type of operating data meets the alarm conditions based on the dynamic baseline and the preset anomaly determination threshold can be as follows: determine the deviation rate of the type of operating data relative to the dynamic baseline; if the deviation rate does not exceed the preset anomaly determination threshold, determine whether the type of operating data of the monitored power station is abnormal by combining the historical operating data of the type of data of other power stations; if an anomaly exists, determine that the type of operating data meets the alarm conditions.

[0041] This method of combining historical operating data of similar power plants with data from other power plants to determine alarms can improve the accuracy of the determination results.

[0042] Step 104: If the alarm conditions are met, output alarm information to the preset alarm receiver.

[0043] In practical implementation, the alarm module can be configured to output alarm information. The alarm module communicates with the anomaly detection module. When the anomaly detection module generates an anomaly record, it automatically calls the email sending interface and pushes an alarm email according to the "alarm recipient list" preset by the configuration management module. The alarm email content includes at least: alarm time, abnormal power station name and ID, abnormal data type, daily baseline value, real-time abnormal value, deviation rate, and anomaly level. The output method of alarm information is not limited to email alarms; it can also be set to telephone alarms, application alarms, etc.

[0044] It should be noted that this is not limited to setting up a separate alarm module. The alarm computer program deployed in the alarm module can be merged into other functional modules for execution, such as merging the alarm computer program into the anomaly detection module. Alternatively, the computer programs in the aforementioned functional modules can be merged into a single module for execution.

[0045] In an optional embodiment, the power plant monitoring and anomaly alarm method provided in this application may further include the following steps: Analyze historical operational data for each type of data to establish a dynamic correlation model between the data types; accordingly, for each type of operational data, the dynamic baseline corresponding to the type can be determined based on historical operational data within a preset historical operational data statistical period and the dynamic correlation model.

[0046] The power plant monitoring and anomaly alarm method provided in this application embodiment of the present invention collects real-time operating data of the power plant to be monitored according to preset monitoring parameters; for each type of operating data, a dynamic baseline corresponding to the type is determined based on historical operating data within a preset historical operating data statistical period; based on the dynamic baseline and a preset anomaly judgment threshold, it is determined whether the type of operating data meets the alarm conditions; if the alarm conditions are met, alarm information is output to a preset alarm receiver. The method provided by this invention has several advantages. First, it determines a dynamic baseline corresponding to a type based on historical operating data within a preset historical operating data statistical period, enabling baseline dynamism and avoiding misjudgments caused by equipment aging or environmental changes due to fixed thresholds, thus improving monitoring accuracy. Second, it automates the entire monitoring process from data collection, baseline calculation, anomaly detection to alarm push without human intervention, enabling unmanned monitoring of multiple power stations and reducing maintenance manpower costs. Third, it triggers alarms promptly after an anomaly occurs, allowing maintenance personnel to quickly locate the abnormal power station and abnormal parameters, shortening fault response time. Fourth, the method supports adding new power stations and new operating data types, and the anomaly threshold and historical data period can be flexibly adjusted through the configuration module to adapt to the monitoring needs of power stations of different scales and types, demonstrating strong scalability.

[0047] The following example illustrates the power plant monitoring and anomaly alarm method provided in this application.

[0048] Example 1: Dynamic monitoring and early warning of battery cluster consistency in Battery Energy Storage Systems (BESS) Application background of Example 1: Energy storage power stations consist of dozens to hundreds of battery clusters connected in parallel. With repeated use, the capacity and internal resistance of each battery cluster will decrease to varying degrees, which increases the inconsistency of the batteries in the cluster. Traditional methods of determining the voltage or temperature threshold cannot accurately reflect the uniqueness and aging status of each cluster, and are prone to triggering false alarms or ignoring early degradation signals under extreme operating conditions.

[0049] The application process of the power plant monitoring and anomaly alarm method provided in this application embodiment in Example 1 is as follows: Dynamic baseline construction: The system automatically learns the historical operating data of each battery cluster over the past 30 days, such as voltage, current, temperature, and SOC (state of charge), to establish a unique "healthy operating range" dynamic baseline for each cluster. For example, for cluster A, its normal voltage range may be 745V-755V, while for cluster B, which ages faster, the range is dynamically adjusted to 740V-750V.

