An energy-saving optimization control method and system for integrated wet and dry cooling towers

Abstract

This invention discloses an energy-saving optimization control method and system for a wet-dry integrated cooling tower, belonging to the field of optimization control technology. The method includes acquiring initial state parameters of the target cooling tower, substituting these initial state parameters into a multi-objective cooling tower evaluation model to obtain a cooling assessment score. The initial state parameters include the frequency of wet-dry section switching, the fan frequency adjustment ratio, and the spray water volume. The initial state parameters are optimized using a multi-objective optimization algorithm to obtain optimal initial state parameters. Rolling optimization is performed based on the optimal initial state parameters to obtain final optimized state parameters. The final optimized state parameters are then transmitted to a terminal to execute corresponding control commands. This invention reduces energy loss and achieves energy-saving effects by performing multi-objective optimization control on the cooling tower's state parameters.

Description

Technical Field

[0001] This invention belongs to the field of optimization control technology, specifically relating to an energy-saving optimization control method and system for a dry-wet integrated cooling tower. Background Technology

[0002] Integrated dry and wet cooling towers, as a new type of cooling equipment combining the advantages of dry air cooling and wet evaporative cooling, are widely used in various scenarios requiring continuous circulating cooling, becoming a core piece of equipment for overcoming the pain points of traditional cooling technologies. Their applications cover multiple industrial and civil sectors, including the power industry, chemical industry, and coal chemical industry; achieving water and energy conservation while ensuring cooling accuracy. Simultaneously, they reduce the risk of pipe corrosion and scaling, extending the service life of downstream equipment, aligning with the current industrial trend towards green, low-carbon, water-saving, and energy-efficient development.

[0003] The prior art (publication number: CN119289761B) discloses an intelligent control method and a dry-wet cooling tower. Through an intelligent control strategy, the louvers, spray pumps, and fans are finely adjusted in stages and sectors to optimize the switching between dry and wet cooling stages, making full use of the heat exchange capacity of the environment, thereby achieving the purpose of improving cooling efficiency and saving energy and reducing consumption. The intelligent control strategy, which combines multiple control algorithms, improves the stability and adaptability of the system under different operating conditions. Through the intelligent control system, the automated management of the dry-wet cooling tower is realized, improving the intelligence level of the system and reducing manual intervention and operational complexity.

[0004] The aforementioned patent improves cooling efficiency and energy saving by optimizing the switching between dry and wet cooling stages; however, in practical applications, it is difficult to accurately predict the switching between dry and wet cooling stages and the fan frequency of the integrated dry and wet cooling tower, which can lead to energy loss due to untimely switching or power loss due to untimely adjustment of fan frequency. Summary of the Invention

[0005] The purpose of this invention is to solve the problem of difficulty in accurately predicting the switching between dry and wet cooling stages and the fan frequency in integrated dry and wet cooling towers, which leads to energy loss due to untimely switching or power loss due to untimely fan frequency adjustment. Therefore, this invention proposes an energy-saving optimization control method and system for integrated dry and wet cooling towers.

[0006] In a first aspect of this invention, an energy-saving optimization control method for a combined wet and dry cooling tower is first proposed, the method comprising: The initial state parameters of the target cooling tower are obtained, and the initial state parameters are substituted into the multi-objective cooling tower evaluation model to obtain the cooling evaluation score; the initial state parameters include the frequency of dry and wet section switching, the fan frequency adjustment ratio, and the spray water volume; The optimal initial state parameters are obtained by optimizing the initial state parameters using a multi-objective optimization algorithm. The final optimized state parameters are obtained by performing rolling optimization based on the optimal initial state parameters. The final optimized state parameters are transmitted to the terminal to execute the corresponding control commands.

