Indirect air cooling power plant temperature control system and use method thereof

Abstract

The invention provides an indirect air cooling power plant temperature control system and a use method thereof, and relates to the field of indirect air cooling power plant temperature control, and the system comprises an environment prediction module which is used for collecting environment data and unit data in real time, predicting the future temperature and back pressure changes, and dividing the cooling demands into a low grade, a middle grade and a high grade according to the prediction result; the spraying control module is used for dynamically adjusting the spraying strength, area and frequency according to the cooling requirement grade, and it is ensured that the cooling effect is uniform and efficient; the back pressure management module is used for monitoring the back pressure of the unit in real time, dynamically adjusting a cooling strategy and ensuring that the back pressure fluctuates within a safe range; and the self-learning optimization module is used for continuously optimizing the environment prediction model and the cooling strategy based on the historical operation data. Through the dynamic environment prediction module, the sliding window method and the ARIMA model are combined to predict the change of the environment temperature and the back pressure in the next one hour, and the cooling demand level is dynamically adjusted according to the prediction result.

Description

Technical Field

[0001] This invention relates to the field of temperature control in indirect air-cooled power plants, and more specifically, to a temperature control system for indirect air-cooled power plants and its usage method. Background Technology

[0002] Indirect air cooling uses air to cool circulating water, which in turn cools the exhaust steam from the turbine. It is suitable for areas with scarce water resources or high ambient temperatures. Traditional indirect air cooling systems mainly rely on air-cooled radiators, fans, etc. for cooling, and adjust the temperature through fixed spray or natural ventilation. It is difficult to dynamically adjust the cooling intensity according to environmental changes, resulting in low cooling efficiency.

[0003] For example, the Chinese invention patent (application number: 202111675345.3) discloses "An Indirect Air-Cooling System for an Ammonia-Blended Power Plant and Its Control Method," which specifies that: The system monitors the power plant's operating data and determines whether to adjust the system based on the temperature difference between the outlet water temperature of the indirect cooling tower and the liquid ammonia vaporization heat exchanger. If adjustment is needed, the circulating water flow rate of the indirect cooling tower is adjusted, and the adjusted temperature difference is calculated. If the temperature difference is less than a first preset temperature, the opening of the indirect cooling tower louvers is reduced or the total circulating water flow rate of the air-cooling system is increased. If the temperature difference is greater than a second preset temperature, the opening of the indirect cooling tower louvers is increased, the total circulating water flow rate of the air-cooling system is reduced, or the unit load is reduced, and then monitoring continues. If the temperature difference is between the first and second preset temperatures, it indicates that the air-cooling system is in optimal operating condition, and monitoring returns to normal. This invention proposes using the temperature difference between the outlet water temperature of the indirect cooling tower and the liquid ammonia vaporization heat exchanger as a standard, and determining different adjustment schemes based on preset conditions, which can effectively improve the cooling effect of the indirect cooling tower. The aforementioned patent can corroborate the deficiencies of the existing technology.

[0004] Therefore, we have made improvements to this and proposed an indirect air-cooled power plant temperature control system and its usage method. Summary of the Invention

[0005] The purpose of this invention is to solve the problem that current indirect air-cooling systems are unable to dynamically adjust the cooling intensity according to environmental changes.

[0006] To achieve the above-mentioned objectives, the present invention provides the following indirect air-cooled power plant temperature control system and its usage method to improve the aforementioned problems.

[0007] The application is as follows: An indirect air-cooled power plant temperature control system includes: Environmental prediction module: used to collect environmental data and unit data in real time, predict future temperature and back pressure changes, and classify cooling demand into three levels: low, medium and high based on the prediction results; Spray control module: used to dynamically adjust the spray intensity, area and frequency according to the cooling demand level, ensuring uniform and efficient cooling effect; Back pressure management module: used to monitor the back pressure of the unit in real time and dynamically adjust the cooling strategy to ensure that the back pressure fluctuates within a safe range; Self-learning optimization module: used to continuously optimize the environmental prediction model and cooling strategy based on historical operation data to improve the overall performance of the system.