[0050] Real-time intelligent monitoring: The system compares real-time data with its respective dynamic baselines 24 / 7. It not only checks for out-of-bounds errors but also analyzes trends. For example, if it finds that the voltage of cluster B drops at a rate of 0.1V per day for five consecutive cycles at full charge, even if it is still within a fixed threshold, the system will trigger an "early performance degradation trend" warning.

[0051] Correlation analysis and root cause inference: The system correlation analysis of the temperature data and cooling system logs of this cluster revealed that its temperature difference was larger than that of other clusters. Combined with historical data, an automatic report was generated: "It is suspected that the large temperature difference inside cluster B is causing accelerated degradation of consistency. It is recommended to check the cooling air duct and cell connection." The power plant monitoring and anomaly alarm method provided in this example transforms fault early warning from "post-event alarm" to "pre-event prediction," guiding operation and maintenance personnel to carry out preventive maintenance, balance the state of battery clusters, delay the overall degradation of the power plant, and improve safety and economy.

[0052] Example 2: Power control accuracy and power quality monitoring at the grid connection point of an energy storage power station Application background of Example 2: Power plants need to strictly control the power at the grid connection point according to dispatch instructions. The accuracy of power control is affected by many factors such as the status of internal equipment, weather, and grid fluctuations. Traditional fixed deviation thresholds, such as ±2%, are not applicable under complex operating conditions.

[0053] The application process of the power plant monitoring and anomaly alarm method provided in this application embodiment in Example 2 is as follows: Dynamic accuracy baseline generation: The system analyzes historical data and automatically establishes a dynamic correlation model between "power control accuracy" and factors such as "command change amplitude", "current total active power output", and "weather conditions". For example, when the command changes significantly or during cloudy or rainy weather, the dynamic allowable deviation range may be automatically widened to ±3%.

[0054] Intelligent over-limit judgment and source tracing: When the real-time power deviation exceeds the dynamic allowable range, the system immediately alarms and automatically traces the source: whether it is caused by an abnormal response of a certain PCS (Power Conversion System) cluster or by a sudden drop in the supporting photovoltaic power. Through correlation analysis, the responsible unit can be quickly located.

[0055] Power quality trend early warning: Dynamic baselines related to the power plant's operating mode are also established for power quality indicators such as harmonics and flicker. An early warning is issued when a slow upward trend in a specific harmonic is detected during discharge, preventing exceedances. Power plant operating modes include: charging mode and discharging mode.

[0056] The power plant monitoring and anomaly alarm method provided in this example can achieve adaptive and intelligent evaluation of grid-connected performance, reduce invalid alarms caused by environmental factors, and quickly locate real anomalies when they occur, ensuring compliant operation of the power plant and maintaining the safety and stability of the power grid.

[0057] Figure 2 The structural block diagram of the power plant monitoring and anomaly alarm device in this application embodiment is shown.

[0058] The power plant monitoring and anomaly alarm device provided in this application includes the following functional modules: The data acquisition module 201 is used to acquire real-time operating data of the power station to be monitored according to preset monitoring parameters; the types of real-time operating data include: power generation, inverter temperature, DC bus voltage, and wind turbine speed. The baseline determination module 202 is used to determine the dynamic baseline corresponding to each type of running data based on historical running data within a preset historical running data statistical period. The judgment module 203 is used to determine whether the type of running data meets the alarm conditions based on the dynamic baseline and the preset anomaly judgment threshold. The alarm module 204 is used to output alarm information to a preset alarm receiver when the alarm conditions are met.

[0059] Optionally, the preset monitoring parameters include: timed scan time, list of power plants to be monitored, data types to be monitored, historical data statistics period, anomaly judgment threshold, and alarm recipient information.