[0007] Optionally, the specific process of the multi-objective optimization algorithm includes: Step 1: Randomly combine the initial state parameters to generate multiple state parameter combinations. Treat any state parameter combination as a chromosome and combine all chromosomes to obtain the initial population. Step 2: Substitute the state parameters of each chromosome into the multi-objective cooling tower evaluation model to obtain the corresponding cooling assessment score, and determine the cooling assessment score as the fitness value of the chromosome; obtain the chromosome with the highest fitness as the current optimal chromosome; Step 3: Update the current population based on the current optimal chromosome to obtain an intermediate population; Step 4: Execute steps 2 and 3. When the preset number of iterations reaches the maximum value, output the optimal chromosome. The working principle of the multi-objective cooling tower evaluation model includes: Energy consumption is calculated for any combination of state parameters of a chromosome to obtain the energy consumption value corresponding to each state parameter. After normalizing the energy consumption value corresponding to each state parameter, a multi-objective energy consumption value is obtained. Obtain the multi-objective energy consumption values ​​of all chromosomes, and use a multi-objective decomposition method to obtain the aggregation function value of the multi-objective energy consumption values ​​of all chromosomes; determine the aggregation function value as the cooling evaluation score.

[0008] Optionally, the formula for the multi-objective decomposition method specifically includes:

[0009] in, This represents the reference value for the i-th target, and its range is... ; This represents the combination of state parameters for the j-th chromosome, where n represents the total number of chromosomes. The symbol representing the function formula of the multi-objective cooling tower evaluation model for the i-th objective; Represents the value of an aggregate function.

[0010] Optionally, the final optimized state parameters are obtained by performing rolling optimization based on the optimal initial state parameters, including: Obtain the cooling water temperature value of the cooling tower after cooling in the current time period, and obtain the preset optimal water temperature value of the cooling tower. Calculate the temperature difference between the cooling water temperature value and the preset optimal water temperature value. Set the fan frequency adjustment ratio to be constant, predict the first temperature difference value of a preset number of time periods based on the temperature difference value of the current time period, and combine the first temperature difference values ​​of the preset number of time periods to obtain the initial prediction vector. A preset number of fan control cycles are set, wherein the fan control cycle is increased by the fan frequency adjustment ratio according to a preset step size; the second temperature difference value corresponding to the preset number of time cycles is obtained by adjusting and predicting according to the fan frequency adjustment ratio; and the second temperature difference values ​​of the preset number of time cycles are combined to obtain the fan prediction vector. The number of fan control cycles (preset number) is determined as columns, and the number of time cycles is determined as rows, thus constructing a sliding matrix; the temperature difference value corresponding to each time cycle of each control cycle is determined as an element in the sliding matrix. The optimal control increment vector is calculated based on the sliding matrix; the optimal fan frequency regulation ratio is calculated based on the optimal control increment vector. Replace the fan frequency adjustment in the optimal initial state parameters with the optimal fan frequency adjustment ratio to generate the final optimized state parameters; The calculation formula for solving the optimal control increment vector is as follows:

[0011] in, This represents the optimal control increment vector; Let Q be the transpose of A, where A is the sliding matrix and Q is the error weighting matrix, which is a diagonal matrix. express The inverse matrix, Represents the wind turbine prediction vector. This represents the initial prediction vector.

[0012] Optionally, the step of adjusting and predicting the second temperature difference value corresponding to a preset number of time periods based on the fan frequency adjustment ratio includes: The formula for calculating the second temperature difference value corresponding to the preset number of time periods is as follows:

[0013] Where k represents the current time period, =1, 2, ..., m, This represents the water temperature after cooling in the w-th time period. It is the initial value of the conversion factor for the preset w-th time period. This indicates the cooled water temperature value for the current time period. This indicates the preset optimal water temperature value; The corresponding second temperature difference values ​​are calculated by comparing the cooled water temperature values ​​corresponding to a preset number of time periods with the preset optimal water temperature values.

