A system optimization method, device, equipment and computer-readable storage medium

Abstract

The present application discloses a system optimization method, apparatus, device and computer-readable storage medium, comprising: obtaining environmental parameters, a trained spatial characteristic prediction model and a system performance prediction model; using the trained spatial characteristic prediction model and the environmental parameters to predict the spatial characteristics to obtain a predicted load and a predicted dew point temperature; using the system performance prediction model, the predicted load and the environmental parameters to predict the system performance to obtain a predicted system energy consumption; optimizing the current system parameters based on the predicted dew point temperature and the predicted system energy consumption to obtain target system parameters; and controlling the system to operate based on the target system parameters.

Description

Technical Field

[0001] The present application relates to the field of control technology, and is related to but not limited to a system optimization method, apparatus, device and computer-readable storage medium. Background Art

[0002] Radiant air conditioning systems originated in the 1950s. After decades of research and development, they have gradually been promoted and applied worldwide. Conventional fan coil units regulate indoor temperature through air convection, making them difficult to adapt to changes in indoor heat and humidity ratios and creating a strong draft. Radiant air conditioning systems, on the other hand, primarily provide cooling through radiation, resulting in uniform indoor temperature distribution, no temperature dead zones, and no draft. They are internationally recognized as the air conditioning terminal system that provides the highest level of indoor comfort.

[0003] To improve indoor air quality, radiant systems are often combined with fresh air units. Radiant systems combined with independent fresh air systems are independent temperature and humidity control systems. The radiant system only bears part or all of the indoor sensible heat load, while the fresh air unit bears the entire indoor latent heat load, the remaining sensible heat load, and the fresh air load. Although radiant systems combined with independent fresh air systems are currently designed and implemented in many regions, the following problems exist in their application, making it difficult for radiant systems to fully realize their advantages:

[0004] Problem 1: The radiant air conditioning system and the fresh air system are completely independent systems with weak interaction and poor matching, resulting in the risk of condensation in the radiant air conditioning system.

[0005] Question 2: Both the radiant air conditioning system and the fresh air unit may operate in a low energy efficiency zone, resulting in high energy consumption. Summary of the Invention

[0006] In view of this, embodiments of the present application provide a system optimization method, apparatus, device, and computer-readable storage medium.

[0007] The technical solution of the embodiment of the present application is implemented as follows:

[0008] The present invention provides a system optimization method, which includes:

[0009] Obtain environmental parameters, trained spatial characteristic prediction models, and system performance prediction models;

[0010] Predicting spatial characteristics using the trained spatial characteristic prediction model and the environmental parameters to obtain predicted load and predicted dew point temperature;

[0011] Predicting system performance using the system performance prediction model, the predicted load, and the environmental parameters to obtain predicted system energy consumption;

[0012] Optimizing current system parameters based on the predicted dew point temperature and the predicted system energy consumption to obtain target system parameters;

[0013] The control system operates based on the target system parameters.

[0014] The present invention provides a system optimization device, which includes:

[0015] An acquisition module is used to obtain environmental parameters, trained spatial characteristic prediction models, and system performance prediction models;

[0016] A first prediction module is used to predict the spatial characteristics by using the trained spatial characteristics prediction model and the environmental parameters to obtain a predicted load and a predicted dew point temperature;

[0017] A second prediction module is used to predict the system performance using the system performance prediction model, the predicted load and the environmental parameters to obtain predicted system energy consumption;

[0018] an optimization module, configured to optimize current system parameters based on the predicted dew point temperature and the predicted system energy consumption to obtain target system parameters;

[0019] A control module is used to control the system to operate based on the target system parameters.

[0020] The present invention provides a system optimization device, comprising:

[0021] processor; and

[0022] a memory for storing a computer program executable on the processor;

[0023] Wherein, the computer program implements the above-mentioned system optimization method when executed by the processor.

[0024] An embodiment of the present application provides a computer-readable storage medium, wherein the computer-executable instructions are stored in the computer-executable storage medium, and the computer-executable instructions are configured to execute the above-mentioned system optimization method.

