Method and related equipment for optimizing the operation of the heater water level

Abstract

Embodiments of the present application disclose a method for optimizing the water level operation of a heater and related equipment, which is used to improve the optimization accuracy under the condition of rapid load change of the unit. The method in the embodiments of the present application includes: obtaining the water level fluctuation probability distribution of the heater, where the water level fluctuation probability distribution is used to represent the water level fluctuation probability of the heater at different historical time points; obtaining the real-time operation data of the unit at the current time point and the load change prediction curve of the unit; inputting the water level fluctuation probability distribution, the real-time operation data and the load change prediction curve into a pre-trained thermal system target simulation model, and the thermal system target simulation model optimizes the water levels of the heater at multiple different future time points; determining the target water level when the preset optimization convergence condition is met, where the target water level is the water levels of the heater at multiple different future time points; and regulating the water level of the heater according to the target water level.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of thermal power generation, and particularly to a method for optimizing the operation of the water level of a heater and related equipment. Background Art

[0002] High and low pressure heaters are important equipment in the thermal power generation system. Relevant technical personnel have also conducted in-depth research on the operation optimization of the water levels of high and low pressure heaters. With the promotion of the national dual-carbon goal, thermal power generation enterprises are facing an increasingly severe situation of energy conservation and emission reduction. The setting of the water levels of high and low pressure heaters also has different impacts on the cycle efficiency of the entire thermal system, and the demand for optimization accuracy is also increasing day by day.

[0003] The optimization of the operation water levels of high and low pressure heaters generally starts from the traditional theory of the thermal system, calculates through the theory of heat consumption difference, combines the test results under different working conditions, and calculates the optimal operation water levels of different high and low pressure heaters under different working conditions as the basis for daily operation.

[0004] The previous optimization of the operation of high and low pressure heaters was based on the accumulation of the current and past periods. It should be noted that for this kind of accumulation method, the water level of the heater is actually in a certain process of back-and-forth fluctuation. The fluctuation range of the water level is generally related to the state of the thermal system, while the previous thermal system did not consider the state of the thermal system, and at the same time, the optimization accuracy under the condition of rapid load change of the unit is weak. Summary of the Invention

[0005] The embodiments of the present application provide a method for optimizing the operation of the water level of a heater and related equipment.

[0006] The first aspect of the embodiments of the present application provides a method for optimizing the operation of the water level of a heater, including:

[0007] Obtaining the probability distribution of the water level fluctuation of the heater, where the probability distribution of the water level fluctuation is used to represent the probability of the water level fluctuation of the heater at different historical time points;

[0008] Obtaining the real-time operation data of the unit at the current time point and the load change prediction curve of the unit;

[0009] Inputting the probability distribution of the water level fluctuation, the real-time operation data, and the load change prediction curve into a pre-trained target simulation model of the thermal system, and the target simulation model of the thermal system optimizes the water levels of the heater at multiple different future time points;

[0010] Determining the target water level when the preset optimization convergence condition is met, where the target water level is the water levels of the heater at the multiple different future time points;

[0011] Regulate the water level of the heater according to the target water level.

[0012] Optionally, before inputting the water level fluctuation probability distribution, the real-time operation data, and the load change prediction curve into a pre-trained target simulation model of the thermal system, the method further includes:

[0013] Construct an initial simulation model of the thermal system, where the initial simulation model of the thermal system includes an initial simulation model of the heater;

[0014] Calculate the characteristic data of the unit under different working conditions according to the historical data of the unit under different working conditions;

[0015] Modify the initial simulation model of the thermal system according to the characteristic data and the coefficient correction pre-mapping to obtain the target simulation model of the thermal system.

[0016] Optionally, input the water level fluctuation probability distribution, the real-time operation data, and the load change prediction curve into a pre-trained target simulation model of the thermal system, and the target simulation model of the thermal system optimizes the water level of the heater at multiple different future time points, including:

[0017] Obtain the load prediction value and the load change rate according to the load change prediction curve;

[0018] Input the water level fluctuation probability distribution, the real-time operation data, the load prediction value, and the load change rate into the pre-trained target simulation model of the thermal system, so that the target simulation model of the thermal system uses the load prediction value and the load change rate as optimization conditions to simulate the water level fluctuation probability distribution and the real-time operation data, and obtain the energy consumption data of the unit at different water levels;

[0019] Calculate the water level of the unit at multiple different future time points according to the energy consumption data through an optimization method.

