A heat supply and demand balance adjusting system for a steam turbine of a thermal power plant

Abstract

This invention discloses a heating and demand balance regulation system for steam turbines in thermal power plants, relating to the field of thermal power plant heating technology. The system includes a data acquisition and processing module: meteorological monitoring equipment and sensors are deployed at key locations in the heating area and at heat users to collect meteorological and heating demand data. After preprocessing, the data is fused and transmitted to subsequent modules. This invention deeply integrates meteorological forecasting and heating regulation systems, using high-precision meteorological monitoring equipment to acquire meteorological parameters in real time and employing machine learning algorithms to accurately predict future heating demand trends. This enables the system to quickly and accurately adjust heating strategies based on different meteorological conditions, prioritizing heating stability and safety, effectively improving the timeliness and accuracy of heating and demand balance regulation, avoiding energy waste caused by insufficient or excessive heating, significantly improving energy utilization efficiency, and reducing the operating costs of thermal power plants.

Description

Technical Field

[0001] This invention relates to the field of heating technology in thermal power plants, specifically to a heating supply and demand balance regulation system for steam turbines in thermal power plants. Background Technology

[0002] In the energy supply sector, thermal power plants, as important energy production units, rely on the stable operation of their heating systems to ensure the heating needs of residents and industrial users. With the increasing demands for energy efficiency and environmental protection, how to achieve precise regulation and efficient operation of thermal power plant heating systems has become an urgent problem to be solved. Meteorological factors, as key external conditions affecting heating demand, can significantly impact users' heating needs due to changes in temperature, humidity, and wind speed under different meteorological conditions. Therefore, deeply integrating meteorological data with the heating regulation system to achieve accurate prediction and intelligent regulation of heating demand has become an important research direction for improving the performance of thermal power plant heating systems.

[0003] In traditional thermal power plant heating systems, the utilization of meteorological data has several shortcomings. First, while existing systems can acquire some meteorological data, they lack refined processing and prioritization of different meteorological elements. In actual operation, different meteorological elements have varying degrees of impact on heating demand. For example, temperature typically has a more direct and significant impact on heating demand, while the impacts of elements such as humidity and wind speed are relatively complex. However, traditional systems fail to fully consider these differences, resulting in an inability to accurately grasp key meteorological elements when formulating heating strategies. This makes it difficult to adjust heating strategies in a timely and accurate manner based on changes in actual meteorological conditions. Second... For medium- and long-term meteorological trends and extreme weather events, existing systems are unable to predict them in advance and take effective countermeasures. Accurate prediction of medium- and long-term meteorological trends is of great significance for the rational arrangement of heating plans and resource allocation. Extreme weather events such as blizzards and severe cold may suddenly lead to a significant increase in heating demand. If early warnings are not given and countermeasures are not prepared, it will seriously affect the stable operation of the heating system and may even lead to safety accidents. In addition, traditional systems perform poorly in terms of the timeliness and accuracy of heating supply and demand balance regulation, often resulting in serious energy waste and increasing heating costs and environmental pressure. Summary of the Invention

[0004] The purpose of this invention is to provide a heating and demand balance regulation system for steam turbines in thermal power plants, so as to solve the problems of low timeliness and accuracy in heating and demand balance regulation of traditional systems.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: Firstly, a method for regulating the heat supply and demand balance of a steam turbine in a thermal power plant includes the following steps: Meteorological monitoring equipment and sensors are deployed at key locations in the heating area and at heat users to collect meteorological data and real-time heating demand data. After preprocessing, the data is fused to obtain fused data of processed meteorological data and real-time heating demand data. Historical data and abnormal signals are retrieved and integrated. The data correlation is analyzed and the priority weights of meteorological elements are set. After the priority weights of the meteorological elements are dynamically adjusted, the heating demand trend is predicted, and early warning information and prediction data are generated for extreme weather events. Based on the aforementioned early warning information, forecast data, and processed real-time heating demand data, and according to the priority weights of the aforementioned meteorological elements, the heating demand is comprehensively analyzed to generate precise control commands, while providing a visual interface to support manual intervention. The equipment is regulated according to the precise control commands to ensure stable pipeline pressure and heating in key areas, optimize flow distribution, control the charging and discharging of the heat storage tank, monitor the energy storage status and provide feedback, and achieve a balance between heating supply and demand.

[0006] In some implementations, the steps of deploying meteorological monitoring equipment and sensors at key locations in the heating area and at heat users to collect meteorological data and real-time heating demand data specifically include: Meteorological monitoring equipment and sensors at key locations in the heating area collect temperature, humidity, wind speed and solar radiation intensity at a fixed frequency. Meteorological monitoring equipment and sensors at heat users adopt a redundant design and collect temperature, flow rate and pressure through multiple verification mechanisms. The data fusion is performed using the following formula:

[0007] in, It is integrated data. For the processed meteorological data, For processed real-time heating demand data, , For different fusion weight coefficients, and ; The meteorological data includes temperature, humidity, wind speed, and solar radiation intensity, while the real-time heating demand data includes temperature, flow rate, and pressure.