[0025] The embodiments of the present application provide a system optimization method, apparatus, equipment and computer-readable storage medium, the system optimization method comprising: first obtaining environmental parameters, a trained spatial characteristic prediction model and a system performance prediction model; then, inputting the environmental parameters into the trained spatial characteristic prediction model, so as to predict the spatial characteristics using the trained spatial characteristic prediction model, and obtain a predicted load and a predicted dew point temperature; further inputting the predicted load and environmental parameters into the system performance prediction model, so as to predict the system performance using the system performance prediction model, and obtain a predicted system energy consumption; then, optimizing the current system parameters based on the predicted dew point temperature and the predicted system energy consumption, so as to optimize the predicted system energy consumption under the premise that the surface temperature of the system radiation panel is higher than the predicted dew point temperature, and predict the target parameters of the system under the optimal predicted system energy consumption; finally, the control system operates based on the target system parameters, so that the entire system operates in a high energy efficiency zone, reduces the overall energy consumption, and avoids the risk of condensation. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In the drawings, which are not necessarily drawn to scale, like reference numerals may describe similar components throughout the different views.The drawings illustrate generally, by way of example and not limitation, various embodiments discussed herein.

[0027] Figure 1 A schematic diagram of an implementation flow of the system optimization method provided in an embodiment of the present application;

[0028] Figure 2 A schematic diagram of an implementation flow for predicting system energy consumption provided in an embodiment of the present application;

[0029] Figure 3 A schematic diagram of an implementation flow for predicting radiation system energy consumption provided in an embodiment of the present application;

[0030] Figure 4 A schematic diagram of an implementation flow of constructing a radiation system prediction sub-model and a fresh air system prediction sub-model provided in an embodiment of the present application;

[0031] Figure 5 A schematic diagram of an implementation flow of obtaining a trained spatial characteristic prediction model through training provided in an embodiment of the present application;

[0032] Figure 6 A block diagram of the system optimization process provided in the embodiment of the present application;

[0033] Figure 7 A schematic diagram of a performance prediction model block diagram of a radiant air conditioning system provided in an embodiment of the present application;

[0034] Figure 8 A schematic diagram of a performance prediction model block diagram of a fresh air system provided in an embodiment of the present application;

[0035] Figure 9 A schematic diagram of the structure of the system optimization device provided in an embodiment of the present application;

[0036] Figure 10 A schematic diagram of the composition structure of the system optimization device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0038] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0039] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0041] To address the problems in the related art, embodiments of the present application provide a system optimization method. The method provided by the embodiments of the present application can be implemented by a computer program. When the computer program is executed, the system optimization method provided by the embodiments of the present application is completed. In some embodiments, the computer program can be executed by a processor in a system optimization device. Figure 1 An implementation process of the system optimization method provided in the embodiment of the present application is as follows: Figure 1 As shown, the system optimization method includes:

[0042] Step S101: Acquire environmental parameters, a trained spatial characteristic prediction model, and a system performance prediction model.

[0043] Here, environmental parameters refer to the parameters of the environment in which the system is located, wherein the environmental parameters may include user parameters, external environmental parameters, indoor environmental parameters and enclosure structure parameters. User parameters refer to the number of users, the type and number of devices, etc.; external environmental parameters refer to external temperature, external humidity, external relative humidity, etc.; indoor environmental parameters refer to indoor temperature, indoor humidity, indoor relative humidity, etc.; enclosure structure refers to building structure, wall thickness, wall insulation performance, etc.

[0044] In the embodiment of the present application, the trained spatial characteristic prediction model is used to predict the spatial characteristics at the next moment, such as the load, temperature, etc. The system performance prediction model is used to predict the system performance at the next moment, such as the system energy consumption at the next moment.

[0045] In some embodiments, the trained spatial characteristic prediction model may be a prediction model based on an artificial intelligence algorithm. Similarly, the system performance prediction model may also be a prediction model based on an artificial intelligence algorithm.

[0046] Step S102 : predicting the spatial characteristics using the trained spatial characteristics prediction model and environmental parameters to obtain predicted load and predicted dew point temperature.

[0047] Here, the environmental parameters can be input into the trained spatial characteristic prediction model to predict the spatial characteristics using the trained spatial characteristic prediction model, that is, to predict the load and dew point temperature, thereby obtaining the predicted load and predicted dew point temperature.

