Intelligent monitoring method based on power plant comprehensive monitoring platform

Abstract

The invention discloses an intelligent monitoring method based on a power plant comprehensive monitoring platform, and relates to the technical field of power plant monitoring, and the method specifically comprises the following steps: obtaining the load response characteristic information of each unit in real time, carrying out the analysis after the obtaining, and generating the load response coefficient and the load adaptation coefficient of each unit; and constructing a load scheduling evaluation model for the generated load response coefficient and the load adaptation coefficient of each unit, generating a load scheduling evaluation coefficient of each unit, performing analysis after generation, and evaluating the load response degree of each unit in the power plant generator set. Dividing each unit into a high-response unit, a medium-response unit and a low-response unit according to an evaluation result. According to the method, the problem of unbalanced power plant unit load scheduling when the power grid load rapidly fluctuates is solved, and the accuracy of power plant load response and the system stability are improved through real-time monitoring and dynamic scheduling optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of power plant monitoring, and in particular to an intelligent monitoring method based on a comprehensive monitoring platform of a power plant. Background Art

[0002] The integrated monitoring platform of a power plant is an efficient system that integrates multiple monitoring, control and management functions. It is designed to comprehensively monitor and manage various types of equipment, facilities and overall operation of the power plant. The platform usually covers multiple modules such as equipment status monitoring, fault diagnosis, performance analysis, energy efficiency management, data storage and analysis, and can obtain the operating data of various types of equipment in the power plant in real time, and summarize, analyze and process them. The core purpose of the integrated monitoring platform of a power plant is to provide a centralized operation interface through integrated management to help power plant operators to grasp the working status of various parts of the power plant in real time, so as to achieve comprehensive monitoring and control of the power plant operation process. The necessity of intelligent monitoring based on this platform lies in that with the increasing complexity of power plant equipment, traditional manual inspections and single monitoring methods can no longer meet the growing safety, efficiency and economy requirements. With the help of advanced technologies such as artificial intelligence, big data and machine learning, intelligent monitoring can analyze various types of operating data in real time, automatically identify potential faults, perform predictive maintenance, and intelligently optimize the operation strategy of the power plant. Through intelligent analysis, the system can not only improve the safety and stability of power plant operation, but also significantly reduce the failure rate, optimize maintenance resources, and reduce manual inspection costs, thereby improving the overall operational efficiency and economic benefits of the power plant. Therefore, intelligent monitoring based on the power plant comprehensive monitoring platform can greatly improve the intelligence and automation level of power plant management, which is the key to promoting the modernization of power plants and enhancing their core competitiveness.

[0003] The existing intelligent monitoring technology based on the integrated monitoring platform of power plants mainly realizes comprehensive monitoring of power plant equipment through multi-level data collection, transmission, processing and analysis. First, various equipment in the power plant continuously collects operating data through sensors and measuring instruments, including key parameters such as temperature, pressure, vibration, flow, etc., and these data are transmitted to the integrated monitoring platform through a real-time transmission system. The platform stores these large-scale data in a unified manner and uses advanced data processing technology for preliminary screening and cleaning. Subsequently, the platform uses big data analysis and artificial intelligence algorithms, such as machine learning and deep learning, to conduct in-depth analysis of the data to evaluate the operating status of the equipment in real time, identify potential faults or abnormal trends, and warn of possible future equipment failures through trend prediction and pattern recognition. If the system finds an abnormality or fault, the intelligent monitoring system will automatically trigger the alarm mechanism, notify the operator in time, and provide the fault type, possible cause and handling suggestions. In addition, the platform can also combine historical operating data and real-time monitoring data to adjust the power plant's operating strategy through optimization algorithms, thereby realizing intelligent optimization management of power plant operations. Through this comprehensive intelligent monitoring technology, power plants can manage equipment operations more efficiently, detect and resolve potential problems in advance, and greatly improve the safety, stability and overall operational efficiency of equipment.

[0004] The prior art has the following deficiencies:

[0005] In the case of rapid fluctuations in grid load, the load dispatching of power plant generator sets may be unbalanced because of differences in the load response characteristics of different units. Due to different manufacturing batches of units, some units have slow load responses, especially when grid load fluctuates greatly. Existing technologies fail to identify the response characteristics of these units in a timely manner, and fail to flexibly adjust dispatching according to their response capabilities. This is because the existing technologies fail to identify and dynamically adjust the response time and load carrying capacity of each unit in real time during the dispatching process, resulting in some units being unable to adjust their output power in a timely manner when grid load fluctuates sharply, causing uneven load distribution. In this way, some units may operate overloaded, increasing equipment losses and failure risks, and may even affect the stability of the grid, increase system maintenance costs, and reduce the overall energy efficiency of the power plant.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide an intelligent monitoring method based on a comprehensive monitoring platform of a power plant to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: an intelligent monitoring method based on a comprehensive monitoring platform of a power plant, specifically comprising the following steps:

[0009] During the grid load fluctuation process, the grid load fluctuation degree is detected in real time, and when the grid load fluctuation is detected to exceed the set threshold, each unit in the power plant generator set is identified and marked;

[0010] Obtain the load response characteristic information of each unit in real time, analyze it after acquisition, and generate the load response coefficient and load adaptation coefficient of each unit respectively;

[0011] A load dispatch evaluation model is constructed for the load response coefficient and load adaptation coefficient of each unit, and the load dispatch evaluation coefficient of each unit is generated. After the generation, the load response degree of each unit in the power plant generator unit is evaluated, and each unit is divided into a high-response unit, a medium-response unit and a low-response unit according to the evaluation results;

[0012] According to the classification results of each unit, corresponding load dispatch strategies are adopted for high-response units, medium-response units and low-response units respectively;

[0013] Continuously monitor the operating status of each unit and dynamically adjust the load scheduling strategy based on real-time monitoring results to ensure the balance of power plant load scheduling and efficient and stable system operation.