[0008] In some implementations, the steps of retrieving historical data and abnormal signals, integrating the fused data, abnormal signals, and historical data, analyzing data correlations, setting priority weights for meteorological elements, dynamically adjusting the priority weights of the meteorological elements to predict heating demand trends, and generating early warning information and forecast data for extreme weather events specifically include: Historical data and anomalies are obtained by retrieving historical databases, user behavior databases and building energy consumption model data. Combined with the fused data, a multi-source data fusion architecture is constructed. The correlation weights between different meteorological elements and heating demand are determined through data correlation analysis, and a dynamic weight adjustment mechanism is established. Based on the dynamic weight adjustment mechanism, the weight matrix of the correlation weights is updated through real-time heating demand data, and time-series prediction is performed based on the multi-source data fusion architecture to generate heating demand prediction sequences at different time scales. Extreme weather events are identified through a preset threshold judgment mechanism to generate early warning information and prediction data. The step of determining the correlation weights between different meteorological elements and heating demand through data correlation analysis is specifically calculated using the following formula:

[0009] in, It is the priority weight of meteorological elements. It is the first The meteorological elements and the first The correlation coefficients of various factors affecting heating demand For the first The importance coefficient of each factor affecting heating demand It refers to the quantity of meteorological elements. It is the number of factors affecting heating demand.

[0010] In some implementations, the step of generating heating demand forecast sequences at different time scales based on the multi-source data fusion architecture is specifically performed using the following formula for time-series forecasting:

[0011] in, It is the predicted heating demand. For the first Predicted values ​​of each meteorological element For the first The weighting coefficients of non-meteorological heating demand influencing factors. For the first Relevant data values ​​for non-meteorological factors affecting heating demand. This is a bias term.

[0012] In some implementations, the heating demand is comprehensively analyzed based on the early warning information, forecast data, and processed real-time heating demand data, and according to the priority weights of the meteorological elements, to generate precise control commands. Simultaneously, a visual interface is provided to support manual intervention. Specifically, this includes: Based on the early warning information, forecast data, and processed real-time heating demand data, a multi-objective optimization decision model is used to process the control requirements corresponding to high-weight meteorological elements, generating a sequence of precise control commands for the equipment. The sequence of precise control commands includes priority sorting and execution timing planning.

[0013] In some implementations, the step of processing the control requirements corresponding to high-weight meteorological elements through a multi-objective optimization decision model to generate a sequence of precise control commands for the equipment is specifically achieved by generating the sequence of precise control commands for the equipment using the following formula:

[0014] in, A set of equipment control commands. For the first Target values ​​for the operating indicators of a heating system In control commands Under the action, the first The actual values ​​of the operating indicators of the heating system.

[0015] Secondly, a heat supply and demand balancing regulation system for a steam turbine in a thermal power plant, the system comprising: Data acquisition and processing module: Meteorological monitoring equipment and sensors are deployed at key locations in the heating area and at heat users to collect meteorological and heating demand data. After preprocessing, the data is merged and transmitted to subsequent modules. Demand Forecasting and Analysis Module: Integrates processed meteorological data, abnormal signals, real-time heating demand data and historical data, analyzes data correlations, sets priority weights for meteorological elements and dynamically adjusts them, forecasts heating demand trends, generates early warning information and forecast data for extreme weather events and sends them to the control decision module. Control Decision Module: Receives early warning information and forecast data, comprehensively analyzes heating demand based on the priority weight of meteorological elements, generates precise control commands and sends them to the equipment regulation and energy storage coordination module, while providing a visual interface to support manual intervention; Equipment control and energy storage coordination module: Connects steam turbine related equipment, circulating water pumps and flow distribution valves, controls equipment according to control commands, ensures stable pipeline pressure and heating in key areas, optimizes flow distribution, controls the thermal storage tank to charge and discharge according to strategy, monitors energy storage status and provides feedback, and coordinates to ensure heating.

[0016] In some implementations, the data acquisition and processing module fuses data. Meteorological monitoring equipment and sensors are deployed at key locations within the heating area and at heat users. The meteorological monitoring equipment is installed at key nodes in the heating area according to a preset spatial distribution, collecting temperature, humidity, wind speed, and solar radiation parameters at a fixed frequency. User-end monitoring equipment employs a redundant design, collecting temperature, flow rate, and pressure data through multiple verification mechanisms. After preliminary processing, the collected data is fused using the following fusion formula: ,in, It is integrated data. The processed meteorological data vector contains parameters such as temperature, humidity, wind speed, and solar radiation intensity. This is a processed vector of heat user heating demand data, containing temperature, flow rate, and pressure parameters. , To integrate the weighting coefficients, and .