[0008] As a preferred technical solution of this application, the environmental prediction module includes: Data acquisition unit: used to monitor the temperature changes in multiple areas in real time, combine with historical temperature trends to calculate the current environmental temperature; dynamically calculate the wind speed and direction by analyzing the temperature difference and pressure changes between adjacent areas; calculate the environmental humidity based on the relationship between the current temperature and the water vapor content in the air; dynamically calculate the back pressure value by monitoring the pressure changes in the steam exhaust pipeline of the steam turbine in real time and combining with the operation status of the unit; dynamically calculate the exhaust steam temperature by analyzing the steam flow state and cooling efficiency and combining with the inlet steam parameters; dynamically estimate the current load demand by monitoring the grid frequency fluctuation in real time and combining with the output of the unit; Prediction model unit: used to adopt the sliding window method, predict the temperature in the next 1 hour through the ARIMA model and establish a quadratic equation and dynamically calibrate the coefficient, which is updated every 24 hours; Cooling demand grading unit: used to divide the cooling demand into three levels of low, medium and high according to the predicted temperature and back pressure data, specifically: low demand (T≤25℃ and P≤30kPa): only start natural ventilation; medium demand (25℃<T≤35℃ and 30kPa<P≤40kPa): start area priority spray; high demand (T>35℃ or P>40kPa): full power spray + reverse wind compensation.

[0009] As a preferred technical solution of this application, the spray control module includes: Spray intensity unit: used to linearly allocate the spray volume according to the demand level, specifically 0L / min for low demand, 30L / min for medium demand, and 50L / min for high demand; Area priority unit: used to obtain the data of high temperature areas (threshold > 40℃), sort according to the evaporation potential formula and preferentially spray the areas with high E value; Reverse wind compensation unit: used to adjust the nozzle angle to when the wind speed > 10m / s, and increase the spray volume by 20% (for example: 50L / min → 60L / min); Resource optimization unit: When the water tank level is <30%, it forces the system to operate under a low-demand strategy and shuts down the spraying of non-critical areas; when the total energy consumption exceeds the system budget, it degrades the spraying areas according to priority.

[0010] As a preferred technical solution of this application, the back pressure management module includes: Back pressure monitoring unit: Used to monitor the unit's back pressure in real time and compare it with the preset safety threshold of 40 kPa. When the back pressure reaches 38 kPa, it immediately switches to the high demand strategy and starts emergency spraying (adding an extra 20 L / min). Emergency Response Unit: Used to activate the backup cold water circulation (pre-stored cold water is injected into the heat dissipation area) when the back pressure change rate ΔP / Δt ≥ 1 kPa / min; and to activate the backup cooling tower when the wind speed > 15 m / s and lasts for ≥ 30 minutes. High wind response unit: When short-term strong winds (wind speed >15m / s and lasting <30 minutes), it activates reverse wind spray and increases the spray volume by 20%.

[0011] As a preferred technical solution of this application, the self-learning optimization module includes: Model update unit: used to refit the temperature-back pressure equation every 24 hours. If the prediction error is >5% for 3 consecutive times, the manual calibration mode is triggered. Strategy optimization unit: Used to dynamically optimize the weight allocation of water saving, energy saving, and cooling effect through a Nash equilibrium model, and solve for the optimal strategy. Among them, weight Real-time demand is dynamically adjusted (e.g., during water shortages). =0.6).

[0012] A method for using an indirect air-cooled power plant temperature control system includes the following steps: Monitor temperature changes in multiple areas and, based on historical temperature trends, estimate the current ambient temperature; analyze temperature differences and pressure changes in adjacent areas to dynamically estimate wind speed and direction; calculate ambient humidity based on the relationship between current temperature and air moisture content; monitor pressure changes in the turbine exhaust pipe and, based on the unit's operating status, dynamically calculate the back pressure value; analyze steam flow patterns and cooling efficiency and, based on inlet steam parameters, dynamically estimate exhaust temperature; monitor grid frequency fluctuations in real time and, based on the unit's output, dynamically estimate current load demand. Using a sliding window method (window size 60 minutes), the temperature for the next hour is predicted using the ARIMA model. Establish a quadratic equation Dynamic calibration coefficient; According to the predicted temperature and back pressure data, the cooling requirements are divided into three levels: low, medium, and high: Low demand (T ≤ 25°C and P ≤ 30 kPa): Only natural ventilation is started; Medium demand (25°C < T ≤ 35°C and 30 kPa < P ≤ 40 kPa): Regional priority spraying is started; High demand (T > 35°C or P > 40 kPa): Full-power spraying + upwind compensation.