[0048] In actual implementation, the trained spatial characteristic prediction model can include a load prediction submodel and a dew point temperature prediction submodel. The load prediction submodel is used to predict the load at the next moment, and the dew point temperature prediction submodel is used to predict the dew point temperature at the next moment. In other words, the load prediction submodel can be used to predict the load at the next moment (equivalent to predicted load), and the temperature prediction submodel can be used to predict the dew point temperature at the next moment (equivalent to predicted dew point temperature).

[0049] Step S103 , using the system performance prediction model, the predicted load and the environmental parameters, the system performance is predicted to obtain the predicted system energy consumption.

[0050] Here, the predicted load and environmental parameters can be input into the system performance prediction model to predict the system performance using the system performance prediction model, that is, to predict the energy consumption of the system, thereby obtaining the predicted system energy consumption.

[0051] In actual implementation, the system can be composed of a radiation system and a fresh air system. Based on this, the system performance prediction model can include a radiation system prediction sub-model and a fresh air system prediction sub-model, wherein the radiation system prediction sub-model is used to predict the energy consumption of the radiation system at the next moment, and the fresh air system prediction sub-model is used to predict the energy consumption of the fresh air system at the next moment.

[0052] In some embodiments, environmental parameters can be input into the radiation system prediction sub-model to predict the energy consumption of the radiation system at the next moment, thereby obtaining the predicted radiation system energy consumption. The predicted radiation system energy consumption and preload can be input into the fresh air system prediction sub-model to predict the energy consumption of the fresh air system at the next moment, thereby obtaining the predicted fresh air system energy consumption.

[0053] Step S104 , optimizing the current system parameters based on the predicted dew point temperature and the predicted system energy consumption to obtain target system parameters.

[0054] Here, to ensure that the system is in a safe and energy-saving operating state, when optimizing the current system parameters, the predicted system energy consumption is optimized and solved to obtain the target system parameters, under the premise that the surface temperature of the system radiation panel is higher than the predicted dew point temperature, that is, under the premise of ensuring system safety.

[0055] In some embodiments, constraints between system parameters and system energy consumption can be constructed, and the system energy consumption can be optimized to obtain target system parameters corresponding to the optimal system energy consumption, which is equivalent to obtaining target system parameters corresponding to the minimum system energy consumption.

[0056] Step S105: The control system operates based on the target system parameters.

[0057] Here, the current system parameters can be adjusted to the target system parameters to control the system to operate based on the target system parameters. In this way, on the one hand, the surface temperature of the system's radiation panel is ensured to be higher than the predicted dew point temperature, that is, the system can be ensured to operate safely, and on the other hand, the system energy consumption is minimized.

[0058] In the embodiment of the present application, since the target system parameters are obtained by optimizing the system energy consumption, the optimal system energy consumption, that is, the minimum system energy consumption, can be achieved by operating the control system according to the target system parameters.

[0059] An embodiment of the present application provides a system optimization method, which includes: first obtaining environmental parameters, a trained spatial characteristic prediction model and a system performance prediction model; then, inputting the environmental parameters into the trained spatial characteristic prediction model, so as to use the trained spatial characteristic prediction model to predict the spatial characteristics and obtain a predicted load and a predicted dew point temperature; further inputting the predicted load and environmental parameters into the system performance prediction model, so as to use the system performance prediction model to predict the system performance and obtain a predicted system energy consumption; then, optimizing the current system parameters based on the predicted dew point temperature and the predicted system energy consumption, so as to optimize the predicted system energy consumption under the premise that the surface temperature of the system radiation panel is higher than the predicted dew point temperature, and predict the target parameters of the system under the optimal predicted system energy consumption; finally, the control system operates based on the target system parameters, so that the entire system operates in a high energy efficiency zone, reduces the overall energy consumption, and avoids the risk of condensation.

[0060] In some embodiments, the system includes a radiation system and a fresh air system. Accordingly, the system performance prediction model includes a radiation system prediction sub-model and a fresh air system prediction sub-model. Based on this, Figure 2 As shown, the above step S103 "using the system performance prediction model, the predicted load and the environmental parameters to predict the system performance and obtain the predicted system energy consumption" can be implemented by the following steps S1031 to S1033:

[0061] Step S1031 : performing prediction processing on the radiation system using the radiation system prediction sub-model and environmental parameters to obtain predicted radiation system energy consumption.