[0020] Optionally, the optimization method includes: a method combining Monte Carlo simulation and particle swarm algorithm or a Monte Carlo tree search optimization method.

[0021] Optionally, regulating the water level of the heater according to the target water level includes:

[0022] Output the target water level so that the operator can regulate the water level of the heater according to the target water level, and the target water level includes the water level at the current time point and the future water level.

[0023] A second aspect of the embodiments of the present application provides a device for optimizing the operation of the water level of a heater, and the device includes:

[0024] A first acquisition unit, configured to acquire the water level fluctuation probability distribution of a heater, where the water level fluctuation probability distribution is used to represent the water level fluctuation probabilities of the heater at different historical time points;

[0025] A second acquisition unit, configured to acquire the real-time operation data of the unit at the current time point and the load change prediction curve of the unit;

[0026] An input unit, configured to input the water level fluctuation probability distribution, the real-time operation data, and the load change prediction curve into a pre-trained target simulation model of the thermal system, and the target simulation model of the thermal system optimizes the water levels of the heater at multiple different future time points;

[0027] A determination unit, configured to determine a target water level when a preset optimization convergence condition is met, where the target water level is the water levels of the heater at the multiple different future time points;

[0028] A regulation unit, configured to regulate the water level of the heater according to the target optimization result.

[0029] Optionally, the device further includes:

[0030] A construction unit, configured to construct an initial simulation model of the thermal system, where the initial simulation model of the thermal system includes an initial simulation model of the heater;

[0031] A calculation unit, configured to calculate the characteristic data of the unit under different working conditions according to the historical data of the unit under different working conditions;

[0032] A correction unit, configured to correct the initial simulation model of the thermal system according to the characteristic data and the coefficient correction pre-mapping to obtain the target simulation model of the thermal system.

[0033] Optionally, the input unit includes:

[0034] An acquisition subunit, configured to acquire a load prediction value and a load change rate according to the load change prediction curve;

[0035] An input subunit, configured to input the water level fluctuation probability distribution, the real-time operation data, the load prediction value, and the load change rate into the pre-trained target simulation model of the thermal system, so that the target simulation model of the thermal system uses the load prediction value and the load change rate as optimization conditions to simulate the water level fluctuation probability distribution and the real-time operation data, and obtain the energy consumption data of the unit at different water levels;

[0036] A calculation subunit, configured to calculate the water levels of the unit at multiple different future time points according to the energy consumption data through an optimization method.

[0037] Optionally, the regulation unit includes:

[0038] An output subunit, configured to output the target water level, so that an operator can regulate the water level of the heater according to the target water level, where the target water level includes the water level at the current time point and the future water level.

[0039] A third aspect of the embodiments of the present application provides a device for optimizing the operation of the water level of a heater, including:

[0040] A central processing unit, a memory, an input / output interface, a wired or wireless network interface, and a power supply;

[0041] The memory is a transient storage memory or a persistent storage memory;

[0042] The central processing unit is configured to communicate with the memory and execute the instruction operations in the memory to execute the method for optimizing the operation of the water level of the heater in the foregoing first aspect.

[0043] The embodiments of the present application provide a computer-readable storage medium, characterized in that the computer-readable storage medium includes instructions, and when the instructions run on a computer, the computer is caused to execute the method for optimizing the operation of the water level of the heater in the foregoing first aspect.

