Frequency modulation control method and system for thermal power generating unit

By collecting and analyzing the load and operating status data of the thermal power unit in real time, identifying nonlinear demand correlations, quantifying and controlling the frequency modulation requirements, designing a global frequency modulation strategy and feedbacking it to the cloud platform, it solves the inaccuracy and accuracy errors in traditional frequency modulation control methods. The major problem has achieved more efficient and reliable grid frequency adjustment.

CN119482554AActive Publication Date: 2025-02-18陕西君创智盈能源科技有限公司

Patent Information

Application Number
CN202510032211.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-01-09
Publication Date
2025-02-18
Estimated Expiration
2045-01-09

AI Technical Summary

Technical Problem

The frequency regulation control method of traditional thermal power units has problems such as inaccurate analysis of losses and delays during energy conversion, as well as large errors in frequency regulation control accuracy.

Method used

The sensor collects the load fluctuation data of the transmission grid of the thermal power unit, conducts timing load trend analysis, collects the status data of thermal power and steam pressure in real time, identifys the nonlinear demand correlation of thermal energy conversion-steam pressure, and performs the quantification of the frequency of power generation and energy investment demand control. , design global frequency modulation control strategies and feedback to the cloud platform.

Benefits of technology

Improve the accuracy of loss and delay analysis during energy conversion, reduce the error of frequency modulation control accuracy, improve the load response capability and energy use efficiency of thermal power units, ensure the stability of grid frequency and the reliability of power supply. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119482554A_ABST
    Figure CN119482554A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of frequency modulation control, in particular to a frequency modulation control method and system for a thermal power generating unit. The method comprises the following steps: collecting and transmitting power grid load fluctuation data through a sensor, and carrying out time sequence load trend analysis to obtain load fluctuation time sequence trend data; then, based on the data, thermal power and steam pressure states are collected in real time, nonlinear demand association identification of thermal energy conversion and steam pressure is carried out, and thermal energy conversion-steam pressure association data are obtained. And according to the data, quantifying the power generation frequency modulation demand of the power grid, and formulating an energy input control strategy. And finally, designing a global frequency modulation control strategy through the control data, and feeding back the global frequency modulation control strategy to the cloud platform to execute the frequency modulation control method. According to the invention, the frequency modulation control technology is optimized, so that the frequency modulation control technology is more perfect.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of frequency modulation control, and in particular to a frequency modulation control method and system for a thermal power unit. Background Art

[0002] As an important part of the power system, thermal power units are responsible for providing stable and reliable power. Especially when the load fluctuates greatly, their frequency control capability is particularly important. Frequency control refers to the process of maintaining the stability of the system frequency by adjusting the output power of the generator set when the power system is disturbed by load fluctuations or changes in the output of the generator set. In the power system, frequency stability is directly related to the safe operation of the power grid and the reliability of power supply. Especially in the system where thermal power units account for a large proportion, frequency control technology is particularly critical. In actual operation, the load fluctuation of thermal power units is affected by many factors, such as weather changes, seasonal load differences, production activities, etc. These fluctuations are usually manifested as complex time series changes, resulting in fluctuations and instability of the power grid frequency. In order to effectively cope with these load fluctuations, thermal power units need to have a fast frequency response capability on the basis of ensuring safe and stable operation. However, a traditional frequency control method for thermal power units has the problems of inaccurate analysis of losses and delays in the energy conversion process, as well as large errors in the accuracy of frequency control. Summary of the invention

[0003] Based on this, it is necessary to provide a frequency regulation control method and system for a thermal power unit to solve at least one of the above technical problems.

[0004] To achieve the above object, a frequency modulation control method for a thermal power unit is provided, the method comprising the following steps: Step S1: collecting transmission grid load fluctuation data of thermal power units through sensors to obtain transmission grid load fluctuation data; performing time series load trend analysis on the transmission grid load fluctuation data to obtain load fluctuation time series trend data; Step S2: Using built-in sensors and based on the load fluctuation time series trend data, real-time status data of thermal power and steam pressure are collected to obtain real-time status data of thermal power and real-time status data of steam pressure respectively; according to the real-time status data of thermal power, the real-time status data of steam pressure is subjected to thermal energy conversion-steam pressure demand association identification to obtain thermal energy conversion-steam pressure nonlinear demand association data; Step S3: quantify the power generation frequency regulation demand of the load fluctuation time series trend data according to the heat energy conversion-steam pressure nonlinear demand correlation data to obtain the power generation frequency regulation demand quantification data of the power grid; control the energy input demand according to the power generation frequency regulation demand quantification data of the power grid to obtain the thermal power energy input control data; Step S4: Design a global frequency modulation control strategy based on the thermal power energy input control data to obtain the energy input global frequency modulation control strategy; feed back the energy input global frequency modulation control strategy to the cloud platform to execute the frequency modulation control method.

[0005] The present invention collects the load fluctuation data of the transmission grid of the thermal power unit through the sensor, and can accurately capture the load change of the grid. After the data are analyzed by the time series load trend, the time series trend of the grid load fluctuation can be extracted, and then the basic data support for the subsequent power dispatching and control can be provided. The load fluctuation time series trend data reveals the change law of the grid load, can provide a reliable basis for the adjustment and optimization of the generator set, and is helpful to improve the stability and dispatching efficiency of the power system. The built-in sensor collects the data of thermal power and steam pressure in real time, and the operation state of the thermal power unit can be accurately monitored by analyzing these real-time status data. By correlating and identifying the nonlinear demand relationship between the real-time status data of thermal power and the real-time status data of steam pressure, the dynamic interactive relationship between thermal energy conversion and steam pressure can be revealed. This nonlinear demand correlation data helps to deeply understand the energy efficiency characteristics of the thermal power unit, optimize the unit operation strategy, improve energy conversion efficiency, and reduce resource waste. Based on the thermal energy conversion-steam pressure nonlinear demand correlation data, the load fluctuation time series trend data is quantified for the power generation frequency modulation demand, and the frequency modulation demand of the grid can be accurately calculated. This process clarifies the power adjustment requirements of the grid for the thermal power unit by quantifying the frequency modulation demand. According to the quantitative results, further energy input demand control can be carried out to reasonably allocate the energy use of thermal power units and ensure that the energy supply is stable and efficient during load fluctuations. This control strategy effectively improves the load response capability of thermal power units and reduces energy waste. According to the thermal power energy input control data, a global frequency regulation control strategy is designed to achieve the optimal regulation of thermal power units in the entire power grid dispatching. This control strategy will ensure that the power grid can efficiently achieve frequency regulation when the load fluctuates, and ensure the stability and reliability of power supply. Feeding back the global frequency regulation control strategy to the cloud platform means that the frequency regulation scheme can be monitored and adjusted in real time to ensure continuous optimization of the regulation effect. The real-time feedback and regulation capabilities of this cloud platform realize the intelligent dispatching of the whole system, so that the thermal power units can respond to the grid dispatching needs more flexibly and efficiently, thereby improving the overall operation efficiency of the power system. Therefore, the present invention is an optimization process made to a traditional frequency regulation control method of a thermal power unit, which solves the problems of inaccurate analysis of losses and delays in the energy conversion process and large errors in the frequency regulation control accuracy in a traditional frequency regulation control method of a thermal power unit, improves the accuracy of loss and delay analysis in the energy conversion process, and reduces the error in frequency control accuracy.

[0006] Preferably, step S1 comprises the following steps: Step S11: collecting transmission grid load fluctuation data of the thermal power unit through sensors to obtain transmission grid load fluctuation data; Step S12: Filling missing values ​​in the transmission grid load fluctuation data to obtain grid load fluctuation filling data; Step S13: Perform time series load trend analysis on the power grid load fluctuation filling data to obtain load fluctuation time series trend data.

[0007] The present invention collects the load fluctuation data of the transmission power grid for the thermal power unit through the sensor, and can monitor the load fluctuation of the power grid in real time. These data provide a basis for subsequent analysis and can reflect the load demand changes of the power grid in different time periods. The beneficial effect of this data collection link is to provide accurate load fluctuation information, which helps to timely discover the laws and anomalies of the load fluctuation of the power grid, and then provide data support for the subsequent load trend analysis, energy scheduling and power generation frequency modulation strategy, and ensure the stability and efficient operation of the power system. In the data collection process, there will be data missing, which affects the accuracy of subsequent analysis. Step S12 ensures the integrity of the data by filling the missing values ​​of the transmission power grid load fluctuation data. Missing value filling is usually processed by interpolation or other statistical methods to avoid analysis deviations caused by missing data. The beneficial effect of this step is to ensure the continuity and stability of the analysis process, so that the subsequent time series load trend analysis can be carried out on the basis of complete load fluctuation data, thereby improving the accuracy and reliability of the analysis results. After completing the data filling, step S13 performs time series load trend analysis on the power grid load fluctuation filling data to extract the trend characteristics of the load fluctuation. This process can reveal the long-term trend and short-term fluctuation of power grid load changes, and help identify the periodic law of load growth and abnormal conditions of sudden fluctuations. Through time series analysis, the future trend of load fluctuations can be effectively predicted, providing a scientific basis for the regulation strategy of thermal power units. The beneficial effect of this step is that it provides data support for load forecasting, energy dispatching and optimal dispatching of power generation units, optimizes energy distribution and utilization efficiency, and improves the flexibility and response speed of the power system.

[0008] Preferably, step S2 comprises the following steps: Step S21: collecting the real-time status of thermal power and steam pressure through built-in sensors and based on the load fluctuation time series trend data, and obtaining the real-time status data of thermal power and the real-time status data of steam pressure respectively; Step S22: evaluating the energy conversion efficiency loss of the steam pressure real-time status data according to the thermal power real-time status data to obtain thermal energy conversion efficiency loss data; Step S23: Based on the heat energy conversion efficiency loss data, the real-time state data of steam pressure is subjected to heat energy conversion-steam pressure demand correlation identification to obtain heat energy conversion-steam pressure demand correlation data; Step S24: performing nonlinear structural analysis on the thermal energy conversion-steam pressure demand correlation data to obtain thermal energy conversion-steam pressure nonlinear demand correlation data.