[0013] As a preferred technical solution of the present application, the following steps are further included: The spraying volume is linearly allocated according to the cooling requirement level (low: 0 L / min, medium: 30 L / min, high: 50 L / min); Obtain the data of the high-temperature area (threshold: > 40°C), and sort according to the evaporation potential and preferentially spray the area with a high E value; When the wind speed > 10 m / s, the nozzle angle is adjusted to , and the spraying volume is increased by 20% (for example: 50 L / min → 60 L / min); When the water tank level < 30%, it is forced to operate according to the "low demand" strategy, and the spraying in non-critical areas is turned off; The power of the spraying pump is bound to the flow rate ( ), and when the total energy consumption > the system budget, the spraying area is downgraded according to the priority.

[0014] As a preferred technical solution of the present application, the following steps are further included: The back pressure of the unit is monitored in real time and compared with the preset safety threshold (such as 40 kPa); When the back pressure reaches 38 kPa, it is immediately switched to the high demand strategy, and emergency spraying is started (extra + 20 L / min); When the back pressure change rate (ΔP / Δt ≥ 1 kPa / min), the standby chilled water circulation is activated (pre-stored chilled water is injected into the heat dissipation area); When the wind speed > 15 m / s and lasts < 30 minutes, upwind spraying + the spraying volume is increased by 20%; When the wind speed > 15 m / s and lasts ≥ 30 minutes, the standby cooling tower is enabled; The temperature-back pressure equation is refitted every 24 hours. If the prediction error > 5% for 3 consecutive times, the manual calibration mode is triggered; Dynamic game is carried out among water conservation (Player A), energy conservation (Player B), and cooling effect (Player C) to solve the optimal strategy: where the weight is dynamically adjusted according to the real-time demand (for example, when water is scarce = 0.6).

[0015] Compared with the prior art, the beneficial effects of the present invention are: In the solution of the present application: 1. By setting up a dynamic environment prediction module, the system combines the sliding window method and the ARIMA model to predict the changes in ambient temperature and back pressure in the next hour, and dynamically adjusts the cooling demand level according to the prediction results, which solves the problem that existing indirect air-cooled systems are difficult to dynamically adjust the cooling intensity according to environmental changes. 2. By setting up a spray control module, the system can dynamically allocate the spray volume according to the cooling demand level and resource constraints, and prioritize cooling of high-temperature areas by calculating the evaporation potential. This solves the problem that existing indirect air cooling systems rely on fixed spray or natural ventilation methods and are difficult to dynamically adjust the cooling intensity according to environmental changes. 3. By setting up a back pressure management module, the system can monitor back pressure changes in real time. When the back pressure reaches 38 kPa, it immediately switches to a high-demand strategy and starts emergency spraying. When the rate of back pressure change is too fast, it activates the backup cold water circulation, which solves the problem of the lack of intelligent emergency response capability in the existing technology. 4. By setting a self-learning optimization module, the system refits the temperature-back pressure equation every 24 hours, and solves the optimal strategy by dynamically playing a game between water saving, energy saving and cooling effect through the Nash equilibrium model, thus solving the problem of the lack of self-learning ability in the existing technology. 5. By setting up a backwind compensation unit, the system can dynamically adjust the nozzle angle and increase the spray volume by 20% when the wind speed is >10m / s, ensuring that the spray covers the high-temperature area and solving the problem of large back pressure fluctuation in the existing technology under strong wind weather; 6. By setting up a resource optimization unit, the system is forced to operate under a "low demand" strategy when the water tank level is less than 30%; when the total energy consumption exceeds the system budget, the spray area is downgraded according to priority, thus solving the problem of serious resource waste in traditional systems in the existing technology. Attached Figure Description

[0016] Figure 1 A system flow diagram of the indirect air-cooled power plant temperature control system provided in this application; Figure 2 A system flowchart of the environmental prediction module in the temperature control system of the indirect air-cooled power plant provided in this application; Figure 3 A system flowchart of the spray control module in the indirect air-cooled power plant temperature control system provided in this application; Figure 4 A system flowchart of the back pressure management module in the temperature control system of the indirect air-cooled power plant provided in this application; Figure 5 The system flowchart of the self-learning optimization module in the temperature control system of the indirect air-cooled power plant provided in this application; Figure 6The system flowchart of the self-learning optimization module and the environmental prediction module in the temperature control system of the indirect air-cooled power plant provided in this application; Figure 7 The system flowchart of the self-learning optimization module and the spray control module in the indirect air-cooled power plant temperature control system provided in this application; Figure 8 The system flowchart of the self-learning optimization module and back pressure management module in the indirect air-cooled power plant temperature control system provided in this application. Detailed Implementation

[0017] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0019] It should be noted that, unless otherwise specified, the embodiments and features and technical solutions in the present invention can be combined with each other.