[0014] Preferably, the load response characteristic information of each unit is acquired in real time, and analyzed after acquisition to generate the load response coefficient and load adaptation coefficient of each unit respectively, which specifically includes the following steps:

[0015] Obtain the load response characteristic information of each unit in real time and perform preprocessing after acquisition;

[0016] Extracting load fluctuation information and response capability information from the pre-processed load response characteristic information of each unit;

[0017] The extracted load fluctuation information and response capability information are analyzed to generate the load response coefficient and load adaptation coefficient of each unit respectively.

[0018] Preferably, the logic for obtaining the load response coefficient of each unit is as follows:

[0019] Extract the load fluctuation information from the pre-processed load response characteristic information of each unit, including the instantaneous voltage change value, instantaneous current change value and response delay time of each unit at different times during a period of time during the load fluctuation process of the power plant, and use the function SV i (t), IR i (t) and TPi (t), t is the time point, SV i (t) represents the instantaneous voltage change value of the i-th unit at time t during a period of time during the load fluctuation of the power plant, IR i (t) represents the instantaneous current change value of the i-th unit at time t during a period of time during the load fluctuation of the power plant, TP i (t) represents the response delay time of the i-th unit at time t during a period of time during the load fluctuation of the power plant, and the time period is defined as [t1, t2], i = 1, 2, 3, ..., k, and k is a positive integer;

[0020] Calculate the load response coefficient of each unit. The specific calculation formula is as follows:

[0021]

[0022] In the formula, LRC i is the load response coefficient of the ith unit.

[0023] Preferably, the logic for obtaining the load adaptation coefficient of each unit is as follows:

[0024] Extract the response capacity information from the pre-processed load response characteristic information of each unit, including the actual output power value of each unit at different times during a period of time during the load fluctuation of the power plant, the frequency of power adjustment, and the maximum load that each unit can withstand, and calibrate them as and DPL i , It represents the actual output power value of the i-th unit at time m during a period of time during the load fluctuation of the power plant. It indicates the frequency of power regulation of the i-th unit at time m during a period of time during load fluctuation of the power plant. i represents the maximum load that the i-th unit can bear, i = 1, 2, 3, ..., k, m = 1, 2, 3, ..., g, k and g are both positive integers;

[0025] Calculate the load adaptation coefficient of each unit. The specific calculation formula is as follows:

[0026]

[0027] Where LAC i is the load adaptation coefficient of the ith unit.

[0028] Preferably, a load dispatching evaluation model is constructed for the generated load response coefficient and load adaptation coefficient of each unit to generate the load dispatching evaluation coefficient of each unit, which specifically includes the following steps:

[0029] Collect the load response coefficients, load adaptation coefficients and corresponding load dispatch evaluation coefficients of several units generated in the past period of time, and calibrate them as and x represents the number of load response coefficients, load adaptation coefficients and corresponding load dispatch evaluation coefficients of several units generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time are formed into a historical data set;

[0030] The multivariate regression model is selected as the load dispatch evaluation model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula:

[0031]

[0032] Where β0, β1 and β2 are regression coefficients;

[0033] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined;

[0034] Using the final regression coefficient, the load response coefficient LRC of each unit generated in real time is input into the constructed load dispatch evaluation model. i and load adaptation factor LAC i , generate the load dispatch evaluation coefficient LDEC of each unit in real time i .

[0035] Preferably, the load dispatch evaluation coefficient LDEC of each unit generated is i and the pre-set load dispatch evaluation coefficient threshold interval [LDEC min , LDEC max ] to compare, and evaluate the load response of each unit in the power plant generator set according to the comparison results, and divide each unit into high-response unit, medium-response unit and low-response unit according to the evaluation results. The specific comparison analysis and division are as follows:

[0036] If LDEC i <LDEC min , the load response degree of the unit among the power plant's generating units is low, and the unit is classified as a low-response unit;

[0037] If LDEC min ≤LDEC i ≤LDEC max , the load response degree of the unit among the power plant's generating units is medium, and the unit is classified as a medium response unit;

[0038] If LDEC i>LDEC max The load response degree of this unit among the power plant's generating units is high, and the unit is classified as a high-response unit.

[0039] Preferably, according to the division results of each unit, corresponding load dispatch strategies are adopted for high-response units, medium-response units and low-response units, specifically:

[0040] For units classified as low-response units, the specific load dispatching strategy is as follows: when the grid load fluctuation is small, the current load output of the unit is maintained without dispatching adjustments; when the grid load fluctuation is large, the load output of the low-response unit is reduced first to avoid overload operation due to slow response, and at the same time, its load fluctuation is monitored in real time to ensure that it does not cause instability to the grid;

[0041] For the units classified as medium-response units, the load dispatching strategy adopted is as follows: in the case of large grid load fluctuations, the load output of the medium-response units is adjusted in real time to ensure that their load response is balanced with grid fluctuations; at the same time, according to the response time and regulation capacity of the units, the dispatching strategy is dynamically adjusted to ensure that the units can respond in time during fluctuations;

[0042] For units classified as high-response units, the load scheduling strategy adopted is as follows: give priority to increasing the load output of high-response units so that they can quickly adjust to grid load fluctuations; at the same time, monitor their load adjustment capabilities and output power in real time to ensure that the units can efficiently and smoothly respond to rapid fluctuations in grid load, and perform dynamic optimization scheduling to reduce wear and loss of the units and ensure the stable operation of the grid and power plants.

[0043] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0044] 1. The present invention realizes accurate load scheduling by real-time monitoring and analysis of the load response characteristics of each unit in the power plant. By collecting key data such as the instantaneous voltage change, instantaneous current change, and response delay of each unit, the load response coefficient and load adaptation coefficient are calculated, and the load response capability of each unit can be accurately evaluated. This refined evaluation method avoids the "one-size-fits-all" approach in traditional scheduling methods, making the load scheduling of power plants more personalized and accurate. By classifying the units and combining them with the real-time grid load fluctuations, the imbalance of unit loads is effectively reduced, and the risk of damage or failure of equipment due to overload operation is avoided, thereby improving the overall operation stability of the power plant.