[0009] The present invention collects the state data of thermal power and steam pressure in real time based on the load fluctuation time series trend data through built-in sensors. This process helps to accurately capture the fluctuation of thermal power output and steam pressure of the thermal power unit in operation, thereby reflecting the real-time working state of the thermal power unit. The real-time data of thermal power and steam pressure can provide an accurate basis for subsequent energy efficiency analysis and scheduling decisions, ensuring that the unit can respond and adjust the operating state in time under load fluctuation conditions to optimize the power generation process and improve the overall energy utilization efficiency of the system. The energy conversion efficiency loss of the steam pressure real-time state data is evaluated according to the real-time state data of thermal power. The thermal energy conversion efficiency of the thermal power unit directly affects the economy and environmental protection of the unit. By evaluating the relationship between thermal power and steam pressure, the efficiency loss in the energy conversion process can be identified, thereby providing a basis for optimizing the operation of the unit. Through this step, potential problems in the operation of the unit (such as low steam pressure leading to a decrease in thermal efficiency) can be revealed, and corresponding measures can be taken to improve them, thereby improving the energy utilization efficiency of the unit and reducing the operating cost. Based on the thermal energy conversion efficiency loss data, step S23 identifies the association between thermal energy conversion and steam pressure demand for the real-time state data of steam pressure. Through this step, the dynamic demand relationship between steam pressure and thermal power in the thermal energy conversion process can be deeply analyzed. This demand association identification helps reveal the impact of steam pressure fluctuations on thermal energy conversion efficiency and provides a basis for predicting the future operation demand of the unit. The beneficial effect of this step is that it can identify the potential relationship between load fluctuations and system efficiency in advance, help adjust steam pressure, optimize unit load regulation, and thus improve the response speed and stability of the unit. By performing nonlinear structural analysis on the thermal energy conversion-steam pressure demand correlation data, the complex interactive relationship between thermal power and steam pressure can be further explored. Since the thermal energy conversion efficiency and steam pressure of thermal power units usually show a nonlinear relationship, traditional linear analysis methods are difficult to accurately capture this complex dependency. Through nonlinear structural analysis, the interactive mechanism between thermal energy conversion and steam pressure can be modeled more accurately and its deep dynamic association can be identified. This process provides more refined data support for the optimization of scheduling strategies, helps to improve the overall operating efficiency of the unit, reduce energy losses, and provide a scientific basis for intelligent scheduling.

[0010] Preferably, step S23 includes the following steps: Step S231: performing time-varying characteristic analysis on the heat energy conversion efficiency loss data to obtain conversion efficiency loss time-varying data; Step S232: Based on the conversion efficiency loss time-varying data, the real-time state data of steam pressure is evaluated for steam pressure response in different time periods to obtain steam pressure responsiveness evaluation data; Step S233: dividing the steam pressure responsiveness evaluation data into response rate gradient grades to obtain pressure response rate gradient grades; Step S235: performing response rate-energy conversion time-varying correlation subset induction on the conversion efficiency loss time-varying data according to the pressure response rate gradient level to obtain a response rate-energy conversion time-varying correlation subset; Step S236: using Takagi-Sugeno reasoning to identify the thermal energy conversion-steam pressure demand association of the response rate-energy conversion time-varying association subset, and obtain thermal energy conversion-steam pressure demand association data.

[0011] The present invention performs time-varying characteristic analysis on the heat conversion efficiency loss data, and can identify the dynamic change trend between thermal power and steam pressure in different time periods. Through the time-varying characteristic analysis, the time dependence of efficiency loss can be revealed, that is, how the conversion efficiency loss changes with time under different load fluctuations. The beneficial effect of this step is to help understand the law of energy efficiency fluctuations, provide more accurate time series data for subsequent scheduling strategies and unit optimization, help to better predict the changes in efficiency loss, and take effective measures to adjust and improve the overall operating efficiency of the unit. Based on the time-varying data of conversion efficiency loss, the real-time state data of steam pressure is evaluated for response in different time periods. This process can reveal the time dependence of steam pressure on the operating efficiency of the unit by evaluating the response of steam pressure to the heat conversion efficiency loss in different time periods. The responsiveness evaluation data of steam pressure helps to understand how steam pressure affects the heat conversion process during load fluctuations and changes in energy demand. The beneficial effect of this step is to provide a more comprehensive perspective on steam pressure management for the scheduling system, ensuring that the dynamic regulation of steam pressure during energy conversion is more reasonable and accurate. Based on the steam pressure responsiveness evaluation data, the response rate gradient level is divided. This step can more clearly characterize the impact and response rate of steam pressure changes on the energy conversion process by defining different pressure response rate gradient levels. For example, a faster response rate level indicates that the unit can be adjusted quickly to avoid efficiency loss, while a slower response rate level indicates potential regulation lag problems. Through this division, more detailed operational guidance can be provided for subsequent unit adjustment and optimization. The beneficial effect of this step is to provide support for the refined management of the regulation strategy by accurately identifying the rate of steam pressure change, ensuring that the unit responds more promptly and effectively. According to the pressure response rate gradient level, the response rate-energy conversion time-varying correlation subsets of the conversion efficiency loss time-varying data are summarized. By summarizing the energy conversion efficiency time-varying correlation subsets at different rates, a more refined correlation model between energy conversion and pressure response can be formed. This step helps to further refine the relationship between thermal energy conversion and steam pressure, and provide quantitative data support for scheduling optimization. The summarized subset data can help identify the specific impact of different response rates on energy conversion, optimize energy management, and improve the ability of the unit to respond to load fluctuations in different periods. The beneficial effect of this step is that it can better achieve dynamic adjustment, ensure the maximum energy utilization efficiency and reduce efficiency loss. The Takagi-Sugeno reasoning method is used to identify the thermal energy conversion-steam pressure demand association for the response rate-energy conversion time-varying association subset. The Takagi-Sugeno reasoning method is a fuzzy reasoning method that can model nonlinear relationships through reasoning rules and identify the complex demand relationship between thermal energy conversion and steam pressure.Through this reasoning method, the deep connection between thermal energy conversion efficiency and steam pressure changes can be revealed from a multi-dimensional and multi-time scale perspective. The beneficial effect of this step is that it can accurately capture the nonlinear relationship between thermal energy conversion and steam pressure, thereby providing more scientific and intelligent decision support for the dispatching, energy efficiency optimization and load management of generator sets, and further improving the stability and energy utilization efficiency of the power system.

[0012] Preferably, step S3 comprises the following steps: Step S31: normalizing the heat energy conversion-steam pressure nonlinear demand correlation data to obtain nonlinear demand correlation normalized data; Step S32: Delay coupling is performed on the load fluctuation time series trend data according to the nonlinear demand associated normalized data to obtain grid load delay data; Step S33: quantifying the power generation and frequency regulation demand of the load fluctuation time series trend data based on the power grid load delay data to obtain the power grid power generation and frequency regulation demand quantification data; Step S34: energy input demand control is performed on the thermal energy conversion-steam pressure nonlinear demand correlation data according to the quantified data of the power grid power generation frequency regulation demand to obtain thermal power energy input control data.

[0013] The present invention normalizes the nonlinear demand-related data of heat energy conversion-steam pressure, aiming to eliminate the dimensional difference of the data, so that data of different dimensions can be compared and analyzed under the same standard. Through normalization, the fluctuation and variation range of the nonlinear demand-related data can be unified into a standard scale, so as to facilitate subsequent analysis, model building and optimization decision-making. This process helps to improve the stability and consistency of the data, ensure the accuracy and reliability of data processing in subsequent steps, and thus provide unified basic data for further optimization algorithms and scheduling strategies. Based on the nonlinear demand-related normalized data, the load fluctuation time series trend data is delayed coupled to reveal the relationship between the dynamic characteristics of the power grid load and the heat energy conversion and steam pressure. Load fluctuations usually have a certain delay effect, that is, the change of the power grid load often has a significant impact on the energy demand after a period of time. Through delayed coupling, the influence of load fluctuations on the operation of the power grid and energy scheduling can be more accurately identified, and timely and reasonable adjustment strategies can be provided for the load scheduling of the power grid. The beneficial effect of this step is that through the delayed analysis of load fluctuations, the power grid scheduling and energy management are more forward-looking and responsive, thereby optimizing the operation efficiency of the power system. Based on the power grid load delay data, the load fluctuation time series trend data is used to quantify the power generation frequency regulation demand. This step quantifies the power adjustment required for power generation frequency regulation by analyzing the delayed response of the power grid load. The load fluctuation of the power grid often leads to frequency instability, so the generator set needs to adjust the frequency in a timely manner according to the load fluctuation. This process quantifies the power generation frequency regulation demand of the power grid, clarifies the power range that the dispatch center needs to adjust, and provides clear dispatch instructions for the unit adjustment. The beneficial effect of this step is that it can help the power grid accurately predict and respond to load fluctuations, reduce the risk of power system instability caused by frequency fluctuations, and thus improve the response speed and stability of power grid dispatch. Based on the quantitative data of the power grid power generation frequency regulation demand, the energy input demand is controlled for the nonlinear demand correlation data of thermal energy conversion-steam pressure. This process adjusts the energy input of the thermal power unit according to the frequency regulation demand of the power grid and the nonlinear relationship between thermal energy conversion and steam pressure, and optimizes the load regulation strategy of the unit. By controlling the energy input, it can ensure that the unit responds effectively under load fluctuations and frequency regulation requirements, while avoiding energy waste and efficiency loss. The beneficial effect of this step is to optimize the thermal energy conversion efficiency through precise energy input control, provide a more stable power supply to the power grid, and improve the operating efficiency and stability of the power system.

[0014] Preferably, step S32 includes the following steps: Step S321: performing heat energy conversion-steam pressure conversion efficiency retardation analysis on the nonlinear demand-related normalized data to obtain energy conversion efficiency retardation data; Step S322: Calculate the energy conversion multi-peak extreme value retardation variance of the nonlinear demand-related normalized data according to the energy conversion efficiency retardation data to obtain the energy conversion multi-peak extreme value retardation variance; Step S323: Delay coupling is performed on the load fluctuation time series trend data based on the energy conversion multi-peak extreme value delay variance to obtain the grid load delay data.

