Generator performance detection method of multi-source heterogeneous big data platform, medium and equipment

Abstract

The invention provides a generator performance detection method of a multi-source heterogeneous big data platform, a medium and equipment, and relates to the technical field of performance detection, and the method comprises the steps: constructing a multi-source heterogeneous monitoring network of a target generator set; reading preset unit operation performance indexes including a primary frequency modulation contribution rate, a small disturbance qualified rate and an automatic power generation control performance index; performing operation performance monitoring to obtain unit operation performance monitoring data; a preset unit operation performance standard is read and input into the unit performance analysis model, and a unit performance analysis result is obtained; defect performance marking is carried out, and performance defect early warning information including a first early warning level is generated; and when the preset early warning level is reached, operating parameter regulation and control are carried out. The technical problem that in the prior art, generator performance detection is usually evaluated through off-line calculation or based on historical data, the capability of real-time monitoring and real-time adjustment on unit performance is lacked, and consequently system scheduling precision and flexibility are insufficient is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of performance detection, and in particular to a generator performance detection method, medium and equipment on a multi-source heterogeneous big data platform. Background Art

[0002] At present, the traditional generator performance monitoring and assessment system has a lag, that is, the operating personnel can only obtain the performance assessment results of the unit on the next day. This time delay makes it impossible for the unit to make effective adjustments or optimizations immediately when performance problems occur. For example, when the AGC performance is lower than the requirement, it often takes until the next day to get feedback and take improvement measures, which may cause the unit to lose the initiative to participate in the bidding for access to the grid, thereby affecting the unit's economic efficiency. In addition, traditional generator performance monitoring methods usually rely on a single data source or a relatively isolated monitoring system, lacking the ability to integrate multi-source heterogeneous data. When faced with the complex needs of power grid dispatch, it is impossible to achieve cross-system data integration and intelligent analysis. The dispatch instructions between the power grid and the power plant often cannot fully consider the dynamic changes and real-time performance indicators of different units, resulting in insufficient flexibility and accuracy in dispatch decisions. Summary of the invention

[0003] This application aims to solve the technical problem that the generator performance detection in the prior art is usually performed through offline calculation or evaluation based on historical data, lacks the ability to monitor and adjust the unit performance in real time, resulting in insufficient system scheduling accuracy and flexibility by providing a generator performance detection method, medium and equipment for a multi-source heterogeneous big data platform.

[0004] The first aspect disclosed in the present application provides a generator performance detection method for a multi-source heterogeneous big data platform, the method comprising: constructing a multi-source heterogeneous monitoring network of a target generator set, wherein the multi-source heterogeneous monitoring network comprises a remote terminal unit, a distributed control system, and a primary frequency regulation homologous device; reading predetermined unit operation performance indicators, wherein the unit operation performance indicators comprise a primary frequency regulation contribution rate, a small disturbance qualification rate, and an automatic power generation control performance indicator; monitoring the operation performance of the target generator set through the multi-source heterogeneous monitoring network according to the predetermined unit operation performance indicators, and obtaining unit operation performance monitoring data; reading predetermined unit operation performance standards, inputting the predetermined unit operation performance standards and the unit operation performance monitoring data into a unit performance analysis model, and obtaining unit performance analysis results; marking defective performance based on the unit performance analysis results, and generating performance defect warning information according to the defective performance marking results, wherein the performance defect warning information comprises a first warning level; when the first warning level reaches a preset warning level, regulating the operation parameters of the target generator set according to the defective performance marking results.

[0005] The second aspect disclosed in the present application provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the generator performance detection method for a multi-source heterogeneous big data platform in the first aspect.

[0006] The third aspect disclosed in the present application provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the generator performance detection method of the multi-source heterogeneous big data platform in the first aspect.

[0007] One or more technical solutions provided in this application have at least the following beneficial effects:

[0008] Utilizing a multi-source heterogeneous monitoring network, including remote terminal units, distributed control systems, and primary frequency regulation homologous devices, the operating performance of the target generator set can be monitored in real time. This real-time monitoring can timely capture deviations in performance indicators such as the primary frequency regulation contribution rate, small disturbance qualification rate, and automatic power generation control of the unit, ensuring that problems can be diagnosed and measures can be taken in the early stages to reduce potential risks. By inputting the unit's operating performance monitoring data and predetermined performance standards into the unit's performance analysis model, accurate performance analysis results can be generated. This process can accurately evaluate the unit's current operating status, discover performance defects in a timely manner, and generate defective performance markers and early warning signals. Information is collected to help operation and maintenance personnel make timely adjustments. When performance defects are found, an early warning level is automatically generated based on the defect performance mark, and the operating status of the unit is optimized in real time by adjusting the unit operating parameters. This optimization control improves the response speed and frequency regulation accuracy of the unit, ensuring that the unit always maintains the best working condition. Through comprehensive data processing based on the big data platform, it supports dynamic adjustment and optimization of unit performance, real-time data collection, statistical analysis and multi-source data fusion, ensuring the stability and reliability of the system. In addition, the big data platform can provide rich historical data support for future performance evaluation, laying the foundation for continuous optimization of the system and intelligent decision-making.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of a method for detecting generator performance on a multi-source heterogeneous big data platform is provided for an embodiment of the present application.

[0011] Figure 2A schematic diagram of the operating performance monitoring process in a generator performance detection method on a multi-source heterogeneous big data platform is provided for an embodiment of the present application.

[0012] Figure 3 A schematic diagram of the structure of an exemplary computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] The present application solves the technical problem that the generator performance detection in the prior art is usually performed through offline calculation or evaluation based on historical data, lacks the ability to monitor and adjust the unit performance in real time, resulting in insufficient system scheduling accuracy and flexibility by providing a generator performance detection method, medium and equipment for a multi-source heterogeneous big data platform.