[0014] In a second aspect of this invention, an energy-saving optimization control system for a combined wet and dry cooling tower is proposed, the system comprising: Data acquisition module: acquires the initial state parameters of the target cooling tower, and substitutes the initial state parameters into the multi-objective cooling tower evaluation model to obtain a cooling evaluation score; the initial state parameters include the frequency of dry and wet section switching, the fan frequency adjustment ratio, and the spray water volume; Multi-objective optimization module: Optimizes the initial state parameters using a multi-objective optimization algorithm to obtain the optimal initial state parameters; Rolling optimization module: Performs rolling optimization based on the optimal initial state parameters to obtain the final optimized state parameters; Execution control module: Transmits the final optimized state parameters to the terminal to execute the corresponding control instructions; Optionally, the multi-objective optimization module is further used for: Step 1: Randomly combine the initial state parameters to generate multiple state parameter combinations. Treat any state parameter combination as a chromosome and combine all chromosomes to obtain the initial population. Step 2: Substitute the state parameters of each chromosome into the multi-objective cooling tower evaluation model to obtain the corresponding cooling assessment score, and determine the cooling assessment score as the fitness value of the chromosome; obtain the chromosome with the highest fitness as the current optimal chromosome; Step 3: Update the current population based on the current optimal chromosome to obtain an intermediate population; Step 4: Execute steps 2 and 3. When the preset number of iterations reaches the maximum value, output the optimal chromosome. The working principle of the multi-objective cooling tower evaluation model includes: Energy consumption is calculated for any combination of state parameters of a chromosome to obtain the energy consumption value corresponding to each state parameter. After normalizing the energy consumption value corresponding to each state parameter, a multi-objective energy consumption value is obtained. Obtain the multi-objective energy consumption values ​​of all chromosomes, and use a multi-objective decomposition method to obtain the aggregation function value of the multi-objective energy consumption values ​​of all chromosomes; determine the aggregation function value as the cooling evaluation score.

[0015] Optionally, the formula for the multi-objective decomposition method specifically includes:

[0016] in, This represents the reference value for the i-th target, and its range is... ; This represents the combination of state parameters for the j-th chromosome, where n represents the total number of chromosomes. The symbol representing the function formula of the multi-objective cooling tower evaluation model for the i-th objective; Represents the value of an aggregate function.

[0017] Optionally, the rolling optimization module includes: a first temperature difference module, a second temperature difference module, a sliding matrix module, and an optimal control increment vector module. The first temperature difference module is used to obtain the cooling water temperature value of the cooling tower after cooling in the current time period, and obtain the preset optimal water temperature value of the cooling tower, calculate the temperature difference between the cooling water temperature value and the preset optimal water temperature value; set the fan frequency adjustment ratio to be constant, predict the first temperature difference value of a preset number of time periods based on the temperature difference value of the current time period, and combine the first temperature difference values ​​of the preset number of time periods to obtain the initial prediction vector. The second temperature difference module is used to set a preset number of fan control cycles, wherein the fan control cycle is to increase the fan frequency adjustment ratio according to a preset step size; the second temperature difference value corresponding to the preset number of time cycles is obtained by adjusting and predicting according to the fan frequency adjustment ratio; and the second temperature difference values ​​of the preset number of time cycles are combined to obtain the fan prediction vector. The sliding matrix module is used to determine the number of a preset number of fan control cycles as columns and the number of time cycles as rows to construct a sliding matrix; and to determine the temperature difference value corresponding to each time cycle of each control cycle as an element in the sliding matrix. The optimal control increment vector module is used to calculate the optimal control increment vector based on the sliding matrix; calculate the optimal fan frequency adjustment ratio based on the optimal control increment vector; and replace the fan frequency adjustment in the optimal initial state parameters with the optimal fan frequency adjustment ratio to generate the final optimized state parameters. The calculation formula for solving the optimal control increment vector is as follows:

[0018] in, This represents the optimal control increment vector; Let Q be the transpose of A, where A is the sliding matrix and Q is the error weighting matrix, which is a diagonal matrix. express The inverse matrix, Represents the wind turbine prediction vector. This represents the initial prediction vector.

[0019] Optionally, the step of adjusting and predicting the second temperature difference value corresponding to a preset number of time periods based on the fan frequency adjustment ratio includes: The formula for calculating the second temperature difference value corresponding to the preset number of time periods is as follows:

[0020] Where k represents the current time period, =1, 2, ..., m, This represents the water temperature after cooling in the w-th time period. It is the initial value of the conversion factor for the preset w-th time period. This indicates the cooled water temperature value for the current time period. This indicates the preset optimal water temperature value; The corresponding second temperature difference values ​​are calculated by comparing the cooled water temperature values ​​corresponding to a preset number of time periods with the preset optimal water temperature values.