[0017] In some implementations, the demand forecasting and analysis module receives a multidimensional dataset from the data acquisition module, and simultaneously retrieves historical databases, user behavior databases, and building energy consumption model data to construct a multi-source data fusion architecture. Through data correlation analysis, it determines the correlation weights between different meteorological elements and heating demand, establishes a dynamic weight adjustment mechanism, updates the weight matrix based on real-time data, performs time-series forecasting based on the fused data, generates heating demand forecast sequences at different time scales, and identifies the risk of extreme weather events through a threshold judgment mechanism, generating early warning signals and forecast data packets to be sent to the decision-making module.

[0018] In some implementations, the demand forecasting and analysis module determines the correlation weights between different meteorological elements and heating demand through data correlation analysis, and the calculation formula is as follows: ,in, It is the priority weight of meteorological elements. It is the first The meteorological elements and the first The correlation coefficients of various factors affecting heating demand For the first The importance coefficient of each factor affecting heating demand It refers to the quantity of meteorological elements. It is the number of factors affecting heating demand.

[0019] In some implementations, the demand forecasting and analysis module performs time-series forecasting based on fused data, generating heating demand forecast sequences at different time scales, with the following forecasting formula:

[0020] in, It is the predicted heating demand. For the first Predicted values ​​of each meteorological element For the first The weighting coefficients of non-meteorological heating demand influencing factors. For the first Relevant data values ​​for non-meteorological factors affecting heating demand. This is a bias term.

[0021] In some implementations, the control decision module receives early warning signals and forecast data from the prediction module and real-time data from the acquisition module. It processes the control requirements corresponding to high-weight meteorological parameters through a multi-objective optimization decision model, generates a sequence of equipment control commands, including priority sorting and execution timing planning. The decision-making process supports human-machine collaborative intervention, and displays multi-dimensional data and decision-making schemes through a visual interface. Operators can modify commands through an access verification mechanism.

[0022] In some implementations, the control decision module processes the control requirements corresponding to high-weight meteorological parameters through a multi-objective optimization decision model, generating a sequence of equipment control commands. The command generation formula is as follows: ,in, For the possible set of device control commands, For the first The target values ​​for the operating indicators of the heating system are set initially through theoretical analysis and simulation tests, based on the design objectives of the heating system and the operating characteristics of the equipment. In control commands Under the action, the first The actual values ​​of each operating indicator of the heating system are monitored in real time during system operation to determine the deviations between the actual values ​​and target values, as well as their interrelationships. If the deviation of a certain indicator has a significant impact, its weight in the formula is increased. An optimization algorithm is used to balance the weights of each indicator, and finally, the set of control commands that minimizes the objective function is determined. Send to the equipment control and energy storage coordination module.

[0023] In some implementations, the equipment control and energy storage coordination module is connected to the turbine inlet steam regulating valve, extraction steam regulating valve, and heating steam bypass system. It also controls the circulating water pump speed and the opening of the heating network branch flow distribution valve. Based on the instructions of the control decision module, it precisely controls the turbine heating-related equipment to determine the turbine's steam intake, prioritizes heating in key areas during extreme weather event warnings, monitors heating network parameters in real time and dynamically optimizes flow distribution, and uses heat storage tanks equipped with complete insulation measures. Based on the charging and discharging strategy formulated by the control decision module, it stores thermal energy before extreme weather events and releases thermal energy to coordinate with the turbine for heating during peak heating demand. It monitors its own energy storage status parameters in real time and feeds them back to the control decision module to adjust the charging and discharging strategy.

[0024] In some implementations, the equipment regulation and energy storage coordination module precisely regulates the turbine heating-related equipment according to the instructions of the control decision module, thereby determining the steam inlet flow rate of the turbine. The formula for determining the steam inlet flow rate is as follows: ,in, This indicates the adjusted steam intake volume of the steam turbine. This represents the basic steam intake volume of the steam turbine under normal operating conditions. The steam inlet volume adjustment value, calculated based on the priority weights of meteorological elements and changes in meteorological parameters, reflects the impact of meteorological conditions on the steam inlet volume. This formula is used to calculate the adjusted steam turbine intake value, which is obtained by calculating the difference between the predicted heating demand and the current actual heating load, to meet changes in heating demand. Control the steam turbine inlet regulating valve equipment to ensure stable pipeline pressure and heating in key areas.

[0025] In some implementations, the equipment regulation and energy storage coordination module formulates a charging and discharging strategy based on the control decision module, specifically using the formula: , in, This is the operation command for the energy storage device, with a value of This indicates a charging operation, with a value of [value to be filled in]. This indicates a discharge operation; a value of 0 indicates that no charge / discharge operation is performed. The current remaining energy of the energy storage device; , The set charge and discharge thresholds for the energy storage device, and Used to control the start conditions for charging and discharging. Forecast heating demand This represents the actual heating capacity of the current steam turbine and other heating equipment.