[0045] 2. The present invention constructs a load scheduling evaluation model based on load response coefficient and load adaptation coefficient through the accumulation and regression analysis of historical data, and optimizes it using the regression coefficient. The model can flexibly adjust the load scheduling strategy of each unit according to the real-time changes in the grid load fluctuations. Unlike traditional fixed scheduling strategies, this dynamic adjustment mechanism can quickly respond and optimize the scheduling plan when the grid load fluctuates rapidly, ensuring that the load regulation capability of each unit can be consistent with the grid fluctuations, avoiding the problem of over-scheduling or scheduling lag. This optimized scheduling strategy can improve the load response efficiency of the power plant while reducing the operating cost and maintenance risk of the unit.

[0046] 3. The present invention realizes the intelligence and automation of power plant dispatching, and further improves the operating efficiency and economy of the power plant. Through real-time monitoring, data analysis and model optimization, the entire dispatching process can realize automatic adjustment without human intervention, reducing the errors and efficiency losses that may be caused by manual dispatching. At the same time, the present invention can perform adaptive optimization according to the response capabilities and dispatching requirements of different units, thereby avoiding the human factors and blindness in traditional dispatching methods. By reducing equipment failures and downtime, the overall energy efficiency of the power plant is improved, and the operation and maintenance costs are reduced. In addition, the dynamic dispatching strategy based on the intelligent monitoring system also provides the power plant with a more flexible response mechanism, which can cope with the complex changes in future power grid load fluctuations, improve the stability and adaptability of the power plant in a complex operating environment, and ensure the long-term safe and stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0048] Figure 1 The present invention is a flow chart of an intelligent monitoring method based on a comprehensive monitoring platform of a power plant. DETAILED DESCRIPTION

[0049] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0050] The present invention provides Figure 1 An intelligent monitoring method based on a power plant integrated monitoring platform is shown, which specifically includes the following steps:

[0051] During the grid load fluctuation process, the grid load fluctuation degree is detected in real time, and when the grid load fluctuation is detected to exceed the set threshold, each unit in the power plant generator set is identified and marked;

[0052] During the load fluctuation of the power grid, real-time detection of the degree of load fluctuation of the power grid can be achieved through a multi-dimensional data acquisition system. Multiple monitoring nodes distributed in the power grid collect parameters such as voltage, current, frequency and power in real time through sensors. For real-time monitoring of power grid load fluctuations, the data acquisition frequency used must be high enough to ensure that instantaneous load changes can be captured. The collected data can be preliminarily processed by edge computing devices, and the changes in frequency and amplitude can be detected using time series data analysis algorithms such as fast Fourier transform (FFT) or wavelet transform. These data processing methods can identify the periodic characteristics, amplitude changes and sudden fluctuations of power grid load fluctuations, and evaluate the degree of load fluctuations in real time by calculating the rate of change of power grid frequency or power. On this basis, the system can promptly detect whether abnormal fluctuations occur in the power grid, and the early warning system will trigger further load scheduling optimization or unit load adjustment mechanism, providing an accurate basis for the next decision.

[0053] When the load fluctuation of the power grid exceeds the set threshold, the system needs to automatically link the real-time load response data of the power plant generator set for analysis. First, through the comprehensive monitoring platform of the power plant, the operating data of each generator set is collected in real time, including key parameters such as real-time load, power generation, load response time, load adaptability, and unit status. These parameters will be used through advanced data analysis and model prediction, combined with historical data of load fluctuations, to evaluate the load response characteristics of the unit in real time. Specifically, the load response of the unit can be graded through machine learning or rule-based judgment models, and those units with longer response time and poor load adaptability can be automatically marked. These units will be marked as "affected" units and optimized according to their current load capacity. In this way, the system can quickly identify and mark the units that need attention when the load fluctuation of the power grid is too large, so as to avoid these units from being unable to adjust their output power in time when the load fluctuates, thereby causing uneven load distribution and overload.

[0054] The key purpose of this operation mode is to deal with the imbalance problem caused by grid load fluctuations on power plant load scheduling, and avoid risks such as overload, damage and grid instability caused by differences in unit response. In the case of large grid load fluctuations, if the load response characteristics of each unit cannot be identified in time, some units may not be able to adjust their output power within the expected time, resulting in uneven load distribution. This not only increases the risk of overload operation of the unit, but may also affect the stability of the grid and even cause systemic failures. By marking the load response capabilities of each unit in real time when the grid load fluctuation exceeds the threshold, the system can adjust the unit in a targeted manner to ensure that the load scheduling is more flexible and accurate. This mechanism can effectively avoid overload operation and loss of units caused by load fluctuations, optimize the operating efficiency of power plants, improve the stability of the grid, and reduce equipment failures and maintenance costs. This is the core goal of this technical solution, which aims to solve the problem of unbalanced unit scheduling that may occur when power plants respond to rapid load fluctuations, thereby improving the overall operating efficiency of power plants and grid stability.

[0055] Obtain the load response characteristic information of each unit in real time, analyze it after acquisition, and generate the load response coefficient and load adaptation coefficient of each unit respectively;

[0056] In this embodiment, the load response characteristic information of each unit is obtained in real time, and analyzed after being obtained to generate the load response coefficient and load adaptation coefficient of each unit respectively, which specifically includes the following steps:

[0057] Obtain the load response characteristic information of each unit in real time and perform preprocessing after acquisition;

[0058] To obtain the load response characteristics of each unit in real time, data can be collected through the integrated monitoring system of the power plant, combined with various sensors and data acquisition modules. These sensors include real-time data collection devices for current, voltage, speed, temperature and other equipment, and transmit the data of each unit to the central data processing platform through wireless communication protocols (such as LoRa, Wi-Fi, Zigbee, etc.). During the load fluctuation of the power grid, the system can continuously monitor the state of the power grid and automatically identify the operating status, load response characteristics, power generation capacity, etc. of each unit through the collected real-time data. The data acquisition process should be able to be dynamically updated at the millisecond level to ensure real-time performance, and use frequent sampling and data transmission of sensors to ensure that the information is accurate.