[0014] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0015] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a generator performance detection method for a multi-source heterogeneous big data platform, the method comprising:

[0016] A multi-source heterogeneous monitoring network for a target generator set is constructed, wherein the multi-source heterogeneous monitoring network includes a remote terminal unit, a distributed control system, and a primary frequency modulation homologous device.

[0017] The remote terminal unit is used to collect various operating data of the generator set in real time. These data include important parameters such as temperature, pressure, current, voltage, etc. The remote terminal unit equipment is responsible for transmitting these data to the control center or data analysis platform through the communication network. Specifically, the remote terminal unit equipment is installed in the key parts of the generator set (such as generators, control devices, etc.), the equipment is configured to collect data with various systems of the generator set, and the equipment is set up for data transmission and feedback with other equipment to ensure efficient and reliable data transmission.

[0018] The distributed control system is a core platform for control and monitoring, responsible for receiving, processing and storing data from remote terminal units. It can perform real-time monitoring and adjust the operating status of the unit according to preset strategies. Specifically, the distributed control system is configured to ensure that it can receive various sensor data from the remote terminal units, set the processing algorithm and control logic of the distributed control system, and can judge the various performance indicators of the unit operation in real time based on the received data. The distributed control system can be dynamically adjusted according to control requirements, such as adjusting the power output and frequency modulation of the generator set.

[0019] The primary frequency regulation homologous device is used to support the frequency regulation function of the generator set to ensure the stability of the grid frequency. The device can automatically adjust the output power of the unit according to the grid frequency fluctuation to respond to the grid demand. Specifically, a primary frequency regulation homologous device is installed in the generator set to ensure that the equipment can receive the grid frequency signal in real time, configure the equipment to communicate with other systems such as remote terminal units and distributed control systems to ensure the synchronization of data and frequency regulation requirements, set the frequency regulation control strategy, and automatically adjust the output power of the generator set according to the actual situation of the grid frequency fluctuation to achieve real-time frequency regulation.

[0020] Through the collaboration of the above multi-source heterogeneous monitoring networks, the operating status of the generator sets can be monitored and adjusted in real time, and the needs of the power grid can be responded to in a timely manner, ensuring that the generator sets can efficiently and reliably support the operation of the power grid in terms of frequency regulation and peak regulation.

[0021] Read the predetermined unit operation performance indicators, wherein the unit operation performance indicators include primary frequency regulation contribution rate, small disturbance qualification rate, and automatic power generation control performance indicators.

[0022] The primary frequency regulation contribution rate refers to the ability of a generator set to respond to frequency modulation signals when the grid frequency fluctuates. Usually, changes in grid frequency will lead to a mismatch between power demand and power generation. The generator set needs to make real-time adjustments based on changes in grid frequency to maintain frequency stability. Specifically, the generator set's frequency modulation data is collected to calculate its response capability under specific frequency fluctuations. These data include information such as frequency changes and power output changes of the generator set.

[0023] The small disturbance pass rate refers to the ability of the generator set to effectively respond to smaller disturbances in the power grid (such as load changes or small frequency fluctuations). The higher the small disturbance pass rate, the more likely the generator set can operate stably under smaller power grid fluctuations and will not affect the security of the power grid. Specifically, historical data analysis and real-time data collection are used to evaluate the stability performance of the generator set when experiencing small disturbances. These disturbances include small load fluctuations or slight frequency changes. The pass rate can be measured by the number of times the computer group can recover to a stable state within a certain period of time. Qualified units show higher recovery speed and stability.

[0024] The automatic power generation control performance index refers to the ability of the generator set to automatically adjust its own output power to meet the grid load demand after the grid dispatching center issues a command. This index covers aspects such as regulation rate, response accuracy and stability. Specifically, its performance is evaluated by analyzing the data of the unit's automatic power generation control system. Usually, the automatic power generation control system will automatically adjust the unit's power output according to changes in the grid load to ensure grid load balance. Specific indicators include regulation accuracy (whether the target power can be accurately reached), regulation rate (whether the adjustment speed meets the requirements), and regulation stability (whether it can maintain a long-term stable operating state).

[0025] By reading and processing the operating data of the unit, we ensure that the performance of the generator set in frequency regulation, load fluctuation response and automatic regulation meets the predetermined standards, and continuously monitor and evaluate it. Through real-time analysis of these indicators, we can promptly discover problems in the operation of the unit and optimize and adjust the unit according to performance changes.

[0026] According to the predetermined unit operation performance index, the target generator set is monitored for operation performance through the multi-source heterogeneous monitoring network to obtain unit operation performance monitoring data.

[0027] The multi-source heterogeneous monitoring network includes data acquisition units of various sources and types. The monitoring network collects the unit's operating data through various sensors and terminal units based on the predetermined operating performance indicators. It also performs data cleaning and standardization processing to eliminate noise, fill in missing data, and ensure the accuracy and reliability of the monitoring data. It ultimately generates unit operating performance monitoring data, which includes all real-time data related to the predetermined operating performance indicators as the basis for the next step of analysis.

[0028] The predetermined unit operation performance standard is read, and the predetermined unit operation performance standard and the unit operation performance monitoring data are input into the unit performance analysis model to obtain the unit performance analysis result.

[0029] Read and refer to the predetermined unit operating performance standards, which are set based on historical data analysis, technical specifications and grid demand. The operating performance standards include reasonable ranges or qualified standards for various performance indicators, such as the standard value of the primary frequency regulation contribution rate, the target value of the small disturbance qualified rate, the requirements for AGC regulation accuracy, etc. These standards provide a basis for comparison for subsequent performance analysis and evaluation.