[0044] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages: When performing optimization, the load prediction curve of the unit and the real-time operation data are considered, and optimization is performed on the basis of determining the boundary of the water level fluctuation range and the data probability density of the heater, thereby improving the optimization accuracy under the condition of rapid load change of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic flowchart of a method for optimizing the operation of the water level of the heater in an embodiment of the present application;

[0046] Figure 2 It is another schematic flowchart of a method for optimizing the operation of the water level of the heater in an embodiment of the present application;

[0047] Figure 3 It is a schematic structural diagram of a device for optimizing the operation of a circulating water system in an embodiment of the present application;

[0048] Figure 4 It is another schematic structural diagram of a device for optimizing the operation of a circulating water system in an embodiment of the present application;

[0049] Figure 5 It is another schematic structural diagram of a device for optimizing the operation of a circulating water system in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0051] The embodiments of the present application provide a method and related equipment for optimizing the operation of the heater water level, which is used to improve the optimization accuracy under the condition of rapid load change of the unit.

[0052] In the entire thermal system, the unit is a component of the thermal system, and the heater is an important equipment of the unit. In the embodiments of the present application, it can be understood that the subsequent described thermal system includes the unit and the heater, and the specific subsequent description will not be repeated.

[0053] Please refer to Figure 1 , a process of the method for optimizing the operation of the heater water level in the embodiments of the present application includes steps 101-105.

[0054] 101. Obtain the probability distribution of the water level fluctuation of the heater.

[0055] Before optimizing the water level of the heater in the thermal system, it is necessary for the operator or the thermal system to obtain the probability distribution of the water level fluctuation of the heater according to the historical operation data of the heater. It is not difficult to understand that during the historical operation of the heater, the generated data will be saved by the system. When the system needs to call the operation data, the system can call the historical operation data from the storage space in the memory of the heater.

[0056] Specifically, the probability distribution of the water level fluctuation is generally an expression of the boundary range and data probability density under different load and load command states, and this expression is generally updated regularly from several days to several months, and specific details are not limited here.

[0057] Specifically, the probability distributions of the water level fluctuations at multiple different time points can be understood as a function with the time axis as the abscissa and the water level fluctuation probability as the ordinate. It can be understood that, for the convenience of understanding, the probability distribution of the water level fluctuation is described in the form of a function. It is not difficult to understand that this water level fluctuation probability can also be understood as that under a water level control target, the actual water level fluctuation will be distributed within a range. From this, it can be seen that under different water level control targets, the probability distributions will also have some corresponding differences. In this embodiment, it can also be understood in other forms, and specific details are not limited here.

[0058] 102. Obtain the real-time operation data and load change prediction curve of the unit at the current time point.

[0059] Before optimizing the water level of the heater in the thermal system, it is also necessary to obtain the real-time operation data of the unit and the load change prediction curve. When the unit is in operation, the system can obtain various parameters of the unit during operation, including but not limited to the operating power and load of the unit.

[0060] Among them, the real-time operation data also includes relevant data of each heater. Specifically, the relevant data of the heater generally includes the water level, flow rate, etc. of the heater. It can be understood that the relevant data of the heater also includes relevant parameters of other heaters, which are not specifically limited here.

[0061] Specifically, the load change prediction curve for a future period can be obtained through the relevant load prediction system.

[0062] In this embodiment, steps 101 and 102 are not limited. Step 101 can be executed first and then step 102, or step 102 can be executed first and then step 101, which is not specifically limited here.

[0063] 103. Input the water level fluctuation probability distribution, real-time operation data, and load change prediction curve into the pre-trained target simulation model of the thermal system.

[0064] After inputting the water level fluctuation probability distribution, real-time operation data, and load change prediction curve into the pre-trained target simulation model of the thermal system under different working conditions, the target simulation model of the thermal system can optimize the water level of the heater at each time point according to the probability distribution of the water level fluctuation of the heater under different system states obtained in the previous step 101.

[0065] It can be understood that the pre-trained target simulation model of the thermal system represents a thermal system simulation model with a coefficient correction pre-mapping added. For the convenience of understanding, it will be described as the actual simulation model of the thermal system later, and no further description will be given here.

[0066] 104. Determine the target water level when the preset optimization convergence condition is met.

[0067] When the preset optimization convergence condition is met, the optimization ends, the water level at the end of the optimization is determined, and this water level is determined as the target water level. In practical applications, the optimization convergence condition is determined by the operator according to experience. It can be that the improvement amplitude of the optimization result is less than the setting or the preset specified number of optimization times within a certain number of optimization times, which is not specifically limited here.