[0015] The present invention performs a thermal energy conversion-steam pressure conversion efficiency retardation analysis for nonlinear demand-related normalized data. This analysis aims to reveal the hysteresis effect of steam pressure on thermal energy conversion efficiency during energy conversion, that is, the response time delay between steam pressure change and conversion efficiency. Through this retardation analysis, the impact of dynamic changes in conversion efficiency on system response can be accurately identified, especially when load fluctuations or steam pressure adjustments occur, and the change in efficiency occurs gradually. The beneficial effect of this step is that it can provide reliable time series data for subsequent dispatch optimization, so that the power system can timely identify and adjust the system operation strategy when facing load fluctuations, thereby reducing the negative impact of hysteresis effects on system stability and efficiency. Based on the energy conversion efficiency retardation data obtained in step S321, the energy conversion multi-peak extreme value retardation variance calculation is performed. The multi-peak extreme value retardation variance calculation is mainly to evaluate the response lag and variance of changes of different peaks during thermal energy conversion. By performing retardation analysis on the extreme values ​​at different time points, the response speed difference of the system in the face of different load peaks and fluctuations can be reflected. The beneficial effect of this step is that it helps quantify the response time and regulation efficiency of the energy conversion system under different load changes, providing a basis for optimizing unit scheduling. Through accurate delay variance data, the unit response strategy can be adjusted to avoid energy waste and efficiency loss caused by hysteresis, and improve the overall energy utilization rate. Based on the multi-peak extreme delay variance data of energy conversion, the load fluctuation time series trend data is delayed coupled. The core goal of this process is to identify and quantify the delayed response of power grid load fluctuations, and by combining with the energy conversion efficiency delay data, a more accurate relationship between load changes and energy conversion is established. Delay coupling can reveal the specific impact of power grid load fluctuations on the energy conversion process in different time periods, especially the hysteresis effect caused by load fluctuations. The beneficial effect of this step is that it provides more dynamic and time-series data support for power grid scheduling and energy management, enabling the power grid system to better cope with load fluctuations and system changes, ensuring the stability of energy supply and the efficiency of system scheduling, thereby improving the operational stability and energy efficiency of the power grid.

[0016] Preferably, step S34 includes the following steps: Step S341: Perform power regulation demand analysis on the power grid power generation frequency regulation demand quantified data to obtain power generation power regulation demand data; Step S342: Approximate the instability mutation amplitude of the power generation power regulation demand data to obtain power demand instability approximate data; Step S343: performing time series collaborative optimization on the thermal energy conversion-steam pressure nonlinear demand correlation data according to the power demand instability approximate data to obtain the steam pressure collaborative optimization demand data; Step S344: Perform energy input demand control based on the steam pressure collaborative optimization demand data to obtain thermal power energy input control data.

[0017] The present invention first analyzes the power regulation demand of the power grid power generation frequency regulation demand quantification data. The core goal of this step is to quantify the required regulation power by analyzing the power demand fluctuation of the power grid under different load and frequency regulation conditions. The power regulation demand analysis provides a clear regulation range for power grid dispatching and determines the power generation power required to be regulated under different power load fluctuation conditions. This process helps the power system to clarify the real-time power generation dispatching demand, thereby providing a scientific basis for the subsequent power generation unit regulation and control, ensuring the stability of the power grid frequency and sufficient energy supply. The power generation power regulation demand data is approximated by the instability mutation amplitude. This analysis is mainly used to quantify the sudden load fluctuations that occur in power grid dispatching, especially large and rapid load changes. By approximating the instability mutation amplitude, the system instability that occurs when the power grid encounters sudden load fluctuations can be predicted. The beneficial effect of this process is that it can help the power grid identify potential instability risks in advance and take preventive measures in actual dispatching to avoid large-scale power instability and failures, thereby improving the reliability and safety of the system. Based on the power demand instability approximation data, the thermal energy conversion-steam pressure nonlinear demand correlation data is time-series collaboratively optimized. This step aims to analyze the amplitude of the unstable mutation of power demand and combine it with the steam pressure change in the thermal energy conversion process to optimize the timing. By coordinating the timing relationship between steam pressure adjustment and grid load change, the best match between dynamic regulation of generator sets and load demand can be achieved. The beneficial effect of this process is that it can optimize the dynamic response of the energy conversion system, avoid efficiency loss and system fluctuations caused by delayed or uncoordinated steam pressure adjustment, and thus improve the load response capability and energy efficiency of the grid. Based on the steam pressure collaborative optimization demand data, energy input demand control is carried out to obtain thermal power energy input control data. The goal of this process is to accurately control the energy input of thermal power units according to the optimized steam pressure collaborative demand to ensure that it matches the grid frequency regulation and load fluctuation requirements. By optimizing the energy input of thermal power units, energy waste and excessive consumption can be avoided while meeting the frequency regulation requirements, thereby improving the overall energy utilization efficiency. The beneficial effect of this step is that it can achieve collaborative optimization between the grid and the generator sets, ensuring that the generator sets can meet the grid stability requirements during the dispatching process, while maximizing energy utilization efficiency and reducing unnecessary energy consumption and emissions.

[0018] Preferably, step S342 includes the following steps: Performing a time-series demand increase analysis on the power generation regulation demand data to obtain time-series demand increase data; Discretize the time-series point demand increase data to obtain discrete time-series point demand increase data; According to the discrete data of the demand increase at the time point, the demand increase data at the time point is subjected to the symmetrical instability time series deviation between different time series points to obtain the symmetrical instability time series deviation data; The instability mutation amplitude is approximated based on the symmetrical instability timing deviation data to obtain the approximate data of power demand instability.

[0019] The present invention first performs a time point demand increase analysis on the power generation power regulation demand data. The time point demand increase analysis helps identify the trend and intensity of load demand fluctuations by calculating the change amplitude of the power grid power regulation demand at different time points. The core value of this step is to reveal the speed and amplitude of the power demand change in the power grid dispatching process, and provide clear quantitative data for subsequent load regulation. This enables the power grid to more accurately predict future load changes, facilitate timely adjustment of the power output of the generator set, and ensure the stability and reliability of the power grid. The time point demand increase data is discretized to obtain discrete data of the time point demand increase. The main purpose of this step is to convert the continuous power demand increase data into discrete data points for further analysis and calculation. Through discretization processing, the power grid dispatching system can more easily analyze the load increase of each time point independently, reducing the complexity of data processing. The discretized data can provide more detailed load fluctuation information, so that the control system can more accurately respond to the dispatching needs of the power grid and reduce the risk of instability. According to the discrete data of the time point demand increase, the time point demand increase data is analyzed for symmetrical instability time series deviations between different time points. By calculating the deviations between different time points, the instability phenomenon of the power grid when facing load fluctuations at different time points can be revealed, especially the symmetrical instability deviation. The analysis of symmetrical instability time series deviation data helps to identify the system deviation or response lag caused by power grid dispatching under certain specific load changes. This analysis can provide a powerful early warning signal for power grid dispatchers to ensure that timely countermeasures can be taken to prevent system instability when instability risks occur. The instability mutation amplitude is approximated based on the symmetrical instability time series deviation data to obtain the approximate power demand instability data. The instability mutation amplitude approximation simulates and predicts the sudden load changes that occur in power grid dispatching and quantifies their impact on power grid operation. This process helps to evaluate the load imbalance or instability that occurs in the power grid during the response process under extreme load fluctuations. By approximate calculation of the mutation amplitude, the potential instability risk of the power grid in the face of large load changes can be identified and predicted in advance, thereby providing timely adjustment suggestions for power grid dispatching to ensure the safe operation of the power system.

[0020] Preferably, step S4 comprises the following steps: Step S41: iteratively learning the thermal power energy input control data to obtain energy input control iterative data; Step S42: designing a global frequency modulation control strategy according to the energy input control iteration data to obtain an energy input global frequency modulation control strategy; Step S43: Feedback the energy input global frequency modulation control strategy to the cloud platform to execute the frequency modulation control method.

[0021] The present invention can continuously optimize the energy input strategy of thermal power units by iteratively learning the thermal power energy input control data. Iterative learning enables the system to gradually improve the accuracy and efficiency of energy input under different operating conditions by repeatedly training and optimizing the model. The beneficial effect of this step is that by continuously adjusting the learning process, the system can identify and respond to the complex pattern of grid load changes, improve the energy dispatching of thermal power units, make energy input more accurate, ensure that the grid load demand is met in a timely and stable manner, and avoid energy waste and excessive consumption. According to the energy input control iteration data obtained by iterative learning, a global frequency regulation control strategy is designed. This process integrates the dispatching data of different generator sets to form a comprehensive frequency regulation control scheme, thereby realizing accurate regulation of the grid frequency. The global frequency regulation control strategy not only takes into account the energy input demand of thermal power units, but also integrates the load changes and dispatching needs of the grid, aiming to optimize the overall grid frequency stability. The beneficial effect of this step is that it can provide a global perspective and solution, improve the ability of the grid to cope with sudden load changes, reduce the risk of frequency fluctuations and system instability, and ensure the safe and efficient operation of the grid. Feedback the designed energy input global frequency control strategy to the cloud platform to execute the frequency control method. This process ensures the real-time execution and dynamic adjustment of the frequency control strategy through the centralized computing and control capabilities of the cloud platform. By receiving and processing real-time data from each generator set, the cloud platform can quickly respond to frequency fluctuations in the power grid and make precise adjustments. The beneficial effect of this step is that the real-time feedback mechanism of the cloud platform makes frequency control more flexible and efficient, and can dynamically adjust the strategy according to the real-time status of the power grid, improve the automation level of the system, and ensure the stability and safety of the power grid in various complex load changes and emergencies.

[0022] Preferably, the present invention further provides a frequency regulation control system of a thermal power unit, which is used to execute the frequency regulation control method of the thermal power unit as described above. The frequency regulation control system of the thermal power unit comprises: The time series load trend analysis module is used to collect the load fluctuation data of the transmission power grid of the thermal power unit through sensors to obtain the load fluctuation data of the transmission power grid; perform time series load trend analysis on the load fluctuation data of the transmission power grid to obtain the load fluctuation time series trend data; The demand management identification module is used to collect the real-time status of thermal power and steam pressure through built-in sensors and based on the load fluctuation time series trend data, and obtain the real-time status data of thermal power and steam pressure respectively; perform thermal energy conversion-steam pressure demand association identification on the real-time status data of steam pressure according to the real-time status data of thermal power, and obtain the thermal energy conversion-steam pressure nonlinear demand association data; The energy input demand control module is used to quantify the power generation frequency regulation demand of the load fluctuation time series trend data according to the heat energy conversion-steam pressure nonlinear demand correlation data, and obtain the power generation frequency regulation demand quantification data; the energy input demand is controlled according to the power generation frequency regulation demand quantification data of the power grid, and the thermal power energy input control data is obtained; The global frequency regulation control strategy design module is used to design the global frequency regulation control strategy according to the thermal power energy input control data, and obtain the energy input global frequency regulation control strategy; the energy input global frequency regulation control strategy is fed back to the cloud platform to execute the frequency regulation control method.