[0059] The purpose of preprocessing the data acquired in real time is to ensure data quality and eliminate noise, thereby ensuring the accuracy of subsequent analysis. The preprocessing steps include data denoising, standardization, and missing value filling. First, the algorithm is used to remove abnormal fluctuation data caused by factors such as sensor errors or electromagnetic interference; then, the data between different units are processed in a unified dimension using a standardized method to avoid the impact of different data scales on subsequent analysis; finally, for missing data caused by network delays or equipment failures, interpolation or model prediction methods are used to fill in the missing parts to ensure data integrity. Through these preprocessing measures, the reliability of the data and the accuracy of the analysis results can be effectively improved, thereby providing a high-quality data foundation for the subsequent calculation of the load response coefficient and adaptation coefficient.

[0060] Extracting load fluctuation information and response capability information from the pre-processed load response characteristic information of each unit;

[0061] Extracting the load fluctuation information and response capability information from the pre-processed load response characteristic information of each unit can be done through data analysis and feature extraction technology. First, the load fluctuation information can be extracted by performing time series analysis on real-time load data by computer. Specifically, the system will perform differential and smoothing processing on the load data of each unit within a certain period of time, identify the amplitude, frequency and fluctuation mode of load changes, and then analyze the intensity and periodicity of load fluctuations. This information can be obtained through methods such as Fourier transform, sliding window or autoregressive model to extract the frequency component and fluctuation amplitude of load fluctuations. The extraction of response capability information focuses on analyzing the response speed and regulation capability of the unit under the change of grid load. By performing regression analysis on the correlation between the real-time output power of the unit and the grid load fluctuation, the response time and regulation amplitude of the unit under different load fluctuation conditions can be extracted. In addition, the ability of the unit to respond to load fluctuations can be simulated by combining the control system parameters of the unit (such as fuel input, steam pressure, etc.) through computer modeling and simulation. All these extraction processes can be automated through the software platform, and data mining and machine learning algorithms can be used to further optimize the extraction process, ensuring that the extracted load fluctuation information and response capability information accurately reflect the real-time status and performance changes of the unit.

[0062] The extracted load fluctuation information and response capability information are analyzed to generate the load response coefficient and load adaptation coefficient of each unit respectively.

[0063] In this embodiment, the logic for obtaining the load response coefficient of each unit is as follows:

[0064] Extract the load fluctuation information from the pre-processed load response characteristic information of each unit, including the instantaneous voltage change value, instantaneous current change value and response delay time of each unit at different times during a period of time during the load fluctuation process of the power plant, and use the function SV i (t), IR i (t) and TP i (t), t is the time point, SV i (t) represents the instantaneous voltage change value of the i-th unit at time t during a period of time during the load fluctuation of the power plant, IR i (t) represents the instantaneous current change value of the i-th unit at time t during a period of time during the load fluctuation of the power plant, TP i (t) represents the response delay time of the i-th unit at time t during a period of load fluctuation in the power plant, and the time period is defined as [t1, t2], i = 1, 2, 3, ..., k, where k is a positive integer;

[0065] Real-time acquisition of the instantaneous voltage change value, instantaneous current change value and response delay time of each unit in the process of load fluctuation in the power plant can be carried out by installing high-precision voltage and current sensors at the output end of each unit for monitoring. These sensors use digital voltage measurement technology and Hall effect or current transformer technology to capture instantaneous changes in voltage and current in real time with millisecond or microsecond accuracy. These data are transmitted to the monitoring platform through a high-speed data acquisition system, and the instantaneous voltage change value and instantaneous current change value of each unit are recorded and provided in real time. The response delay time is calculated in real time by monitoring the time difference between the load fluctuation signal trigger and the power adjustment in the control system of each unit. These data are collected, processed and analyzed in real time by software, providing an accurate basis for the subsequent calculation of the load response coefficient.

[0066] Calculate the load response coefficient of each unit. The specific calculation formula is as follows:

[0067]

[0068] In the formula, LRC i is the load response coefficient of the ith unit.

[0069] Calculate the load response factor LRC of each unit i When we first perform weighted processing on the load fluctuation information within a period of time by integration, we evaluate the unit's ability to respond to grid load fluctuations. The part shows the instantaneous voltage change SV of the unit during load fluctuation i (t) and current change IR i(t), where the product of voltage and current reflects the intensity of unit load fluctuation, and the square of the denominator is the response delay time TP i (t) is the compensation for the fluctuation hysteresis effect, which avoids the excessive influence of the slow-responding units on the evaluation results. -TPi(t) This is to further attenuate the impact of the longer response delay time and ensure that the unit's response capability can quickly respond to load fluctuations. The integral operation and time period [t1, t2] reflect the comprehensive performance of the unit's response to fluctuations within a certain period of time. Overall, these steps can more accurately evaluate the unit's load response coefficient and reflect the unit's response speed and adaptability to load fluctuations.

[0070] Load response coefficient LRC of the i-th unit i The size of is directly related to the load response degree of the power plant's generator set. The larger the load response coefficient, the stronger the unit's ability to respond to grid load fluctuations, and the faster and more effectively it can adjust the output power to adapt to grid changes. This is because the load response coefficient comprehensively considers the voltage change, instantaneous current change, and response delay time of the unit during load fluctuations, and reflects the sensitivity and rapidity of the unit's response during fluctuations. Specifically, a higher load response coefficient indicates that the unit can effectively follow grid load fluctuations in a shorter period of time, while a lower coefficient may mean that the unit responds slowly or insufficiently to load fluctuations. Therefore, by evaluating the load response coefficient of each unit, the response degree of each unit to grid load fluctuations can be quantified, and decision support can be provided for load scheduling to ensure efficient and stable load scheduling of power plants.

