Model Determination Method, Device, Electronic Device, and Storage Medium

Abstract

The present disclosure provides a model determination method, apparatus, electronic device, and storage medium, relating to the field of artificial intelligence, and particularly to the fields of deep learning and data processing technologies. The specific implementation solution is as follows: Obtain the heat exchange data and first environmental data of the air-cooled island, where multiple heat exchangers are deployed in the air-cooled island; Based on the heat exchange data and the first environmental data, establish a first heat exchange model for each heat exchanger to obtain a plurality of first heat exchange models, where each first heat exchange model is used to quantitatively describe the heat exchange capacity of the corresponding heat exchanger; Based on the plurality of first heat exchange models, establish a target heat exchange model, where the target heat exchange model is used to quantitatively describe the heat exchange capacity of the air-cooled island.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and particularly to the fields of deep learning and data processing technology. Background Art

[0002] Currently, when quantitatively describing the heat exchange capacity of an air-cooled island, the air-cooled island is usually directly regarded as a whole for heat exchange modeling. For example, the overall heat exchange capacity of the air-cooled island is directly obtained through artificial intelligence algorithms and data. Summary of the Invention

[0003] The present disclosure provides a method, an apparatus, a device, and a storage medium for model determination.

[0004] According to one aspect of the present disclosure, a model determination method is provided, including: obtaining heat exchange data and first environmental data of an air-cooled island, where multiple heat exchangers are deployed in the air-cooled island; based on the heat exchange data and the first environmental data, establishing a first heat exchange model for each heat exchanger to obtain a plurality of first heat exchange models, where each first heat exchange model is used to quantitatively describe the heat exchange capacity of the corresponding heat exchanger; and establishing a target heat exchange model based on the plurality of first heat exchange models, where the target heat exchange model is used to quantitatively describe the heat exchange capacity of the air-cooled island.

[0005] Optionally, establishing a first heat exchange model for each heat exchanger based on the heat exchange data and the first environmental data includes: determining the convective heat transfer coefficient of each heat exchanger based on the heat exchange data and the first environmental data, where the convective heat transfer coefficient is used to represent the heat exchange capacity of the corresponding heat exchanger; and establishing a first heat exchange model for each heat exchanger based on the convective heat transfer coefficient of each heat exchanger.

[0006] Optionally, establishing a target heat exchange model based on the plurality of first heat exchange models includes: performing weighted averaging on the plurality of first heat exchange models to obtain a first target heat exchange model, where the first target heat exchange model is used to quantitatively describe the overall heat exchange capacity of the air-cooled island.

[0007] Optionally, establishing a target heat exchange model based on the plurality of first heat exchange models includes: arranging the plurality of first heat exchange models according to the positions of the corresponding plurality of heat exchangers in space to obtain a second target heat exchange model, where the second target heat exchange model is used to quantitatively describe the local heat exchange capacity of the air-cooled island.

[0008] According to another aspect of the present disclosure, a data processing method is provided, including: obtaining a first target back pressure of an air-cooled island and second environmental data; and processing the first target back pressure and the second environmental data based on the target heat exchange model to obtain the heat load of each heat exchanger among the multiple heat exchangers of the air-cooled island, where the target heat exchange model is obtained by the model determination method of the embodiments of the present disclosure.

[0009] According to another aspect of the present disclosure, another data processing method is provided, including: obtaining a second target back pressure after the first target back pressure of the air-cooled island changes; processing the second target back pressure based on a target heat transfer model to obtain first adjustment data, where the first adjustment data is used to adjust the heat transfer capacity of the air-cooled island, and the target heat transfer model is obtained by the model determination method of the embodiments of the present disclosure.

[0010] According to another aspect of the present disclosure, another data processing method is provided, including: obtaining third environmental data after the second environmental data of the air-cooled island changes; processing the third environmental data based on a target heat transfer model to obtain second adjustment data, where the second adjustment data is used to adjust the heat transfer capacity of the air-cooled island, and the target heat transfer model is obtained by the model determination method of the embodiments of the present disclosure.

[0011] According to another aspect of the present disclosure, a model determination device is provided, including: a first acquisition unit configured to acquire heat transfer data and first environmental data of the air-cooled island, where multiple heat exchangers are deployed in the air-cooled island; a first establishment unit configured to establish a first heat transfer model for each heat exchanger based on the heat transfer data and the first environmental data to obtain a plurality of first heat transfer models, where each first heat transfer model is used to quantitatively describe the heat transfer capacity of the corresponding heat exchanger; a second establishment unit configured to establish a target heat transfer model based on the plurality of first heat transfer models, where the target heat transfer model is used to quantitatively describe the heat transfer capacity of the air-cooled island. According to another aspect of the present disclosure, a data processing device is provided, including: a second acquisition unit configured to acquire the first target back pressure and second environmental data of the air-cooled island; a first processing unit configured to process the first target back pressure and the second environmental data based on the target heat transfer model to obtain the heat load of each heat exchanger, where the target heat transfer model is obtained by the model determination method of the embodiments of the present disclosure.

[0012] According to another aspect of the present disclosure, another data processing device is provided, including: a third acquisition unit configured to acquire a second target back pressure after the first target back pressure of the air-cooled island changes; a second processing unit configured to process the second target back pressure based on the target heat transfer model to obtain first adjustment data, where the first adjustment data is used to adjust the heat transfer capacity of the air-cooled island, and the target heat transfer model is obtained by the model determination method of the embodiments of the present disclosure.

[0013] According to another aspect of the present disclosure, another data processing device is provided, including: a fourth acquisition unit configured to acquire third environmental data after the second environmental data of the air-cooled island changes; a third processing unit configured to process the third environmental data based on the target heat transfer model to obtain second adjustment data, where the second adjustment data is used to adjust the heat transfer capacity of the air-cooled island, and the target heat transfer model is obtained by the model determination method of the embodiments of the present disclosure.

[0014] According to another aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the model determination and data processing methods of the embodiments of the present disclosure.

[0015] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the model determination and data processing methods of the embodiments of the present disclosure.

[0016] According to another aspect of the present disclosure, there is provided a computer program product, including a computer program, which implements the model determination and data processing methods of the embodiments of the present disclosure when executed by a processor.

[0017] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. Description of the Drawings

[0018] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0019] Figure 1 is a schematic diagram of a model determination method according to an embodiment of the present disclosure;

[0020] Figure 2 is a flowchart of a data processing method according to an embodiment of the present disclosure;

[0021] Figure 3 is a flowchart of another data processing method according to an embodiment of the present disclosure;

[0022] Figure 4 is a flowchart of another data processing method according to an embodiment of the present disclosure;

[0023] Figure 5 is a schematic diagram of a method for establishing an air-cooled island heat transfer model according to an embodiment of the present disclosure;

[0024] Figure 6 is a schematic diagram of an air-cooled island operation system based on a heat transfer model according to an embodiment of the present disclosure;

[0025] Figure 7 is a schematic diagram of a model determination device according to an embodiment of the present disclosure;

[0026] Figure 8 is a schematic diagram of a data processing device according to an embodiment of the present disclosure;

[0027] Figure 9 It is a schematic diagram of another data processing device according to an embodiment of the present disclosure;

[0028] Figure 10 It is a schematic diagram of another data processing device according to an embodiment of the present disclosure;

[0029] Figure 11 It is a schematic block diagram of an electronic device according to an embodiment of the present disclosure. Detailed implementation manners

[0030] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, descriptions of well-known functions and structures are omitted below for clarity and conciseness.