[0030] The unit operation performance monitoring data and the predetermined operation performance standards are input into the unit performance analysis model. The performance analysis model is used to analyze the current operation status of the unit and determine whether it meets the standards. The model contains multiple layers, among which the input layer is used to receive the actual monitoring data and the predetermined standards; the performance defect identification layer is used to analyze whether there are performance defects, such as insufficient frequency regulation response, low regulation accuracy, etc.; the performance defect analysis layer is used to further analyze the causes of the defects and provide solutions based on historical data and operation trends; the output layer is used to output the analysis results, including whether it meets the standards, the severity of the performance defects, possible improvement measures, etc. Based on the performance analysis model, the unit performance analysis results are generated, including the performance defect index, which is used to evaluate the performance of the unit in various indicators.

[0031] Defective performance marking is performed based on the unit performance analysis result, and performance defect warning information is generated according to the defective performance marking result, wherein the performance defect warning information includes a first warning level.

[0032] Defective performance marking refers to identifying and marking defects in unit operation based on the results of unit performance analysis. These defects include deviations in performance indicators such as insufficient frequency regulation response, low regulation accuracy, and slow regulation rate. First, potential performance defects are identified through the unit performance analysis model, which is specifically manifested as certain operating indicators failing to meet the predetermined performance standards. Based on these analysis results, performance markings are generated for each defect, such as low frequency contribution rate, small disturbance qualification rate not meeting the standards, etc. Each defect is marked as a certain type of performance problem, and these defects have different degrees of severity, which affect the subsequent decision-making of the system.

[0033] When the unit has performance defects, early warning information of the performance defects is generated. This information helps operation and maintenance personnel identify the problem early and take corresponding measures. The early warning information includes the defect type (such as poor frequency response, low AGC adjustment accuracy, etc.), defect severity, impact range (whether it is a local problem or a global problem), etc. The early warning information also includes the first warning level, that is, the threshold of the preliminary warning. This warning level is used to indicate the severity of the problem. The warning level is obtained through a comprehensive assessment of the type and severity of the defect. The warning level is generally divided into multiple levels, such as no alarm, mild alarm, moderate alarm, severe alarm, etc. Each warning level corresponds to different response measures and control strategies.

[0034] When the first warning level reaches a preset warning level, the operating parameters of the target generator set are regulated according to the defect performance marking result.

[0035] When the first warning level of performance defects reaches the preset warning threshold, the operating parameter adjustment is triggered. The preset warning threshold is the preset warning level, which can be set according to historical data, operating experience and grid demand. This threshold corresponds to the degree of deviation of a certain performance indicator. If the deviation reaches this value, it means that the unit may affect the stability of the grid and immediate measures must be taken. This setting ensures that unit intervention and parameter adjustment will only be carried out when the problem is more serious.

[0036] When the warning level reaches the standard, the operating parameters of the unit are automatically adjusted according to the defect performance marking results of the unit. The purpose of the regulation is to improve the frequency regulation capability, AGC performance, load regulation rate, etc. of the unit. Specifically, according to different types of defects, the frequency regulation control parameters of the generator set are adjusted, such as adjusting the primary frequency regulation contribution rate, the regulation accuracy of the AGC system, the regulation rate, etc. If the defect is caused by the slow response speed of the unit or the low regulation accuracy, the response speed of the AGC can be optimized or the flexibility of the regulation can be increased. The load adjustment strategy of the unit may also be adjusted to reduce load fluctuations and ensure the stable operation of the power grid. In some cases, intelligent optimization algorithms, such as particle swarm optimization algorithms and genetic algorithms, are used to dynamically optimize the operating parameters of the unit to achieve the maximum performance improvement and ensure that the unit can operate in a more efficient and stable state.

[0037] Furthermore, if Figure 2 As shown, the target generator set is monitored for operating performance according to the predetermined generator set operating performance indicator through the multi-source heterogeneous monitoring network to obtain generator set operating performance monitoring data, including:

[0038] The operation data of the target generator set is collected through the multi-source heterogeneous monitoring network to obtain multi-source heterogeneous operation monitoring data; the multi-source heterogeneous operation monitoring data is pre-processed through a data cleaning domain to obtain standard operation monitoring data, wherein the data cleaning domain includes a data denoising channel, a missing data filling channel, an abnormal data correction channel, and a data standardization channel; based on the predetermined unit operation performance indicators, the standard operation monitoring data is performance monitored to obtain the unit operation performance monitoring data.

[0039] The multi-source heterogeneous monitoring network realizes comprehensive monitoring of the target generator set through the joint work of multiple data acquisition systems of different sources and types. Specifically, various operating data of the unit are collected through the remote terminal unit (RTU) and distributed control system (DCS) equipment to obtain key parameters such as the generator set's power output, frequency regulation data, load fluctuation data, temperature, pressure, humidity, etc. The frequency modulation data collected by the primary frequency modulation homologous device and parameters related to the grid frequency are time series data, which records the changes in various operating parameters of the unit. This data provides a basis for subsequent analysis and processing.

[0040] The data cleaning domain is a module that performs a series of processing on the collected raw data. The purpose is to remove noise, correct outliers, fill missing data, and standardize the data to ensure data quality. The data cleaning domain includes multiple processing channels, among which the data denoising channel is used to remove noise and interference in the data. Usually, filtering algorithms such as low-pass filtering and high-pass filtering can be used to remove irrelevant signals outside the frequency range; the missing data filling channel is used to deal with missing data. Interpolation methods such as linear interpolation, spline interpolation, etc., or filling algorithms based on historical data are used to fill missing values; the abnormal data correction channel is used to deal with abnormal values ​​caused by equipment failure or acquisition errors. For example, extreme values ​​in the data may not conform to the actual situation and need to be identified and corrected by setting thresholds; the data standardization channel is used to unify the collected data into a standard range to ensure that data from different sources and different units can be directly compared. Standardization is usually performed by subtracting the mean and dividing by the standard deviation. After data cleaning, the standard operation monitoring data does not contain obvious noise and errors, and the missing data has been reasonably filled, the outliers have been corrected, and all data have been standardized on a unified scale.