[0071] In this embodiment, the logic for obtaining the load adaptation coefficient of each unit is as follows:

[0072] Extract the response capacity information from the pre-processed load response characteristic information of each unit, including the actual output power value of each unit at different times during a period of time during the load fluctuation of the power plant, the frequency of power adjustment, and the maximum load that each unit can withstand, and calibrate them as and DPL i , It represents the actual output power value of the i-th unit at time m during a period of time during the load fluctuation of the power plant. It indicates the frequency of power regulation of the i-th unit at time m during a period of time during load fluctuation of the power plant. i represents the maximum load that the i-th unit can bear, i = 1, 2, 3, ..., k, m = 1, 2, 3, ..., g, k and g are both positive integers;

[0073] During the load fluctuation process, the power plant obtains the actual output power value of each unit, the frequency of power adjustment, and the maximum load value of the unit, which can be obtained in real time through the integrated monitoring system and sensor equipment. First, the actual output power value can be directly read from the power meter value of the generator unit through the monitoring system of the power plant. These data are usually obtained through a real-time data acquisition system (such as a SCADA system). The sensor measures the power output of each unit and uploads it to the central control platform in real time. The frequency of power adjustment needs to be measured by measuring the adjustment frequency of the unit regulator, which is usually monitored in real time by the control system in the power plant. The data is collected in real time through the sensor or control signal of the frequency regulation device. As for the maximum load that the unit can withstand, this value is usually based on the technical specifications and design parameters of the unit. It can be obtained from the unit's operating manual or database, and can be associated with the unit's operating status (such as temperature, vibration, etc.) through the real-time monitoring system to determine the unit's current load-bearing capacity. These data are obtained in real time through the integration of IoT sensors, data acquisition equipment, and intelligent monitoring systems, and transmitted to the centralized management platform. After data processing and storage, they provide basic data for subsequent analysis.

[0074] Calculate the load adaptation coefficient of each unit. The specific calculation formula is as follows:

[0075]

[0076] Where LAC i is the load adaptation coefficient of the ith unit.

[0077] This calculation formula is used to evaluate the adaptability of each unit to load changes during load fluctuations. First, the difference between the actual output power and the maximum load carrying capacity is calculated. It measures the adaptability of the unit to load fluctuations. Secondly, the frequency of power adjustment As the denominator, the importance of the unit's response speed is emphasized by squaring. The higher the frequency, the stronger the unit's adaptability. Furthermore, the exponential decay function This reflects the nonlinear effect of load changes on adaptability. An increase in load will lead to a decrease in adaptability. Finally, the results of multiple moments over a period of time are averaged to ensure the comprehensiveness and stability of the evaluation. This calculation logic combines actual output, load carrying capacity, response frequency, and adaptability to load changes, and can accurately evaluate the load adaptability of the unit, providing a scientific basis for scheduling.

[0078] Load adaptation coefficient LAC of the i-th unit iIt reflects the adaptability of the unit to load changes during grid load fluctuations, and mainly measures its regulation and carrying capacity during instantaneous load changes. The larger the load adaptation coefficient, the more flexible the unit can adjust its output power, respond quickly to grid load fluctuations, and maintain a stable working state when carrying a larger load. On the contrary, a smaller load adaptation coefficient indicates that the unit has poor response ability during load fluctuations, and may not be able to adjust the output in time or carry too much load, thus affecting the load balance of the grid. By comparing the load adaptation coefficients of each unit, the load response degree of each unit can be effectively evaluated, the possible weak links in load scheduling can be identified, and the scheduling strategy can be provided based on the evaluation results to ensure that the power plant can maintain balance during load fluctuations and optimize the operating efficiency of the unit.

[0079] A load dispatch evaluation model is constructed for the load response coefficient and load adaptation coefficient of each unit, and the load dispatch evaluation coefficient of each unit is generated. After the generation, the load response degree of each unit in the power plant generator unit is evaluated, and each unit is divided into a high-response unit, a medium-response unit and a low-response unit according to the evaluation results;

[0080] In this embodiment, a load dispatch evaluation model is constructed based on the generated load response coefficient and load adaptation coefficient of each unit to generate the load dispatch evaluation coefficient of each unit, which specifically includes the following steps:

[0081] Collect the load response coefficients, load adaptation coefficients and corresponding load dispatch evaluation coefficients of several units generated in the past period of time, and calibrate them as and x represents the number of load response coefficients, load adaptation coefficients and corresponding load dispatch evaluation coefficients of several units generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time are formed into a historical data set;

[0082] To collect the load response coefficient, load adaptation coefficient and corresponding load dispatch evaluation coefficient of each unit generated in the past period of time, it can be achieved through a real-time monitoring system and a data acquisition platform. First, each unit in the power plant will measure key power parameters such as instantaneous voltage, current, power value, etc. in real time through sensors and monitoring equipment, and these parameters will be uploaded to the data acquisition system. Through these devices, the load response coefficient and load adaptation coefficient generated in real time will be synchronously stored in the database. Secondly, the load dispatch evaluation coefficient, as a result of calculation, will also be generated in the data processing module and automatically updated to the data warehouse. In order to ensure the comprehensiveness and accuracy of the data, historical data can be collected through regular or real-time data extraction and storage mechanisms. Specifically, the data acquisition system needs to have the function of regularly extracting and storing historical data, and mark the data source through timestamps to ensure that it can be accurately traced back to the specific time node. All these data will be integrated and stored in the historical data set for subsequent regression analysis and model training.

[0083] The value of x is limited to positive integers greater than or equal to 3. In order to accurately calculate the value of the regression coefficient, there must be enough data points to construct and solve multiple systems of equations. The goal of regression analysis is to fit an equation based on a historical data set, which contains a dependent variable and multiple independent variables. Since three regression coefficients (β0, β1, and β2) need to be calculated, at least three independent equations are required to form a valid linear equation system, and then these coefficients are solved by the least squares method. If the value of x is less than 3, the number of equations in the equation system will not be enough to support the calculation of the regression coefficient, which may result in the inability to accurately obtain the regression coefficient or overfitting problems. Therefore, the restriction of x ≥ 3 is selected to ensure that there is enough historical data to train the model, thereby improving the accuracy of the regression coefficient calculation and the stability of the model.