[0031] The model determination method of the embodiments of the present disclosure is introduced below.

[0032] In the related art, a dependent variable related to the heat exchange capacity of the air-cooled island is directly used as the input, and the convective heat transfer coefficient of the air-cooled island is used as the output. Through intelligent algorithms such as artificial neural networks and support vector machines, a prediction method for the convective heat transfer coefficient of the air-cooled island is constructed. That is to say, when quantitatively describing the heat exchange of the air-cooled island, the air-cooled island is directly regarded as a whole for heat exchange modeling, resulting in problems such as poor modeling accuracy and the inability of the modeling heat exchange results to meet the refined regulation and operation requirements of the air-cooled island. In addition, each feature vector is not made dimensionless in the modeling process, and the universality of the model is poor, thus there is a technical problem that the heat exchange capacity of the air-cooled island cannot be effectively modeled.

[0033] This application combines machine learning with the big data of power plant operation, and based on the basic heat exchange mechanism of the air-cooled island, establishes a quantitative description model for the heat exchange capacity of the air-cooled island to achieve refined regulation and energy-saving and efficient operation of the air-cooled island.

[0034] Figure 1 It is a flowchart of a model determination method according to an embodiment of the present disclosure, as Figure 1 shown, and the method may include the following steps:

[0035] Step S102, obtain the heat exchange data and the first environmental data of the air-cooled island, where multiple heat exchangers are deployed on the air-cooled island.

[0036] In the technical solution provided in step S102 of the present disclosure, heat transfer data and first environmental data of the air-cooled island are obtained. For example, when quantitatively describing the heat transfer capacity of the air-cooled island, a heat transfer model of the air-cooled island can be established by combining machine learning and large power plant operation data. First, operation parameters related to heat transfer of the air-cooled island and environmental parameters during the operation of the air-cooled island need to be obtained.

[0037] In this embodiment, the heat transfer data may be data related to heat transfer of the air-cooled island. For example, the heat load of the air-cooled island, the fan speed of the air-cooled island, the ambient temperature, the ambient wind speed and direction, the condenser pressure of the air-cooled island, the condenser temperature of the air-cooled island, etc.

[0038] In this embodiment, the first environmental data may be environmental parameters during the operation of the air-cooled island. For example, the ambient temperature, radiation conditions, ambient wind speed, ambient wind direction, etc. There is no specific limitation here.

[0039] In this embodiment, the heat transfer data and the first environmental data can be obtained through the sensors already existing in the power plant itself, or can be obtained by additionally installing temperature sensors on the air-cooled island according to actual modeling requirements.

[0040] Step S104, based on the heat transfer data and the first environmental data, establish a first heat transfer model for each heat exchanger, and obtain a plurality of first heat transfer models, where each first heat transfer model is used to quantitatively describe the heat transfer capacity of the corresponding heat exchanger.

[0041] In the technical solution provided in step S104 of the present disclosure, based on the heat transfer data and the first environmental data, establish a first heat transfer model for each heat exchanger, and obtain a plurality of first heat transfer models. For example, after obtaining the operation parameters related to heat transfer of the air-cooled island and the environmental parameters during the operation of the air-cooled island, calculate the convective heat transfer coefficient of each heat exchanger of the air-cooled island, and then establish a first heat transfer model for each heat exchanger to obtain a plurality of first heat transfer models.

[0042] In this embodiment, each first heat transfer model is used to quantitatively describe the heat transfer capacity of the corresponding heat exchanger. For example, due to differences in design and manufacturing, installation location, operation and maintenance, etc., the heat transfer capacities of heat exchangers at different positions on the air-cooled island are often different. Especially, the influence of the installation location on the heat transfer capacity of the heat exchanger is more significant. Therefore, each first heat transfer model is used to quantitatively describe the heat transfer capacity of the corresponding heat exchanger.

[0043] In this embodiment, the first heat transfer model may be a single heat exchanger heat transfer model and / or a local heat transfer model.

[0044] In this embodiment, optionally, based on the heat transfer data and the first environmental data, determine the convective heat transfer coefficient of each heat exchanger, where the convective heat transfer coefficient is used to represent the heat transfer capacity of the corresponding heat exchanger.

[0045] In this embodiment, optionally, the heat exchange data and the first environmental data are determined as feature variables, and the convective heat transfer coefficient of each heat exchanger is determined as a label variable. Then, based on the feature variables and the label variable, the first heat exchange model of each heat exchanger is determined.

[0046] In this embodiment, optionally, a machine learning algorithm such as Gaussian Process Regression (GPR for short) is used to establish the first heat exchange model of each heat exchanger in the air-cooled island.

[0047] Step S106: Establish a target heat exchange model based on multiple first heat exchange models, where the target heat exchange model is used to quantitatively describe the heat exchange capacity of the air-cooled island.

[0048] In the technical solution provided in step S106 of the present disclosure above, a target heat exchange model is established based on multiple first heat exchange models. For example, according to the different heat exchange areas and heat exchange capacities of each heat exchanger, a quantitative description model of the overall heat exchange capacity of the air-cooled island is obtained through weighted average.

[0049] In this embodiment, optionally, multiple first heat exchange models are weighted and averaged to obtain a first target heat exchange model, where the first target heat exchange model is used to quantitatively describe the overall heat exchange capacity of the air-cooled island.

[0050] In this embodiment, optionally, the heat exchange area of each heat exchanger is obtained, and then multiple first heat exchange models are weighted and averaged based on the heat exchange area of each heat exchanger to obtain a first target heat exchange model.

[0051] In this embodiment, optionally, multiple first heat exchange models are arranged according to the positions of the corresponding multiple heat exchangers in space to obtain a quantitative description model of the overall heat exchange capacity of the air-cooled island.

[0052] Through the above steps S102 to S106, the heat exchange data and the first environmental data of the air-cooled island are obtained, where multiple heat exchangers are deployed in the air-cooled island; based on the heat exchange data and the first environmental data, the first heat exchange model of each heat exchanger is established to obtain multiple first heat exchange models, where each first heat exchange model is used to quantitatively describe the heat exchange capacity of the corresponding heat exchanger; a target heat exchange model is established based on multiple first heat exchange models, where the target heat exchange model is used to quantitatively describe the heat exchange capacity of the air-cooled island. That is to say, by establishing the heat exchange modeling of a single heat exchanger in the air-cooled island and conducting the heat exchange modeling based on a single heat exchanger to establish a quantitative description model of the heat exchange capacity of the air-cooled island, the refined control and energy-saving and efficient operation of the air-cooled island are realized, thereby solving the technical problem that the heat exchange capacity of the air-cooled island cannot be effectively modeled and achieving the technical effect of effectively modeling the heat exchange capacity of the air-cooled island.

[0053] The above method of this embodiment will be further introduced in detail below.

[0054] As an alternative implementation, in step S104, establishing the first heat transfer model for each heat exchanger based on the heat transfer data and the first environmental data includes: determining the convective heat transfer coefficient of each heat exchanger based on the heat transfer data and the first environmental data, where the convective heat transfer coefficient is used to represent the heat transfer capacity of the corresponding heat exchanger; establishing the first heat transfer model for each heat exchanger based on the convective heat transfer coefficient of each heat exchanger.