[0021] The beneficial effects of this invention are: This invention proposes an energy-saving optimization control method and system for integrated wet and dry cooling towers. By employing a multi-objective optimization method, the optimal initial state parameters can be determined, thereby comprehensively optimizing multiple state variables and improving the comprehensiveness of the optimization process. Simultaneously, based on a rolling optimization strategy, the state parameters for future periods can be predicted in advance, enabling the early identification of potential risks and achieving precise control of each state parameter. This effectively reduces energy consumption and achieves the goal of energy-saving operation of the integrated wet and dry cooling tower. Attached Figure Description

[0022] The invention will now be further described with reference to the accompanying drawings.

[0023] Figure 1 A flowchart illustrating an energy-saving optimization control method for a wet-dry integrated cooling tower provided in an embodiment of the present invention; Figure 2 A flowchart of a multi-objective optimization algorithm provided in an embodiment of the present invention; Figure 3 This is a framework diagram of an energy-saving optimization control system for an integrated dry and wet cooling tower provided in an embodiment of the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and B can represent: A alone, A and B simultaneously, and B alone. Furthermore, descriptions involving "first," "second," etc., in this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" can explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0025] Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] This invention provides an energy-saving optimization control method for a combined wet and dry cooling tower. See also... Figure 1 , Figure 1 A flowchart illustrating an energy-saving optimization control method for a combined wet and dry cooling tower, provided as an embodiment of the present invention. The method includes the following steps: The initial state parameters of the target cooling tower are obtained, and the initial state parameters are substituted into the multi-objective cooling tower evaluation model to obtain the cooling evaluation score. The initial state parameters include the frequency of dry and wet section switching, the fan frequency adjustment ratio, and the spray water volume. The optimal initial state parameters are obtained by optimizing the initial state parameters using a multi-objective optimization algorithm. The final optimized state parameters are obtained by performing rolling optimization based on the optimal initial state parameters. The final optimized state parameters are transmitted to the terminal to execute the corresponding control commands.

[0027] Based on the energy-saving optimization control method for a dry-wet integrated cooling tower provided by the embodiments of the present invention, the optimal initial state parameters are obtained through multi-objective optimization, which realizes the optimization of multiple state parameters and increases the comprehensiveness of the optimization; the state parameters for future time periods are predicted through rolling optimization, which reduces risks by predicting in advance and accurately controls various state parameters of the cooling tower, thereby reducing energy loss and achieving energy-saving effect of the cooling tower.

[0028] In one implementation, see [link to implementation details]. Figure 2 , Figure 2A flowchart of a multi-objective optimization algorithm provided in this embodiment of the invention is shown. The specific process of the multi-objective optimization algorithm includes: Step 1: Generate multiple state parameter combinations by randomly combining the initial state parameters. Treat any state parameter combination as a chromosome and combine all chromosomes to obtain the initial population. Step 2: Substitute the state parameters of each chromosome into the multi-objective cooling tower evaluation model to obtain the corresponding cooling assessment score, and determine the cooling assessment score as the fitness value of the chromosome; obtain the chromosome with the highest fitness as the current optimal chromosome; Step 3: Update the current population based on the current optimal chromosome to obtain an intermediate population; Step 4: Execute steps 2 and 3. When the preset number of iterations reaches the maximum value, output the optimal chromosome. The working principle of the multi-objective cooling tower evaluation model includes: Energy consumption is calculated for any combination of state parameters of a chromosome to obtain the energy consumption value corresponding to each state parameter. After normalizing the energy consumption value corresponding to each state parameter, the multi-objective energy consumption value is obtained. Obtain the multi-objective energy consumption values ​​of all chromosomes, and use a multi-objective decomposition method to obtain the aggregation function value of the multi-objective energy consumption values ​​of all chromosomes; determine the aggregation function value as the cooling evaluation score.