[0084] The multivariate regression model is selected as the load dispatch evaluation model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula:

[0085]

[0086] Where β0, β1 and β2 are regression coefficients;

[0087] The multivariate regression model is a statistical method used to analyze the relationship between multiple independent variables (such as load response coefficient and load adaptation coefficient) and the dependent variable (load dispatch evaluation coefficient). In the load dispatch evaluation, since multiple factors jointly affect the load response degree of the unit, the selection of a multivariate regression model can simultaneously consider the combined effect of these factors. By training the model with historical data sets, the regression coefficient can be determined in order to accurately predict the load dispatch evaluation coefficient. The regression coefficient β0 is the intercept term of the model, which represents the baseline value when all independent variables are zero; β1 represents the load response coefficient right The influence weight of right These regression coefficients help quantify the specific impact of different factors on load dispatch assessment, thereby optimizing the load management of power plants.

[0088] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined;

[0089] The practice of optimizing regression coefficients is to ensure that the regression model can best fit the historical data by minimizing the error between the predicted value and the actual value, thereby improving the accuracy of the prediction. In regression analysis, the goal is to make the output of the model as close to the actual observed value as possible by adjusting the regression coefficients (β0, β1, and β2), that is, to minimize the error between the predicted value and the actual value. The specific method is to use the Least Squares Method, which calculates the sum of squares of the error (the sum of squares of the difference between the predicted value and the actual value) and continuously adjusts the value of the regression coefficient until the error is minimized. In this way, the value of the regression coefficient can be optimized, making the model more accurate, thereby improving the accuracy of the load dispatch assessment of the power plant. In actual operation, these coefficients can be iteratively solved through software tools and algorithms, and finally the regression coefficient that best fits the historical data set is determined.

[0090] Using the final regression coefficient, the load response coefficient LRC of each unit generated in real time is input into the constructed load dispatch evaluation model. i and load adaptation factor LAC i , generate the load dispatch evaluation coefficient LDEC of each unit in real time i .

[0091] In this embodiment, the load dispatch evaluation coefficient LDEC of each unit is generated i and the pre-set load dispatch evaluation coefficient threshold interval [LDEC min , LDEC max] to compare, and evaluate the load response of each unit in the power plant generator set according to the comparison results, and divide each unit into high-response unit, medium-response unit and low-response unit according to the evaluation results. The specific comparison analysis and division are as follows:

[0092] If LDEC i <LDEC min , the load response degree of the unit among the power plant's generating units is low, and the unit is classified as a low-response unit;

[0093] Low-response units mean that these units cannot adjust their output power in a timely or effective manner during load fluctuations, resulting in weak response capabilities. Their load dispatch assessment coefficient is lower than the set minimum threshold, indicating that these units have poor adaptability to load changes. This may be due to factors such as technical limitations of the units themselves, equipment aging, or the failure of the control system to adjust in real time. The classification of these units helps power plants identify units that require special attention, and their response capabilities may need to be improved through equipment upgrades, enhanced control strategies, or increased spare capacity. If these units continue to have low responses, it may affect the overall load regulation capabilities of the power plant, thereby affecting the stability of the power grid and the operating efficiency of the power plant.

[0094] If LDEC min ≤LDEC i ≤LDEC max , the load response degree of the unit among the power plant's generating units is medium, and the unit is classified as a medium response unit;

[0095] The load dispatch evaluation coefficient of medium-response units is within the preset threshold range, indicating that these units have a certain responsiveness when the load fluctuates, but may not be the best choice. They can make moderate adjustments to load changes, but due to certain limitations, they may not be able to make the best response under rapidly changing load conditions. These units can generally operate efficiently when the load is stable and the changes are not drastic, but their responsiveness may be limited in extreme load fluctuations or emergencies. Therefore, classifying these units as medium-response units can help power plants to carry out hierarchical management, and reasonably dispatch medium-response units according to different degrees of load changes to improve the flexibility and safety of the system. By monitoring the long-term performance of these units, power plants can also optimize their operating strategies to ensure maximum utilization of power plant resources.

[0096] If LDEC i >LDEC max The load response degree of this unit among the power plant's generating units is high, and the unit is classified as a high-response unit.

[0097] The load dispatch assessment coefficient of high-response units is greater than the maximum threshold value, which means that these units can quickly and accurately adjust their power output when the load fluctuates, and have extremely strong load response capabilities. These units can respond to rapid load changes in a short period of time, provide rapid adjustment and support, and ensure the stable operation of the power plant and the load balance of the power grid. The existence of high-response units enables power plants to effectively respond to extreme load fluctuations, improve the overall dispatch efficiency and flexibility of power plants, and reduce the risk of power shortages or surpluses caused by load imbalance. The division of these units helps power plants to give priority to dispatching high-response units when load fluctuations are large, ensuring that power plants have strong adjustment capabilities and higher reliability, thereby improving the overall safety and economic benefits of power plants.

[0098] The "pre-set threshold interval of load dispatch evaluation coefficient" can be determined by combining data analysis with historical operation data. Specifically, first, the load dispatch evaluation coefficients of each unit in the past period of time can be extracted from the historical data of the power plant, and these data can be statistically analyzed, such as calculating their mean, standard deviation, maximum value and minimum value. Based on these statistical indicators, the software system can set a reasonable threshold interval, for example, the range of mean ± one standard deviation is selected as the interval of medium response units, those below the mean are divided into low response units, and those above the mean are divided into high response units. In addition, the threshold interval can also be dynamically adjusted by simulating different load fluctuation scenarios in combination with the operating objectives and operating requirements of the power plant to ensure that the interval can effectively reflect the actual load response capability of the unit. After determining the threshold interval, the interval setting can be optimized through continuous monitoring and adjustment, so as to ensure that the load response degree of the unit can be more accurately evaluated and dispatched in actual applications.