[0041] Compare the standard operation monitoring data with the predetermined unit operation performance indicators, and perform performance monitoring based on these data. For example, based on the standard of primary frequency regulation contribution rate, monitor the unit's regulation ability when the grid frequency fluctuates; based on the small disturbance qualification rate, evaluate the unit's stability and response ability when the load fluctuates slightly; based on the AGC performance indicators, judge whether the unit can respond to the grid dispatch command quickly and accurately. Through these performance monitoring, the unit's operating status is evaluated in real time, and the unit's performance status is judged. The performance monitoring data obtained provides real-time data on various performance indicators of the unit, providing a basis for subsequent performance analysis and parameter control.

[0042] Furthermore, the reading of the predetermined unit operation performance standard includes:

[0043] Based on the target generator set, a generator set retrieval source is set, wherein the generator set retrieval source includes the target generator set and multiple generator sets of the same type as the target generator set; historical unit operation records are retrieved according to the generator set retrieval source, and a first historical unit operation record is extracted according to the retrieval result, and a first unit operation performance interval is identified, wherein the first unit operation performance standard includes a primary frequency regulation contribution rate interval, a small disturbance qualified rate interval, and an automatic power generation control performance interval; the retrieval results are traversed until the identification of the Nth unit operation performance interval is completed, and the intersection of the first unit operation performance interval to the Nth unit operation performance interval is screened to obtain the predetermined unit operation performance standard.

[0044] The generator set retrieval source is a collection of historical data and performance records related to the target generator set, where the target generator set is a specific generator set that is undergoing performance evaluation, and multiple similar generator sets of the target generator set are other generator sets that are similar to the target generator set in terms of technical specifications, performance requirements, functional configuration, etc. The data of these similar units can be used as a control group to obtain more extensive reference data.

[0045] From the generator set retrieval source, search according to the type, performance indicators, operation date and other conditions of the unit to obtain the historical operation records of the target unit and similar units. These records reflect the performance of the unit under different operating conditions and include the performance data of the unit in different operation stages (such as normal operation, frequency regulation, load fluctuation, etc.).

[0046] According to the retrieved historical records, the first historical unit operation record is randomly selected as the analysis object, and the indicator data related to the target unit performance is extracted from it to identify the operating performance range of the first unit. The performance range refers to the normal range of the performance indicator of the unit under different operating conditions. For example, the primary frequency regulation contribution rate has a minimum and a maximum value. Within this range, the unit can be considered to perform normally. Based on the historical records, the normal operating range of each performance indicator is identified, where the primary frequency regulation contribution rate range includes the minimum and maximum frequency regulation contributions of the unit under the frequency regulation response; the small disturbance qualified rate range is the performance range of the unit under small disturbance conditions; the AGC performance range is the normal range of AGC regulation accuracy, response time, etc.

[0047] All the retrieved historical unit operation records are traversed, the performance interval of each unit is extracted, all the retrieved historical operation data are analyzed, and the interval of its performance index is determined. Intersection screening is to perform intersection analysis on the performance intervals of different units to ensure that the operating performance standard of the target unit can cover the normal operating range that appears in all historical data. Specifically, the operating performance interval of the first unit and the operating performance intervals of other N-1 units are analyzed to screen out the interval set containing the normal performance range of all units. This intersection screening process ensures that the operating performance standard of the target unit covers the normal operating range of similar units and ensures the wide applicability of the standard. Through intersection screening, the predetermined operating performance standard of the target unit is finally determined. This standard provides a basis for subsequent performance monitoring and evaluation, ensuring that the target unit meets the requirements of the power grid during operation and can be reasonably adjusted and optimized.

[0048] Further, the performing intersection screening on the first unit operating performance interval to the Nth unit operating performance interval to obtain the predetermined unit operating performance standard includes:

[0049] When the intersection screening result is empty, perform pairwise enumeration calculations on the first unit operating performance interval to the Nth unit operating performance interval to obtain a unit operating performance interval distance set; traverse the unit operating performance interval distance set, perform interval outlier coefficient evaluation, and generate an interval outlier coefficient evaluation value set; according to the interval outlier coefficient evaluation value set, eliminate the unit operating performance intervals whose interval outlier coefficient evaluation values ​​are greater than or equal to the interval outlier coefficient threshold value to obtain a centralized unit operating performance interval set; based on the centralized unit operating performance interval set, perform intersection screening to obtain the predetermined unit operating performance standard.

[0050] When the performance interval obtained by intersection screening is empty, it means that the historical data of the target unit and similar units have no overlapping performance intervals. This may occur when the performance differences between the units are large or the data ranges are very inconsistent.

[0051] In order to address this problem, a pairwise enumeration calculation method is adopted, that is, the performance intervals of every two units are paired for analysis to obtain a reasonable set of performance intervals. Pairwise enumeration calculation refers to the combination and calculation of any two groups of operating performance intervals one by one, so as to determine the distance and overlapping range between the unit operating performance intervals. Specifically, for each pair of units, their performance intervals are compared and the distance between them is calculated. This distance represents the difference between the two units in the same performance indicators. Through pairwise enumeration calculation, the distance set between the unit performance intervals is obtained. This distance set represents the difference in performance indicators of different units and provides a basis for subsequent outlier identification and performance interval screening.