[0023] The beneficial effect of the present invention is that the load fluctuation data of the transmission grid of the thermal power unit is collected by the sensor, and the load change of the grid can be accurately captured. After the time-series load trend analysis, the time-series trend of the grid load fluctuation can be extracted, and then the basic data support for the subsequent power dispatching and control can be provided. The load fluctuation time-series trend data reveals the change law of the grid load, can provide a reliable basis for the adjustment and optimization of the generator set, and is helpful to improve the stability and dispatching efficiency of the power system. The built-in sensor collects the data of thermal power and steam pressure in real time, and the operation status of the thermal power unit can be accurately monitored by analyzing these real-time status data. By correlating and identifying the nonlinear demand relationship between the real-time status data of thermal power and the real-time status data of steam pressure, the dynamic interactive relationship between thermal energy conversion and steam pressure can be revealed. This nonlinear demand correlation data helps to deeply understand the energy efficiency characteristics of the thermal power unit, optimize the unit operation strategy, improve energy conversion efficiency, and reduce resource waste. Based on the nonlinear demand correlation data of thermal energy conversion-steam pressure, the load fluctuation time-series trend data is quantified for the power generation frequency modulation demand, and the frequency modulation demand of the grid can be accurately calculated. This process clarifies the power adjustment requirements of the grid for the thermal power unit by quantifying the frequency modulation demand. According to the quantitative results, further energy input demand control can be carried out to reasonably allocate the energy use of thermal power units and ensure that the energy supply is stable and efficient during load fluctuations. This control strategy effectively improves the load response capability of thermal power units and reduces energy waste. According to the thermal power energy input control data, a global frequency regulation control strategy is designed to achieve the optimal regulation of thermal power units in the entire power grid dispatching. This control strategy will ensure that the power grid can efficiently achieve frequency regulation when the load fluctuates, and ensure the stability and reliability of power supply. Feeding back the global frequency regulation control strategy to the cloud platform means that the frequency regulation scheme can be monitored and adjusted in real time to ensure continuous optimization of the regulation effect. The real-time feedback and regulation capabilities of this cloud platform realize the intelligent dispatching of the whole system, so that the thermal power units can respond to the grid dispatching needs more flexibly and efficiently, thereby improving the overall operation efficiency of the power system. Therefore, the present invention is an optimization process made to a traditional frequency regulation control method of a thermal power unit, which solves the problems of inaccurate analysis of losses and delays in the energy conversion process and large errors in the frequency regulation control accuracy in a traditional frequency regulation control method of a thermal power unit, improves the accuracy of loss and delay analysis in the energy conversion process, and reduces the error in frequency control accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of the steps of a frequency modulation control method for a thermal power unit; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0025] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0026] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0027] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0028] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0029] To achieve this, please refer to Figures 1 to 3 , a frequency modulation control method for a thermal power unit, the method comprising the following steps: Step S1: collecting transmission grid load fluctuation data of thermal power units through sensors to obtain transmission grid load fluctuation data; performing time series load trend analysis on the transmission grid load fluctuation data to obtain load fluctuation time series trend data; Step S2: Using built-in sensors and based on the load fluctuation time series trend data, real-time status data of thermal power and steam pressure are collected to obtain real-time status data of thermal power and real-time status data of steam pressure respectively; according to the real-time status data of thermal power, the real-time status data of steam pressure is subjected to thermal energy conversion-steam pressure demand association identification to obtain thermal energy conversion-steam pressure nonlinear demand association data; Step S3: quantify the power generation frequency regulation demand of the load fluctuation time series trend data according to the heat energy conversion-steam pressure nonlinear demand correlation data to obtain the power generation frequency regulation demand quantification data of the power grid; control the energy input demand according to the power generation frequency regulation demand quantification data of the power grid to obtain the thermal power energy input control data; Step S4: Design a global frequency modulation control strategy based on the thermal power energy input control data to obtain the energy input global frequency modulation control strategy; feed back the energy input global frequency modulation control strategy to the cloud platform to execute the frequency modulation control method.

[0030] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a flow chart of the steps of a frequency modulation control method for a thermal power unit according to the present invention. In this example, the frequency modulation control method for a thermal power unit includes the following steps: Step S1: collecting transmission grid load fluctuation data of thermal power units through sensors to obtain transmission grid load fluctuation data; performing time series load trend analysis on the transmission grid load fluctuation data to obtain load fluctuation time series trend data; In the embodiment of the present invention, the load fluctuation of the transmission power grid is first collected in real time by multiple sensors installed in the thermal power unit. The sensors should include current sensors, voltage sensors, power meters, etc. These sensors record the load change data of the power grid in real time when monitoring the load fluctuation. All the collected data will be recorded in a time series manner to obtain preliminary "transmission power grid load fluctuation data". Then, these load fluctuation data are analyzed by time series load trend analysis method. This process mainly relies on trend analysis methods based on statistics, such as time series analysis and autoregressive integrated moving average (ARIMA) model, to identify long-term trends and short-term fluctuations of load fluctuations. The specific steps are: the collected load data is segmented by hours or minutes, short-term noise is removed by smoothing technology, and trend components, seasonal components and residual components are extracted by time series analysis, and finally "load fluctuation time series trend data" are obtained. This data describes the long-term change trend of power grid load fluctuations, as well as the pattern of seasonal and sudden fluctuations, providing important basic data for subsequent control and prediction.

[0031] Step S2: Using built-in sensors and based on the load fluctuation time series trend data, real-time status data of thermal power and steam pressure are collected to obtain real-time status data of thermal power and real-time status data of steam pressure respectively; according to the real-time status data of thermal power, the real-time status data of steam pressure is subjected to thermal energy conversion-steam pressure demand association identification to obtain thermal energy conversion-steam pressure nonlinear demand association data; In the embodiment of the present invention, the real-time status of thermal power and steam pressure is first collected by built-in sensors. Thermal power sensors and steam pressure sensors should be set at various key parts of the unit to record the thermal power data output by the boiler and the pressure data in the steam system respectively. These real-time data will form "real-time status data of thermal power" and "real-time status data of steam pressure". Based on the "load fluctuation time series trend data", combined with the real-time collected thermal power and steam pressure data, the thermal energy conversion-steam pressure demand association identification is performed. The core of this process is to quantitatively analyze the relationship between thermal power and steam pressure through physical principles. The specific method is to use thermodynamic analysis and thermal energy conversion efficiency formula, calculate the influence of steam pressure on thermal energy conversion efficiency according to real-time thermal power and steam pressure data, and identify the nonlinear demand association between the two. This association analysis mainly relies on nonlinear regression analysis and least squares optimization. By inputting thermal power and steam pressure data into the thermal energy conversion efficiency formula, "thermal energy conversion-steam pressure nonlinear demand association data" is obtained. This data reveals the nonlinear mutual dependence between thermal power and steam pressure under different load conditions, which is the basis for precise control.

[0032] Step S3: quantify the power generation frequency regulation demand of the load fluctuation time series trend data according to the heat energy conversion-steam pressure nonlinear demand correlation data to obtain the power generation frequency regulation demand quantification data of the power grid; control the energy input demand according to the power generation frequency regulation demand quantification data of the power grid to obtain the thermal power energy input control data; In an embodiment of the present invention, the "thermal energy conversion-steam pressure nonlinear demand association data" is used in combination with the "load fluctuation time series trend data" to quantify the power generation frequency regulation demand. The specific operation is: first, the nonlinear demand association data is standardized so as to be associated with the load fluctuation time series trend data. Then, the load fluctuation time series trend data is used to quantify the power generation frequency regulation demand. The dynamic programming algorithm determines the required power regulation amount in each time period based on the historical load fluctuations and equipment response. Finally, the energy input demand is controlled based on the frequency regulation demand quantification results. By analyzing the frequency regulation demand in each time period, a suitable energy input amount is formulated to achieve the purpose of balancing the load fluctuations of the power grid. This process relies on the gradual iterative optimization of the data to ensure the accuracy and adaptability of each control strategy. Finally, the "thermal power energy input control data" is generated, and input data is provided for the subsequent frequency regulation control strategy design.

[0033] Step S4: Design a global frequency modulation control strategy based on the thermal power energy input control data to obtain the energy input global frequency modulation control strategy; feed back the energy input global frequency modulation control strategy to the cloud platform to execute the frequency modulation control method.

[0034] In the embodiment of the present invention, a global frequency regulation control strategy is designed based on the previously generated "thermal power energy input control data". First, the "thermal power energy input control data" is deeply analyzed, and the relationship between each parameter is modeled and simulated using a multi-parameter collaborative optimization algorithm based on system dynamics. The simulation process includes the dynamic changes of multiple parameters such as load fluctuations, power generation efficiency, steam pressure, and thermal power. Through the PID control algorithm in control theory, the changes of these parameters are finely adjusted to obtain the optimal "energy input global frequency regulation control strategy". This strategy can ensure that the thermal power unit can respond accurately and smoothly adjust the power generation under different load fluctuations. Finally, the obtained control strategy is fed back to the cloud platform through a safe and reliable communication protocol to execute the real-time frequency regulation control method. The cloud platform will adjust the unit in real time according to the control strategy to achieve accurate matching of the power generation load and ensure the stable operation of the power grid.

[0035] Preferably, step S1 comprises the following steps: Step S11: collecting transmission grid load fluctuation data of the thermal power unit through sensors to obtain transmission grid load fluctuation data; Step S12: Filling missing values ​​in the transmission grid load fluctuation data to obtain grid load fluctuation filling data; Step S13: Perform time series load trend analysis on the power grid load fluctuation filling data to obtain load fluctuation time series trend data.