[0068] It can be understood that the optimization result in this embodiment refers to the optimization result, and no further description will be given here.

[0069] 105. Regulate the water level of the heater according to the target water level.

[0070] Based on the target water level determined in step 104, control the operation of the heater to achieve the control of the water level of the heater. In practical applications, the content of regulating the water level of the heater includes: the optimization scheme for the water level of the heater at the current moment and the operation optimization strategy for the water level of the heater at different subsequent moments.

[0071] In this embodiment, when optimizing the water level of the heater, measurement data of the current state of the unit and the future load prediction curve are introduced. Under the constraint conditions of the probability distribution of the water level fluctuation of the heater, it is truly realized that the control of the water level of the heater is not only based on the data at the current time point and historical data, but also based on the expected results of future load prediction and the load change state, making the whole operation logical and enabling the optimization result to consider the optimization requirements of the actual dynamic thermal system in the regulation fluctuation to the greatest extent.

[0072] The following specifically describes the operation optimization method for the water level of the heater in the embodiments of the present application. Please refer to Figure 2 , another process of the embodiments of the present application includes steps 201 to 207.

[0073] 201. Construct an ideal simulation model of the thermal system including the heater.

[0074] Construct an ideal simulation model of the thermal system. This ideal simulation model of the thermal system includes an ideal simulation model of the heater, and this model can perform accurate off-design simulations under the original design state.

[0075] It can be understood that the simple heater model included in the general thermal system simulation model is not sufficient to support the requirements of this model. Therefore, the ideal simulation model of the heater pointed out in this embodiment is a model sufficient to support the requirements of this model. It can also be understood that this ideal simulation model of the thermal system can also include ideal simulation models of other system components, which are not specifically limited here.

[0076] It should be noted that the ideal simulation model of the thermal system described in the embodiments of the present application is the same as the initial simulation model of the thermal system described in the foregoing part, and will not be further explained hereinafter.

[0077] 202. Calculate the characteristic data of different operating conditions in the simulation model according to the unit historical data.

[0078] After obtaining the historical data of the unit, calculate the various characteristic data under different working conditions in the simulation model. This step is to regularly roll and calculate the characteristic data of different equipment and different systems at different times and under different working conditions based on the actual sensor data of the unit. The characteristic data generally includes the actual thermal conductivity of the heat exchanger, the actual flow characteristic coefficient of the turbine stage group, the speed, flow and head characteristics of each water pump, the energy consumption of different equipment, and the resistance coefficient under different valve openings. Specifically, the characteristic data can also include other data, which is not limited here. According to the characteristic data, the ideal simulation model of the thermal system is corrected to the actual simulation model of the thermal system that meets the actual characteristics.

[0079] It is understandable that the calculation precision can be minute level, day level or week level. In actual application, each characteristic data will be updated from day level to week level to obtain the overall characteristic data accumulated from multiple minute levels.

[0080] It can also be understood that the actual simulation model of the thermal system described in the embodiment of the present application is the target simulation model of the thermal system described in the aforementioned part, and no further explanation will be given later.

[0081] 203. Regularly update the actual thermal system simulation model under different working conditions.

[0082] In addition to revising the thermal system simulation model according to various characteristic data under different working conditions, the actual characteristics of the system will continue to change as the thermal system operates. Therefore, the system needs to regularly roll-up the thermal system simulation model under different working conditions to obtain the actual thermal system simulation model that is closest to the real thermal system. It is understandable that in order to reduce the system's repeated revisions of the actual thermal system simulation model, the rolling update cycle is generally selected in the range of several days to several months. It is also understandable that the rolling update cycle is only one of the options, and it can also be other cycles, which are not specifically limited here.

[0083] The specific operation steps are based on the original thermal system simulation model calculation method. On the basis of, add a coefficient to correct the pre-mapping Among them, the coefficient correction pre-mapping is a series of mapping method packages. There are several general method packages to choose from. Choose one of them according to the specific applicable situation. The correction coefficient is generated by a mapping, not a fixed value. Y is related, that is, the energy consumption output, X is related, that is, the main operating conditions, such as a set of vectors such as ambient temperature, load, and heating supply, and G is related to the corrected mapping. Specifically, the coefficient correction pre-mapping can choose simple methods such as multivariate linear and fitting according to the complexity of the object, or it can choose neural networks or more complex machine learning methods to implement it. The specifics are not limited here.