[0029] In one implementation, the formula for the multi-objective decomposition method specifically includes:

[0030] in, This represents the reference value for the i-th target, and its range is... ; This represents the combination of state parameters for the j-th chromosome, where n represents the total number of chromosomes. The symbol representing the function formula of the multi-objective cooling tower evaluation model for the i-th objective; Represents the value of an aggregate function.

[0031] In one implementation, the energy-saving evaluation value of each target is calculated by combining the state parameters of each chromosome. The smaller the energy-saving evaluation value, the better the corresponding energy-saving effect. Finally, the value with the largest value among all targets is selected as the aggregation function value. The maximum energy-saving evaluation value among the targets is optimized to improve the overall energy-saving effect of multiple targets. The reference value of the target is a reference value obtained by the staff through normalization processing based on the historical database. The multi-objective cooling tower evaluation model is constructed based on the neural network model (BP neural network model). The state parameters are iteratively optimized through multi-objective decomposition method, thereby improving the overall energy-saving efficiency of the cooling tower.

[0032] In one implementation, the final optimized state parameters are obtained by rolling optimization based on the optimal initial state parameters, including: Obtain the cooling water temperature value of the cooling tower after cooling in the current time period, and obtain the preset optimal water temperature value of the cooling tower. Calculate the temperature difference between the cooling water temperature value and the preset optimal water temperature value. Set the fan frequency adjustment ratio to be constant, predict the first temperature difference value of a preset number of time periods based on the temperature difference value of the current time period, and combine the first temperature difference values ​​of the preset number of time periods to obtain the initial prediction vector. A preset number of fan control cycles are set, and the fan control cycle is the fan frequency adjustment ratio increased according to a preset step size; the second temperature difference value corresponding to the preset number of time cycles is obtained by adjusting and predicting according to the fan frequency adjustment ratio; the second temperature difference value of the preset number of time cycles is combined to obtain the fan prediction vector. The number of fan control cycles (preset number) is determined as columns, and the number of time cycles is determined as rows, thus constructing a sliding matrix; the temperature difference value corresponding to each time cycle of each control cycle is determined as an element in the sliding matrix. The optimal control increment vector is calculated based on the sliding matrix; the optimal fan frequency regulation ratio is calculated based on the optimal control increment vector. Replace the optimal fan frequency adjustment in the optimal initial state parameters with the optimal fan frequency adjustment ratio to generate the final optimized state parameters; The formula for calculating the optimal control increment vector is as follows:

[0033] in, This represents the optimal control increment vector; Let Q be the transpose of A, where A is the sliding matrix and Q is the error weighting matrix, which is a diagonal matrix. express The inverse matrix, Represents the wind turbine prediction vector. This represents the initial prediction vector.

[0034] In one implementation, the error weighting matrix is ​​obtained by analyzing historical data using a big data model, resulting in a matrix with identical weights on the diagonal. Real-time acquisition of the temperature difference between the cooled water and the optimal water temperature is used. A rolling optimization and multi-cycle prediction strategy is employed. An initial prediction vector is first constructed, and then a fan prediction vector is generated by gradually adjusting the fan frequency adjustment ratio. This vector is then used to construct a sliding matrix for optimization. This approach accurately calculates the optimal control increment and the optimal fan frequency adjustment ratio, replacing the original initial parameters to form the final optimized state parameters. While ensuring stable water temperature control, this approach quickly tracks the target water temperature, reduces the deviation between the actual and optimal water temperatures, and avoids frequent and drastic adjustments to the fan frequency. This effectively reduces fan operating energy consumption and equipment wear, and improves the control accuracy of the cooling tower system.

[0035] In one implementation, the second temperature difference value corresponding to a preset number of time periods is obtained by adjusting and predicting according to the fan frequency adjustment ratio, including: The formula for calculating the second temperature difference value corresponding to the preset number of time periods is:

[0036] Where k represents the current time period, =1, 2, ..., m, This represents the water temperature after cooling in the w-th time period. It is the initial value of the conversion factor for the preset w-th time period. This indicates the cooled water temperature value for the current time period. This indicates the preset optimal water temperature value; The corresponding second temperature difference values ​​are calculated by comparing the cooled water temperature values ​​corresponding to a preset number of time periods with the preset optimal water temperature values.