[0026] Compared with the prior art, the present invention has the following beneficial effects: This invention provides a method for regulating the supply and demand balance of heating in a thermal power plant's steam turbine. By setting priority weights for different meteorological elements under different meteorological conditions based on heating demand, historical heating data, and the correlation between meteorological data and heating demand, the weights can be dynamically adjusted as new data accumulated during system operation and actual heating conditions. When extreme weather events are predicted, the system can automatically generate the highest priority early warning information and take timely countermeasures, enhancing the system's ability to respond to extreme weather events, ensuring stable heating under severe weather conditions, guaranteeing users' heating needs, and improving the reliability and safety of the heating system.

[0027] This invention provides a heating and demand balance regulation system for steam turbines in thermal power plants. By deeply integrating meteorological forecasting and heating regulation systems, it acquires meteorological parameters in real time using high-precision meteorological monitoring equipment and utilizes machine learning algorithms to accurately predict future heating demand trends. This enables the system to quickly and accurately adjust heating strategies based on different meteorological conditions, prioritizing heating stability and safety. It effectively improves the timeliness and accuracy of heating and demand balance regulation, avoids energy waste caused by insufficient or excessive heating, significantly improves energy utilization efficiency, and reduces the operating costs of thermal power plants. Attached Figure Description

[0028] Figure 1 A schematic diagram of a heat supply and demand balance regulation system for a steam turbine in a thermal power plant; Figure 2 This is a flowchart of a steam turbine heating and demand balance regulation system for a thermal power plant. Detailed Implementation

[0029] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0030] Example 1 This embodiment provides a method for regulating the heat supply and demand balance of a steam turbine in a thermal power plant, characterized by the following steps: S1. Meteorological monitoring equipment and sensors are deployed at key locations in the heating area and at heat users to collect meteorological data and real-time heating demand data. After preprocessing (data cleaning and filtering), the data is fused to obtain the fused data of processed meteorological data and real-time heating demand data. S2, retrieve historical data and abnormal signals, integrate the fused data, abnormal signals and historical data, analyze the data correlation and set the priority weight of meteorological elements, dynamically adjust the priority weight of meteorological elements and predict the heating demand trend, and generate early warning information and prediction data for extreme weather events. S3. Based on the early warning information, forecast data, and processed real-time heating demand data, and according to the priority weight of the meteorological elements, comprehensively analyze the heating demand, generate precise control instructions, and provide a visual interface to support manual intervention. S4, according to the precise control command, regulate the equipment to ensure stable pipeline pressure and heating in key areas, optimize flow distribution, control the charging and discharging of the heat storage tank, monitor the energy storage status and provide feedback, and achieve a balance between heating supply and demand.

[0031] In S1, meteorological monitoring equipment and sensors at key locations in the heating area collect temperature, humidity, wind speed and solar radiation intensity at a fixed frequency. Meteorological monitoring equipment and sensors at heat users adopt a redundant design and collect temperature, flow rate and pressure through multiple verification mechanisms. The data fusion is performed using the following formula:

[0032] in, It is integrated data. For the processed meteorological data, For processed real-time heating demand data, , For different fusion weight coefficients, and ; The meteorological data includes temperature, humidity, wind speed, and solar radiation intensity, while the real-time heating demand data includes temperature, flow rate, and pressure.

[0033] In S2, historical data and anomalies are retrieved from historical databases, user behavior databases, and building energy consumption model data. Combined with the fused data, a multi-source data fusion architecture is constructed. Through data correlation analysis, the correlation weights between different meteorological elements and heating demand are determined, and a dynamic weight adjustment mechanism is established. Based on the dynamic weight adjustment mechanism, the weight matrix of the correlation weights is updated through real-time heating demand data, and time-series prediction is performed based on the multi-source data fusion architecture to generate heating demand prediction sequences at different time scales. Extreme weather events are identified through a preset threshold judgment mechanism to generate early warning information and prediction data. The step of determining the correlation weights between different meteorological elements and heating demand through data correlation analysis is specifically calculated using the following formula:

[0034] in, It is the priority weight of meteorological elements. It is the first The meteorological elements and the first The correlation coefficients of various factors affecting heating demand For the first The importance coefficient of each factor affecting heating demand It refers to the quantity of meteorological elements. It is the number of factors affecting heating demand.

[0035] In S2, the step of generating heating demand forecast sequences at different time scales based on the multi-source data fusion architecture is specifically performed using the following formula for time-series forecasting:

[0036] in, It is the predicted heating demand. For the first Predicted values ​​of each meteorological element For the first The weighting coefficients of non-meteorological heating demand influencing factors. For the first Relevant data values ​​for non-meteorological factors affecting heating demand. This is a bias term.