[0060] Optionally, the baseline determination module includes: The first submodule is used to obtain historical operation data of the type within a preset historical operation data statistical period for each type of operation data; The second submodule is used to calculate the average value of historical running data of the aforementioned type; The third submodule is used to generate a dynamic baseline corresponding to the type based on the average value.

[0061] Optionally, the determination module is specifically used for: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; If the deviation rate exceeds the preset anomaly determination threshold, the type of operating data is determined to meet the alarm conditions. If the deviation rate does not exceed the preset anomaly determination threshold, it is determined that the type of operating data does not meet the alarm conditions.

[0062] Optionally, the determination module is specifically used for: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; Determine the trend of change in the operational data of the aforementioned type; If the deviation rate does not exceed the preset anomaly detection threshold, and the trend of change indicates an anomaly risk, Determine that the type of runtime data meets the alarm conditions.

[0063] Optionally, the determination module is specifically used for: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; If the deviation rate does not exceed the preset anomaly determination threshold, the system combines historical operating data of the same type from other power plants to determine whether there is an anomaly in the operating data of the same type from the power plant to be monitored. If an anomaly is found, determine that the operational data of that type meets the alarm conditions.

[0064] Optionally, the device further includes: Establish a module to analyze historical operational data of various data types and build a dynamic correlation model between data types; The baseline determination module is specifically used to: determine the dynamic baseline corresponding to each type of operational data based on historical operational data within a preset historical operational data statistical period and the dynamic association model.

[0065] The power plant monitoring and anomaly alarm device provided in this application has several advantages. First, it determines a dynamic baseline corresponding to a type based on historical operating data within a preset historical operating data statistical period, thereby enabling baseline dynamism and avoiding misjudgments caused by equipment aging or environmental changes due to fixed thresholds, thus improving monitoring accuracy. Second, it automates the entire monitoring process from data acquisition, baseline calculation, anomaly judgment to alarm push without human intervention, enabling unmanned monitoring of multiple power plants and reducing maintenance manpower costs. Third, it triggers alarms promptly after an anomaly occurs, allowing maintenance personnel to quickly locate the abnormal power plant and abnormal parameters, thus shortening fault response time.

[0066] In the embodiments of this application Figure 2The power plant monitoring and anomaly alarm device shown can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application does not specifically limit the specific operating system used.

[0067] The embodiments provided in this application Figure 2 The power plant monitoring and anomaly alarm device shown can achieve Figure 1 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0068] Optionally, embodiments of this application also provide an electronic device, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the various processes of the above-mentioned power plant monitoring and abnormal alarm method and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0069] It should be noted that the electronic device in this application embodiment includes the server described above.

[0070] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0071] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0072] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for monitoring and abnormality alarming of a power plant, characterized by, The method includes: Real-time operating data of the power station to be monitored is collected according to preset monitoring parameters; the types of real-time operating data include: power generation, inverter temperature, DC bus voltage, and wind turbine speed. For each type of operational data, a dynamic baseline corresponding to that type is determined based on historical operational data within a preset historical operational data statistical period; Based on the dynamic baseline and the preset anomaly detection threshold, determine whether the type of operational data meets the alarm conditions; When the alarm conditions are met, the alarm information is output to the preset alarm receiver.

2. The method of claim 1, wherein, The preset monitoring parameters include: timed scan time, list of power plants to be monitored, data types to be monitored, historical data statistics period, anomaly detection threshold, and alarm recipient information.

3. The method of claim 1, wherein, The step of determining the dynamic baseline corresponding to each type of operational data based on historical operational data within a preset historical operational data statistical period includes: For each type of operational data, obtain the historical operational data of that type within a preset historical operational data statistical period; Calculate the average value of historical running data for this type; A dynamic baseline corresponding to the type is generated based on the average value.

4. The method of claim 2, wherein, The step of determining whether the type of operational data meets the alarm conditions based on the dynamic baseline and the preset anomaly detection threshold includes: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; If the deviation rate exceeds the preset anomaly determination threshold, the type of operating data is determined to meet the alarm conditions. If the deviation rate does not exceed the preset anomaly determination threshold, it is determined that the type of operating data does not meet the alarm conditions.