[0052] The interval outlier coefficient evaluation is used to assess whether there are obvious deviations in the performance intervals of different units. The outlier coefficient determines whether an interval is an abnormal interval by comparing the differences in the performance intervals of different units. If the difference is significant, the interval may be an outlier interval. Specifically, the interval outlier coefficient calculation formula is used to analyze the differences between the unit performance intervals. If the performance interval of a unit is significantly different from that of other units and is not within the normal operating range of most units, then the interval is considered to be an outlier interval. The calculation of the outlier coefficient can be based on indicators such as the standard deviation and average distance between the performance intervals of each unit. Usually, by comparing the deviations between the performance intervals of different units and the overall distribution, it is determined which intervals may be outliers.

[0053] The outlier coefficients of all calculated performance intervals are summarized, and the final outlier coefficient evaluation value set is the set of outlier coefficient results of all performance intervals generated by the outlier coefficient evaluation. Each performance interval will be assigned an outlier coefficient value, which indicates whether there is an abnormality in the interval. The outlier coefficient evaluation values ​​are usually sorted by numerical value. The higher the outlier coefficient, the less consistent the interval is with the overall distribution and the more likely it is to be an outlier. The outlier coefficient evaluation value set is used to further optimize the performance criteria to ensure that the selected interval best represents the stable operating state of the unit.

[0054] Set the interval outlier coefficient threshold, that is, when the outlier coefficient of a certain performance interval is greater than or equal to the threshold, it is considered that the performance interval may be abnormal and needs to be eliminated. For each unit performance interval in the outlier coefficient evaluation value set, check whether its outlier coefficient is greater than or equal to the set outlier coefficient threshold. If the outlier coefficient of a unit's performance interval exceeds the threshold, it indicates that the performance of the unit is significantly different from that of other units, so it is considered abnormal and should be eliminated. After eliminating these performance intervals, what remains is the screened set of centralized unit operation performance intervals. These intervals represent the typical performance of each unit under normal operating conditions, which can better reflect the normal operating conditions of most units and provide a more reliable basis for performance standards. By eliminating abnormal data, the unit performance intervals used are more accurate and consistent, avoiding the interference of abnormal values ​​on performance standards.

[0055] Based on the centralized unit performance interval set, intersection screening is performed, that is, all these performance intervals are subjected to intersection analysis to ensure that the obtained performance standards can cover the performance of all normal units. The results of intersection screening provide a comprehensive set of performance intervals, which cover the performance range of all units under normal operating conditions. The performance standards obtained in this way can be applied to different types of units at the same time without deviation due to the special performance of certain units.

[0056] Furthermore, the method of inputting the predetermined unit operation performance standard and the unit operation performance monitoring data into a unit performance analysis model to obtain a unit performance analysis result includes:

[0057] Construct the unit performance analysis model, wherein the unit performance analysis model includes an input layer, a performance defect identification layer, a performance defect analysis layer, and an output layer; input the predetermined unit operation performance standard and the unit operation performance monitoring data into the performance defect identification layer through the input layer, perform performance defect identification, and obtain a unit performance defect identification result; input the unit performance defect identification result into the performance defect analysis layer to obtain a unit performance analysis result, wherein the unit performance analysis result includes a performance defect index; and output the unit performance analysis result through the output layer.

[0058] Construct a unit performance analysis model. The unit performance analysis model is a multi-level analysis system designed to process unit operation data and identify its performance defects. The model consists of multiple levels, each of which is responsible for different functions. Among them, the input layer receives data from the outside, including the predetermined unit operation performance standards and the actual unit operation monitoring data. The task of this layer is to prepare the data and pass it to the next layer of the model; the main function of the performance defect identification layer is to analyze the input data, identify potential performance defects, and judge the abnormalities or non-standard places in the data; the performance defect analysis layer further analyzes the identified defects after defect identification, including the diagnosis of the cause of the defect and the assessment of the scope of influence. This layer analyzes the data through complex algorithms to find the root cause of the performance problem; the output layer outputs the analysis results in an easy-to-understand way, including the unit's performance report, defect diagnosis, optimization suggestions, etc. The results of the output layer are usually displayed in numerical or visual ways to facilitate users to make subsequent decisions. The model can process a large amount of unit operation data, automatically identify and report performance problems, and greatly improve the efficiency and accuracy of performance monitoring.

[0059] The predetermined unit operation performance standards and unit operation performance monitoring data are input into the performance defect identification layer through the input layer. The function of the input layer is to standardize or format the data to adapt it to the processing requirements of the performance defect identification layer. In the performance defect identification layer, the difference between the predetermined performance standards and the actual monitoring data is analyzed, and potential performance defects are identified through comparison. After being processed by the performance defect identification layer, the unit performance defect identification results are obtained, including defect types, such as insufficient primary frequency regulation contribution rate, slow AGC response, etc.; defect severity, that is, according to the degree of impact of the defect, a defect severity assessment is given, such as mild defects, severe defects, etc.; the performance range where the defect is located, so as to clearly point out which performance indicators of the unit have problems, such as frequency regulation, load response, etc.

[0060] The unit performance defect identification results are passed to the performance defect analysis layer. The task of this layer is to further analyze the identified defects, diagnose the root causes of the problems, and quantitatively evaluate the impact of the defects. Specifically, the defect types are classified and deeply analyzed. For example, determine which factors (such as equipment failure, scheduling delays, environmental changes, etc.) may lead to a decrease in the frequency regulation contribution rate, and use data analysis or machine learning algorithms to further analyze the causes of the defects. For example, through regression analysis, decision tree analysis and other methods, find out the key factors that cause the defects. Finally, the performance defect analysis layer outputs detailed performance analysis results about the unit, including the performance defect index, which quantifies the overall performance defects of the unit. Usually, it is calculated based on multiple performance indicators (such as frequency regulation contribution rate, AGC accuracy, etc.), reflecting the degree of deviation of the overall operating status of the unit. The performance defect index is used to measure the gap between the unit performance and the predetermined standard, and provide a basis for subsequent adjustments and optimizations.