[0037] In S3, based on the early warning information, forecast data, and processed real-time heating demand data, and according to the priority weights of the meteorological elements, the heating demand is comprehensively analyzed to generate precise control commands. A visual interface is also provided to support manual intervention. Specifically, this includes: Based on the early warning information, forecast data, and processed real-time heating demand data, a multi-objective optimization decision model is used to process the control requirements corresponding to high-weight meteorological elements, generating a sequence of precise control commands for the equipment. The sequence of precise control commands includes priority sorting and execution timing planning.

[0038] In S3, the step of processing the control requirements corresponding to high-weight meteorological elements through a multi-objective optimization decision model and generating a sequence of precise control commands for the equipment is specifically generated by the following formula:

[0039] in, A set of equipment control commands. For the first Target values ​​for the operating indicators of a heating system In control commands Under the action, the first The actual values ​​of the operating indicators of the heating system.

[0040] Specifically, in the process of precisely controlling the equipment, the steam turbine heating-related equipment is adjusted to determine the steam inlet flow rate of the steam turbine. The formula for determining the steam inlet flow rate is as follows: ,in, This indicates the adjusted steam intake volume of the steam turbine. This represents the basic steam intake volume of the steam turbine under normal operating conditions. The steam inlet volume adjustment value, calculated based on the priority weights of meteorological elements and changes in meteorological parameters, reflects the impact of meteorological conditions on the steam inlet volume. This formula is used to calculate the adjusted steam turbine intake value, which is obtained by calculating the difference between the predicted heating demand and the current actual heating load, to meet changes in heating demand. Control the steam turbine inlet regulating valve equipment to ensure stable pipeline pressure and heating in key areas.

[0041] Before controlling the charging and discharging of the thermal storage tank, a charging and discharging strategy needs to be formulated. The charging and discharging strategy is formulated using the following formula: , in, This is the operation command for the energy storage device, with a value of This indicates a charging operation, with a value of [value to be filled in]. This indicates a discharge operation; a value of 0 indicates that no charge / discharge operation is performed. The current remaining energy of the energy storage device; , The set charge and discharge thresholds for the energy storage device, and Used to control the start conditions for charging and discharging. Forecast heating demand This represents the actual heating capacity of the current steam turbine and other heating equipment.

[0042] Example 2 like Figure 1 and Figure 2 As shown in the figure, this embodiment provides a steam turbine heating and demand balance regulation system for thermal power plants. The system includes: Data acquisition and processing module: Meteorological monitoring equipment and sensors are deployed at key locations in the heating area and at heat users to collect meteorological and heating demand data. After preprocessing, the data is merged and transmitted to subsequent modules. Demand Forecasting and Analysis Module: Integrates processed meteorological data, abnormal signals, real-time heating demand data and historical data, analyzes data correlations, sets priority weights for meteorological elements and dynamically adjusts them, forecasts heating demand trends, generates early warning information and forecast data for extreme weather events and sends them to the control decision module. Control Decision Module: Receives early warning information and forecast data, comprehensively analyzes heating demand based on the priority weight of meteorological elements, generates precise control commands and sends them to the equipment regulation and energy storage coordination module, while providing a visual interface to support manual intervention; Equipment control and energy storage coordination module: Connects steam turbine related equipment, circulating water pumps and flow distribution valves, controls equipment according to control commands, ensures stable pipeline pressure and heating in key areas, optimizes flow distribution, controls the thermal storage tank to charge and discharge according to strategy, monitors energy storage status and provides feedback, and coordinates to ensure heating.

[0043] The following is an introduction to the application of this system in the southern and northern regions: (1) In a frigid region in northern my country, the local thermal power plant started the installation and commissioning of the system one month before the start of the heating season. In terms of data acquisition and processing modules, the technicians made careful arrangements in the heating area and evenly set up 10 meteorological monitoring points within a 5-kilometer radius around the power plant. Each monitoring point was equipped with high-precision temperature, humidity, wind speed and solar radiation intensity sensors. These sensors transmitted the data to the power plant's data processing center in real time through the 5G transmission network. At the heat user end, more than 3,000 redundant temperature, flow and pressure sensors were installed at the heat exchange stations in residential areas, the steam inlets of factories and the main heating pipes of public buildings to ensure the accuracy and reliability of the heating demand data acquisition. During the commissioning process, the staff calibrated the accuracy of the sensors one by one and tested the stability of the data transmission multiple times to ensure that the data could be transmitted to the subsequent modules accurately and in a timely manner.

[0044] After the heating season officially begins, the system enters real-time operation. At 2 a.m. one day, the temperature sensor of the data acquisition and processing module detected that the temperature dropped sharply by 8°C within 1 hour. Based on the preset rules, this abnormal meteorological signal was identified, and all the collected meteorological and heating demand data were quickly cleaned and filtered. The processed data was then transmitted to the demand forecasting and analysis module.