[0055] In this embodiment, based on the heat transfer data and the first environmental data, the convective heat transfer coefficient of each heat exchanger is determined, where the convective heat transfer coefficient refers to the heat transfer capacity between a fluid and a solid. For example, when the temperature difference between the surface of an object and the nearby air is 1 degree, the amount of heat exchanged with the nearby air through convection per unit area per unit time (1 second).

[0056] In this embodiment, based on the convective heat transfer coefficient of each heat exchanger, the first heat transfer model for each heat exchanger is established. For example, after calculating the convective heat transfer coefficient of each heat exchanger in the air-cooled island, the convective heat transfer coefficient of each heat exchanger is determined as a label variable, and the parameters related to heat transfer in the power plant operation data are determined as feature variables, and a machine learning algorithm is used to establish the first heat transfer model for each heat exchanger in the air-cooled island.

[0057] In this embodiment, the convective heat transfer coefficient of each heat exchanger can be determined as a label variable.

[0058] In this embodiment, optionally, the convective heat transfer coefficient of each heat exchanger is dimensionless processed.

[0059] In this embodiment, the first heat transfer model for each heat exchanger in the air-cooled island can be established by a Gaussian process regression algorithm.

[0060] As an alternative implementation, establishing the first heat transfer model for each heat exchanger based on the convective heat transfer coefficient of each heat exchanger includes: determining the heat transfer data and the first environmental data as feature variables, and determining the convective heat transfer coefficient of each heat exchanger as a label variable; determining the first heat transfer model for each heat exchanger based on the feature variables and the label variable.

[0061] In this embodiment, the feature variable can be an input variable, that is, the x variable in simple linear regression. A simple machine learning project may use a single feature variable, while a more complex machine learning project may use millions of feature variables.

[0062] In this embodiment, the label variable can be the thing to be predicted, that is, the y variable in simple linear regression. For example, in practical applications, the label variable can be the future price of wheat and the meaning of an audio clip or anything else.

[0063] In this embodiment, a first heat transfer model for each heat exchanger is determined based on the feature variables and the label variables. For example, data related to heat exchange with the air-cooled island and the environmental parameters during the operation of the air-cooled island are used as input variables, and the convective heat transfer coefficient of each heat exchanger is used as the label variable to be predicted. Through a machine learning algorithm such as the Gaussian process regression algorithm, a quantitative description model of the convective heat transfer coefficient of a single heat exchanger in the air-cooled island is established, so as to obtain the first heat transfer model of each heat exchanger.

[0064] As an alternative implementation, determining the first heat transfer model for each heat exchanger based on the feature variables and the label variables includes: performing dimensionless processing on the feature variables to obtain a first processing result, and performing dimensionless processing on the label variables to obtain a second processing result; training the first heat transfer model for each heat exchanger based on the first processing result and the second processing result.

[0065] In this embodiment, the feature variables are subjected to dimensionless processing to obtain a first processing result, and the label variables are subjected to dimensionless processing to obtain a second processing result. For example, the dimensionless coefficients related to heat transfer are derived from the fluid mechanics NS equation, the continuity equation, and the energy equation, mainly including the Grashof number (Gr), the Prandtl number (Pr), and the Reynolds number (Re).

[0066] In this embodiment, the first heat transfer model for each heat exchanger is trained based on the first processing result and the second processing result. For example, dimensionless processing refers to removing part or all of the units of an equation involving physical quantities through a suitable variable substitution to simplify experiments or calculations. After the feature variables and the label variables are subjected to dimensionless processing, the experiments can be simplified, and then a quantitative description model of the convective heat transfer coefficient of each heat exchanger in the air-cooled island can be trained through a machine learning algorithm.

[0067] As an alternative implementation, training the first heat transfer model for each heat exchanger based on the first processing result and the second processing result includes: performing Gaussian process regression on the first processing result and the second processing result to train the first heat transfer model for each heat exchanger.

[0068] In this embodiment, the Gaussian process can be one of the random processes, which is a set of a series of normally distributed random variables within an exponential set. Here, the exponent can be understood as the dimension. From the perspective of machine learning, the random variables on each exponent can be correspondingly understood as the features on each dimension. There is a correlation between the features of the samples in the Gaussian process, and this correlation can be reflected by the covariance matrix. For example, in some time series models, the time series output by each variable will show a certain degree of correlation before and after time.

[0069] In this embodiment, Gaussian process regression can be a non-parametric model that performs regression analysis on data using a Gaussian process prior.

[0070] As an alternative implementation, step S106 of establishing a target heat transfer model based on multiple first heat transfer models includes: performing weighted averaging on the multiple first heat transfer models to obtain a first target heat transfer model, where the first target heat transfer model is used to quantitatively describe the overall heat transfer capacity of the air-cooled island.

[0071] In this embodiment, the multiple first heat transfer models are weighted averaged to obtain a first target heat transfer model. For example, weighted averaging refers to an averaging method that takes weights into account. After obtaining the observed values of the heat transfer capacities of the multiple heat exchangers on the air-cooled island through the multiple first heat transfer models, the multiple observed values are weighted averaged to obtain a first target heat transfer model for quantitatively describing the overall heat transfer capacity of the air-cooled island.

[0072] As an alternative implementation, performing weighted averaging on the multiple first heat transfer models to obtain a first target heat transfer model, the method further includes: obtaining the heat transfer area of each heat exchanger; performing weighted averaging on the multiple first heat transfer models to obtain a first target heat transfer model, including: performing weighted averaging on the multiple first heat transfer models based on the heat transfer area of each heat exchanger to obtain a first target heat transfer model.

[0073] In this embodiment, due to differences in conditions such as design and manufacturing, installation location, and operation and maintenance, the heat transfer capacities of the heat exchangers at different positions on the air-cooled island are often different. Therefore, a first target heat transfer model can be obtained by performing weighted averaging on the multiple first heat transfer models.

[0074] As an alternative implementation, step S106 of establishing a target heat transfer model based on multiple first heat transfer models includes: arranging the multiple first heat transfer models according to the positions of the corresponding multiple heat exchangers in space to obtain a second target heat transfer model, where the second target heat transfer model is used to quantitatively describe the local heat transfer capacity of the air-cooled island.

[0075] In this embodiment, the multiple first heat transfer models are arranged according to the positions of the corresponding multiple heat exchangers in space to obtain a second target heat transfer model. For example, by modeling each heat exchanger, a spatial distribution map of the heat transfer capacity of the air-cooled island can be obtained, realizing refined control of the operation of the air-cooled island and achieving the minimum overall power consumption of the air-cooled island.

[0076] In this embodiment, the second target model can be a model array composed of multiple first heat transfer models, which is used to quantitatively describe the local heat transfer capacity of the air-cooled island.

[0077] In this embodiment, the air-cooled island can be a building-like structure. There are hundreds of heat exchangers on each air-cooled island, and each heat exchanger has a convective heat transfer coefficient. Thus, there are hundreds of heat transfer coefficients corresponding to the spatial positions of the hundreds of heat exchangers on the air-cooled island.