[0084] 204. Obtain the boundary of the water level fluctuation range and the probability distribution of data density of the heater according to the historical data of the heater.

[0085] Before optimizing the water level of the heater, it is also necessary to obtain the boundary of the water level fluctuation range and the probability distribution of data density of the heater according to the historical operation data of the heater. Specifically, the boundary range and data probability density are expressed under different load and load command states, and this expression is generally updated regularly from several days to several months.

[0086] 205. Obtain the real-time operation data of the unit and input it into the prediction environment and load curve.

[0087] Before performing optimization, it is also necessary to obtain the real-time operation data of the unit and input the predicted load curve. It can be understood that historical data can be regarded as characteristics, and a large number of characteristic points form a stable and reliable characteristic. Future data is used for prediction, that is, if there is no operating state, there is no energy consumption.

[0088] The specific implementation of this step includes: on the one hand, collect the thermal system of the unit in real-time operation to obtain the real-time operation data of the unit. Among them, the real-time operation data also includes the relevant data of each heater. Specifically, the relevant data of the heater generally includes the water level, flow rate, etc. of the heater. It can be understood that the relevant data of the heater also includes other relevant parameters of the heater, which are not specifically limited here.

[0089] On the other hand, obtain the predicted load change curve within a future period of time through the relevant system for load prediction. The refresh rate of the load prediction curve is generally selected from 5 to 15 minutes or a lower refresh rate, which is not specifically limited here.

[0090] It can also be understood that this embodiment does not limit the relevant system for obtaining the predicted load change curve. The predicted load change curve can directly read the data sent by systems such as the distributed computer system (DCS) across the network gateway, or read the system data of the supervisory information system (SIS). It is not difficult to understand that there can be a dedicated system for load prediction, which is not specifically limited here.

[0091] In this embodiment, steps 204 and 205 are not limited. Step 204 can be executed first and then step 205, or step 205 can be executed first and then step 204, which is not specifically limited here.

[0092] 206. The optimization module performs optimization.

[0093] After obtaining the actual simulation model of the thermal system that is closest to the real thermal system, optimization can be performed through the optimization module.

[0094] Specifically, after inputting the aforementioned coefficient correction pre-mapping, the real-time operation data of the unit, and the load prediction change curve into the optimization module, the optimization module calls the aforementioned actual simulation model of the thermal system. This actual simulation model of the thermal system is a simulation model with a coefficient correction pre-mapping added, and optimizes the heater water levels at multiple different future time points based on the probability distribution of heater water level fluctuations under the different system states obtained above.

[0095] Specifically, the optimization method uses the future load prediction value and its change rate as conditions, and adopts an optimization method that combines Monte Carlo simulation and particle swarm optimization algorithms or Monte Carlo tree search optimization method for the future. Specifically, it is not limited here. First, through the probability distribution of water level fluctuations at multiple different historical time points obtained above, and then through the actual simulation model of the thermal system that is closest to the real thermal system, the energy consumption data under different water level targets are simulated, and the optimal water level targets at multiple different future time points are optimized one by one through particle swarm optimization algorithms and other optimization algorithms.

[0096] It can be understood that the future load prediction value and its change rate are obtained by calculating and analyzing the aforementioned load change prediction curve.

[0097] Specifically, the probability distribution of water level fluctuations at multiple different time points can be understood as a function with the time axis as the abscissa and the water level fluctuation probability as the ordinate. It can be understood that for the convenience of understanding, the probability distribution of water level fluctuations is described in the form of a function. In this embodiment, it can also be understood as other forms, which are not limited here specifically.

[0098] It can also be understood that the optimization module can also optimize the water level of the heater through other optimization algorithms. It is not difficult to understand that the relatively common one is the particle swarm algorithm, and similar optimization algorithms can also be implemented, such as: ant colony algorithm, wolf pack algorithm, bird flock algorithm, whale school algorithm and other MATLAB algorithms of this kind, which are not limited here specifically.