[0037] In one implementation, the preset number of time periods can be the next ten consecutive time periods (the time period can be 1 minute, etc.); the preset number of control periods can be 3 control periods, etc.; the preset optimal water temperature value is obtained based on the experience of the staff in detecting the cooling tower (the optimal water temperature value can be 32℃); the cooling water temperature value of the current time period (the cooling water temperature value can be 33℃); the initial value of the conversion factor can be 0.7. In a specific embodiment, when w=1 (the first minute in the future): =32.7℃; when w=2 (2 minutes in the future). =32.49℃; when w=3 (3rd minute in the future). =32.34℃; ...; then w=4 to 10, and so on, finally obtaining the water temperature value after cooling for each time period; then calculate each second temperature difference value. As w increases, the second temperature difference value gets closer to zero; indicating that the more stable the temperature difference value, the more accurate the predicted water temperature; based on the water temperature value after cooling by the cooling tower gradually decreasing, stable control is ensured. Based on the same inventive concept, this invention also provides an energy-saving optimization control system for an integrated wet and dry cooling tower. See also Figure 3 , Figure 3 A framework diagram of an energy-saving optimization control system for an integrated wet and dry cooling tower provided in an embodiment of the present invention includes: Data acquisition module: Acquires the initial state parameters of the target cooling tower, substitutes the initial state parameters into the multi-objective cooling tower evaluation model to obtain the initial cooling assessment score; the initial state parameters include the frequency of dry and wet section switching, the fan frequency adjustment ratio, and the spray water volume; Multi-objective optimization module: Optimizes the multi-objective cooling tower evaluation model using a multi-objective optimization algorithm to obtain the optimal initial state parameters; The rolling optimization module performs rolling optimization based on the optimal initial state parameters to obtain the final optimized state parameters. Execution control module: Based on the final optimized state parameters, transmit the corresponding control instructions to the terminal.

[0038] Based on the energy-saving optimization control system of the integrated dry and wet cooling tower provided by the embodiments of the present invention, the optimal initial state parameters are obtained through multi-objective optimization, and the optimization of multiple state parameters is realized, which increases the comprehensiveness of the optimization; the state parameters of future time periods are predicted through rolling optimization, and the risks are reduced by predicting in advance, and the various state parameters of the cooling tower are precisely controlled, thereby reducing energy loss and realizing the energy-saving effect of the cooling tower.

[0039] The foregoing has described one embodiment of the present invention in detail, but this content is merely a preferred embodiment and should not be considered as limiting the scope of the present invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the scope of the claims of this invention.

Claims

1. An energy-saving optimization control method for a combined wet and dry cooling tower, characterized in that, The method includes: The initial state parameters of the target cooling tower are obtained, and the initial state parameters are substituted into the multi-objective cooling tower evaluation model to obtain the cooling evaluation score; the initial state parameters include the frequency of dry and wet section switching, the fan frequency adjustment ratio, and the spray water volume; The optimal initial state parameters are obtained by optimizing the initial state parameters using a multi-objective optimization algorithm. The final optimized state parameters are obtained by performing rolling optimization based on the optimal initial state parameters. The final optimized state parameters are transmitted to the terminal to execute the corresponding control commands.