[0099] According to the classification results of each unit, corresponding load dispatch strategies are adopted for high-response units, medium-response units and low-response units respectively;

[0100] In this embodiment, according to the classification results of each unit, corresponding load dispatch strategies are adopted for high-response units, medium-response units and low-response units respectively, specifically:

[0101] For units classified as low-response units, the specific load dispatching strategy is as follows: when the grid load fluctuation is small, the current load output of the unit is maintained without dispatching adjustments; when the grid load fluctuation is large, the load output of the low-response unit is reduced first to avoid overload operation due to slow response, and at the same time, its load fluctuation is monitored in real time to ensure that it does not cause instability to the grid;

[0102] The load dispatching strategy for low-response units can be implemented through a real-time monitoring system. First, the power plant can use the data interface between the load dispatching system and the power grid monitoring platform to obtain the power grid load fluctuations and the real-time load output data of the unit in real time. When the power grid load fluctuations are small, the system will maintain the current load output of the unit and will not make scheduling adjustments; when the power grid load fluctuations are large, the system will automatically reduce the load output of the low-response unit according to the set scheduling rules to avoid overload operation caused by its response delay. Specifically, the system dynamically adjusts the load output based on the load response coefficient and actual operating status of the unit to ensure that the low-response unit will not have an adverse effect on the stability of the power grid. At the same time, the load fluctuations of the unit are monitored and warned in real time to ensure the flexibility and stability of the system.

[0103] For the units classified as medium-response units, the load dispatching strategy adopted is as follows: in the case of large grid load fluctuations, the load output of the medium-response units is adjusted in real time to ensure that their load response is balanced with grid fluctuations; at the same time, according to the response time and regulation capacity of the units, the dispatching strategy is dynamically adjusted to ensure that the units can respond in time during fluctuations;

[0104] For the load dispatching strategy of medium-response units, the power plant can realize dynamic adjustment of load dispatching. This process requires the power plant's load dispatching system to be combined with the real-time grid status monitoring system. When the grid load fluctuates greatly, the grid load situation is obtained in real time through the data interface and the load output of the unit is adjusted accordingly. The system adjusts according to the response capability and historical data of the medium-response unit to ensure the balance between its load output and grid load fluctuations. To achieve this, computer-aided modeling can be used to set the dispatching strategy and adjust it in real time in combination with the adjustment frequency and adjustment amplitude of each unit. The dispatching system will automatically make dynamic adjustments based on the load response characteristics of the unit to ensure that the output power of the unit is consistent with the grid load fluctuation, while avoiding system instability caused by excessive adjustment.

[0105] For units classified as high-response units, the load scheduling strategy adopted is as follows: give priority to increasing the load output of high-response units so that they can quickly adjust to grid load fluctuations; at the same time, monitor their load adjustment capabilities and output power in real time to ensure that the units can efficiently and smoothly respond to rapid fluctuations in grid load, and perform dynamic optimization scheduling to reduce wear and loss of the units and ensure the stable operation of the grid and power plants.

[0106] For the load dispatching strategy of high-response units, the load dispatching system can be implemented through an enhanced dispatching optimization algorithm. When the grid load fluctuates greatly, the system will give priority to increasing the load output of high-response units, and ensure that the units can respond quickly to load fluctuations by real-time monitoring and analysis of the dynamic load adjustment capabilities of high-response units. These units generally have higher adjustment capabilities and faster response times, and the system will automatically adjust their load output to cope with changes in grid load. By real-time monitoring of their output power, load adjustment capabilities, and the actual situation of grid load fluctuations, the dispatching system will automatically optimize the load output of the units to ensure that the units can efficiently and stably cope with load fluctuations, reduce the risk of system overload, and extend the service life of the units.

[0107] Continuously monitor the operating status of each unit and dynamically adjust the load scheduling strategy based on real-time monitoring results to ensure the balance of power plant load scheduling and efficient and stable system operation.

[0108] To continuously monitor the operating status of each unit, an integrated intelligent monitoring system can be used to track the real-time operating data of each unit. The system can continuously obtain key operating parameters of the unit, such as load output, voltage, current, temperature, and vibration, through sensors and data acquisition equipment. The software platform processes and analyzes this data in real time, and evaluates the health status and work efficiency of the unit through algorithm models. If a unit is found to be operating abnormally or beyond the preset operating range, the system can immediately issue an alarm and intervene through the dispatching system. Real-time monitoring can not only help to detect problems in a timely manner, but also provide an accurate basis for subsequent load dispatching strategy adjustments. In this way, the power plant can ensure that the operating status of each unit is understood in a timely manner, thereby ensuring the smooth operation of the system.

[0109] Specifically, the real-time monitoring results will be automatically fed back to the load dispatching system through the data analysis platform to dynamically adjust the load dispatching strategy. The dispatching system automatically calculates the adjusted load distribution plan based on the real-time load response, carrying capacity, load fluctuation and other information of each unit. When the grid load fluctuates violently, the system adjusts the dispatching strategy based on the unit's response capability and current operating status to ensure that the load output of each unit matches the grid demand. Through this intelligent dispatching adjustment, the load distribution of the unit can be dynamically optimized to avoid overload or insufficient power supply, thereby ensuring the stability of the grid.

[0110] In addition, the dynamic adjustment of the load dispatching strategy must take into account the efficient and stable long-term operation of the system. To this end, the software system will combine historical data, real-time monitoring results, and the operating objectives of the power plant to continuously optimize the load dispatching. Through algorithms such as machine learning, the system can automatically learn the best strategy for load dispatching according to different time periods and operating environments, and predict and warn future load fluctuations. In this way, the system can not only respond to grid load fluctuations in the short term, but also adjust itself according to long-term trends to ensure that the load dispatching of the power plant operates in an efficient and stable state. This continuous optimization mechanism can help power plants reduce operating costs, improve energy efficiency, and improve the overall stability of the system.

[0111] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0112] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center containing one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0113] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0114] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0115] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0116] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0118] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent monitoring method based on a comprehensive monitoring platform of a power plant, characterized in that: The specific steps include: During the grid load fluctuation process, the grid load fluctuation degree is detected in real time, and when the grid load fluctuation is detected to exceed the set threshold, each unit in the power plant generator set is identified and marked; Obtain the load response characteristic information of each unit in real time, analyze it after acquisition, and generate the load response coefficient and load adaptation coefficient of each unit respectively; A load dispatch evaluation model is constructed for the load response coefficient and load adaptation coefficient of each unit, and the load dispatch evaluation coefficient of each unit is generated. After the generation, the load response degree of each unit in the power plant generator unit is evaluated, and each unit is divided into a high-response unit, a medium-response unit and a low-response unit according to the evaluation results; According to the classification results of each unit, corresponding load dispatch strategies are adopted for high-response units, medium-response units and low-response units respectively; Continuously monitor the operating status of each unit and dynamically adjust the load scheduling strategy based on real-time monitoring results to ensure the balance of power plant load scheduling and efficient and stable system operation.