[0045] After receiving the data, the demand forecasting and analysis module quickly retrieves heating data from the historical heating database under the same sudden temperature drop conditions. It then combines this data with current user heating habits (such as generally higher temperature settings during nighttime sleep) and building energy consumption model data, applying the meteorological element priority weighting calculation formula. Due to the sudden drop in temperature, the priority weight of temperature was increased from 0.7 to 0.9 after recalculation. It is the correlation coefficient between temperature and various factors affecting heating demand. The importance coefficients of each factor influencing heating demand are then determined using the heating demand forecasting formula. ,in These are forecast values ​​for meteorological elements. The weighting coefficients for non-meteorological factors influencing heating demand. These are relevant data values ​​for factors influencing non-meteorological heating demand. As a bias term, due to the sudden drop in temperature, this module increases the priority weight of temperature from the original 0.7 to 0.9. Through complex data calculation and analysis, it predicts that the heating demand will surge by 30% in the next 24 hours, and generates the highest priority early warning information and detailed forecast data, which are sent to the control decision module.

[0046] Upon receiving early warning information and forecast data, the control decision module immediately activates the emergency response mechanism and generates formulas through control commands. ,in, For the possible set of device control commands, For the first The target values ​​for the operating indicators of the heating system are set initially through theoretical analysis and simulation tests, based on the design objectives of the heating system and the operating characteristics of the equipment. In control commands Under the action, the first Based on the actual values ​​of the operating indicators of the heating system, and after comprehensive analysis of the operating indicators of the heating system, this module sends a series of precise control commands to the equipment control and energy storage coordination module: First, it requires the steam turbine inlet regulating valve to increase the opening by 20%, increasing the steam inlet flow from 500 tons per hour to 600 tons per hour, while the extraction steam regulating valve is adjusted synchronously to quickly increase the heat output of the steam turbine. Second, it commands the heat storage tank to release the currently stored 100,000 GJ of heat energy into the heating network at a rate of 20,000 GJ per hour. Finally, it instructs the circulating water pump to increase its speed by 15% and increase the heat medium circulation flow to ensure that heat can be quickly delivered to each heat user.

[0047] The equipment control and energy storage coordination module strictly executes control commands, and the turbine operators respond quickly, gradually increasing the steam inlet flow through the automated control system. The formula for determining the steam inlet flow is: ,in, This indicates the adjusted steam intake volume of the steam turbine. This represents the basic steam intake volume of the steam turbine under normal operating conditions. The steam inlet volume adjustment value, calculated based on the priority weights of meteorological elements and changes in meteorological parameters, reflects the impact of meteorological conditions on the steam inlet volume. To adjust the steam intake based on the difference between the predicted heating demand and the current actual heating load, and to closely monitor various operating parameters of the steam turbine to ensure safe and stable operation of the equipment, the control system of the heat storage tank automatically opens the heat release valve, continuously injecting the stored heat energy into the heating network. Upon receiving the instruction, the circulating water pump increases its speed within 5 minutes, significantly increasing the heat medium circulation flow. Throughout the heating process, each module continuously monitors parameters such as pressure and temperature of the heating network in real time and feeds the data back to the control decision module. Based on the feedback data, the control decision module makes a fine adjustment to the heating strategy every 15 minutes to ensure that the heating system is always in optimal operating condition. Thanks to the system's rapid response and precise adjustment, the indoor temperature of residents has remained between 20℃ and 22℃, and the factory's production equipment is also operating normally due to the stable heat supply, effectively resisting the impact of this cold wave.

[0048] (2) In recent years, a city in the south has vigorously promoted centralized heating, and a local thermal power plant is responsible for providing winter heating services.