[0020] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0021] Example 1 Please refer to Figure 1 An indirect air-cooled power plant temperature control system, comprising: The environmental prediction module collects environmental data in real time and predicts future temperature and back pressure changes, providing a basis for the cooling demand classification of the spray control module and ensuring the accurate execution of the spray strategy. The spray control module adjusts the spray intensity, area, and frequency according to the cooling demand level and resource constraints to ensure the cooling effect. The back pressure management module monitors the unit's back pressure in real time and adjusts the cooling strategy to ensure that the back pressure fluctuates within a safe range. The self-learning optimization module continuously optimizes the environment prediction module and cooling strategy based on historical operating data, thereby improving the overall system performance.

[0022] Furthermore, such as Figure 1 and Figure 2 As shown, the environmental prediction module includes: The data acquisition unit monitors temperature changes in multiple areas in real time, calculates the current ambient temperature by combining historical temperature trends, analyzes airflow patterns, calculates wind speed and direction by combining temperature differences and pressure changes in adjacent areas, dynamically calculates ambient humidity based on the relationship between current temperature and water vapor content in the air, and updates temperature, wind speed, and humidity data every 1 to 5 seconds to ensure real-time information. It also monitors pressure changes in the turbine exhaust pipe in real time, dynamically calculates back pressure values ​​by combining unit operating status, analyzes steam flow patterns and cooling efficiency, and dynamically calculates exhaust temperature by combining inlet steam parameters. Furthermore, it monitors grid frequency fluctuations in real time, dynamically estimates current load demand by combining unit output, and updates back pressure, exhaust temperature, and load power data every 1 to 5 seconds. The prediction model unit uses a sliding window method (window size 60 minutes) to predict the temperature for the next hour using the ARIMA model, establishing a quadratic equation. Dynamic calibration coefficients (updated every 24 hours); ARIMA (Autoregressive Integral Moving Average) is a time series forecasting method consisting of three parts: Autoregressive (AR): Using historical temperature data to build a linear regression model, for example ; Difference (I): Difference processing (e.g., first-order difference) of non-stationary temperature sequences. Eliminate trends; Moving average (MA): A model optimized by incorporating historical prediction errors, for example... ; Prediction steps: Data preprocessing: Stationarity test and differencing of historical temperature data; Parameter selection: The optimal AR order (p), difference order (d), and MA order (q) are determined by the AIC criterion. Model training: The least squares method is used to fit historical data to generate prediction equations; Real-time forecast: Model parameters are updated every 15 minutes, providing rolling forecasts of temperature for the next hour; For example, if the current temperature sequence is [25℃, 26℃, 27℃, 28℃], after differencing, a stationary sequence [1℃, 1℃, 1℃] is obtained. The ARIMA(1,1,1) model can predict that the temperature at the next moment will be 29℃.

[0023] Cooling demand classification unit, which classifies cooling demands into three levels: low, medium, and high according to the predicted temperature and back pressure data: Low demand (T ≤ 25°C and P ≤ 30 kPa): Only natural ventilation is started; Medium demand (25°C < T ≤ 35°C and 30 kPa < P ≤ 40 kPa): Area priority spraying is started; High demand (T > 35°C or P > 40 kPa): Full-power spraying + upwind compensation.

[0024] Further, as Figure 1 and Figure 3 shown, the spray control module includes: Spray intensity unit, which linearly distributes the spray volume according to the demand level (Low: 0 L / min, Medium: 30 L / min, High: 50 L / min); Area priority unit, which obtains high-temperature area data (threshold: > 40°C), sorts according to the evaporation potential and preferentially sprays areas with high E values; Upwind compensation unit, when the wind speed > 10 m / s, the nozzle angle is adjusted to , and the spray volume is increased by 20% (for example: 50 L / min → 60 L / min); Resource optimization unit, when the water tank level < 30%, it is forced to operate according to the "low demand" strategy, and the spraying in non-critical areas is shut down. The spray pump power is bound to the flow rate ( ), and when the total energy consumption > the system budget, the spraying areas are downgraded according to the priority.