2. The intelligent monitoring method based on the power plant integrated monitoring platform according to claim 1 is characterized in that: The load response characteristic information of each unit is obtained in real time, and analyzed after acquisition to generate the load response coefficient and load adaptation coefficient of each unit respectively, which specifically includes the following steps: Obtain the load response characteristic information of each unit in real time and perform preprocessing after acquisition; Extracting load fluctuation information and response capability information from the pre-processed load response characteristic information of each unit; The extracted load fluctuation information and response capability information are analyzed to generate the load response coefficient and load adaptation coefficient of each unit respectively.

3. The intelligent monitoring method based on the power plant integrated monitoring platform according to claim 2 is characterized in that: The logic for obtaining the load response coefficient of each unit is as follows: Extract the load fluctuation information from the pre-processed load response characteristic information of each unit, including the instantaneous voltage change value, instantaneous current change value and response delay time of each unit at different times during a period of time during the load fluctuation process of the power plant, and use the function SV i (t), IR i (t) and TP i (t), t is the time point, SV i (t) represents the instantaneous voltage change value of the i-th unit at time t during a period of time during the load fluctuation of the power plant, IR i (t) represents the instantaneous current change value of the i-th unit at time t during a period of time during the load fluctuation of the power plant, TP i (t) represents the response delay time of the i-th unit at time t during a period of load fluctuation in the power plant, and the time period is defined as [t1, t2], i = 1, 2, 3, ..., k, where k is a positive integer; Calculate the load response coefficient of each unit. The specific calculation formula is as follows: In the formula, LRC i is the load response coefficient of the ith unit.

4. The intelligent monitoring method based on the power plant integrated monitoring platform according to claim 3 is characterized in that: The logic for obtaining the load adaptation coefficient of each unit is as follows: Extract the response capacity information from the pre-processed load response characteristic information of each unit, including the actual output power value of each unit at different times during a period of time during the load fluctuation of the power plant, the frequency of power adjustment, and the maximum load that each unit can withstand, and calibrate them as and DPL i , It represents the actual output power value of the i-th unit at time m during a period of time during the load fluctuation of the power plant. It indicates the frequency of power regulation of the i-th unit at time m during a period of time during load fluctuation of the power plant. i represents the maximum load that the i-th unit can bear, i = 1, 2, 3, ..., k, m = 1, 2, 3, ..., g, k and g are both positive integers; Calculate the load adaptation coefficient of each unit. The specific calculation formula is as follows: Where LAC i is the load adaptation coefficient of the ith unit.

5. The intelligent monitoring method based on the power plant integrated monitoring platform according to claim 4 is characterized in that: A load dispatch evaluation model is constructed based on the generated load response coefficient and load adaptation coefficient of each unit to generate the load dispatch evaluation coefficient of each unit, which specifically includes the following steps: Collect the load response coefficients, load adaptation coefficients and corresponding load dispatch evaluation coefficients of several units generated in the past period of time, and calibrate them as and x represents the number of load response coefficients, load adaptation coefficients and corresponding load dispatch evaluation coefficients of several units generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time are formed into a historical data set; The multivariate regression model is selected as the load dispatch evaluation model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula: Where β0, β1 and β2 are regression coefficients; By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined; Using the final regression coefficient, the load response coefficient LRC of each unit generated in real time is input into the constructed load dispatch evaluation model. i and load adaptation factor LAC i , generate the load dispatch evaluation coefficient LDEC of each unit in real time i .

6. The intelligent monitoring method based on the power plant integrated monitoring platform according to claim 5 is characterized in that: The load dispatch evaluation coefficient LDEC of each unit generated i and the pre-set load dispatch evaluation coefficient threshold interval [LDEC min , LDEC max ] to compare, and evaluate the load response of each unit in the power plant generator set according to the comparison results, and divide each unit into high-response unit, medium-response unit and low-response unit according to the evaluation results. The specific comparison analysis and division are as follows: If LDEC i <LDEC min , the load response degree of the unit among the power plant's generating units is low, and the unit is classified as a low-response unit; If LDEC min ≤LDEC i ≤LDEC max , the load response degree of the unit among the power plant's generating units is medium, and the unit is classified as a medium response unit; If LDEC i >LDEC max The load response degree of this unit among the power plant's generating units is high, and the unit is classified as a high-response unit.

7. The intelligent monitoring method based on the power plant integrated monitoring platform according to claim 6 is characterized in that: According to the classification results of each unit, corresponding load dispatch strategies are adopted for high-response units, medium-response units and low-response units, specifically: For units classified as low-response units, the specific load dispatching strategy is as follows: when the grid load fluctuation is small, the current load output of the unit is maintained without dispatching adjustments; when the grid load fluctuation is large, the load output of the low-response unit is reduced first to avoid overload operation due to slow response, and at the same time, its load fluctuation is monitored in real time to ensure that it does not cause instability to the grid; For the units classified as medium-response units, the load dispatching strategy adopted is as follows: in the case of large grid load fluctuations, the load output of the medium-response units is adjusted in real time to ensure that their load response is balanced with grid fluctuations; at the same time, according to the response time and regulation capacity of the units, the dispatching strategy is dynamically adjusted to ensure that the units can respond in time during fluctuations; For units classified as high-response units, the load scheduling strategy adopted is as follows: give priority to increasing the load output of high-response units so that they can quickly adjust to grid load fluctuations; at the same time, monitor their load adjustment capabilities and output power in real time to ensure that the units can efficiently and smoothly respond to rapid fluctuations in grid load, and perform dynamic optimization scheduling to reduce wear and loss of the units and ensure the stable operation of the grid and power plants.

Images