[0049] During the system installation phase, the data acquisition and processing module fully considered the characteristics of the southern climate. In addition to conventional temperature, humidity, and wind speed sensors, the meteorological monitoring equipment also included a body temperature sensor. Twenty meteorological monitoring points were set up in representative locations in different areas of the city, such as the city center, suburbs, and riverside, to ensure comprehensive and accurate collection of meteorological data. At the heat user end, temperature, flow, and pressure sensors of different accuracies and types were installed to cater to the different heating characteristics of residential communities, commercial complexes, and government office buildings. For example, high-precision, high-frequency sensors were installed on the restaurant floors of commercial complexes, where heating demand fluctuates greatly. In residential communities, a sensor configuration that balances accuracy and cost was adopted. After installation, technicians conducted a week-long trial operation monitoring of all sensors to evaluate and optimize the accuracy and stability of data acquisition. On a winter evening, the data acquisition and processing module detected that the air humidity rose from 60% to 85% within 3 hours, while the temperature dropped by 3°C. After quickly processing the data, the module transmitted the relevant information to the demand forecasting and analysis module. This module, combined with historical heating data, found that under similar high humidity and low temperature weather conditions, the heating demand of residents and commercial users would increase by 20%-25%. Therefore, the module increased the priority weights of humidity and temperature to 0.8 and 0.7, respectively. After comprehensively analyzing various data, it predicted that the heating demand would increase by 22% in the next 12 hours and promptly sent early warning and forecast data to the control decision module. Upon receiving the information, the control decision module quickly formulates a heating regulation strategy and issues instructions to the equipment control and energy storage coordination module: increase the heating steam pressure of the steam turbine from 0.8MPa to 1.0MPa and increase the flow rate by 18%; at the same time, adjust the flow distribution valves of each branch of the heating network to increase the heat medium flow rate of commercial complexes and residential communities by 20% and 15% respectively; in addition, it orders the heat storage tank to charge during the off-peak heating period at night (23:00-5:00), with the charging power set at 500 kilowatts per hour, in order to store enough heat energy to cope with possible subsequent heating peaks. The equipment control and energy storage coordination module acts according to instructions. Steam turbine operators gradually increase the heating steam pressure and flow rate through the remote control system, while strengthening the inspection of steam turbine equipment to ensure normal operation after parameter adjustment. The intelligent control system of the heating network automatically adjusts the flow distribution valves of each branch, completing the flow adjustment within 30 minutes. The heat storage tank starts the charging program on time at night, storing heat energy during off-peak electricity pricing. During the subsequent heating process, the system continuously monitors the actual heating effect of each heat user. Based on user feedback and real-time data, the heating parameters are optimized and adjusted once per hour. Through the effective adjustment of the system, residents feel warm and comfortable at home, and customers in commercial complexes are no longer affected by damp and cold weather. Heating satisfaction has been greatly improved, effectively meeting the heating needs of southern regions under special climatic conditions.

[0050] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for regulating the supply and demand balance of heat supply in a thermal power plant's steam turbine, characterized in that, Includes the following steps: Meteorological monitoring equipment and sensors are deployed at key locations in the heating area and at heat users to collect meteorological data and real-time heating demand data. After preprocessing, the data is fused to obtain fused data of processed meteorological data and real-time heating demand data. Historical data and abnormal signals are retrieved and integrated. The data correlation is analyzed and the priority weights of meteorological elements are set. After the priority weights of the meteorological elements are dynamically adjusted, the heating demand trend is predicted, and early warning information and prediction data are generated for extreme weather events. Based on the aforementioned early warning information, forecast data, and processed real-time heating demand data, and according to the priority weights of the aforementioned meteorological elements, the heating demand is comprehensively analyzed to generate precise control commands, while providing a visual interface to support manual intervention. The equipment is regulated according to the precise control commands to ensure stable pipeline pressure and heating in key areas, optimize flow distribution, control the charging and discharging of the heat storage tank, monitor the energy storage status and provide feedback, and achieve a balance between heating supply and demand.

2. The method for regulating the heat supply and demand balance of a steam turbine in a thermal power plant according to claim 1, characterized in that, The steps for deploying meteorological monitoring equipment and sensors at key locations within the heating area and at heat users to collect meteorological data and real-time heating demand data specifically include: Meteorological monitoring equipment and sensors at key locations in the heating area collect temperature, humidity, wind speed and solar radiation intensity at a fixed frequency. Meteorological monitoring equipment and sensors at heat users adopt a redundant design and collect temperature, flow rate and pressure through multiple verification mechanisms. The data fusion is performed using the following formula: in, It is integrated data. For the processed meteorological data, For processed real-time heating demand data, , For different fusion weight coefficients, and ; The meteorological data includes temperature, humidity, wind speed, and solar radiation intensity, while the real-time heating demand data includes temperature, flow rate, and pressure.

3. The method for regulating the heat supply and demand balance of a steam turbine in a thermal power plant according to claim 1, characterized in that, The steps of retrieving historical data and abnormal signals, integrating the fused data, abnormal signals, and historical data, analyzing data correlations, setting priority weights for meteorological elements, dynamically adjusting the priority weights of the meteorological elements, predicting heating demand trends, and generating early warning information and forecast data for extreme weather events specifically include: Historical data and anomalies are obtained by retrieving historical databases, user behavior databases and building energy consumption model data. Combined with the fused data, a multi-source data fusion architecture is constructed. The correlation weights between different meteorological elements and heating demand are determined through data correlation analysis, and a dynamic weight adjustment mechanism is established. Based on the dynamic weight adjustment mechanism, the weight matrix of the correlation weights is updated through real-time heating demand data, and time-series prediction is performed based on the multi-source data fusion architecture to generate heating demand prediction sequences at different time scales. Extreme weather events are identified through a preset threshold judgment mechanism to generate early warning information and prediction data. The step of determining the correlation weights between different meteorological elements and heating demand through data correlation analysis is specifically calculated using the following formula: in, It is the priority weight of meteorological elements. It is the first The meteorological elements and the first The correlation coefficients of various factors affecting heating demand For the first The importance coefficient of each factor affecting heating demand It refers to the quantity of meteorological elements. It is the number of factors affecting heating demand.