[0036] In the embodiment of the present invention, firstly, the transmission grid load fluctuation data of the thermal power unit is collected by multiple sensors. In order to ensure the comprehensiveness and accuracy of the data, the types of sensors used include current sensors, voltage sensors and power meters, etc. These sensors are respectively installed at the grid entrance and the key nodes where the unit is connected to the grid. These sensors record the load fluctuation of the grid in real time by detecting the changes in current, voltage and power, and the collected data include detailed records of the changes in the grid load over time. The frequency of data collection needs to be adjusted according to the fluctuation frequency of the grid load, usually between milliseconds and seconds, to ensure that all details of the load fluctuation can be captured. The collected "transmission grid load fluctuation data" forms a set of time series data sets, each record represents the load value at a time point. This data set then provides a basis for subsequent load trend analysis. The key in this process is how to ensure the real-time and accuracy of the collected data, especially in the case of high load fluctuation and load jump, the sensor should be able to quickly capture the instantaneous changes in the grid load to avoid data lag or omission. For the "transmission grid load fluctuation data" collected in step S11, it is first necessary to fill the missing values ​​therein to ensure the integrity and validity of the data. Missing values ​​are usually caused by various factors, such as sensor failure, data transmission problems, etc. Interpolation is used to fill these missing data. The specific method is to use a linear interpolation algorithm based on time series and estimate it by combining the data of adjacent time points. Assuming that the data at a certain time point is missing, it can be filled by the load values ​​of the previous valid data point and the next valid data point through weighted average or linear interpolation. In addition, for long-term missing data, more complex interpolation algorithms such as cubic spline interpolation or Lagrange interpolation will be used. These methods can provide higher accuracy, especially when the load fluctuation is more severe. In the filling process, attention should be paid to the smoothness of the data to ensure that the interpolated data does not introduce too much fluctuation or outliers. After the missing values ​​are filled, the "grid load fluctuation filling data" obtained will become more complete, providing reliable data support for the next step of time series analysis. Use "grid load fluctuation filling data" to perform time series load trend analysis. First, through data preprocessing, the filled grid load data is sorted in chronological order and input into the load trend analysis system in the form of time series. The core of the analysis is to identify the trend and periodic changes of load fluctuations. Specifically, the time series analysis method based on the autoregressive integrated moving average (ARIMA) model is used. This method can accurately predict the load fluctuation trend in the future by modeling the historical trend of load data. In actual operation, the ARIMA model first performs differential processing on the load data to remove the trend component in the data, and then calculates the optimal model parameters. These parameters include autoregressive terms, differential terms, and moving average terms, and the model is fitted by the least squares method to minimize the error.After the model is established, it will fit the input load data and identify the long-term trend, seasonal fluctuations, and sudden load changes in the load fluctuations. Finally, through the analysis of the ARIMA model, the "load fluctuation time series trend data" obtained can reflect the dynamic change law of the power grid load and clarify the rising, falling or fluctuating trend of the power grid load. This data can not only provide a theoretical basis for the design of frequency control strategies, but also help thermal power units to grasp the changing trend of the power grid load in real time, so as to make timely adjustments when the load fluctuates.

[0037] Preferably, step S2 comprises the following steps: Step S21: collecting the real-time status of thermal power and steam pressure through built-in sensors and based on the load fluctuation time series trend data, and obtaining the real-time status data of thermal power and the real-time status data of steam pressure respectively; Step S22: evaluating the energy conversion efficiency loss of the steam pressure real-time status data according to the thermal power real-time status data to obtain thermal energy conversion efficiency loss data; Step S23: Based on the heat energy conversion efficiency loss data, the real-time state data of steam pressure is subjected to heat energy conversion-steam pressure demand correlation identification to obtain heat energy conversion-steam pressure demand correlation data; Step S24: performing nonlinear structural analysis on the thermal energy conversion-steam pressure demand correlation data to obtain thermal energy conversion-steam pressure nonlinear demand correlation data.

[0038] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: collecting the real-time status of thermal power and steam pressure through built-in sensors and based on the load fluctuation time series trend data, and obtaining the real-time status data of thermal power and the real-time status data of steam pressure respectively; In the embodiment of the present invention, firstly, real-time data acquisition is performed through built-in multiple sensors (such as thermal power sensors, pressure sensors, temperature sensors, etc.). The main task of this process is to obtain the real-time status of thermal power and steam pressure of the thermal power unit during operation. Sensors are installed on boilers, steam turbines and other key equipment to monitor the output of thermal power and the change of steam pressure in real time. The thermal power sensor measures the thermal energy generated by the combustion of fuel in the boiler and converts it into the efficiency of electrical energy, and records the thermal power output value of the boiler in real time. The steam pressure sensor obtains the steam pressure data in time by monitoring the pressure of the steam flow in the boiler. These sensors collect data at a frequency of milliseconds to ensure that the impact of instantaneous load changes on the state of the unit can be reflected. Through the real-time data acquisition of built-in sensors, "real-time status data of thermal power" and "real-time status data of steam pressure" are obtained respectively. These two sets of data will serve as the basic data for subsequent thermal energy conversion efficiency analysis and demand association identification. The key to this process is to ensure the accuracy and stability of the sensor, especially in high temperature and high pressure environments, the sensor must have anti-interference ability to ensure the accuracy of data acquisition.

[0039] Step S22: evaluating the energy conversion efficiency loss of the steam pressure real-time status data according to the thermal power real-time status data to obtain thermal energy conversion efficiency loss data; In the embodiment of the present invention, the energy conversion efficiency loss is first evaluated for the "real-time status data of thermal power" and the "real-time status data of steam pressure". By comparing and analyzing these two sets of data, the efficiency loss in the thermal energy conversion process can be identified. In practical applications, an energy conversion efficiency model is usually used to analyze the relationship between thermal power and steam pressure, so as to evaluate the loss in the energy conversion process. Specifically, it is first necessary to establish a functional relationship between thermal power and steam pressure through a mathematical model. A nonlinear regression analysis method can be used to fit the relationship between thermal power and steam pressure data. After fitting, the theoretical ideal conversion efficiency can be calculated, and compared with the actual collected thermal power data, and the gap between the actual conversion efficiency and the ideal efficiency can be calculated. This gap is the thermal energy conversion efficiency loss. On this basis, the "thermal energy conversion efficiency loss data" calculated by the model can provide an important basis for the next step of demand association identification. The core technology of this process is to accurately model the nonlinear relationship between thermal power and steam pressure, and reasonably estimate the size of the efficiency loss. Through accurate evaluation, the efficiency problems existing in the thermal energy conversion process can be effectively found, and a theoretical basis for subsequent optimization can be provided.

[0040] Step S23: Based on the heat energy conversion efficiency loss data, the real-time state data of steam pressure is subjected to heat energy conversion-steam pressure demand correlation identification to obtain heat energy conversion-steam pressure demand correlation data; In the embodiment of the present invention, the heat energy conversion-steam pressure demand association identification is performed on the "steam pressure real-time status data" based on the "heat energy conversion efficiency loss data". First, the data set used is the relationship between the efficiency loss and the steam pressure in the heat energy conversion process. These data can reflect the impact of the steam pressure change on the heat energy conversion process. Therefore, by analyzing the efficiency loss data, the direct impact of the steam pressure change on the system demand can be identified. Specifically, by associating the heat energy conversion efficiency loss data with the steam pressure real-time status data, the multivariate regression analysis technology is applied to identify the nonlinear relationship between the two. At this time, a regression algorithm such as a generalized linear model (GLM) or a support vector regression (SVR) is used. By fitting these data, the specific impact value of the steam pressure change on the heat energy conversion efficiency is obtained. When performing demand association identification, it is particularly noted that the fluctuation of steam pressure not only affects the heat energy conversion efficiency, but also directly affects the load demand of the unit. Therefore, by identifying these associations, the "heat energy conversion-steam pressure demand association data" can be obtained. This data will provide basic information for the subsequent control demand and frequency modulation demand quantification.

[0041] Step S24: performing nonlinear structural analysis on the thermal energy conversion-steam pressure demand correlation data to obtain thermal energy conversion-steam pressure nonlinear demand correlation data.

[0042] In the embodiment of the present invention, the "heat energy conversion-steam pressure demand correlation data" is used for nonlinear structural analysis to further study the complex nonlinear demand correlation between heat energy conversion and steam pressure. The goal of nonlinear structural analysis is to analyze the complex interaction between heat energy conversion and steam pressure by mathematical methods, and to reveal the behavioral characteristics of the system under different loads and different operating conditions. First, the nonlinear least squares method is used to fit the data and model the "heat energy conversion-steam pressure demand correlation data". At this time, a nonlinear model such as the Lennard-Jones potential energy model or the polynomial regression model is selected to capture the complex relationship in the data that cannot be analyzed by the linear model. In the process of model fitting, by continuously adjusting the parameters and minimizing the fitting error, a nonlinear function that can accurately describe the complex interaction between heat energy conversion and steam pressure is finally obtained. After obtaining the nonlinear model, the structural analysis of the system is performed to reveal the nonlinear demand correlation characteristics between steam pressure and heat energy conversion. Through the analysis results, it can be found that the different effects of steam pressure changes under different operating conditions on heat energy conversion efficiency and load demand provide more refined demand data for the design of subsequent frequency modulation control strategies.

[0043] Preferably, step S23 includes the following steps: Step S231: performing time-varying characteristic analysis on the heat energy conversion efficiency loss data to obtain conversion efficiency loss time-varying data; Step S232: Based on the conversion efficiency loss time-varying data, the real-time state data of steam pressure is evaluated for steam pressure response in different time periods to obtain steam pressure responsiveness evaluation data; Step S233: dividing the steam pressure responsiveness evaluation data into response rate gradient grades to obtain pressure response rate gradient grades; Step S235: performing response rate-energy conversion time-varying correlation subset induction on the conversion efficiency loss time-varying data according to the pressure response rate gradient level to obtain a response rate-energy conversion time-varying correlation subset; Step S236: using Takagi-Sugeno reasoning to identify the thermal energy conversion-steam pressure demand association of the response rate-energy conversion time-varying association subset, and obtain thermal energy conversion-steam pressure demand association data.