[0099] 207. Output the current optimization result and the subsequent optimization strategy.

[0100] When the optimization result of the optimization module meets the set optimization convergence condition, the current optimization result and the subsequent optimization strategy are output. It can be understood that this optimization convergence condition is generally that within a certain number of optimization times, the improvement amplitude of the optimization result is less than the pre-set condition, that is, the improvement increment is less than the set error range.

[0101] The specific output form can be based on the location of the system. For example, when an operator operates the system, the output method can be to highlight the node identifier or description that the operator needs to operate on the operation display screen. When the system regulates itself, the output method can be the control instruction for the system or the subsequent optimization curve. The system can regulate the water level of the heater according to this optimization curve. Specifically, the output form is not limited here.

[0102] It can be understood that the current optimization result is the current optimization plan, and the subsequent optimization strategy is the operation optimization plan at different future times.

[0103] It can also be understood that the specific operation method of regulating the water level of the heater can be to control the start and stop of the water pump or the operating frequency of the variable-frequency pump, or to regulate the energy consumption of the unit. It is not difficult to understand that the system can regulate the water level of the heater in multiple ways. Specifically, it is not limited here.

[0104] In this embodiment, a set of mechanisms is adopted to generate a simulation model that conforms to the energy consumption characteristics of the actual thermal system, and this model is used as the core. Starting from the current state of the system for future optimization, the energy consumption levels of different water levels are calculated through the simulation model that conforms to the actual situation with the probability distribution of the water level fluctuations corresponding to different load positions and change rates. Then, the expected energy consumption distribution is obtained through the probability distribution of the water level fluctuations. Finally, algorithms such as particle swarm are used to achieve global optimization, so as to ensure that the entire optimization plan can not only adapt to the changes in the system characteristics and conform to the current state of the system, but also conduct relevant evaluation and decision-making on future loads, making the operation mode of the system include elements such as the actual water level of the heater being affected by the control system state. The optimization result of the system maximally satisfies the economic cost optimization that can be truly operable and achievable.

[0105] The operation optimization method of the water level of the heater in the embodiment of the present application is described above. Next, the operation optimization device of the water level of the heater in the embodiment of the present application will be described. Please refer to Figure 3 , a structure of the operation optimization device of the water level of the heater in the embodiment of the present application includes:

[0106] The first acquisition unit 301 is used to acquire the probability distribution of the water level fluctuations of the heater, and the probability distribution of the water level fluctuations is used to represent the probability of the water level fluctuations of the heater at different historical time points;

[0107] The second acquisition unit 302 is used to acquire the real-time operation data of the unit at the current time point and the load change prediction curve of the unit;

[0108] An input unit 303, configured to input the water level fluctuation probability distribution, real-time operation data, and load change prediction curve into a pre-trained target simulation model of the thermal system, and the target simulation model of the thermal system optimizes the water levels of the heaters at multiple different future time points;

[0109] A determination unit 304, configured to determine a target water level when a preset optimization convergence condition is met, where the target water level is the water levels of the heaters at multiple different future time points;

[0110] An adjustment unit 305, configured to adjust the water levels of the heaters according to the target optimization result.

[0111] In the embodiment of the present application, when the input unit 303 performs optimization, it considers the water level fluctuation probability distribution of the heater obtained by the first unit 301 and the real-time operation data of the unit at the current time point and the load change prediction curve obtained by the second unit 302, and performs optimization on the basis of determining the possible changes of the unit in the future for a period of time, which improves the optimization accuracy under the condition of rapid load change of the unit.