[0061] The output layer outputs the unit performance analysis results, for example, presents the unit performance analysis results in the form of reports, including charts, data tables, etc., to facilitate operators to review in detail and make corresponding adjustments and optimizations. These output results provide an important basis for the maintenance and optimization of unit operations, ensuring that the unit can remain in the best operating state.

[0062] Furthermore, after obtaining the unit performance analysis results, it also includes:

[0063] Reading a predetermined performance defect constraint feature, determining whether the performance defect index satisfies the predetermined performance defect constraint feature; if the performance defect index does not satisfy the predetermined performance defect constraint feature, generating a first warning level according to the degree of deviation of the performance defect index.

[0064] The predetermined performance defect constraint characteristics are a series of standards set during the design to measure the ideal or acceptable range of unit performance. These characteristics are set based on historical data, industry standards or grid requirements, and cover the performance deviation range that the unit can withstand during operation. For example, the minimum and maximum values ​​are set for the primary frequency regulation contribution rate. When the unit's contribution rate exceeds this range, it indicates a performance defect. The performance defect index is compared with the predetermined performance defect constraint characteristics to determine whether the current unit's performance meets these predetermined constraints. If the unit's performance defect index is within the constraint range, it indicates that the unit is operating normally. On the contrary, if it deviates from the preset constraint characteristics, it indicates that the unit has performance problems and requires further regulation or optimization.

[0065] The degree of deviation indicates the gap between the unit's performance defect index and the predetermined performance defect constraint characteristics. This deviation is obtained by calculating the difference between the numerical value of the performance defect index and the standard value. If the unit's performance defect index obviously exceeds the predetermined constraint range, the degree of deviation is large; if the magnitude of the excess is small, the degree of deviation is small.

[0066] The warning level is used to indicate the severity of the defect. The warning level can be divided into multiple levels, such as mild, moderate, severe, etc. Based on the degree of deviation of the unit performance defect index, the first warning level is generated. For example, if the degree of deviation is small (that is, the performance defect index slightly exceeds the predetermined standard), a mild warning is generated, indicating that the unit operation is still within an acceptable range, but needs to be monitored; if the degree of deviation is large (that is, the performance defect index far exceeds the predetermined standard), a higher warning level is generated, and immediate measures need to be taken to adjust or optimize. By generating the first warning level, potential problems in the unit operation can be promptly reminded, and operation and maintenance personnel can be helped to determine whether more active intervention measures are needed to ensure that the unit's operating performance returns to normal.

[0067] Furthermore, after constructing the unit performance analysis model, it also includes:

[0068] The unit performance analysis model is evaluated for analysis effect to obtain the unit performance analysis accuracy; if the unit performance analysis accuracy does not reach a preset accuracy threshold, the accuracy deviation of the unit performance analysis accuracy is calculated as a model optimization deviation; and the unit performance analysis model is optimized and trained based on the model optimization deviation.

[0069] The purpose of evaluating the analysis effect of the unit performance analysis model is to test the performance of the model on actual data and judge its accuracy, reliability and effectiveness. The model evaluation is carried out by comparing the analysis results output by the model with the actual situation. Specifically, a set of real unit data is collected, which can be the performance data collected by the unit during the past operation process. These actual data are input into the unit performance analysis model to generate analysis results. The generated analysis results are compared with the actual unit operation performance to judge the deviation between the model output and the actual performance. During the evaluation process, some standardized indicators such as accuracy, precision, recall rate, etc. are used to quantify the performance of the model. Accuracy is the most commonly used evaluation standard, which indicates the consistency between the model analysis results and the true value. For example, if the defect type predicted by the model is consistent with the defect type actually monitored, it is evaluated as accurate. Through the evaluation, it can be judged whether the current performance analysis model is accurate enough and whether it can correctly identify the performance problems of the unit. If the evaluation results show that the model accuracy is not high enough, the next step of the optimization process is entered.

[0070] The accuracy deviation indicates the gap between the output of the unit performance analysis model and the actual performance standard. If there is a large deviation between the performance analysis results output by the model and the actual monitoring value, the accuracy deviation is large, otherwise the deviation is small. The accuracy deviation of the model is calculated by comparing the gap between the defect index and performance standard of the model analysis and the actual unit performance data. Specifically, the calculation method such as absolute error and relative error can be used. The calculated accuracy deviation is used as the model optimization deviation to provide data support for subsequent optimization training and help identify the parts of the model that need to be improved.

[0071] Based on the calculated model optimization deviation, the unit performance analysis model is optimized. For example, the gradient descent method is used to adjust the model parameters by calculating the gradient of the error, so that the model output is closer to the actual value. The model is optimized through multiple iterations until the accuracy deviation drops below the preset threshold to ensure that the model has sufficient accuracy. Optimization training also includes data enhancement, feature selection or model structure adjustment to ensure that the model can adapt to various operating environments and unit types. Through optimization training, the accuracy of the unit performance analysis model is improved to ensure that it can accurately reflect the operating status and potential problems of the unit, thereby improving the efficiency of performance monitoring and defect warning.

[0072] Furthermore, the method for regulating the operating parameters of the target generator set according to the defect performance marking result includes:

[0073] According to the defect performance marking result, the operation data of the target generator set is traced to obtain the unit operation performance monitoring defect data; the defect cause analysis is performed on the unit operation performance monitoring defect data to obtain the unit defect cause information; using the particle swarm optimization algorithm, the unit operation parameter optimization analysis is performed according to the unit operation performance monitoring defect data and the unit defect cause information to obtain the unit operation optimization parameters; the operation of the target generator set is controlled according to the unit operation optimization parameters.