[0044] In the embodiment of the present invention, the time-varying characteristics of the "heat conversion efficiency loss data" are analyzed, and the goal is to identify the law of the change of the heat conversion efficiency loss over time. First, the heat conversion efficiency loss data over a period of time is collected, and the frequency of data acquisition is ensured to be high enough to reflect the immediate changes in the operation of the system. Through the time series analysis of these data, the sliding average method is used to smooth the data to remove noise and ensure the accuracy of the analysis results. Next, the Fourier transform (FFT) method is used to perform frequency domain analysis on the heat conversion efficiency loss data to identify the periodic fluctuation characteristics therein. If there is a periodic change, the Fourier transform can extract the main frequency component in the data and reveal the behavioral characteristics of the system at different time scales. In addition, the autoregressive model (AR) can be used to model the heat conversion efficiency loss data to evaluate the change trend and law of its time series. The autoregressive model can predict the change of future efficiency loss based on historical data and reveal whether the system has seasonal or periodic fluctuations. Through the above analysis, the "conversion efficiency loss time-varying data" can be obtained, which reflects the law of change of efficiency loss over time in the heat conversion process, and provides a basis for the evaluation and correlation analysis of the subsequent steps. Based on the "time-varying data of conversion efficiency loss", the "real-time status data of steam pressure" is evaluated for the response of steam pressure in different time periods. The goal of this evaluation is to analyze the impact of changes in steam pressure in different time periods on the loss of thermal energy conversion efficiency. First, the steam pressure data is grouped according to different time periods to ensure that the data in each time period is detailed enough for accurate analysis. Next, the linear regression analysis method is used to evaluate the responsiveness of steam pressure changes to efficiency loss by comparing the steam pressure values ​​in each time period with the corresponding thermal energy conversion efficiency loss data. The linear regression model can help identify the linear relationship between steam pressure and efficiency loss and determine whether there is a significant impact. If the efficiency loss caused by the change in steam pressure fluctuates greatly, it means that the steam pressure has a strong responsiveness to thermal energy conversion, otherwise, it means that the impact is small. In addition, the segmented regression analysis method is used to locally model the steam pressure and thermal energy conversion efficiency loss in different time periods to reveal the heterogeneity of steam pressure response in different time periods. Finally, the "steam pressure responsiveness evaluation data" is obtained, which can be used for further analysis of the pressure response rate in the future. The purpose of dividing the response rate gradient level of the "steam pressure responsiveness evaluation data" is to divide the response rate of steam pressure into different levels, so as to more accurately describe the impact of different response levels on the thermal energy conversion process. First, the gradient analysis method is used to calculate the change rate in the steam pressure responsiveness evaluation data. The specific method is to calculate the change rate of steam pressure at different time points through derivation operations, and obtain the response rate at each time point. According to the size of the response rate, the response of steam pressure can be divided into multiple gradient levels.The interval-based division method is adopted to set different threshold ranges, which are specifically divided into low response, medium response and high response levels. The low response level corresponds to a small change in steam pressure, and the system has a weak adaptability to load fluctuations; the medium response level corresponds to a moderate pressure change and a moderate system response; the high response level corresponds to a large change in steam pressure and a strong system response. The key to this process is how to set the threshold of the response rate. The optimal interval division can be determined by cluster analysis based on the distribution of historical data. The "pressure response rate gradient level" obtained after the division can reflect the response ability of the system under different steam pressure change conditions, and provide a basis for the subsequent energy conversion correlation analysis. According to the "pressure response rate gradient level", the "conversion efficiency loss time-varying data" is summarized into response rate-energy conversion time-varying correlation subsets. The goal of this step is to summarize the relationship between steam pressure and thermal energy conversion efficiency loss at different response rate levels into subsets, and further understand the specific impact of steam pressure on thermal energy conversion efficiency loss under different response conditions. First, according to the "pressure response rate gradient level" obtained in the previous step, the response rate is divided into three levels: high, medium and low. Then, for each level, the corresponding "conversion efficiency loss time-varying data" is selected for analysis. For each response rate level, the weighted average method is used to weight the data under this level, and the "energy conversion time-varying correlation subset" that can represent the response characteristics of this level is extracted. In this process, the steam pressure response data of different levels are grouped to ensure that each subset can accurately reflect the impact of the response rate on energy conversion. In the induction process, the adaptive weighted average method (AWM) is used to determine the weight of each data point. This method can dynamically adjust the weight according to the relative importance of the data to ensure that the final subset accurately reflects the impact of the response rate on the loss of thermal energy conversion efficiency. The summarized "response rate-energy conversion time-varying correlation subset" provides a more accurate understanding of the loss of thermal energy conversion efficiency and lays a data foundation for subsequent demand association analysis. The thermal energy conversion-steam pressure demand association is identified for the "response rate-energy conversion time-varying correlation subset" through Takagi-Sugeno reasoning. Takagi-Sugeno reasoning is a reasoning method based on fuzzy logic that can handle complex nonlinear relationships in the system. First, the "response rate-energy conversion time-varying association subset" is input into the Takagi-Sugeno reasoning model, which performs reasoning based on fuzzy rules to identify the impact pattern of steam pressure changes on thermal energy conversion. Specifically, the fuzzy rule set in the Takagi-Sugeno model, such as "if the steam pressure response rate is high, the thermal energy conversion efficiency loss is large", is used to derive the specific demand association between steam pressure and thermal energy conversion.In the reasoning process, the membership function is used to quantify the response rate of steam pressure, which is converted into numerical input to the model for reasoning, and finally the "heat energy conversion-steam pressure demand correlation data" is obtained. This data can provide a more accurate demand quantification basis for the subsequent thermal power unit frequency regulation control strategy.

[0045] Preferably, step S3 comprises the following steps: Step S31: normalizing the heat energy conversion-steam pressure nonlinear demand correlation data to obtain nonlinear demand correlation normalized data; Step S32: Delay coupling is performed on the load fluctuation time series trend data according to the nonlinear demand associated normalized data to obtain grid load delay data; Step S33: quantifying the power generation frequency regulation demand of the load fluctuation time series trend data based on the power grid load delay data to obtain the power grid power generation frequency regulation demand quantification data; Step S34: energy input demand control is performed on the thermal energy conversion-steam pressure nonlinear demand correlation data according to the quantified data of the power grid power generation frequency regulation demand to obtain thermal power energy input control data.

[0046] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: normalizing the heat energy conversion-steam pressure nonlinear demand correlation data to obtain nonlinear demand correlation normalized data; In an embodiment of the present invention, the "thermal energy conversion-steam pressure nonlinear demand correlation data" is normalized for the purpose of unifying the dimensions of the data to adapt it to subsequent analysis and processing. First, the data range analysis is performed on the "thermal energy conversion-steam pressure nonlinear demand correlation data" to identify the maximum and minimum values ​​in the data set, and a linear normalization method is used. For the normalized data, outlier detection is also required, and a box-plot method is used for detection to screen out abnormal data points. This method calculates the quartiles and interquartile range (IQR) of the data, sets the threshold range of the outliers, and ensures that the processed data has a high quality. Through the above steps, the obtained "nonlinear demand correlation normalized data" can provide a consistent and comparable data basis for the subsequent quantification of delayed coupling and power generation frequency regulation demand.

[0047] Step S32: Delay coupling is performed on the load fluctuation time series trend data according to the nonlinear demand associated normalized data to obtain grid load delay data; In the embodiment of the present invention, the "load fluctuation time series trend data" is delayed coupled based on the "nonlinear demand associated normalized data" in order to reveal the time delay effect between load fluctuation and heat energy conversion. First, it is necessary to define the lag period in the load fluctuation data, that is, the time difference between the impact of load fluctuation on the grid load and its change. The time delay correlation between the nonlinear demand associated normalized data and the load fluctuation time series trend data is calculated using the correlation analysis method. Specifically, autocorrelation analysis and cross-correlation analysis are used to detect the time delay relationship between the two. The autocorrelation analysis method helps determine the delay of the impact of load fluctuation on the grid load by calculating the autocorrelation values ​​of the data under different lag periods; while the cross-correlation analysis method identifies the delay effect of load fluctuation on heat energy conversion by calculating the correlation between the two time series under different lag periods. In this way, the response delay time of load fluctuation to the grid load can be accurately obtained, and delay coupling is performed accordingly to obtain "grid load delay data". This delay coupling process can help analyze the actual impact of load fluctuations in different time periods on the heat energy conversion process, thereby providing accurate data support in time for the subsequent quantification of power generation and frequency regulation demand.

[0048] Step S33: quantifying the power generation frequency regulation demand of the load fluctuation time series trend data based on the power grid load delay data to obtain the power grid power generation frequency regulation demand quantification data; In an embodiment of the present invention, the power generation frequency regulation demand is quantified based on the "load fluctuation time series trend data" based on the "power grid load delay data", with the purpose of accurately calculating the power generation frequency regulation demand of the power grid under specific load fluctuations. First, according to the delay effect of the power grid load fluctuation and the actual load data, a relationship model between load fluctuation and power generation frequency regulation demand is established. The model can adopt the method of dynamic system modeling to consider the time series impact of power grid load fluctuation on power generation frequency regulation. Specifically, a discretized difference equation model is used to describe the dynamic relationship between power grid load fluctuation and power generation frequency regulation demand. By introducing a delay term, the power grid load delay data is coupled with the power generation frequency regulation demand. By solving the difference equation, the "power grid power generation frequency regulation demand quantification data" is obtained, which will provide the actual power generation frequency regulation demand value for the frequency regulation control strategy of the thermal power unit, ensuring that the frequency regulation process can effectively cope with power grid load fluctuations.

[0049] Step S34: energy input demand control is performed on the thermal energy conversion-steam pressure nonlinear demand correlation data according to the quantified data of the power grid power generation frequency regulation demand to obtain thermal power energy input control data.

[0050] In the embodiment of the present invention, the energy input demand control is performed on the "thermal energy conversion-steam pressure nonlinear demand correlation data" according to the "power grid power generation frequency regulation demand quantitative data", with the purpose of adjusting the energy input of the thermal power unit according to the power grid power generation frequency regulation demand to achieve the best frequency regulation effect. First, the power generation frequency regulation demand quantitative data is used as input, and the energy input control strategy is formulated in combination with the nonlinear demand relationship between thermal energy conversion and steam pressure. Specifically, a nonlinear optimization method is used to solve the optimal configuration of energy input according to the power grid power generation frequency regulation demand quantitative data and the thermal energy conversion-steam pressure nonlinear demand correlation data. First, by setting the objective function, the matching degree between energy input and power grid demand is maximized. Through this control process, the "thermal power energy input control data" can be obtained, which determines the energy input amount of the thermal power unit, ensuring that the unit can adjust the output in time when facing power grid load fluctuations to achieve accurate frequency regulation effects.