[0078] In the embodiment of the present disclosure, based on heat transfer data and first environmental data, the convective heat transfer coefficient of each heat exchanger is determined, where the convective heat transfer coefficient is used to represent the heat transfer capacity of the corresponding heat exchanger. Then, based on the convective heat transfer coefficient of each heat exchanger, a first heat transfer model of each heat exchanger is established; a weighted average is performed on multiple first heat transfer models to obtain a first target heat transfer model, where the first target heat transfer model is used to quantitatively describe the overall heat transfer capacity of the air-cooled island; the multiple first heat transfer models are arranged according to the spatial positions of the corresponding multiple heat exchangers to obtain a second target heat transfer model, where the second target heat transfer model is used to quantitatively describe the local heat transfer capacity of the air-cooled island. That is to say, by establishing a heat transfer model for a single heat exchanger in the air-cooled island and performing heat transfer modeling based on a single heat exchanger, a quantitative description model of the heat transfer capacity of the air-cooled island is established, realizing the refined control and energy-saving and efficient operation of the air-cooled island, thereby solving the technical problem of being unable to effectively model the heat transfer capacity of the air-cooled island and achieving the technical effect of effectively modeling the heat transfer capacity of the air-cooled island.

[0079] The data processing method of the embodiment of the present disclosure is introduced below.

[0080] Figure 2 is a flowchart of a data processing method according to an embodiment of the present disclosure. As Figure 2 shown, the method may include the following steps:

[0081] Step S202, obtain the first target back pressure of the air-cooled island and second environmental data.

[0082] In the technical solution provided in step S202 of the present disclosure, the first target back pressure of the air-cooled island and second environmental data are obtained. For example, when the back pressure value and environmental conditions are determined, the back pressure value set by the power plant operator and the environmental conditions during the operation of the air-cooled island are obtained.

[0083] In this embodiment, the second environmental data may be the environmental conditions during the operation of the air-cooled island, such as the heat load of the air-cooled island, environmental temperature, wind speed, and wind direction.

[0084] Step S204, process the first target back pressure and second environmental data based on the target heat transfer model to obtain the heat load of each heat exchanger among the multiple heat exchangers of the air-cooled island, where the target heat transfer model is obtained by the model determination method of the embodiment of the present disclosure.

[0085] In the technical solution provided in step S204 of the present disclosure above, the first target back pressure and the second environmental data are processed based on the target heat transfer model to obtain the heat load of each heat exchanger among multiple heat exchangers in the air-cooled island. For example, when the power plant operator sets the back pressure value, the heat load of the air-cooled island and conditions such as environmental temperature, wind speed, and wind direction are known, and correspondingly, a quantitative requirement for the heat transfer capacity of the air-cooled island is given. Then, according to the different heat transfer capacities of different heat exchangers in the air-cooled island, the heat load of each heat exchanger on the air-cooled island is accurately allocated.

[0086] Through steps S202 to S204 of the embodiments of the present disclosure above, the first target back pressure and the second environmental data of the air-cooled island are obtained, and then the first target back pressure and the second environmental data are processed based on the target heat transfer model to obtain the heat load of each heat exchanger among multiple heat exchangers in the air-cooled island. That is to say, when the power plant operator sets the back pressure value, the heat load of the air-cooled island and conditions such as environmental temperature, wind speed, and wind direction are known, and correspondingly, a quantitative requirement for the heat transfer capacity of the air-cooled island is given. According to the different heat transfer capacities of different heat exchangers in the air-cooled island, the heat load of each heat exchanger on the air-cooled island is accurately allocated, so that the overall heat transfer capacity of the air-cooled island meets the requirement of the operating back pressure, and at the same time, the overall power consumption of the air-cooled island is the lowest, realizing the refined control and energy-saving and efficient operation of the air-cooled island, thereby solving the technical problem that the heat transfer capacity of the air-cooled island cannot be effectively modeled, and achieving the technical effect of effectively modeling the heat transfer capacity of the air-cooled island.

[0087] Figure 3 It is a flowchart of another data processing method according to an embodiment of the present disclosure, as Figure 3 shown. This method may include the following steps:

[0088] Step S302, obtain the second target back pressure after the change of the first target back pressure of the air-cooled island.

[0089] In the technical solution provided in step S202 of the present disclosure above, the second target back pressure after the change of the first target back pressure of the air-cooled island is obtained. For example, when the target back pressure changes due to changes in operating parameters such as the steam turbine load, the target back pressure is converted into input parameters and input into the heat transfer model of the air-cooled island.

[0090] Step S304, process the second target back pressure based on the target heat transfer model to obtain the first adjustment data, where the first adjustment data is used to adjust the heat transfer capacity of the air-cooled island, and the target heat transfer model is obtained by the model determination method of the embodiments of the present disclosure.

[0091] In the technical solution provided in step S304 of the present disclosure, the second target back pressure is processed based on the target heat exchange model to obtain the first adjustment data. For example, when operating parameters such as the steam turbine load change, the target back pressure changes. The target back pressure is used as an input parameter and input into the heat exchange model of the air-cooled island, which can give a quantitative adjustment plan for the operation of the air-cooled island.

[0092] In this embodiment, the first adjustment data may be the rotational speeds of hundreds of fans corresponding to hundreds of heat exchangers on the air-cooled island (one heat exchanger corresponds to one fan, and each fan has one rotational speed).

[0093] It should be noted that in step S304 above, after obtaining the first adjustment data, it may be that the operator adjusts the air-cooled island fans according to the new rotational speeds to adjust the heat dissipation capacity of the air-cooled island, or it may be directly connected to the automatic control system to complete the automatic adjustment, which is not limited here.

[0094] In the embodiment of the present disclosure, through steps S302 to S304 above, the second target back pressure after the change of the first target back pressure of the air-cooled island is obtained, and then the second target back pressure is processed based on the target heat exchange model to obtain the first adjustment data. Among them, the first adjustment data is used to adjust the heat exchange capacity of the air-cooled island. The target heat exchange model is obtained by the model determination method of the embodiment of the present disclosure. That is to say, when operating parameters such as the steam turbine load change, the target back pressure changes. The target back pressure value is used as an input parameter and input into the heat exchange model established according to the model determination method of the embodiment of the present disclosure, which can give an adjustment plan for the operation of the air-cooled island, meet the real-time optimal operation requirements of the air-cooled island, realize the refined control and energy-saving and efficient operation of the air-cooled island, and thus solve the technical problem that the heat exchange capacity of the air-cooled island cannot be effectively modeled, and achieve the technical effect of effectively modeling the heat exchange capacity of the air-cooled island.

[0095] Figure 4 This is another data processing method according to the embodiment of the present disclosure, as Figure 4 shown, this method may include the following steps:

[0096] Step S402, obtain the third environmental data after the change of the air-cooled island from the second environmental data.

[0097] In the technical solution provided in step S402 of the present disclosure, the third environmental data after the change of the air-cooled island from the second environmental data is obtained. For example, when the environmental conditions change, the second environmental data such as environmental temperature, radiation conditions, environmental wind speed, environmental wind direction, etc. are converted into input parameters.

[0098] Step S404: Process the third environmental data based on the target heat transfer model to obtain second adjustment data, where the second adjustment data is used to adjust the heat transfer capacity of the air-cooled island, and the target heat transfer model is obtained by the model determination method of the embodiments of the present disclosure.