[0025] Further, as Figure 1 and Figure 4 shown, the back pressure management module includes: Back pressure monitoring unit, which monitors the back pressure of the unit in real time, compares it with the preset safety threshold (such as 40 kPa), and when the back pressure reaches 38 kPa, immediately switches to the high demand strategy and starts emergency spraying (extra + 20 L / min); Emergency response unit, primary response (P ≥ 38 kPa): Immediately switch to the high demand strategy and start emergency spraying (extra + 20 L / min); secondary response (ΔP / Δt ≥ 1 kPa / min): Activate the standby cold water circulation (inject pre-stored cold water into the heat dissipation area); High wind response unit, short-term high wind (wind speed > 15 m / s and duration < 30 minutes): Upwind spraying + spray volume increased by 20%; continuous high wind (wind speed > 15 m / s and duration ≥ 30 minutes): Activate the standby cooling tower.

[0026] Embodiment 2 The temperature control system of the indirect air-cooled power plant provided in Embodiment 1 is further optimized. Specifically, as Figure 1 , Figure 5 , Figure 6 , Figure 7 and Figure 8 As shown in Figure 8 , the self-learning optimization module includes: Module update unit, refitting the temperature-back pressure equation every 24 hours , if the prediction error > 5% for three consecutive times, remind the staff to ensure the model accuracy; analyze the correlation between ambient temperature and back pressure based on historical operation data, and dynamically adjust the model parameters; Strategy optimization unit, Nash equilibrium model: dynamically game among water conservation (Player A), energy conservation (Player B), and cooling effect (Player C), and solve the optimal strategy: where the weight Dynamically adjust according to real-time demand (for example: when water is scarce = 0.6); According to real-time operation data, dynamically adjust the weight parameters to ensure the optimal balance among water conservation, energy conservation, and cooling effect of the system. When water resources are tense, prioritize water conservation ( weight increases); when the energy consumption approaches the upper limit, prioritize energy conservation ( weight increases).

[0027] Example 3 Please refer to Figure 1 , Figure 6 , Figure 7 and Figure 8 , a usage method of a temperature control system for an indirect air-cooled power plant, which includes the following steps: I. Ambient data collection and prediction: Real-time monitor the temperature changes in multiple regions, combine with historical temperature trends to calculate the current ambient temperature. Analyze the temperature difference and pressure changes between adjacent regions to dynamically calculate the wind speed and direction. Calculate the ambient humidity based on the relationship between the current temperature and the water vapor content in the air. Real-time monitor the pressure changes in the steam exhaust pipe of the steam turbine, combine with the unit operation status to dynamically calculate the back pressure value. Analyze the steam flow state and cooling efficiency, combine with the inlet steam parameters to dynamically calculate the exhaust steam temperature. Real-time monitor the grid frequency fluctuations, combine with the unit output to dynamically estimate the current load demand. Use the sliding window method (window size 60 minutes), and predict the temperature in the next 1 hour through the ARIMA model.

[0028] II. Spray control and cooling demand classification: According to the predicted temperature and back pressure data, classify the cooling demand into three levels: low, medium, and high: low demand (T ≤ 25°C and P ≤ 30 kPa): only start natural ventilation; medium demand (25°C < T ≤ 35°C and 30 kPa < P ≤ 40 kPa): start regional priority spraying; high demand (T > 35°C or P > 40 kPa): full-power spraying + reverse wind compensation.

[0029] The spray volume is linearly allocated according to the demand level (low: 0L / min, medium: 30L / min, high: 50L / min).

[0030] Acquire high-temperature region data (threshold: >40℃), categorized by evaporation potential. Sort the areas and prioritize spraying areas with high E values.

[0031] When the wind speed is >10m / s, the nozzle angle is adjusted to The spray volume is increased by 20% (e.g., 50L / min → 60L / min).

[0032] When the water level in the tank is less than 30%, the system will be forced to operate under a "low demand" strategy and the spraying of non-critical areas will be turned off.

[0033] Spray pump power is tied to flow rate ( When total energy consumption exceeds system budget, spray areas are downgraded according to priority.

[0034] III. Back Pressure Management and Emergency Response: Monitor the unit back pressure in real time and compare it with a preset safety threshold (e.g., 40 kPa). When the back pressure reaches 38 kPa, immediately switch to a high-demand strategy and activate emergency spray (additional +20 L / min). When the back pressure change rate (ΔP / Δt ≥ 1 kPa / min): activate the backup chilled water circulation (pre-stored chilled water is injected into the heat dissipation area).