[0051] Preferably, step S32 includes the following steps: Step S321: performing heat energy conversion-steam pressure conversion efficiency retardation analysis on the nonlinear demand-related normalized data to obtain energy conversion efficiency retardation data; Step S322: Calculate the energy conversion multi-peak extreme value retardation variance of the nonlinear demand-related normalized data according to the energy conversion efficiency retardation data to obtain the energy conversion multi-peak extreme value retardation variance; Step S323: Delay coupling is performed on the load fluctuation time series trend data based on the energy conversion multi-peak extreme value delay variance to obtain the grid load delay data.

[0052] In an embodiment of the present invention, the thermal energy conversion-steam pressure conversion efficiency retardation analysis is first performed on the "nonlinear demand-related normalized data", with the purpose of revealing the time delay characteristics between steam pressure and conversion efficiency during the thermal energy conversion process. The analysis is performed by calculating the hysteresis and retardation of the time series of the "nonlinear demand-related normalized data". The specific operation is: the "nonlinear demand-related normalized data" is subjected to time series analysis, and the time delay effect of the thermal energy conversion process is obtained by calculating the data autocorrelation function under different lag periods (for example, 1 hour, 2 hours, etc.). By analyzing the autocorrelation values ​​under different lag periods, the retardation of the conversion efficiency can be quantified to obtain the "energy conversion efficiency retardation data". The energy conversion multi-peak extreme value retardation variance calculation is performed based on the "energy conversion efficiency retardation data". The core of this step is to identify the multi-peak characteristics existing in the process of energy conversion efficiency change through statistical analysis, and to evaluate the impact of the retardation of these extreme values ​​on the entire conversion process. First, it is necessary to identify the multi-peak extreme values ​​of the "energy conversion efficiency sluggishness data" and use statistical methods such as local extreme value detection (for example, determining the local maximum and minimum values ​​by differential method or filtering method) to mark the multi-peak positions. Subsequently, for these extreme points, the sluggishness variance is calculated. The calculation of the sluggishness variance is completed by the following steps: performing time interval analysis on the identified extreme points and calculating the time difference between adjacent extreme values. Then, by calculating the variance, the slow change characteristics between the multi-peak extreme values ​​can be obtained, that is, the "energy conversion multi-peak extreme value sluggishness variance". Through this sluggishness variance data, we can understand the multiple extreme value changes and their sluggish effects in the energy conversion process, thereby revealing the hysteresis response characteristics of the system to steam pressure changes. Based on the "energy conversion multi-peak extreme value sluggishness variance", the "load fluctuation time series trend data" is delayed coupled, with the aim of further analyzing the timing impact of grid load fluctuations on the frequency regulation demand of the power generation system after considering the hysteresis response characteristics of the conversion efficiency. This step identifies the delayed relationship between load fluctuation and energy conversion efficiency by coupling the hysteresis variance data with the time series of load fluctuation data. The specific operation includes the following steps: calculating the cross-correlation between the "multi-peak extreme value hysteresis variance of energy conversion" and the load fluctuation time series trend data, combining the cross-correlation data, and adjusting the load fluctuation time series trend data through the delay coupling method. The coupling method aligns the time period with a large hysteresis effect with the load fluctuation time series data through weighted averaging or interpolation, thereby obtaining the "grid load delay data". This data can reflect the delay effect of load fluctuation and its impact on the power grid's power generation and frequency regulation needs, providing more accurate input data for subsequent power generation and frequency regulation control.

[0053] Preferably, step S34 includes the following steps: Step S341: Perform power regulation demand analysis on the power grid power generation frequency regulation demand quantified data to obtain power generation power regulation demand data; Step S342: Approximate the instability mutation amplitude of the power generation power regulation demand data to obtain power demand instability approximate data; Step S343: performing time series collaborative optimization on the thermal energy conversion-steam pressure nonlinear demand correlation data according to the power demand instability approximate data to obtain the steam pressure collaborative optimization demand data; Step S344: Perform energy input demand control based on the steam pressure collaborative optimization demand data to obtain thermal power energy input control data.

[0054] In the embodiment of the present invention, the power regulation demand analysis is first performed on the "quantized data of power grid power generation frequency regulation demand". The purpose of this analysis is to extract the real-time demand data required for power generation regulation from the time series data of power grid load fluctuation. The specific operation includes calculating the instantaneous change of load fluctuation data, obtaining its rapid fluctuation part, and analyzing the adjustment amount of power demand in combination with historical load data. By differential calculation of load fluctuation (such as first-order difference method), the load change rate can be obtained, and the power regulation demand is further calculated according to the load change rate. In step S342, the "power generation power regulation demand data" is further approximated for the instability mutation amplitude. The core of this step is to detect and approximate the mutation point in the power grid power generation frequency regulation demand, and identify the power demand mutation amplitude when the system is unstable. This step analyzes the mutation part in the power demand by setting a threshold. First, the change rate of the power demand data is calculated. If the change rate is greater than the set threshold, it is considered that the system is unstable. The amplitude of the power demand change is calculated by gradient analysis or second-order difference method, and an approximate value of the mutation amplitude is obtained. In step S343, the "thermal energy conversion-steam pressure nonlinear demand correlation data" is optimized in a time series based on the "power demand instability approximate data". The goal of this process is to optimize the response of steam pressure during frequency modulation by coupling the nonlinear relationship between the power demand instability mutation amplitude and the steam pressure change. First, the response characteristics of the power demand instability moment and the steam pressure are analyzed, and the time series correlation analysis method, such as cross-correlation or cross-correlation, is used to establish the time series coupling relationship between power demand and steam pressure. Then, these data are optimized in a co-optimized manner using an optimization algorithm (such as gradient descent method, Newton method, etc.) to obtain the best strategy for steam pressure adjustment. In step S344, energy input demand control is performed based on the "steam pressure co-optimization demand data", and finally the "thermal power energy input control data" is obtained. The core goal of this step is to reasonably arrange the energy input of the thermal power unit according to the steam pressure regulation demand. By analyzing the steam pressure demand and combining the energy conversion characteristics of the unit, the appropriate energy input is determined. The process uses the PID control algorithm in control theory to set a control target, such as the stability of steam pressure, and calculates the adjustment amount of energy input based on the regulation requirements.

[0055] Preferably, step S342 includes the following steps: Performing a time-series demand increase analysis on the power generation regulation demand data to obtain time-series demand increase data; Discretize the time-series point demand increase data to obtain discrete time-series point demand increase data; According to the discrete data of the demand increase at the time point, the demand increase data at the time point is subjected to the symmetrical instability time series deviation between different time series points to obtain the symmetrical instability time series deviation data; The instability mutation amplitude is approximated based on the symmetrical instability timing deviation data to obtain the approximate data of power demand instability.

[0056] In the embodiment of the present invention, the power generation power regulation demand data is first analyzed for the demand increase at the time point. The goal of this process is to identify the demand change amplitude of the power regulation demand data at each moment in the time series. The specific operation method is to obtain the demand increase between the time points by calculating the power regulation demand difference between adjacent time points. The increase calculation method adopts the time difference method, that is, in the time series, the data at each moment is taken and the data at the previous moment is differentiated to obtain the increase data. Next, the time point demand increase data is discretized. The purpose of this step is to convert the continuous time series data into discrete points so as to further analyze the changes between the time points. The specific operation method is to discretize the time point demand increase data in segments and discretize the increase data according to a predetermined interval or threshold. For example, by setting a fixed increase interval, the demand increase data is distinguished according to the interval to obtain the discretized time point demand increase data. The discretization method can use equal interval segmentation technology or non-uniform segmentation based on data distribution characteristics so as to better capture the important features of power demand changes. Based on the discrete data of the demand increase at the timing points, the symmetrical instability timing deviation analysis is performed between different timing points. The purpose of this step is to identify the symmetric difference in the power demand increase between the timing points, that is, to analyze the deviation of the power demand in the symmetrical time interval. The specific method is to compare and analyze the increase at the symmetrical time points and calculate the deviation of the demand increase in the previous and next time intervals. This deviation reflects the instability characteristics of the power demand change. Finally, based on the symmetrical instability timing deviation data, the instability mutation amplitude is approximated. The purpose of this step is to approximate the instability mutation amplitude in the power regulation demand through the analysis of the timing deviation. The specific operation method is to identify the mutation amplitude that occurs in the system at a specific moment by approximating the instability timing data. The calculation of the mutation amplitude is usually based on the maximum change rate of the data, and the high-frequency difference method or the local extreme value detection method is used to identify the change amplitude of the power demand under the unstable state.

[0057] Preferably, it is characterized in that step S4 comprises the following steps: Step S41: iteratively learning the thermal power energy input control data to obtain energy input control iterative data; Step S42: designing a global frequency modulation control strategy according to the energy input control iteration data to obtain an energy input global frequency modulation control strategy; Step S43: Feedback the energy input global frequency modulation control strategy to the cloud platform to execute the frequency modulation control method.

[0058] In the embodiment of the present invention, the thermal power energy input control data is firstly iteratively learned to optimize the energy input control strategy. The key to this process is to gradually adjust and improve the control parameters by repeatedly learning historical data and real-time feedback information. In the specific implementation, the parameters of the control strategy are repeatedly updated by applying an iterative optimization algorithm, such as a gradient descent method or a Newton method. Each iteration is adjusted based on the output of the previous round and the feedback data of the current system, so as to gradually reduce the error and optimize the frequency control effect. In each round of iteration, the control data is used to evaluate the effectiveness of the current strategy, and the iteration direction is guided by calculating the error function. The error function is usually defined based on the deviation between the actual and the expected, and the parameter update is guided by minimizing the error function, and finally a set of iterative data is obtained, which can describe how the system adjusts the energy input according to the historical frequency modulation effect. The global frequency control strategy is designed according to the energy input control iterative data. The goal of this process is to design a global frequency control strategy based on the iterative learning results, so that the thermal power unit can achieve stable operation under various load changes. The specific implementation method is to perform global optimization based on iterative learning data, and use an optimization algorithm based on feedback control theory, such as the linear quadratic regulator (LQR) method, to design a global frequency regulation controller. The controller can adjust the energy input in real time according to the change of grid load to ensure the best match between the output power of the thermal power unit and the grid load fluctuation. The design of the control strategy needs to consider the energy conversion efficiency, the change of steam pressure and the nonlinear relationship of thermal energy conversion. Through the comprehensive analysis of these factors, a control scheme that can effectively cope with different load fluctuation scenarios is obtained. The designed energy input global frequency regulation control strategy is fed back to the cloud platform to execute the frequency regulation control method. The core of this step is to pass the optimized control strategy to the cloud platform for execution in a distributed environment. In the specific implementation, the control strategy is transmitted to the cloud platform through a secure network communication protocol. After receiving the control strategy, the cloud platform performs real-time frequency regulation operations according to real-time grid data and the operating status of the thermal power unit. The cloud platform will instruct the thermal power unit to adjust its energy input according to the load fluctuation to ensure that the output of the generator unit matches the demand of the grid load. Through the cloud platform, remote scheduling and optimization control of the thermal power unit can be realized to enhance the system's responsiveness and frequency regulation efficiency. At the same time, the cloud platform can realize coordinated scheduling among multiple units to ensure the stability of the entire power system and maximize energy utilization.