[0099] In the technical solution provided in step S404 of the present disclosure above, the third environmental data is processed based on the target heat transfer model to obtain second adjustment data. For example, when environmental conditions (such as environmental temperature, radiation conditions, environmental wind speed, environmental wind direction, etc.) change, it is necessary to adjust the heat transfer capacity of the air-cooled island (reflected in the fan speed) so that the back pressure is maintained at the target back pressure value. The environmental factors are used as input parameters and input into the established heat transfer model of the air-cooled island, thereby giving an adjustment plan for the operation of the air-cooled island to meet the real-time optimal operation requirements of the air-cooled island.

[0100] In the embodiments of the present disclosure, through the above steps S402 to S404, the third environmental data after the change of the second environmental data of the air-cooled island is obtained, and then the third environmental data is processed based on the target heat transfer model to obtain second adjustment data, where the second adjustment data is used to adjust the heat transfer capacity of the air-cooled island, and the target heat transfer model is obtained by the model determination method of the embodiments of the present disclosure. That is to say, when environmental conditions change, it is necessary to adjust the heat transfer capacity of the air-cooled island (reflected in the fan speed) so that the back pressure is maintained at the target back pressure value. The environmental factors are used as input parameters and input into the established heat transfer model of the air-cooled island, thereby giving an adjustment plan for the operation of the air-cooled island to meet the real-time optimal operation requirements of the air-cooled island, realizing the refined control and energy-saving and efficient operation of the air-cooled island, thus solving the technical problem of being unable to effectively model the heat transfer capacity of the air-cooled island and achieving the technical effect of effectively modeling the heat transfer capacity of the air-cooled island.

[0101] The following further introduces the model determination and data processing methods of the present disclosure in combination with preferred embodiments.

[0102] The present invention combines machine learning with the large data of power plant operation. Based on the basic heat transfer mechanism of the air-cooled island, a quantitative description model of the heat transfer capacity of the air-cooled island is established to realize the refined control and energy-saving and efficient operation of the air-cooled island. The present invention has the advantages of refinement, low cost, real-time online monitoring and control, easy reuse, etc. The operation optimization method and system of the power plant air-cooled island proposed by the present invention include two parts: the method for establishing the heat transfer model of the air-cooled island and the operation system of the air-cooled island based on the heat transfer model.

[0103] Figure 5 is a schematic diagram of a method for establishing a heat transfer model of an air-cooled island according to an embodiment of the present disclosure, as Figure 5As shown, based on the large amount of operation data of the power plant, mainly referring to the data related to the heat exchange of the air-cooled island (such as the heat load of the air-cooled island, the rotational speed of the air-cooled island fans, the ambient temperature, the ambient wind speed and direction, the condensing pressure of the air-cooled island, the condensing temperature of the air-cooled island, etc.), the convective heat transfer coefficient of each heat exchanger of the air-cooled island is calculated, and the data is dimensionless processed. Using the parameters related to heat exchange in the power plant operation data as characteristic variables and the calculated convective heat transfer coefficient of each heat exchanger as the label variable, machine learning algorithms such as Gaussian process regression are used to establish a quantitative description model of the convective heat transfer coefficient of a single heat exchanger in the air-cooled island. Modeling is carried out for each heat exchanger to obtain the spatial distribution map of the heat exchange capacity of the air-cooled island. Due to differences in design and manufacturing, installation location, operation and maintenance, etc., the heat exchange capacities of heat exchangers at different positions on the air-cooled island are often different, especially the influence of the installation location on the heat exchange capacity of the heat exchanger is more significant. On this basis, according to the different heat exchange areas and heat exchange capacities of each heat exchanger, a quantitative description model of the overall heat exchange capacity of the air-cooled island is obtained through weighted average, so as to obtain a refined heat exchange model of the air-cooled island. The large amount of operation data during the modeling process can be obtained through the sensors already available in the power plant itself, or can be obtained by additionally installing temperature sensors on the air-cooled island according to actual modeling requirements.

[0104] Figure 6 is a schematic diagram of an air-cooled island operation system based on a heat exchange model according to an embodiment of the present disclosure, as Figure 6 shown, the system can regulate the air-cooled island when the back pressure is fixed and the environmental conditions are fixed, the environmental conditions change, and the target back pressure changes.

[0105] Operation of the air-cooled island under fixed back pressure and fixed environmental conditions: The traditional operation method of the air-cooled island is that the power plant operator sets a target back pressure value, and then manually regulates the air-cooled island fans according to experience, so as to gradually approach the target back pressure. This process relies heavily on experience, has a long adjustment time, and poor effects. The heat exchange model of the air-cooled island established according to the model determination method of the embodiment of the present disclosure has been able to accurately describe the heat transfer coefficient of each heat exchanger of the air-cooled island, so the precise regulation of the operation of each heat exchanger fan of the air-cooled island can be realized. When the power plant operator sets the back pressure value, the heat load of the air-cooled island and environmental conditions such as ambient temperature, wind speed and direction are known, and correspondingly, a quantitative requirement for the heat exchange capacity of the air-cooled island is given. According to the different heat exchange capacities of different heat exchangers on the air-cooled island, the heat load is accurately distributed to each heat exchanger on the air-cooled island, so that the overall heat exchange capacity of the air-cooled island meets the requirements of the operating back pressure, and at the same time, the overall power consumption of the air-cooled island is the lowest.

[0106] Operation regulation of the air-cooled island when environmental conditions change: When environmental conditions (such as environmental temperature, radiation conditions, environmental wind speed, environmental wind direction, etc.) change, it is necessary to adjust the heat exchange capacity of the air-cooled island (reflected in the fan speed) so that the back pressure is maintained at the target back pressure value. The environmental factors are input as input parameters into the heat exchange model established according to the model determination method of the embodiments of the present disclosure, so as to give an adjustment plan for the operation of the air-cooled island and meet the real-time optimal operation requirements of the air-cooled island.

[0107] Operation regulation of the air-cooled island when the target back pressure changes due to changes in operating parameters such as steam turbine load: When operating parameters such as steam turbine load change, the target back pressure changes. Therefore, it is necessary to adjust the heat exchange capacity of the air-cooled island (reflected in the fan speed). The target back pressure value is input as an input parameter into the heat exchange model established according to the model determination method of the embodiments of the present disclosure, and an adjustment plan for the operation of the air-cooled island can be given to meet the real-time optimal operation requirements of the air-cooled island.

[0108] In the embodiments of the present disclosure, first, the physical quantities related to the heat exchange of the air-cooled island are dimensionless processed to make the model more general; in the heat exchange modeling of the air-cooled island, first, the heat exchange modeling of a single heat exchanger in the air-cooled island is established, and the spatial distribution of the heat exchange capacity of the air-cooled island is obtained; according to the heat exchange model of a single heat exchanger in the air-cooled island, through weighted calculation, a quantitative model of the overall heat exchange capacity of the air-cooled island is obtained; based on the spatial difference of the spatial heat exchange capacity of the air-cooled island, the heat load is distributed in the space of the air-cooled island to realize the refined regulation of the operation of the air-cooled island and achieve the minimum overall power consumption of the air-cooled island; according to the changes in operating parameters such as the thermal load of the steam turbine and environmental conditions, a real-time adjustment strategy for the operation of the air-cooled island is given to ensure real-time optimal operation. That is to say, by establishing the heat exchange modeling of a single heat exchanger in the air-cooled island and performing the heat exchange modeling based on a single heat exchanger to establish a quantitative description model of the heat exchange capacity of the air-cooled island, the refined regulation and energy-saving and efficient operation of the air-cooled island are realized, thereby solving the technical problem that the heat exchange capacity of the air-cooled island cannot be effectively modeled and achieving the technical effect of effectively modeling the heat exchange capacity of the air-cooled island.