[0112] The following will describe in detail the heater water level operation optimization device in the embodiment of the present application. Please refer to Figure 4 , another structure of the heater water level operation optimization device in the embodiment of the present application includes:

[0113] A first acquisition unit 401, configured to acquire the water level fluctuation probability distribution of the heater, where the water level fluctuation probability distribution is used to represent the water level fluctuation probability of the heater at different historical time points;

[0114] A second acquisition unit 402, configured to acquire the real-time operation data of the unit at the current time point and the load change prediction curve of the unit;

[0115] An input unit 403, configured to input the water level fluctuation probability distribution, real-time operation data, and load change prediction curve into a pre-trained target simulation model of the thermal system, and the target simulation model of the thermal system optimizes the water levels of the heaters at multiple different future time points;

[0116] A determination unit 404, configured to determine a target water level when a preset optimization convergence condition is met, where the target water level is the water levels of the heaters at multiple different future time points;

[0117] An adjustment unit 405, configured to adjust the water levels of the heaters according to the target optimization result.

[0118] The device further includes: a construction unit 406, a calculation unit 407, and a correction unit 408.

[0119] A construction unit 406, configured to construct an initial simulation model of the thermal system, where the initial simulation model of the thermal system includes an initial simulation model of the heater;

[0120] The calculation unit 407 is configured to calculate the characteristic data of the unit under different working conditions according to the historical data of the unit under different working conditions;

[0121] The correction unit 408 is configured to correct the initial simulation model of the thermal system according to the characteristic data and coefficients to obtain the target simulation model of the thermal system.

[0122] The input unit 403 includes: an acquisition subunit 4031, an input subunit 4032, and a calculation subunit 4033.

[0123] The acquisition subunit 4031 is configured to obtain the load prediction value and the load change rate according to the load change prediction curve;

[0124] The input subunit 4032 is configured to input the water level fluctuation probability distribution, the real-time operation data, the load prediction value, and the load change rate into the pre-trained target simulation model of the thermal system, so that the target simulation model of the thermal system uses the load prediction value and the load change rate as the optimization conditions to simulate the water level fluctuation probability distribution and the real-time operation data, and obtain the energy consumption data of the unit at different water levels;

[0125] The calculation subunit 4033 is configured to calculate the water levels of the unit at multiple different future time points by an optimization method according to the energy consumption data.

[0126] The regulation unit 405 includes: an output subunit 4051.

[0127] The output subunit 4051 is configured to output the target water level, so that the operator can regulate the water level of the heater according to the target water level, and the target water level includes the water level at the current time point and the water levels in the future.

[0128] The optimization method is a method combining Monte Carlo simulation and particle swarm optimization algorithm or Monte Carlo tree search optimization method.

[0129] In this embodiment, each unit in the heater water level operation optimization device executes the operations of the heater water level operation optimization method in the foregoing Figures 1 to 2 illustrated embodiment, which will not be elaborated here specifically.

[0130] Next, please refer to Figure 5 , another embodiment of the heater water level operation optimization device in the embodiment of the present application includes:

[0131] A central processing unit 501, a memory 505, an input / output interface 504, a wired or wireless network interface 503, and a power supply 902;

[0132] The memory 505 is a short-term storage memory or a persistent storage memory;

[0133] The central processing unit 501 is configured to communicate with the memory 505 and execute the instruction operations in the memory 505 to perform the method in the foregoing Figures 1 to 2 illustrated embodiment.

[0134] An embodiment of the present application further provides a chip system, which is characterized in that the chip system includes at least one processor and a communication interface, the communication interface and the at least one processor are interconnected through a line, and the at least one processor is used to run a computer program or instruction to perform the method in the foregoing Figures 1 to 2 illustrated embodiment.

[0135] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0136] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, the functional units in each embodiment of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software function units.

[0139] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, read-only memory), random access memories (RAM, random access memory), magnetic disks, or optical discs that can store program codes.