2. The energy-saving optimization control method for a combined wet and dry cooling tower according to claim 1, characterized in that, The specific process of the multi-objective optimization algorithm includes: Step 1: Randomly combine the initial state parameters to generate multiple state parameter combinations. Treat any state parameter combination as a chromosome and combine all chromosomes to obtain the initial population. Step 2: Substitute the state parameters of each chromosome into the multi-objective cooling tower evaluation model to obtain the corresponding cooling assessment score, and determine the cooling assessment score as the fitness value of the chromosome; obtain the chromosome with the highest fitness as the current optimal chromosome; Step 3: Update the current population based on the current optimal chromosome to obtain an intermediate population; Step 4: Execute steps 2 and 3. When the preset number of iterations reaches the maximum value, output the optimal chromosome. The working principle of the multi-objective cooling tower evaluation model includes: Energy consumption is calculated for any combination of state parameters of a chromosome to obtain the energy consumption value corresponding to each state parameter. After normalizing the energy consumption value corresponding to each state parameter, a multi-objective energy consumption value is obtained. Obtain the multi-objective energy consumption values ​​of all chromosomes, and use a multi-objective decomposition method to obtain the aggregation function value of the multi-objective energy consumption values ​​of all chromosomes; determine the aggregation function value as the cooling evaluation score.

3. The energy-saving optimization control method for a combined wet and dry cooling tower according to claim 2, characterized in that, The formula for the multi-objective decomposition method specifically includes: in, This represents the reference value for the i-th target, and its range is... ; This represents the combination of state parameters for the j-th chromosome, where n represents the total number of chromosomes. The symbol representing the function formula of the multi-objective cooling tower evaluation model for the i-th objective; Represents the value of an aggregate function.

4. The energy-saving optimization control method for a combined wet and dry cooling tower according to claim 1, characterized in that, The final optimized state parameters obtained by rolling optimization based on the optimal initial state parameters include: Obtain the cooling water temperature value of the cooling tower after cooling in the current time period, and obtain the preset optimal water temperature value of the cooling tower. Calculate the temperature difference between the cooling water temperature value and the preset optimal water temperature value. Set the fan frequency adjustment ratio to be constant, predict the first temperature difference value of a preset number of time periods based on the temperature difference value of the current time period, and combine the first temperature difference values ​​of the preset number of time periods to obtain the initial prediction vector. A preset number of fan control cycles are set, wherein the fan control cycle is increased by the fan frequency adjustment ratio according to a preset step size; the second temperature difference value corresponding to the preset number of time cycles is obtained by adjusting and predicting according to the fan frequency adjustment ratio; and the second temperature difference values ​​of the preset number of time cycles are combined to obtain the fan prediction vector. The number of fan control cycles (preset number) is determined as columns, and the number of time cycles is determined as rows, thus constructing a sliding matrix; the temperature difference value corresponding to each time cycle of each control cycle is determined as an element in the sliding matrix. The optimal control increment vector is calculated based on the sliding matrix; the optimal fan frequency regulation ratio is calculated based on the optimal control increment vector. Replace the fan frequency adjustment in the optimal initial state parameters with the optimal fan frequency adjustment ratio to generate the final optimized state parameters.

5. The energy-saving optimization control method for a combined wet and dry cooling tower according to claim 4, characterized in that, The step of adjusting and predicting the second temperature difference value corresponding to a preset number of time periods based on the fan frequency adjustment ratio includes: The formula for calculating the second temperature difference value corresponding to the preset number of time periods is as follows: Where k represents the current time period, =1, 2, ..., m, This represents the water temperature after cooling in the w-th time period. It is the initial value of the conversion factor for the preset w-th time period. This indicates the cooled water temperature value for the current time period. This indicates the preset optimal water temperature value; The corresponding second temperature difference values ​​are calculated by comparing the cooled water temperature values ​​corresponding to a preset number of time periods with the preset optimal water temperature values.

6. An energy-saving optimization control system for a combined wet and dry cooling tower, characterized in that, The system includes: Data acquisition module: acquires the initial state parameters of the target cooling tower, and substitutes the initial state parameters into the multi-objective cooling tower evaluation model to obtain a cooling evaluation score; the initial state parameters include the frequency of dry and wet section switching, the fan frequency adjustment ratio, and the spray water volume; Multi-objective optimization module: Optimizes the initial state parameters using a multi-objective optimization algorithm to obtain the optimal initial state parameters; Rolling optimization module: Performs rolling optimization based on the optimal initial state parameters to obtain the final optimized state parameters; Execution control module: Based on the final optimized state parameters, transmit the corresponding control instructions to the terminal.