[0059] Preferably, the present invention further provides a frequency regulation control system of a thermal power unit, which is used to execute the frequency regulation control method of the thermal power unit as described above. The frequency regulation control system of the thermal power unit comprises: The time series load trend analysis module is used to collect the load fluctuation data of the transmission power grid of the thermal power unit through sensors to obtain the load fluctuation data of the transmission power grid; perform time series load trend analysis on the load fluctuation data of the transmission power grid to obtain the load fluctuation time series trend data; The demand management identification module is used to collect the real-time status of thermal power and steam pressure through built-in sensors and based on the load fluctuation time series trend data, and obtain the real-time status data of thermal power and steam pressure respectively; perform thermal energy conversion-steam pressure demand association identification on the real-time status data of steam pressure according to the real-time status data of thermal power, and obtain the thermal energy conversion-steam pressure nonlinear demand association data; The energy input demand control module is used to quantify the power generation frequency regulation demand of the load fluctuation time series trend data according to the heat energy conversion-steam pressure nonlinear demand correlation data, and obtain the power generation frequency regulation demand quantification data; the energy input demand is controlled according to the power generation frequency regulation demand quantification data of the power grid, and the thermal power energy input control data is obtained; The global frequency regulation control strategy design module is used to design the global frequency regulation control strategy according to the thermal power energy input control data, and obtain the energy input global frequency regulation control strategy; the energy input global frequency regulation control strategy is fed back to the cloud platform to execute the frequency regulation control method.

[0060] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0061] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. 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 invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A frequency modulation control method for a thermal power unit, characterized in that: The following steps are involved: Step S1: collecting transmission grid load fluctuation data of the thermal power unit through sensors to obtain transmission grid load fluctuation data; Conduct time series load trend analysis on load fluctuation data of transmission power grid to obtain load fluctuation time series trend data; Step S2: Using built-in sensors and based on the load fluctuation time series trend data, real-time status data of thermal power and steam pressure are collected to obtain real-time status data of thermal power and real-time status data of steam pressure respectively; according to the real-time status data of thermal power, the real-time status data of steam pressure is subjected to thermal energy conversion-steam pressure demand association identification to obtain thermal energy conversion-steam pressure nonlinear demand association data; Step S3: quantify the power generation frequency regulation demand of the load fluctuation time series trend data according to the heat energy conversion-steam pressure nonlinear demand correlation data to obtain the power generation frequency regulation demand quantification data of the power grid; control the energy input demand according to the power generation frequency regulation demand quantification data of the power grid to obtain the thermal power energy input control data; Step S4: Design a global frequency modulation control strategy based on the thermal power energy input control data to obtain the energy input global frequency modulation control strategy; feed back the energy input global frequency modulation control strategy to the cloud platform to execute the frequency modulation control method.

2. The frequency modulation control method of a thermal power unit according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: collecting transmission grid load fluctuation data of the thermal power unit through sensors to obtain transmission grid load fluctuation data; Step S12: Filling missing values ​​in the transmission grid load fluctuation data to obtain grid load fluctuation filling data; Step S13: Perform time series load trend analysis on the power grid load fluctuation filling data to obtain load fluctuation time series trend data.

3. The frequency modulation control method of a thermal power unit according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: collecting the real-time status of thermal power and steam pressure through built-in sensors and based on the load fluctuation time series trend data, and obtaining the real-time status data of thermal power and the real-time status data of steam pressure respectively; Step S22: evaluating the energy conversion efficiency loss of the steam pressure real-time status data according to the thermal power real-time status data to obtain thermal energy conversion efficiency loss data; Step S23: Based on the heat energy conversion efficiency loss data, the real-time state data of steam pressure is subjected to heat energy conversion-steam pressure demand correlation identification to obtain heat energy conversion-steam pressure demand correlation data; Step S24: performing nonlinear structural analysis on the thermal energy conversion-steam pressure demand correlation data to obtain thermal energy conversion-steam pressure nonlinear demand correlation data.

4. The frequency modulation control method of a thermal power unit according to claim 3, characterized in that: Step S23 includes the following steps: Step S231: performing time-varying characteristic analysis on the heat energy conversion efficiency loss data to obtain conversion efficiency loss time-varying data; Step S232: Based on the conversion efficiency loss time-varying data, the real-time state data of steam pressure is evaluated for steam pressure response in different time periods to obtain steam pressure responsiveness evaluation data; Step S233: dividing the steam pressure responsiveness evaluation data into response rate gradient grades to obtain pressure response rate gradient grades; Step S235: performing response rate-energy conversion time-varying correlation subset induction on the conversion efficiency loss time-varying data according to the pressure response rate gradient level to obtain a response rate-energy conversion time-varying correlation subset; Step S236: using Takagi-Sugeno reasoning to identify the thermal energy conversion-steam pressure demand association of the response rate-energy conversion time-varying association subset, and obtain thermal energy conversion-steam pressure demand association data.

5. The frequency modulation control method of a thermal power unit according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: normalizing the heat energy conversion-steam pressure nonlinear demand correlation data to obtain nonlinear demand correlation normalized data; Step S32: Delay coupling is performed on the load fluctuation time series trend data according to the nonlinear demand associated normalized data to obtain grid load delay data; Step S33: quantifying the power generation and frequency regulation demand of the load fluctuation time series trend data based on the power grid load delay data to obtain the power grid power generation and frequency regulation demand quantification data; Step S34: energy input demand control is performed on the thermal energy conversion-steam pressure nonlinear demand correlation data according to the quantified data of the power grid power generation frequency regulation demand to obtain thermal power energy input control data.

6. The frequency modulation control method of a thermal power unit according to claim 5, characterized in that: Step S32 includes the following steps: Step S321: performing heat energy conversion-steam pressure conversion efficiency retardation analysis on the nonlinear demand-related normalized data to obtain energy conversion efficiency retardation data; Step S322: Calculate the energy conversion multi-peak extreme value retardation variance of the nonlinear demand-related normalized data according to the energy conversion efficiency retardation data to obtain the energy conversion multi-peak extreme value retardation variance; Step S323: Delay coupling is performed on the load fluctuation time series trend data based on the energy conversion multi-peak extreme value delay variance to obtain the grid load delay data.

7. The frequency modulation control method of a thermal power unit according to claim 5, characterized in that: Step S34 includes the following steps: Step S341: Perform power regulation demand analysis on the power grid power generation frequency regulation demand quantified data to obtain power generation power regulation demand data; Step S342: Approximate the instability mutation amplitude of the power generation power regulation demand data to obtain power demand instability approximate data; Step S343: performing time series collaborative optimization on the thermal energy conversion-steam pressure nonlinear demand correlation data according to the power demand instability approximate data to obtain the steam pressure collaborative optimization demand data; Step S344: Perform energy input demand control based on the steam pressure collaborative optimization demand data to obtain thermal power energy input control data.

8. The frequency modulation control method of a thermal power unit according to claim 7, characterized in that: Step S342 includes the following steps: Performing a time-series demand increase analysis on the power generation regulation demand data to obtain time-series demand increase data; Discretize the time-series point demand increase data to obtain discrete time-series point demand increase data; According to the discrete data of the demand increase at the time point, the demand increase data at the time point is subjected to the symmetrical instability time series deviation between different time series points to obtain the symmetrical instability time series deviation data; The instability mutation amplitude is approximated based on the symmetrical instability timing deviation data to obtain the approximate data of power demand instability.

9. The frequency modulation control method of a thermal power unit according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: iteratively learning the thermal power energy input control data to obtain energy input control iterative data; Step S42: Design a global frequency modulation control strategy according to the energy input control iteration data to obtain an energy input global frequency modulation control strategy; Step S43: Feedback the energy input global frequency modulation control strategy to the cloud platform to execute the frequency modulation control method.

10. A frequency modulation control system for a thermal power unit, characterized in that: Used to execute the frequency regulation control method of a thermal power unit according to claim 1, the frequency regulation control system of the thermal power unit comprises: The time series load trend analysis module is used to collect the load fluctuation data of the transmission power grid of the thermal power unit through sensors to obtain the load fluctuation data of the transmission power grid; perform time series load trend analysis on the load fluctuation data of the transmission power grid to obtain the load fluctuation time series trend data; The demand management identification module is used to collect the real-time status of thermal power and steam pressure through built-in sensors and based on the load fluctuation time series trend data, and obtain the real-time status data of thermal power and steam pressure respectively; perform thermal energy conversion-steam pressure demand association identification on the real-time status data of steam pressure according to the real-time status data of thermal power, and obtain the thermal energy conversion-steam pressure nonlinear demand association data; The energy input demand control module is used to quantify the power generation frequency regulation demand of the load fluctuation time series trend data according to the heat energy conversion-steam pressure nonlinear demand correlation data, and obtain the power generation frequency regulation demand quantification data; the energy input demand is controlled according to the power generation frequency regulation demand quantification data of the power grid, and the thermal power energy input control data is obtained; The global frequency regulation control strategy design module is used to design the global frequency regulation control strategy according to the thermal power energy input control data, and obtain the energy input global frequency regulation control strategy; the energy input global frequency regulation control strategy is fed back to the cloud platform to execute the frequency regulation control method.

Citation Information

Patent Citations

  • Optimization method for improving primary frequency modulation qualification rate of thermal power generating unit

    CN110174838A

  • Thermal generator set coordination control system based on internal model control structure

    CN111429010A

  • Frequency modulation control method for improving AGC performance of thermal power generating unit

    CN115133579A

  • Thermal power generating unit primary frequency modulation control method, system and equipment and storage medium

    CN116365545A

  • Power system active frequency control method and system based on data driving

    CN117277307A

Cited By

  • Intelligent steam supply regulation and control system and method based on data analysis

    CN120779729A