[0035] When the wind speed is >15m / s and lasts for <30 minutes, the spray volume increases by 20% when spraying against the wind.

[0036] When the wind speed is >15m / s and lasts for ≥30 minutes, the backup cooling tower will be activated.

[0037] IV. Self-learning and optimization: The temperature-backpressure equation is refitted every 24 hours. If the prediction error is greater than 5% for three consecutive times, the manual calibration mode is triggered.

[0038] Find the optimal strategy by engaging in a dynamic game among water conservation (Player A), energy conservation (Player B), and cooling effect (Player C): Among them, weight Real-time demand is dynamically adjusted (e.g., during water shortages). =0.6).

[0039] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0040] Obviously, the embodiments described above are merely some embodiments of the present invention, not all embodiments. The accompanying drawings show preferred embodiments of the present invention, but do not limit the patent scope of the present invention. The present invention can be implemented in many different forms; rather, these embodiments are provided to provide a more thorough and complete understanding of the disclosure of the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the patent protection scope of this invention.

Claims

1. A temperature control system for an indirect air-cooled power plant, characterized in that, It includes: An environmental prediction module: used to collect environmental data and unit data in real time, predict future temperature and back pressure changes, and classify cooling requirements into three levels: low, medium, and high according to the prediction results; A spray control module: used to dynamically adjust the spray intensity, area, and frequency according to the cooling requirement level to ensure uniform and efficient cooling effect; A back pressure management module: used to monitor the unit back pressure in real time and dynamically adjust the cooling strategy to ensure that the back pressure fluctuates within a safe range; A self-learning optimization module: used to continuously optimize the environmental prediction model and cooling strategy based on historical operation data to improve the overall performance of the system.

2. The indirect air-cooled power plant temperature control system according to claim 1, characterized in that, The environmental prediction module includes: A data collection unit: used to monitor the temperature changes in multiple areas in real time, combine with historical temperature trends to calculate the current environmental temperature; dynamically calculate the wind speed and direction by analyzing the temperature difference and pressure changes in adjacent areas; calculate the environmental humidity based on the relationship between the current temperature and the water vapor content in the air; dynamically calculate the back pressure value by monitoring the pressure changes in the steam exhaust pipeline of the steam turbine in real time and combining with the unit operation status; dynamically calculate the exhaust steam temperature by analyzing the steam flow state and cooling efficiency and combining with the inlet steam parameters; dynamically estimate the current load demand by monitoring the power grid frequency fluctuations in real time and combining with the unit output; Prediction model unit: Used to predict the temperature for the next hour using the ARIMA model with a sliding window method, and to establish a quadratic equation. Dynamic calibration coefficients, updated every 24 hours; A cooling requirement classification unit: used to classify cooling requirements into three levels: low, medium, and high according to the predicted temperature and back pressure data. Specifically, low demand (T≤25℃ and P≤30kPa): only start natural ventilation; medium demand (25℃<T≤35℃ and 30kPa<P≤40kPa): start area priority spraying; high demand (T>35℃ or P>40kPa): full-power spraying + reverse wind compensation.

3. The indirect air-cooled power plant temperature control system according to claim 2, characterized in that, The spray control module includes: A spray intensity unit: used to linearly allocate the spray volume according to the demand level. Specifically, low demand is 0L / min, medium demand is 30L / min, and high demand is 50L / min; Regional priority unit: Used to acquire data for high-temperature areas (threshold > 40℃), according to the evaporation potential formula. Sort the spraying and prioritize areas with high E values; Headwind compensation unit: Used to adjust the nozzle angle when the wind speed is >10m / s. The spray volume increased by 20%; A resource optimization unit: used to force the operation according to the low demand strategy and close the spraying in non-critical areas when the water tank level < 30%; when the total energy consumption exceeds the system budget, downgrade the spraying area according to the priority.

4. The indirect air-cooled power plant temperature control system according to claim 3, characterized in that, The back pressure management module includes: A back pressure monitoring unit: used to monitor the unit back pressure in real time and compare it with the preset safety threshold of 40kPa. When the back pressure reaches 38kPa, immediately switch to the high demand strategy and start emergency spraying (an additional 20L / min); An emergency response unit: used to activate the standby cold water circulation (inject pre-stored cold water into the heat dissipation area) when the back pressure change rate ΔP / Δt≥1kPa / min; enable the standby cooling tower when the wind speed > 15m / s and lasts for ≥ 30 minutes; A strong wind response unit: used to start reverse spraying and increase the spray volume by 20% during short-term strong winds (wind speed > 15m / s and lasts < 30 minutes).