7. The energy-saving optimization control system for a dry-wet integrated cooling tower according to claim 6, characterized in that, The multi-objective optimization module is also used for: Step 1: Randomly combine the initial state parameters to generate multiple state parameter combinations. Treat any state parameter combination as a chromosome and combine all chromosomes to obtain the initial population. Step 2: Substitute the state parameters of each chromosome into the multi-objective cooling tower evaluation model to obtain the corresponding cooling assessment score, and determine the cooling assessment score as the fitness value of the chromosome; obtain the chromosome with the highest fitness as the current optimal chromosome; Step 3: Update the current population based on the current optimal chromosome to obtain an intermediate population; Step 4: Execute steps 2 and 3. When the preset number of iterations reaches the maximum value, output the optimal chromosome. The working principle of the multi-objective cooling tower evaluation model includes: Energy consumption is calculated for any combination of state parameters of a chromosome to obtain the energy consumption value corresponding to each state parameter. After normalizing the energy consumption value corresponding to each state parameter, a multi-objective energy consumption value is obtained. Obtain the multi-objective energy consumption values ​​of all chromosomes, and use a multi-objective decomposition method to obtain the aggregation function value of the multi-objective energy consumption values ​​of all chromosomes; determine the aggregation function value as the cooling evaluation score.

8. The energy-saving optimization control system for a wet-dry integrated cooling tower according to claim 7, characterized in that, The formula for the multi-objective decomposition method specifically includes: in, This represents the reference value for the i-th target, and its range is... ; This represents the combination of state parameters for the j-th chromosome, where n represents the total number of chromosomes. The symbol representing the function formula of the multi-objective cooling tower evaluation model for the i-th objective; Represents the value of an aggregate function.

9. The energy-saving optimization control system for a wet-dry integrated cooling tower according to claim 6, characterized in that, The rolling optimization module includes: a first temperature difference module, a second temperature difference module, a sliding matrix module, and an optimal control increment vector module. The first temperature difference module is used to obtain the cooling water temperature value of the cooling tower after cooling in the current time period, and obtain the preset optimal water temperature value of the cooling tower, calculate the temperature difference between the cooling water temperature value and the preset optimal water temperature value; set the fan frequency adjustment ratio to be constant, predict the first temperature difference value of a preset number of time periods based on the temperature difference value of the current time period, and combine the first temperature difference values ​​of the preset number of time periods to obtain the initial prediction vector. The second temperature difference module is used to set a preset number of fan control cycles, wherein the fan control cycle is to increase the fan frequency adjustment ratio according to a preset step size; the second temperature difference value corresponding to the preset number of time cycles is obtained by adjusting and predicting according to the fan frequency adjustment ratio; and the second temperature difference values ​​of the preset number of time cycles are combined to obtain the fan prediction vector. The sliding matrix module is used to determine the number of a preset number of fan control cycles as columns and the number of time cycles as rows to construct a sliding matrix; and to determine the temperature difference value corresponding to each time cycle of each control cycle as an element in the sliding matrix. The optimal control increment vector module is used to calculate the optimal control increment vector based on the sliding matrix; calculate the optimal fan frequency adjustment ratio based on the optimal control increment vector; and replace the fan frequency adjustment in the optimal initial state parameters with the optimal fan frequency adjustment ratio to generate the final optimized state parameters.

10. The energy-saving optimization control system for a dry-wet integrated cooling tower according to claim 9, characterized in that, The step of adjusting and predicting the second temperature difference value corresponding to a preset number of time periods based on the fan frequency adjustment ratio includes: The formula for calculating the second temperature difference value corresponding to the preset number of time periods is as follows: Where k represents the current time period, =1, 2, ..., m, This represents the water temperature after cooling in the w-th time period. It is the initial value of the conversion factor for the preset w-th time period. This indicates the cooled water temperature value for the current time period. This indicates the preset optimal water temperature value; The corresponding second temperature difference values ​​are calculated by comparing the cooled water temperature values ​​corresponding to a preset number of time periods with the preset optimal water temperature values.

Images