[0109] The embodiments of the present disclosure also provide a device for executing Figure 1 the model determination device shown in the embodiments.

[0110] Figure 7 is a schematic diagram of a model determination device according to the embodiments of the present disclosure, as Figure 8 shown, the model determination device 70 may include: a first acquisition unit 71, a first establishment unit 72, and a second establishment unit 73.

[0111] The first acquisition unit 71 is configured to acquire heat exchange data of the air-cooled island and first environmental data, wherein multiple heat exchangers are deployed in the air-cooled island;

[0112] The first establishing unit 72 is configured to establish a first heat transfer model for each heat exchanger based on heat transfer data and first environmental data, obtaining a plurality of first heat transfer models, where each first heat transfer model is used to quantitatively describe the heat transfer capacity of the corresponding heat exchanger;

[0113] The second establishing unit 73 is configured to establish a target heat transfer model based on the plurality of first heat transfer models, where the target heat transfer model is used to quantitatively describe the heat transfer capacity of the air-cooled island.

[0114] Optionally, the first establishing unit 72 includes a first establishing module and a second establishing module, where the second establishing module may include: a first determining sub-module and a second determining sub-module, where the second determining sub-module may include: a first processing unit and a first training unit, where the first training unit may include: a first regression unit.

[0115] Among them, the first establishing module is configured to determine the convective heat transfer coefficient of each heat exchanger based on heat transfer data and first environmental data, where the convective heat transfer coefficient is used to represent the heat transfer capacity of the corresponding heat exchanger; the second establishing module is configured to establish a first heat transfer model for each heat exchanger based on the convective heat transfer coefficient of each heat exchanger; the first determining sub-module is configured to determine the heat transfer data and first environmental data as feature variables, and determine the convective heat transfer coefficient of each heat exchanger as a label variable; the second determining sub-module is configured to determine the first heat transfer model of each heat exchanger based on the feature variables and the label variable; the first processing unit is configured to perform dimensionless processing on the feature variables to obtain a first processing result, and perform dimensionless processing on the label variable to obtain a second processing result; the first training unit is configured to train a first heat transfer model for each heat exchanger based on the first processing result and the second processing result; the first regression unit is configured to perform Gaussian process regression on the first processing result and the second processing result to train a first heat transfer model for each heat exchanger.

[0116] Optionally, the second establishing unit includes: a weighting module and an arranging module, where the weighting module may include: a third obtaining unit and a weighting sub-module. Among them, the weighting module is configured to perform weighted averaging on the plurality of first heat transfer models to obtain a first target heat transfer model, where the first target heat transfer model is used to quantitatively describe the overall heat transfer capacity of the air-cooled island; the third obtaining unit is configured to obtain the heat transfer area of each heat exchanger; the weighting sub-module is configured to perform weighted averaging on the plurality of first heat transfer models based on the heat transfer area of each heat exchanger to obtain a first target heat transfer model; the arranging module is configured to arrange the plurality of first heat transfer models according to the positions of the corresponding plurality of heat exchangers in space to obtain a second target heat transfer model, where the second target heat transfer model is used to quantitatively describe the local heat transfer capacity of the air-cooled island.

[0117] In an embodiment of the present disclosure, a first acquisition unit 71 acquires heat exchange data and first environmental data of an air-cooled island, where multiple heat exchangers are deployed in the air-cooled island; a first establishment unit 72 establishes a first heat exchange model for each heat exchanger based on the heat exchange data and the first environmental data, obtaining multiple first heat exchange models, where each first heat exchange model is used to quantitatively describe the heat exchange capacity of the corresponding heat exchanger; a second establishment unit 73 establishes a target heat exchange model based on the multiple first heat exchange models, where the target heat exchange model is used to quantitatively describe the heat exchange capacity of the air-cooled island. That is to say, by establishing the heat exchange modeling of a single heat exchanger in the air-cooled island and performing the heat exchange modeling based on a single heat exchanger to establish a quantitative description model of the heat exchange capacity of the air-cooled island, the refined regulation and energy-saving and efficient operation of the air-cooled island are realized, thus solving the technical problem that the heat exchange capacity of the air-cooled island cannot be effectively modeled and achieving the technical effect of effectively modeling the heat exchange capacity of the air-cooled island.

[0118] The embodiment of the present disclosure also provides a data processing device for executing Figure 2 the data processing shown in the embodiment.

[0119] Figure 8 is a schematic diagram of a data processing device according to an embodiment of the present disclosure, as Figure 8 shown, the data processing device 80 may include: a second acquisition unit 81 and a first processing unit 82.

[0120] The second acquisition unit 81 is configured to acquire a first target back pressure and second environmental data of the air-cooled island;

[0121] The first processing unit 82 is configured to process the first target back pressure and the second environmental data based on the target heat exchange model to obtain the heat load of each heat exchanger, where the target heat exchange model is obtained by the model determination method of the embodiment of the present disclosure.

[0122] In the embodiment of the present disclosure, the second acquisition unit 81 acquires the first target back pressure and the second environmental data of the air-cooled island; the first processing unit 82 processes the first target back pressure and the second environmental data based on the target heat exchange model to obtain the heat load of each heat exchanger, where the target heat exchange model is obtained by the model determination method of the embodiment of the present disclosure. That is to say, when the power plant operator sets the back pressure value, the heat load of the air-cooled island and conditions such as environmental temperature, wind speed, and wind direction are known, and correspondingly, a quantitative requirement for the heat exchange capacity of the air-cooled island is given. According to the different heat exchange capacities of different heat exchangers on the air-cooled island, the heat load of each heat exchanger on the air-cooled island is accurately allocated, so that the overall heat exchange capacity of the air-cooled island meets the requirement of the operating back pressure, and at the same time, the overall power consumption of the air-cooled island is minimized, realizing the refined regulation and energy-saving and efficient operation of the air-cooled island, thus solving the technical problem that the heat exchange capacity of the air-cooled island cannot be effectively modeled and achieving the technical effect of effectively modeling the heat exchange capacity of the air-cooled island.

[0123] The embodiments of the present disclosure also provide a data processing device for executing Figure 3 the data processing device shown in the embodiments.

[0124] Figure 9 FIG. is a schematic diagram of another data processing device according to an embodiment of the present disclosure, as Figure 9 shown. The data processing device 90 may include: a third acquisition unit 91 and a second processing unit 92.

[0125] The third acquisition unit 91 is configured to acquire a second target back pressure after the first target back pressure of the air-cooled island changes;

[0126] The second processing unit 92 is configured to process the second target back pressure based on a target heat transfer model to obtain first adjustment data, where the first adjustment data is used to adjust the heat transfer capacity of the air-cooled island, and the target heat transfer model is obtained by the model determination method of the embodiments of the present disclosure.