[0062] In actual implementation, Figure 3 As shown, step S1031 can be implemented by following steps S311 to S314:

[0063] Step S311 : determining the surface temperature of the radiation panel of the radiation system based on the environmental parameters.

[0064] Here, the surface temperature of the radiation panel and the air temperature (i.e., the indoor temperature) satisfy a first coupling relationship. Therefore, the surface temperature of the radiation panel can be determined based on the air temperature and the first coupling relationship. The air temperature is an environmental parameter, and thus, the surface temperature of the radiation panel can be determined based on the environmental parameter and the first coupling relationship.

[0065] Step S312: determining the total heat flux density of the radiation system based on the surface temperature of the radiation panel.

[0066] Here, the total heat flux density of the radiation system and the surface temperature of the radiation plate satisfy the second coupling relationship. Therefore, the total heat flux density of the radiation system can be determined based on the surface temperature of the radiation plate and the second coupling relationship.

[0067] Step S313: determining the energy generated by the radiation system based on the total heat flux density.

[0068] Here, the energy generated by the radiation system and the total heat flux density satisfy the third coupling relationship. Therefore, the energy generated by the radiation system can be determined by the total heat flux density and the third coupling relationship.

[0069] Step S314: Determine the predicted energy consumption of the radiation system based on the first performance parameter and the radiation system preparation energy.

[0070] Here, the first performance parameter is a performance parameter corresponding to the radiation system, and the first performance parameter is used to characterize the heat exchange capacity of the radiation system.

[0071] In an actual radiation system, the predicted radiation system energy consumption satisfies the fourth coupling relationship with the radiation system preparation energy and the first performance parameter. Therefore, the predicted radiation system energy consumption can be determined based on the radiation system preparation energy, the first performance parameter, and the fourth coupling relationship. For example, the quotient of the radiation system preparation energy and the first performance parameter can be determined as the predicted radiation system energy consumption.

[0072] Step S1032 , using the fresh air system prediction sub-model, the predicted radiation system energy consumption and the predicted load to perform prediction processing on the fresh air system to obtain the predicted fresh air system energy consumption.

[0073] In actual implementation, step S1032 can be implemented by following steps S321 to S322:

[0074] Step S321: Determine the energy prepared by the fresh air system based on the predicted radiation system energy consumption and the predicted load.

[0075] Here, the difference between the predicted load and the predicted radiation system can be used to determine the fresh air system energy production. In actual implementation, the difference between the predicted load and the predicted radiation system can be first determined, and then the difference can be used to determine the fresh air system energy production. The fresh air system energy production refers to the energy required to be produced by the fresh air system, which can be either heating or cooling capacity.

[0076] Step S322: Determine and predict the energy consumption of the fresh air system based on the prepared energy of the fresh air system and the second performance parameter.

[0077] Here, the second performance parameter is a performance parameter corresponding to the fresh air system, and the second performance parameter is used to characterize the heat exchange capacity of the fresh air system.

[0078] In the embodiment of the present application, the predicted fresh air system energy consumption, the fresh air system generated energy, and the second performance parameter satisfy the fifth coupling relationship. Therefore, the predicted fresh air system energy consumption can be determined based on the fresh air system generated energy, the second performance parameter, and the fifth coupling relationship. For example, the quotient of the fresh air system generated energy and the second performance parameter can be determined as the predicted fresh air system energy consumption.

[0079] Step S1033: Determine the sum of the predicted radiation system energy consumption and the predicted fresh air system energy consumption as the predicted system energy consumption.

[0080] Here, the sum of the predicted radiation system energy consumption and the predicted fresh air system energy consumption is the system's comprehensive energy efficiency, where the system's comprehensive energy efficiency is equivalent to the predicted system energy consumption. Therefore, the sum of the predicted radiation system energy consumption and the predicted fresh air system energy consumption can be determined first, and then the sum of the energy consumption can be determined as the predicted system energy consumption.