5. The method of claim 1, wherein, The step of determining whether the type of operational data meets the alarm conditions based on the dynamic baseline and the preset anomaly detection threshold includes: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; Determine the trend of change in the operational data of the aforementioned type; If the deviation rate does not exceed the preset anomaly detection threshold, and the trend of change indicates an anomaly risk, Determine that the type of runtime data meets the alarm conditions.

6. The method of claim 1, wherein, The step of determining whether the type of operational data meets the alarm conditions based on the dynamic baseline and the preset anomaly detection threshold includes: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; If the deviation rate does not exceed the preset anomaly determination threshold, the system combines historical operating data of the same type from other power plants to determine whether there is an anomaly in the operating data of the same type from the power plant to be monitored. If an anomaly is found, determine that the operational data of that type meets the alarm conditions.

7. The method of claim 1, wherein, The method further includes: Analyze historical operational data for each type of data and establish a dynamic correlation model between the data types. The step of determining the dynamic baseline corresponding to each type of operational data based on historical operational data within a preset historical operational data statistical period includes: For each type of operational data, a dynamic baseline corresponding to that type is determined based on historical operational data within a preset historical operational data statistical period and the dynamic correlation model.

8. A power plant monitoring and anomaly alarm device, characterized in that, The device includes: The data acquisition module is used to collect real-time operating data of the power station to be monitored according to preset monitoring parameters; the types of real-time operating data include: power generation, inverter temperature, DC bus voltage, and wind turbine speed. The baseline determination module is used to determine the dynamic baseline corresponding to each type of operational data based on historical operational data within a preset historical operational data statistical period. The judgment module is used to determine whether the type of running data meets the alarm conditions based on the dynamic baseline and the preset anomaly judgment threshold. The alarm module is used to output alarm information to preset alarm recipients when alarm conditions are met.

9. The apparatus of claim 8, wherein, The preset monitoring parameters include: timed scan time, list of power plants to be monitored, data types to be monitored, historical data statistics period, anomaly detection threshold, and alarm recipient information.

10. The apparatus of claim 8, wherein, The baseline determination module includes: The first submodule is used to obtain historical operation data of the type within a preset historical operation data statistical period for each type of operation data; The second submodule is used to calculate the average value of historical running data of the aforementioned type; The third submodule is used to generate a dynamic baseline corresponding to the type based on the average value.

11. The apparatus of claim 9, wherein, The judgment module is specifically used for: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; If the deviation rate exceeds the preset anomaly determination threshold, the type of operating data is determined to meet the alarm conditions. If the deviation rate does not exceed the preset anomaly determination threshold, it is determined that the type of operating data does not meet the alarm conditions.

12. The apparatus of claim 8, wherein, The judgment module is specifically used for: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; Determine the trend of change in the operational data of the aforementioned type; If the deviation rate does not exceed the preset anomaly detection threshold, and the trend of change indicates an anomaly risk, Determine that the type of runtime data meets the alarm conditions.

13. The apparatus of claim 8, wherein, The judgment module is specifically used for: Determine the deviation rate of the operational data of the aforementioned type relative to the dynamic baseline; If the deviation rate does not exceed the preset anomaly determination threshold, the system combines historical operating data of the same type from other power plants to determine whether there is an anomaly in the operating data of the same type from the power plant to be monitored. If an anomaly is found, determine that the operational data of that type meets the alarm conditions.

14. The apparatus of claim 8, wherein, The device further includes: Establish a module to analyze historical operational data of various data types and build a dynamic correlation model between data types; The baseline determination module is specifically used to: determine the dynamic baseline corresponding to each type of operational data based on historical operational data within a preset historical operational data statistical period and the dynamic association model.

15. An electronic device, comprising: The electronic device comprises a processor, a memory, and a program or instructions stored on the memory and executable on the processor, and the processor executes the steps of the power station monitoring and abnormality alarming method according to any one of claims 1-7.

Images