[0074] The defective performance marking results are the unit performance problems identified in the previous analysis steps based on the unit's performance monitoring data and predetermined operating standards. These marking results indicate which performance indicators of the unit have defects. These markings include the type of defect (such as insufficient frequency contribution), the severity of the defect (such as mild, moderate or severe defects), and the time when the defect occurred or the specific operating conditions.

[0075] Based on the defect marking results, the historical operating data of the unit is traced back to identify the source of the defect problem. Through tracing, it is determined at which operation or operation stage the unit deviated, and finally the unit operation performance monitoring defect data is obtained. These data reflect the specific situation when the defect occurred, the performance of the unit and possible abnormal factors.

[0076] Defect cause analysis aims to identify the root causes of unit performance defects. Through in-depth analysis of various data during the operation of the unit, specific factors affecting the performance of the unit, such as hardware failure, improper control strategy, environmental changes, etc., are found. Specifically, data mining and pattern recognition methods are used to analyze historical data and use data mining and pattern recognition technology to identify potential factors related to defects. For example, under certain specific conditions (such as large load changes), the response accuracy of the unit deteriorates, resulting in performance defects; regression analysis methods are used to determine the degree of influence of different factors (such as fuel quality, operating mode, etc.) on unit performance through regression analysis, and find out the key factors that are most likely to cause performance defects. Through defect cause analysis, unit defect cause information is generated, including defect type and cause, influencing factors, and potential risk assessment. Through defect cause analysis, specific cause diagnosis can be provided, providing a basis for subsequent optimization and adjustment.

[0077] The particle swarm optimization algorithm is an optimization algorithm that simulates the foraging behavior of particle groups in nature. It is used to solve complex optimization problems. The algorithm continuously updates the position of each particle in the group to find the global optimal solution. In the optimization of unit operating parameters, the particle swarm algorithm can be used to find the optimal unit operating parameters to improve the performance of the unit. Specifically, firstly, multiple particles are randomly initialized, each particle represents a possible solution, that is, a combination of a set of unit operating parameters. For each particle, its fitness is calculated. The fitness function is based on the unit's operating defects and optimization objectives, such as maximizing the primary frequency modulation contribution rate, minimizing the response delay, etc. The particle swarm optimization algorithm updates the position of the particle, that is, the unit's operating parameters, according to the fitness of each particle and the current optimal solution, so as to find a better solution. Through multiple iterations, the unit operating parameters are gradually optimized until the optimal solution is found. Through the particle swarm optimization algorithm, the best unit operating parameters are found in the multidimensional space. These parameters can optimize the unit performance to the greatest extent, reduce defects, and meet the needs of power grid dispatching.

[0078] The optimized operating parameters are transmitted to the control system of the unit, and the various operating parameters of the unit are adjusted in real time through the control system, including adjusting the response time and regulation accuracy of the unit when the grid frequency changes, and optimizing the load regulation strategy of the unit according to the grid load changes to ensure that the unit can smoothly adapt to load fluctuations, and adjusting the automatic power generation control parameters of the unit according to the optimization results to ensure that it can accurately and quickly respond to grid dispatch instructions. By controlling according to the optimized unit operating parameters, it is ensured that the unit can achieve the best performance in actual operation and meet the frequency regulation and peak regulation requirements of the grid.

[0079] In summary, the generator performance detection method of the multi-source heterogeneous big data platform provided in the embodiment of the present application has the following technical effects:

[0080] Utilizing a multi-source heterogeneous monitoring network, including remote terminal units, distributed control systems, and primary frequency regulation homologous devices, the operating performance of the target generator set can be monitored in real time. This real-time monitoring can timely capture deviations in performance indicators such as the primary frequency regulation contribution rate, small disturbance qualification rate, and automatic power generation control of the unit, ensuring that problems can be diagnosed and measures can be taken in the early stages to reduce potential risks. By inputting the unit's operating performance monitoring data and predetermined performance standards into the unit's performance analysis model, accurate performance analysis results can be generated. This process can accurately evaluate the unit's current operating status, discover performance defects in a timely manner, and generate defective performance markers and early warning signals. Information is collected to help operation and maintenance personnel make timely adjustments. When performance defects are found, an early warning level is automatically generated based on the defect performance mark, and the operating status of the unit is optimized in real time by adjusting the unit operating parameters. This optimization control improves the response speed and frequency regulation accuracy of the unit, ensuring that the unit always maintains the best working condition. Through comprehensive data processing based on the big data platform, it supports dynamic adjustment and optimization of unit performance, real-time data collection, statistical analysis and multi-source data fusion, ensuring the stability and reliability of the system. In addition, the big data platform can provide rich historical data support for future performance evaluation, laying the foundation for continuous optimization of the system and intelligent decision-making.

[0081] Embodiment 2 provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, any step of embodiment 1 is implemented.

[0082] Embodiment three, as Figure 3 The figure is a schematic diagram of the structure of an exemplary computer device of the present application. Figure 3 In the embodiment, the bus architecture is represented by bus 300, which may include any number of interconnected buses and bridges, and bus 300 connects various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, namely a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when performing operations.