[0081] In an embodiment of the present application, through the above steps S1031 to S1033, the environmental parameters can be first input into the radiation system prediction sub-model to obtain the predicted radiation system energy consumption; then the radiation system energy consumption and the predicted load are input into the fresh air system prediction sub-model to obtain the predicted fresh air system energy consumption. Since the output of the radiation system prediction sub-model (predicted radiation system energy consumption) is input into the fresh air system prediction sub-model, the interactivity between the radiation system and the fresh air system can be enhanced; finally, the sum of the predicted radiation system energy consumption and the predicted fresh air system energy consumption is determined as the predicted system energy, thereby providing variables to be optimized for system optimization, and ultimately making the system operate in a high energy efficiency zone, saving system energy consumption.

[0082] In some embodiments, before executing the above step S101 "obtaining environmental parameters, trained spatial characteristic prediction model and system performance prediction model", it is necessary to build a system performance prediction model, that is, to build a radiation system prediction sub-model and a fresh air system prediction sub-model, such as Figure 4 As shown, the radiation system prediction sub-model and the fresh air system prediction sub-model can be constructed by following steps S001 to S004:

[0083] Step S001: Acquire a first structural parameter corresponding to the radiation system and a first performance parameter corresponding to the radiation system.

[0084] Here, the first structural parameter is used to characterize the structure of the pipeline in the radiation system; the first performance parameter is a performance parameter corresponding to the radiation system, and the first performance parameter is used to characterize the heat exchange capacity of the radiation system.

[0085] In the embodiment of the present application, the first performance parameter is determined as the material of the radiation system is determined. For example, when the radiation system is made of a material with good thermal conductivity, the first performance parameter indicates a strong heat transfer capacity. Furthermore, after the radiation system is successfully constructed, the first structural parameter is determined accordingly.

[0086] Step S002: Acquire a second structural parameter corresponding to the fresh air system and a second performance parameter corresponding to the fresh air system.

[0087] Here, the implementation process of step S002 is similar to the implementation process of the above step S001. Therefore, the implementation process of step S002 can refer to the implementation process of the above step S001.

[0088] Step S003: constructing a radiation system prediction sub-model based on the first structural parameter and the first performance parameter.

[0089] Here, other system parameters can be fitted based on the first structural parameter, and then a radiation system prediction sub-model can be constructed based on the first structural parameter, the other system parameters, and the first performance parameter. The other system parameters represent structural parameters that cannot be directly obtained.

[0090] Step S004: constructing a fresh air system prediction sub-model based on the second structural parameter and the second performance parameter.

[0091] Here, the implementation process of step S004 is similar to the implementation process of the above step S003. Therefore, the implementation process of step S004 can refer to the implementation process of the above step S003.

[0092] In the embodiment of the present application, through the above steps S001 to S004, a radiation system prediction sub-model can be constructed using the first structural parameter and first performance parameter corresponding to the radiation system; and a fresh air system prediction sub-model can also be constructed using the second structural parameter and second performance parameter corresponding to the fresh air system. This allows the radiation system prediction sub-model to more closely resemble the actual radiation system, improving the accuracy of the radiation system energy consumption prediction; similarly, it also allows the fresh air system prediction sub-model to more closely resemble the actual fresh air system, improving the accuracy of the fresh air system energy consumption prediction.

[0093] In some embodiments, the trained spatial characteristic prediction model includes a load prediction sub-model and a temperature prediction sub-model, and the spatial characteristics include load and dew point temperature. Based on this, the above step S102 "using the trained spatial characteristic prediction model and environmental parameters to predict the spatial characteristics to obtain predicted load and predicted dew point temperature" can be implemented by the following steps S1021 and S1022:

[0094] Step S1021 , predicting the load using the load prediction sub-model and environmental parameters to obtain a predicted load.

[0095] Here, the environmental parameters may be input into the load prediction sub-model to predict the load using the load prediction sub-model, and based on this, the load prediction sub-model will output the predicted load.

[0096] In an embodiment of the present application, the environmental parameters input into the load prediction sub-model may include user parameters, external environmental parameters, indoor environmental parameters, and enclosure parameters.

[0097] Step S1022: predicting the dew point temperature using the temperature prediction sub-model and environmental parameters to obtain a predicted dew point temperature.