[0127] In the embodiments of the present disclosure, the third acquisition unit 91 acquires the second target back pressure after the first target back pressure of the air-cooled island changes; the second processing unit 92 processes the second target back pressure based on the target heat transfer model to obtain first adjustment data, where the first adjustment data is used to adjust the heat transfer capacity of the air-cooled island, and the target heat transfer model is obtained by the model determination method of the embodiments of the present disclosure. That is to say, when operating parameters such as the steam turbine load change, the target back pressure changes. By inputting the target back pressure value as an input parameter into the heat transfer model established according to the model determination method of the embodiments of the present disclosure, an adjustment scheme for the operation of the air-cooled island can be given, meeting the real-time optimal operation requirements of the air-cooled island, realizing the refined control and energy-saving and efficient operation of the air-cooled island, thereby solving the technical problem that the heat transfer capacity of the air-cooled island cannot be effectively modeled, and achieving the technical effect of effectively modeling the heat transfer capacity of the air-cooled island.

[0128] The embodiments of the present disclosure also provide a data processing device for executing Figure 4 the data processing device shown in the embodiments.

[0129] Figure 10 FIG. is a schematic diagram of another data processing device according to an embodiment of the present disclosure, as Figure 10 shown. The data processing device 100 may include: a fourth acquisition unit 101 and a third processing unit 102.

[0130] The fourth acquisition unit 101 is configured to acquire third environmental data after the second environmental data of the air-cooled island changes;

[0131] A third processing unit 102, configured to process the third environmental data based on a target heat exchange model to obtain second adjustment data, where the second adjustment data is used to adjust the heat exchange capacity of the air-cooled island, and the target heat exchange model is obtained by the model determination method of the embodiments of the present disclosure.

[0132] In the embodiments of the present disclosure, a fourth acquisition unit 101 is used to acquire the third environmental data of the air-cooled island after the change of the second environmental data; the third processing unit 102 processes the third environmental data based on the target heat exchange model to obtain second adjustment data, where the second adjustment data is used to adjust the heat exchange capacity of the air-cooled island, and the target heat exchange model is obtained by the model determination method of the embodiments of the present disclosure. That is to say, when the environmental conditions change, it is necessary to adjust the heat exchange capacity of the air-cooled island (reflected in the fan speed) so that the back pressure is maintained at the target back pressure value. The environmental factors are used as input parameters and input into the established heat exchange model of the air-cooled island, so as to give an adjustment plan for the operation of the air-cooled island, meet the real-time optimal operation requirements of the air-cooled island, realize the refined control and energy-saving and efficient operation of the air-cooled island, thereby solving the technical problem that the heat exchange capacity of the air-cooled island cannot be effectively modeled, and achieving the technical effect of effectively modeling the heat exchange capacity of the air-cooled island.

[0133] In the embodiments of the present disclosure, in the technical solutions of the present disclosure, the acquisition, storage, and application of the user's personal information involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0134] According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0135] The embodiments of the present disclosure provide an electronic device, which may include: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the model determination and data processing methods of the embodiments of the present disclosure.

[0136] Optionally, the above-mentioned electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the above-mentioned processor, and the input / output device is connected to the above-mentioned processor.

[0137] Optionally, in this embodiment, the above-mentioned non-volatile storage medium may be configured to store a computer program for performing the following steps:

[0138] Step S102, acquiring heat exchange data and first environmental data of the air-cooled island, where multiple heat exchangers are deployed on the air-cooled island;

[0139] Step S104: Based on the heat exchange data and the first environmental data, establish a first heat exchange model for each heat exchanger, obtaining a plurality of first heat exchange models, where each first heat exchange model is used to quantitatively describe the heat exchange capacity of the corresponding heat exchanger.

[0140] Step S106: Based on the plurality of first heat exchange models, establish a target heat exchange model, where the target heat exchange model is used to quantitatively describe the heat exchange capacity of the air-cooled island.

[0141] Step S202: Obtain the first target back pressure and the second environmental data of the air-cooled island.

[0142] Step S204: Based on the target heat exchange model, process the first target back pressure and the second environmental data to obtain the heat load of each heat exchanger in the multiple heat exchangers of the air-cooled island, where the target heat exchange model is obtained by the model determination method of the present disclosure embodiment.

[0143] Step S302: Obtain the second target back pressure after the change of the first target back pressure of the air-cooled island.

[0144] Step S304: Based on the target heat exchange model, process the second target back pressure to obtain a first adjustment data, where the first adjustment data is used to adjust the heat exchange capacity of the air-cooled island, and the target heat exchange model is obtained by the model determination method of the present disclosure embodiment.

[0145] Step S402: Obtain the third environmental data after the change of the second environmental data of the air-cooled island.

[0146] Step S404: Based on the target heat exchange model, process the third environmental data to obtain a second adjustment data, where the second adjustment data is used to adjust the heat exchange capacity of the air-cooled island, and the target heat exchange model is obtained by the model determination method of the present disclosure embodiment.

[0147] Optionally, in this embodiment, the above non-transitory computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the above. More specific examples of the readable storage medium would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0148] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, including a computer program, which when executed by a processor, implements the following steps:

[0149] Step S102: Obtain the heat exchange data and the first environmental data of the air-cooled island, where multiple heat exchangers are deployed in the air-cooled island.

[0150] Step S104: Based on the heat exchange data and the first environmental data, establish a first heat exchange model for each heat exchanger to obtain multiple first heat exchange models, where each first heat exchange model is used to quantitatively describe the heat exchange capacity of the corresponding heat exchanger.

[0151] Step S106: Based on the multiple first heat exchange models, establish a target heat exchange model, where the target heat exchange model is used to quantitatively describe the heat exchange capacity of the air-cooled island.

[0152] Step S202: Obtain the first target back pressure and the second environmental data of the air-cooled island.

[0153] Step S204: Based on the target heat exchange model, process the first target back pressure and the second environmental data to obtain the heat load of each heat exchanger among the multiple heat exchangers of the air-cooled island, where the target heat exchange model is obtained by the model determination method of the embodiments of the present disclosure.

[0154] Step S302: Obtain the second target back pressure after the change of the first target back pressure of the air-cooled island.

[0155] Step S304: Based on the target heat exchange model, process the second target back pressure to obtain the first adjustment data, where the first adjustment data is used to adjust the heat exchange capacity of the air-cooled island, and the target heat exchange model is obtained by the model determination method of the embodiments of the present disclosure.

[0156] Step S402: Obtain the third environmental data after the change of the second environmental data of the air-cooled island.

[0157] Step S404: Based on the target heat exchange model, process the third environmental data to obtain the second adjustment data, where the second adjustment data is used to adjust the heat exchange capacity of the air-cooled island, and the target heat exchange model is obtained by the model determination method of the embodiments of the present disclosure.

[0158] Figure 11 It is a schematic block diagram of an electronic device according to an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described herein and / or claimed.