5. The indirect air-cooled power plant temperature control system according to claim 4, characterized in that, The self-learning optimization module includes: A model update unit: used to refit the temperature-back pressure equation every 24 hours. If the prediction error > 5% for three consecutive times, trigger the manual calibration mode; A strategy optimization unit: used to dynamically optimize the weight allocation of water saving, energy saving, and cooling effect through the Nash equilibrium model and solve the optimal strategy: Among them, weight Adjustments are made dynamically based on real-time demand.

6. The indirect air-cooled power plant temperature control system according to claim 5, characterized in that, The environmental data update frequency of the data acquisition unit is once every 1 - 5 seconds, and the unit data update frequency is once every 1 - 5 seconds, ensuring real-time performance and data synchronization.

7. The indirect air-cooled power plant temperature control system according to claim 6, characterized in that, For the nozzle angle adjustment and spray volume increase of the upwind compensation unit, by dynamically calculating the real-time changes in wind direction and wind speed, it ensures that the spray covers the high-temperature area and offsets the impact of strong wind on back pressure.

8. A method of using an indirect air-cooled power plant temperature control system, comprising using the indirect air-cooled power plant temperature control system as described in claim 7, characterized in that, It includes the following steps: Monitor the temperature changes in multiple areas, combine with historical temperature trends to estimate the current ambient temperature; analyze the temperature differences and pressure changes in adjacent areas to dynamically estimate wind speed and wind direction; calculate the ambient humidity based on the relationship between the current temperature and the water vapor content in the air; monitor the pressure changes in the steam exhaust pipeline of the steam turbine, combine with the unit operation status to dynamically calculate the back pressure value; analyze the steam flow state and cooling efficiency, combine with the inlet steam parameters to dynamically estimate the exhaust steam temperature; real-time monitor the grid frequency fluctuations, combine with the unit output to dynamically estimate the current load demand; Adopt the sliding window method (window size 60 minutes), and predict the temperature in the next 1 hour through the ARIMA model; Establish a quadratic equation Dynamic calibration coefficient; According to the predicted temperature and back pressure data, divide the cooling demand into three levels: low demand (T ≤ 25°C and P ≤ 30 kPa): only start natural ventilation; Medium demand (25°C < T ≤ 35°C and 30 kPa < P ≤ 40 kPa): start area-priority spraying; high demand (T > 35°C or P > 40 kPa): full-power spraying + upwind compensation.

9. The method of using an indirect air-cooled power plant temperature control system according to claim 8, characterized in that, It also includes the following steps: Linearly allocate the spray volume according to the cooling demand level (low: 0 L / min, medium: 30 L / min, high: 50 L / min); By acquiring data from high-temperature regions (threshold: >40℃), based on evaporation potential... Sort the spraying and prioritize areas with high E values; When the wind speed is >10m / s, the nozzle angle is adjusted to The spray volume increased by 20%; When the water tank level is less than 30%, the system will be forced to operate under a "low demand" strategy and will shut down spraying in non-critical areas; the spray pump power is tied to the flow rate. When total energy consumption exceeds system budget, spray areas are downgraded according to priority.

10. The method of using an indirect air-cooled power plant temperature control system according to claim 9, characterized in that, It also includes the following steps: Real-time monitor the unit back pressure, and compare it with the preset safety threshold (such as 40 kPa); when the back pressure reaches 38 kPa, immediately switch to the high-demand strategy and start emergency spraying (extra + 20 L / min); when the back pressure change rate (ΔP / Δt ≥ 1 kPa / min), activate the standby cold water circulation (inject pre-stored cold water into the heat dissipation area); When the wind speed > 15 m / s and lasts < 30 minutes, upwind injection + 20% increase in spray volume; when the wind speed > 15 m / s and lasts ≥ 30 minutes, activate the standby cooling tower; refit the temperature-back pressure equation every 24 hours, if the prediction error > 5% for 3 consecutive times, trigger the manual calibration mode; dynamically play a game among water conservation (Player A), energy conservation (Player B), and cooling effect (Player C) to solve the optimal strategy: Among them, weight Adjustments are made dynamically based on real-time demand.

Images