[0098] Here, the environmental parameters may be input into the temperature prediction sub-model to predict the dew point temperature using the temperature prediction sub-model, and based on this, the temperature prediction sub-model will output the predicted dew point temperature.

[0099] In an embodiment of the present application, the environmental parameters input into the temperature prediction sub-model may be indoor environmental parameters, which include indoor temperature, indoor humidity, indoor relative humidity, and the like.

[0100] In some embodiments, the above step S1021 may be executed first, or the above step S1022 may be executed first. In addition, the above step S1021 and the above step S1022 may be executed simultaneously. The embodiment of the present application does not limit the order in which the two are executed.

[0101] In an embodiment of the present application, through the above-mentioned steps S1021 and S1022, when predicting the spatial characteristics, the environmental parameters are input into the load prediction sub-model to predict the load through the load prediction sub-model to obtain the predicted load; the environmental parameters are also input into the temperature prediction sub-model to predict the dew point temperature through the temperature prediction sub-model to obtain the predicted dew point temperature, thereby providing a reference value of the surface temperature of the radiation panel to ensure the safe operation of the system and also providing a basis for subsequent system optimization.

[0102] In some embodiments, before executing step S101 "obtaining environmental parameters, trained spatial characteristic prediction model and system performance prediction model", it is necessary to obtain a trained spatial characteristic prediction model through training, that is, to obtain a load prediction sub-model and a temperature prediction sub-model through training. Therefore, Figure 5 As shown, before the above step S101, the following steps S001' to S007' may be performed:

[0103] Step S001 ′: obtaining a preset load prediction sub-model, a preset temperature prediction sub-model and sample environmental parameters.

[0104] Here, the sample environment parameters include training environment parameters and test environment parameters, wherein the training environment parameters are used to train the preset load prediction sub-model and the preset temperature prediction sub-model to obtain a preliminarily trained load prediction sub-model and a preliminarily trained temperature prediction sub-model; the test environment parameters are used to test the preliminarily trained load prediction sub-model and the preliminarily trained temperature prediction sub-model to determine whether the training termination conditions are met.

[0105] Step S002 ′: using the training environment parameters to train the preset load prediction sub-model and the preset temperature prediction sub-model respectively, to obtain a preliminarily trained load prediction sub-model and a preliminarily trained temperature prediction sub-model.

[0106] Here, the first target sample load and the first target sample dew point temperature corresponding to the training sample environmental parameters are also obtained.

[0107] In an embodiment of the present application, when using training environment parameters to train the preset load prediction sub-model, the training environment parameters can be first input into the preset load prediction sub-model to obtain the training load; then the first error information between the training load and the first target sample load is determined; finally, based on the first error information and the first preset error threshold, the preset load prediction sub-model is back-propagated and trained to obtain a preliminarily trained load prediction sub-model.

[0108] Similarly, when using the training environment parameters to train the preset temperature prediction sub-model, the training environment parameters can be first input into the preset temperature prediction sub-model to obtain the training dew point temperature; then the second error information between the training dew point temperature and the first target sample dew point is determined; finally, based on the second error information and the second preset error threshold, the preset temperature prediction sub-model is back-propagated and trained to obtain a preliminarily trained temperature prediction sub-model.

[0109] Step S003 ′: using the test environment parameters, respectively evaluate the preliminarily trained load prediction sub-model and the preliminarily trained temperature prediction sub-model to obtain evaluation index values.

[0110] Here, a second target sample load and a second target sample dew point temperature corresponding to the test environment parameters are also obtained.

[0111] In the embodiments of the present application, the evaluation index value may be accuracy, precision, recall, etc. In actual implementation, the test environment parameters are input into a preliminarily trained load prediction sub-model to obtain a test load, and then, based on the test load and the second target sample load, the first evaluation index value corresponding to the load prediction sub-model is determined. Similarly, the test environment parameters are also input into a preliminarily trained temperature prediction sub-model to obtain a test dew point temperature, and then, based on the test dew point temperature and the second target sample dew point temperature, the second evaluation index value corresponding to the temperature prediction sub-model is determined.

[0112] Step S004': determine whether the evaluation index value is less than a preset index threshold.