[0159] Figure 11FIG. shows a schematic block diagram of an exemplary electronic device 1100 that can be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0160] As Figure 11 shown, the device 1100 includes a computing unit 1101 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the device 1100 can also be stored. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0161] Multiple components in the device 1100 are connected to the I / O interface 1105, including: an input unit 1106, such as a keyboard, a mouse, etc.; an output unit 1107, such as various types of displays, speakers, etc.; a storage unit 1108, such as a magnetic disk, an optical disk, etc.; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1109 allows the device 1100 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0162] The computing unit 1101 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1101 executes the various methods and processes described above, such as the method of establishing a target heat transfer model based on multiple first heat transfer models. For example, in some embodiments, the method of establishing a target heat transfer model based on multiple first heat transfer models can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1108. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 1100 via the ROM 1102 and / or the communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the method of establishing a target heat transfer model based on multiple first heat transfer models described above can be executed. Alternatively, in other embodiments, the computing unit 1101 can be configured to execute the method of establishing a target heat transfer model based on multiple first heat transfer models in any other suitable way (e.g., by means of firmware).

[0163] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-a-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0164] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general purpose computer, a special purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0165] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0166] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0167] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0168] A computer system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, or a server of a distributed system, or a server incorporating a blockchain.

[0169] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this is not limited herein.

[0170] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A method for determining a model, comprising: obtaining heat transfer data and first environmental data of an air-cooled island, wherein a plurality of heat exchangers are deployed in the air-cooled island; determining the convective heat transfer coefficient of each heat exchanger based on the heat transfer data and the first environmental data; determining the heat transfer data and the first environmental data as feature variables, and determining the convective heat transfer coefficient of each heat exchanger as a label variable; performing dimensionless processing on the feature variables to obtain a first processing result, and performing dimensionless processing on the label variables to obtain a second processing result; performing Gaussian process regression on the first processing result and the second processing result to train a first heat transfer model for each heat exchanger, obtaining a plurality of the first heat transfer models, wherein each first heat transfer model is used to quantitatively describe the heat transfer capacity of the corresponding heat exchanger; establishing a target heat transfer model based on the plurality of first heat transfer models, wherein the target heat transfer model is used to quantitatively describe the heat transfer capacity of the air-cooled island, including: arranging the plurality of first heat transfer models according to the spatial positions of the corresponding plurality of heat exchangers to obtain a second target heat transfer model, wherein the second target heat transfer model is used to quantitatively describe the local heat transfer capacity of the air-cooled island.

2. According to the method of claim 1, establishing a target heat transfer model based on the plurality of first heat transfer models further comprises: performing weighted averaging on the plurality of first heat transfer models to obtain a first target heat transfer model, wherein the first target heat transfer model is used to quantitatively describe the overall heat transfer capacity of the air-cooled island.

3. According to the method of claim 2, the method further comprises: obtaining the heat transfer area of each heat exchanger; performing weighted averaging on the plurality of first heat transfer models to obtain a first target heat transfer model, including: performing weighted averaging on the plurality of first heat transfer models based on the heat transfer area of each heat exchanger to obtain the first target heat transfer model.

4. A data processing method, comprising: obtaining a first target back pressure and second environmental data of an air-cooled island; processing the first target back pressure and the second environmental data based on the target heat transfer model to obtain the heat load of each heat exchanger among the plurality of heat exchangers of the air-cooled island, wherein the target heat transfer model is obtained by the model determination method according to any one of claims 1 to 3.

5. A data processing method, comprising: obtaining a second target back pressure after a change in the first target back pressure of the air-cooled island; processing the second target back pressure based on the target heat transfer model to obtain first adjustment data, wherein the first adjustment data is used to adjust the heat transfer capacity of the air-cooled island, and the target heat transfer model is obtained by the model determination method according to any one of claims 1 to 3.

6. A data processing method, comprising: obtaining third environmental data after a change in the second environmental data of the air-cooled island; Process the third environmental data based on the target heat transfer model to obtain second adjustment data, where the second adjustment data is used to adjust the heat transfer capacity of the air-cooled island, and the target heat transfer model is obtained by the model determination method described in any one of claims 1 to 3.

7. A model determination device comprising: A first acquisition unit configured to acquire heat transfer data and first environmental data of an air-cooled island, where a plurality of heat exchangers are deployed on the air-cooled island; A first establishment unit configured to establish a first heat transfer model for each of the heat exchangers based on the heat transfer data and the first environmental data, obtaining a plurality of the first heat transfer models, where each of the first heat transfer models is used to quantitatively describe the heat transfer capacity of the corresponding heat exchanger; A second establishment unit configured to establish a target heat transfer model based on the plurality of first heat transfer models, where the target heat transfer model is used to quantitatively describe the heat transfer capacity of the air-cooled island; wherein the first establishment unit includes: a first establishment module configured to determine the convective heat transfer coefficient of each of the heat exchangers based on the heat transfer data and the first environmental data, where the convective heat transfer coefficient is used to represent the heat transfer capacity of the corresponding heat exchanger; a second establishment module including: a first determination sub-module configured to determine the heat transfer data and the first environmental data as feature variables, and determine the convective heat transfer coefficient of each of the heat exchangers as a label variable; a second determination sub-module configured to determine the first heat transfer model of each of the heat exchangers based on the feature variables and the label variable through the following steps: perform dimensionless processing on the feature variables to obtain a first processing result, and perform dimensionless processing on the label variables to obtain a second processing result; perform Gaussian process regression on the first processing result and the second processing result to train and obtain the first heat transfer model of each of the heat exchangers; The second establishment unit includes: an arrangement module configured to arrange the plurality of first heat transfer models according to the spatial positions of the corresponding plurality of heat exchangers to obtain a second target heat transfer model, where the second target heat transfer model is used to quantitatively describe the local heat transfer capacity of the air-cooled island.

8. The device according to claim 7, the second establishment unit further comprises: A weighting module configured to perform weighted averaging on the plurality of first heat transfer models to obtain a first target heat transfer model, where the first target heat transfer model is used to quantitatively describe the overall heat transfer capacity of the air-cooled island.

9. The device according to claim 8, the device further comprises: A third acquisition unit configured to acquire the heat transfer area of each of the heat exchangers; The weighting module includes: a weighting sub-module configured to perform weighted averaging on the plurality of first heat transfer models based on the heat transfer area of each of the heat exchangers to obtain the first target heat transfer model.

10. A data processing device comprising: A second acquisition unit configured to acquire the first target back pressure and second environmental data of the air-cooled island; The first processing unit is configured to process the first target back pressure and the second environmental data based on a target heat exchange model to obtain the heat load of each heat exchanger, where the target heat exchange model is obtained by the model determination method described in any one of claims 1 to 3.

11. A data processing device, comprising: A third acquisition unit configured to acquire a second target back pressure after a change in the first target back pressure of the air-cooled island; A second processing unit configured to process the second target back pressure based on a target heat exchange model to obtain first adjustment data, where the first adjustment data is used to adjust the heat exchange capacity of the air-cooled island, and the target heat exchange model is obtained by the model determination method described in any one of claims 1 to 3.

12. A data processing device, comprising: A fourth acquisition unit configured to acquire third environmental data after a change in the second environmental data of the air-cooled island; A third processing unit configured to process the third environmental data based on a target heat exchange model to obtain second adjustment data, where the second adjustment data is used to adjust the heat exchange capacity of the air-cooled island, and the target heat exchange model is obtained by the model determination method described in any one of claims 1 to 3.

13. An electronic device, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method described in any one of claims 1-6.

15. A computer program product comprising a computer program, where the computer program, when executed by a processor, implements the method described in any one of claims 1-6.

Images