Claims

1. A method for optimizing the water level operation of a heater, characterized in that The method includes: Obtaining the water level fluctuation probability distribution of the heater, where the water level fluctuation probability distribution is used to represent the water level fluctuation probability of the heater at different historical time points; Obtaining the real-time operation data of the unit at the current time point and the load change prediction curve of the unit; the real-time operation data includes at least the water level data, flow data or operation power data of the heater, the load change prediction curve is obtained by a load prediction system, and the load change prediction curve includes at least future load prediction values and change rates; Inputting the water level fluctuation probability distribution, the real-time operation data and the load change prediction curve into a pre-trained target simulation model of the thermal system, and optimizing the water level of the heater at multiple different future time points by the target simulation model of the thermal system; Determining the target water level when a preset optimization convergence condition is met, where the target water level is the water level of the heater at the multiple different future time points; Regulating the water level of the heater according to the target water level; Before inputting the water level fluctuation probability distribution, the real-time operation data and the load change prediction curve into a pre-trained target simulation model of the thermal system, the method further includes: Constructing an initial simulation model of the thermal system, where the initial simulation model of the thermal system includes an initial simulation model of the heater; Calculating the characteristic data of the unit under different working conditions according to the historical data of the unit under different working conditions; Correcting the initial simulation model of the thermal system according to the characteristic data and the coefficient correction pre-mapping to obtain the target simulation model of the thermal system; Inputting the water level fluctuation probability distribution, the real-time operation data and the load change prediction curve into a pre-trained target simulation model of the thermal system, and optimizing the water level of the heater at multiple different future time points by the target simulation model of the thermal system, including: Obtaining the load prediction value and the load change rate according to the load change prediction curve; Inputting the water level fluctuation probability distribution, the real-time operation data, the load prediction value and the load change rate into the pre-trained target simulation model of the thermal system, so that the target simulation model of the thermal system uses the load prediction value and the load change rate as optimization conditions to simulate the water level fluctuation probability distribution and the real-time operation data, and obtain the energy consumption data of the unit at different water levels; Calculating the water level of the unit at multiple different future time points according to the energy consumption data through an optimization method.

2. The method for optimizing water level operation according to claim 1, characterized in that The optimization method includes: a method combining Monte Carlo simulation and particle swarm algorithm or a Monte Carlo tree search optimization method.

3. The method according to claim 1, characterized in that, Regulating the water level of the heater according to the target water level includes: Outputting the target water level so that an operator can regulate the water level of the heater according to the target water level, where the target water level includes the water level at the current time point and the future water level.

4. A device for optimizing the operation of the water level of a heater, characterized in that, The device includes: A first acquisition unit for acquiring the water level fluctuation probability distribution of the heater, where the water level fluctuation probability distribution is used to represent the water level fluctuation probability of the heater at different historical time points; A second acquisition unit, configured to acquire the real-time operation data of the unit at the current time point and the load change prediction curve of the unit; An input unit, configured to input the water level fluctuation probability distribution, the real-time operation data, and the load change prediction curve into a pre-trained target simulation model of the thermal system, and the target simulation model of the thermal system optimizes the water levels of the heater at multiple different future time points; A determination unit, configured to determine a target water level when a preset optimization convergence condition is met, where the target water level is the water levels of the heater at the multiple different future time points; A regulation unit, configured to regulate the water level of the heater according to the target optimization result; The device further includes: A construction unit, configured to construct an initial simulation model of the thermal system, where the initial simulation model of the thermal system includes an initial simulation model of the heater; A calculation unit, configured to calculate the characteristic data of the unit under different working conditions according to the historical data of the unit under different working conditions; A correction unit, configured to correct the initial simulation model of the thermal system according to the characteristic data and coefficient correction pre-mapping to obtain the target simulation model of the thermal system; The input unit includes: An acquisition subunit, configured to acquire a load prediction value and a load change rate according to the load change prediction curve; An input subunit, configured to input the water level fluctuation probability distribution, the real-time operation data, the load prediction value, and the load change rate into the pre-trained target simulation model of the thermal system, so that the target simulation model of the thermal system uses the load prediction value and the load change rate as optimization conditions to simulate the water level fluctuation probability distribution and the real-time operation data, and obtain the energy consumption data of the unit at different water levels; A calculation subunit, configured to calculate the water levels of the unit at multiple different future time points according to the energy consumption data through an optimization method.

5. A water level operation optimization device, characterized in that, including: A central processing unit, a memory, and an input / output interface; The memory is a transient storage memory or a persistent storage memory; The central processing unit is configured to communicate with the memory and execute the instruction operations in the memory to execute the method according to any one of claims 1 to 3.

6. A computer storage medium, characterized in that, Instructions are stored in the computer storage medium, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 3.

Images