[0113] Here, the preset indicator thresholds may include an accuracy threshold, a precision threshold, a recall threshold, etc. For example, the accuracy threshold may be 85%, 90%, 92%, etc.

[0114] During actual implementation, the size relationship between the above-mentioned first evaluation index value and the preset index threshold will be compared. If the first evaluation index value is less than the preset index threshold, it is considered that the initially trained load prediction sub-model cannot accurately perform load prediction, and further training is required, and the process enters step S005'; if the first evaluation index value is greater than or equal to the preset index threshold, it is considered that the initially trained load prediction sub-model can accurately perform load prediction, and the process enters step S007'.

[0115] Similarly, the size relationship between the above-mentioned second evaluation index value and the preset index threshold will be compared. If the second evaluation index value is less than the preset index threshold, it is considered that the initially trained temperature prediction sub-model cannot accurately predict the dew point temperature, and further training is required, and the process enters step S005'; if the second evaluation index value is greater than or equal to the preset index threshold, it is considered that the initially trained temperature prediction sub-model can accurately predict the dew point temperature, and the process enters step S007'.

[0116] In some embodiments, the preliminarily trained load prediction sub-model and the preliminarily trained temperature prediction sub-model are independent of each other, and may be successfully trained at the same time; or one of them may be successfully trained while the other still needs to be trained.

[0117] Step S005', obtaining the training environment parameters again.

[0118] Here, in order to expand the diversity of sample parameters, parameters different from the training environment parameters in the above step S002 ′ are obtained.

[0119] Step S006', continue training the preliminarily trained load prediction sub-model and the preliminarily trained temperature prediction sub-model using the re-acquired training environment parameters until the evaluation index value reaches the index threshold, thereby obtaining the trained load prediction sub-model and the trained temperature prediction sub-model.

[0120] Here, the pre-trained load prediction sub-model and temperature prediction sub-model are further trained using the newly acquired training environment parameters. The training process can be found in step S002' above. Furthermore, the trained models are tested until the test results indicate that the evaluation index value reaches the index threshold. Thus, the trained load prediction sub-model and temperature prediction sub-model are obtained.

[0121] Step S007 ′: the preliminarily trained load prediction sub-model and the preliminarily trained temperature prediction sub-model are determined as the trained load prediction sub-model and the trained temperature prediction sub-model.

[0122] At this time, the evaluation index value is greater than or equal to the preset index threshold, that is, the first evaluation index value is greater than or equal to the preset index threshold, and the second evaluation index value is also greater than or equal to the preset index threshold. Based on this, the preliminarily trained load prediction sub-model can accurately perform load prediction, and the preliminarily trained temperature prediction sub-model can accurately perform dew point temperature prediction. The preliminarily trained load prediction sub-model and the preliminarily trained temperature prediction sub-model are then determined as the trained load prediction sub-model and the trained temperature prediction sub-model.

[0123] In an embodiment of the present application, through the above steps S001' to S007', the preset load prediction sub-model and the preset temperature prediction sub-model will be trained through the training environment parameters to obtain a preliminary trained load prediction sub-model and a preliminary trained temperature prediction sub-model; then, the preliminary trained load prediction sub-model and the preliminary trained temperature prediction sub-model will be evaluated and tested through the test environment parameters to obtain an evaluation index value; finally, when the evaluation index value is greater than or equal to the preset index threshold, it is considered that the trained load prediction sub-model and the trained temperature prediction sub-model are obtained. In this way, the trained load prediction sub-model can be used to achieve accurate prediction of the load, and the trained temperature prediction sub-model can also be used to achieve accurate prediction of the dew point temperature.

[0124] Based on the above embodiments, the embodiments of the present application further provide a system optimization method, which is applied to a system composed of a radiant air-conditioning system and a fresh air system. The overall logic of the system optimization (also referred to as optimization control) method proposed in the embodiments of the present application is based on the operating parameters of the current system and space. By changing the control parameters, the operating characteristics of the system and environmental space at the next time step (minute level) are predicted to determine the optimal control parameter change direction and size. Among them, the system includes a radiant air-conditioning system and a fresh air unit. The operating characteristics of the system and the environmental space are characterized by a system performance prediction model and a space characteristic prediction model. The control parameters include parameters for adjusting the performance of the radiant air-conditioning system and the fresh air unit, such as compressor speed, expansion valve opening, fan speed, etc.