[0083] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A generator performance detection method based on a multi-source heterogeneous big data platform, characterized in that: The method comprises: Constructing a multi-source heterogeneous monitoring network for a target generator set, wherein the multi-source heterogeneous monitoring network includes a remote terminal unit, a distributed control system, and a primary frequency modulation homologous device; Reading predetermined unit operation performance indicators, wherein the unit operation performance indicators include primary frequency regulation contribution rate, small disturbance qualification rate, and automatic power generation control performance indicators; According to the predetermined unit operation performance index, the target generator set is monitored for operation performance through the multi-source heterogeneous monitoring network to obtain unit operation performance monitoring data; Reading a predetermined unit operation performance standard, inputting the predetermined unit operation performance standard and the unit operation performance monitoring data into a unit performance analysis model, and obtaining a unit performance analysis result; Performing defective performance marking based on the unit performance analysis result, and generating performance defect warning information according to the defective performance marking result, wherein the performance defect warning information includes a first warning level; When the first warning level reaches a preset warning level, the operating parameters of the target generator set are regulated according to the defect performance marking result.

2. The generator performance detection method for a multi-source heterogeneous big data platform according to claim 1, characterized in that: The step of monitoring the target generator set's operating performance according to the predetermined generator set operating performance indicator through the multi-source heterogeneous monitoring network to obtain the generator set's operating performance monitoring data includes: Collecting operation data of the target generator set through the multi-source heterogeneous monitoring network to obtain multi-source heterogeneous operation monitoring data; Preprocessing the multi-source heterogeneous operation monitoring data through a data cleaning domain to obtain standard operation monitoring data, wherein the data cleaning domain includes a data denoising channel, a missing data filling channel, an abnormal data correction channel, and a data standardization channel; Based on the predetermined unit operation performance index, performance monitoring is performed on the standard operation monitoring data to obtain the unit operation performance monitoring data.

3. The generator performance detection method for a multi-source heterogeneous big data platform according to claim 1, characterized in that: The reading of the predetermined unit operation performance standard includes: Based on the target generator group, a generator group search source is set, wherein the generator group search source includes the target generator group and multiple generator groups of the same type as the target generator group; Performing a historical unit operation record search according to the generator unit search source, extracting a first historical unit operation record according to the search result, and identifying a first unit operation performance interval, wherein the first unit operation performance standard includes a primary frequency regulation contribution rate interval, a small disturbance qualified rate interval, and an automatic power generation control performance interval; The search results are traversed until the Nth unit operation performance interval is identified, and intersection screening is performed on the first unit operation performance interval to the Nth unit operation performance interval to obtain the predetermined unit operation performance standard.

4. The generator performance detection method for a multi-source heterogeneous big data platform according to claim 3 is characterized in that: The performing intersection screening on the first unit operation performance interval to the Nth unit operation performance interval to obtain the predetermined unit operation performance standard includes: When the intersection screening result is empty, performing enumeration calculations on the first unit operating performance interval to the Nth unit operating performance interval in pairs to obtain a unit operating performance interval distance set; Traversing the unit operation performance interval distance set, performing interval outlier coefficient evaluation, and generating an interval outlier coefficient evaluation value set; According to the interval outlier coefficient evaluation value set, the unit operation performance intervals whose interval outlier coefficient evaluation values ​​are greater than or equal to the interval outlier coefficient threshold are eliminated to obtain a centralized unit operation performance interval set; Based on the centralized unit operating performance interval set, intersection screening is performed to obtain the predetermined unit operating performance standard.

5. The generator performance detection method for a multi-source heterogeneous big data platform according to claim 1, characterized in that: The method of inputting the predetermined unit operation performance standard and the unit operation performance monitoring data into the unit performance analysis model to obtain the unit performance analysis result includes: Constructing the unit performance analysis model, wherein the unit performance analysis model includes an input layer, a performance defect identification layer, a performance defect analysis layer, and an output layer; Inputting the predetermined unit operation performance standard and the unit operation performance monitoring data into the performance defect identification layer through the input layer, performing performance defect identification, and obtaining a unit performance defect identification result; Inputting the unit performance defect identification result into the performance defect analysis layer to obtain a unit performance analysis result, wherein the unit performance analysis result includes a performance defect index; The unit performance analysis result is output through the output layer.

6. The generator performance detection method of the multi-source heterogeneous big data platform according to claim 5 is characterized in that: After obtaining the unit performance analysis results, it also includes: Reading a predetermined performance defect constraint feature, and determining whether the performance defect index satisfies the predetermined performance defect constraint feature; If the performance defect index does not satisfy the predetermined performance defect constraint feature, a first warning level is generated according to the degree of deviation of the performance defect index.

7. The generator performance detection method for a multi-source heterogeneous big data platform according to claim 5, characterized in that: After constructing the unit performance analysis model, it also includes: Evaluating the analysis effect of the unit performance analysis model to obtain the unit performance analysis accuracy; If the unit performance analysis accuracy does not reach a preset accuracy threshold, calculating the accuracy deviation of the unit performance analysis accuracy as a model optimization deviation; The unit performance analysis model is optimized and trained based on the model optimization deviation.

8. The generator performance detection method for a multi-source heterogeneous big data platform according to claim 1, characterized in that: The method of regulating the operating parameters of the target generator set according to the defect performance marking result includes: According to the defect performance marking result, the operating data of the target generator set is traced to obtain the defect data of the generator set operating performance monitoring; Performing defect cause analysis on the unit operation performance monitoring defect data to obtain unit defect cause information; Using a particle swarm optimization algorithm, performing unit operation parameter optimization analysis based on the unit operation performance monitoring defect data and the unit defect cause information to obtain unit operation optimization parameters; The operation of the target generator set is controlled according to the unit operation optimization parameters.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the generator performance detection method for a multi-source heterogeneous big data platform described in any one of claims 1 to 8 are implemented.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: The processor executes the computer program to implement the steps of the generator performance detection method for a multi-source heterogeneous big data platform according to any one of claims 1 to 8.

Images