4. The method for regulating the heat supply and demand balance of a steam turbine in a thermal power plant according to claim 3, characterized in that, The step of generating heating demand forecast sequences at different time scales based on the multi-source data fusion architecture is specifically performed using the following formula: in, It is the predicted heating demand. For the first Predicted values ​​of each meteorological element For the first The weighting coefficients of non-meteorological heating demand influencing factors. For the first Relevant data values ​​for non-meteorological factors affecting heating demand. This is a bias term.

5. The method for regulating the heat supply and demand balance of a steam turbine in a thermal power plant according to claim 1, characterized in that, Based on the aforementioned early warning information, forecast data, and processed real-time heating demand data, and according to the priority weights of the aforementioned meteorological elements, a comprehensive analysis of heating demand is conducted to generate precise control commands. Simultaneously, a visual interface is provided to support manual intervention. Specifically, this includes the following steps: Based on the early warning information, forecast data, and processed real-time heating demand data, a multi-objective optimization decision model is used to process the control requirements corresponding to high-weight meteorological elements, generating a sequence of precise control commands for the equipment. The sequence of precise control commands includes priority sorting and execution timing planning.

6. The method for regulating the heat supply and demand balance of a steam turbine in a thermal power plant according to claim 1, characterized in that, The step of generating a sequence of precise control commands for the equipment by processing the control requirements corresponding to high-weight meteorological elements through a multi-objective optimization decision model is specifically achieved by generating the sequence of precise control commands for the equipment using the following formula: in, A set of equipment control commands. For the first Target values ​​for the operating indicators of a heating system In control commands Under the action, the first The actual values ​​of the operating indicators of the heating system.

7. A heating and demand balance regulation system for a steam turbine in a thermal power plant, characterized in that, include: The data acquisition and processing module is used to deploy meteorological monitoring equipment and sensors at key locations in the heating area and at heat users to collect meteorological data and real-time heating demand data. After preprocessing, the data is fused to obtain fused data of processed meteorological data and real-time heating demand data. The demand forecasting and analysis module is used to retrieve historical data and abnormal signals, integrate the fused data, abnormal signals and historical data, analyze the data correlation and set the priority weight of meteorological elements, dynamically adjust the priority weight of the meteorological elements and predict the heating demand trend, and generate early warning information and forecast data for extreme weather events. The control decision module is used to comprehensively analyze the heating demand based on the early warning information, forecast data, and processed real-time heating demand data, and according to the priority weight of the meteorological elements, to generate precise control commands, while providing a visual interface to support manual intervention. The equipment regulation and energy storage coordination module is used to regulate the equipment according to the precise control commands, ensure stable pipeline pressure and heating in key areas, optimize flow distribution, control the charging and discharging of the heat storage tank, monitor the energy storage status and provide feedback, and achieve a balance between heating supply and demand.

8. A power plant steam turbine heating and demand balance regulation system according to claim 7, characterized in that, The equipment regulation and energy storage coordination module is connected to the turbine inlet steam regulating valve, extraction steam regulating valve, and heating steam bypass system. It also controls the circulating water pump speed and the opening of the heating network branch flow distribution valve. Based on the precise control commands generated by the control decision module, it precisely regulates the turbine heating-related equipment to determine the turbine's steam intake. It prioritizes heating in key areas during extreme weather event warnings, monitors heating network parameters in real time and dynamically optimizes flow distribution. It also uses heat storage tanks equipped with complete insulation measures, and formulates charging and discharging strategies based on the control decision module. It stores thermal energy before extreme weather events and releases thermal energy to coordinate with the turbine for heating during peak heating demand. It monitors its own energy storage status parameters in real time and feeds them back to the control decision module to adjust the charging and discharging strategies.

9. A power plant steam turbine heating and demand balance regulation system according to claim 7, characterized in that, In the step where the equipment regulation and energy storage coordination module precisely regulates the turbine heating-related equipment according to the instructions of the control decision module, thereby determining the steam inlet volume of the turbine, the formula for determining the steam inlet volume is as follows: in, This indicates the adjusted steam intake volume of the steam turbine. This represents the basic steam intake volume of the steam turbine under normal operating conditions. This is the steam inlet adjustment value calculated based on the priority weights of meteorological elements and changes in meteorological parameters. This is the steam intake adjustment value calculated based on the difference between the predicted heating demand and the current actual heating load.

10. A power plant steam turbine heating and demand balance regulation system according to claim 7, characterized in that, The equipment regulation and energy storage coordination module formulates a charging and discharging strategy based on the control decision module, specifically through the following formula: in, This is the operation command for the energy storage device, with a value of This indicates a charging operation, with a value of [value to be filled in]. This indicates a discharge operation; a value of 0 indicates that no charge / discharge operation is performed. The current remaining energy of the energy storage device; , Different charge and discharge thresholds are set for different energy storage devices, and Used to control the start conditions for charging and discharging. For the predicted heating demand, This represents the actual heating capacity of the current steam turbine and other heating equipment.

Images