[0125] Figure 6 A principle block diagram of a system optimization process provided in an embodiment of the present application is shown as follows: Figure 6 As shown, the data acquisition and processing system 601 is used to collect, process, and store a series of parameters, including user parameters, external environment parameters, indoor environment parameters, enclosure parameters, and operating parameters of the radiant air conditioning system and fresh air unit. Parameters related to the environmental space are divided into a training data set 602 and a test data set 603 according to a certain ratio. The training data set 602 is used to train the spatial characteristics prediction module 604 to generate a load prediction model 6041 and a temperature prediction model 6042 (including ambient temperature and dew point temperature, etc.). The test data set 603 is mainly used to test the accuracy of the model and assist in the generation of the correction module 605.

[0126] On the other hand, system-related parameters are used in the radiant system parameter module 606 and the fresh air unit parameter module 607, which are used to generate or update the radiant system fitting parameters and the fresh air unit fitting parameters, respectively. These parameters are used in the system performance prediction module 608, which is used in the simplified radiant system performance prediction model 6081 and the simplified fresh air unit performance prediction model 6082, respectively. The simplified performance prediction model also requires product performance characteristic parameters 609, which are generally provided by the manufacturer. The outputs of the spatial characteristic prediction module 604 and the system performance prediction module 608 are input into the optimization calculation module 610 to optimize and calculate the optimal control and adjustment parameters. The outputs are then deployed to the radiant system and the fresh air unit, obtaining new feedback and continuing to the next time step, thereby continuously optimizing the control of the radiant air conditioning and fresh air system. The optimization calculation module can take different forms, such as constructing a cost function or based on a classic genetic algorithm. The constraints include at least the radiant surface temperature not being lower than the dew point temperature of the space.

[0127] Among them, the training data set 602 is equivalent to the training environment parameters in the above embodiment, the test data set 603 is equivalent to the test environment parameters in the above embodiment, the spatial characteristic prediction module 604 is equivalent to the spatial characteristic prediction model in the above embodiment, the load prediction model 6041 is equivalent to the load prediction sub-model in the above embodiment, the temperature prediction model 6042 is equivalent to the temperature prediction sub-model in the above embodiment, the system performance prediction module 608 is equivalent to the system performance prediction model in the above embodiment, the radiation system performance prediction simplified model 6081 is equivalent to the radiation system prediction sub-model in the above embodiment, and the fresh air unit performance prediction simplified model 6082 is equivalent to the fresh air system prediction sub-model in the above embodiment.

[0128] In some embodiments, the performance prediction model of the radiant air conditioning system is as follows: Figure 7 As shown, reference Figure 7 It can be seen that the radiation panel surface temperature 701 can be determined based on the product performance characteristic parameters, and then the general total heat flux density simplified model 702 can be determined based on the radiation panel surface temperature 701. The radiation system cooling capacity 703 can also be determined based on the general total heat flux density simplified model 702. Finally, the radiation system energy consumption 705 can be determined based on the radiation system cooling capacity 703 and the conversion rate between energy and heat of the radiation system (Coefficient of Performance, COP) 704. Among them, the radiation system COP RAD It can be determined by product performance parameters.

[0129] exist Figure 7 In, T op is the operating temperature, T w is the water supply temperature, T s is the surface temperature of the radiation panel, T ai is the air temperature, T mr is the mean radiation temperature. The unit of the above temperature is Kelvin (K).

[0130] Based on this, the surface temperature of the radiation panel T s It can be expressed by formula (1):

[0131] T s =a*T a m +b*T w n (1);

[0132] Among them, a, b, m, n are constants, T a Refers to the ambient temperature, the ambient temperature T a Including the above air temperature T ai and water supply temperature T w .

[0133] The total heat flux density q of the radiation system can be expressed by formula (2):

[0134] q=c*(T op -T w ) d (2);

[0135] Among them, c and d are constants. The expression can be represented by T op and T w Get the surface temperature T of the radiation plate s , based on the surface temperature T of the radiation panel s , operating temperature T op And the water supply temperature T w Determine the total heat flux q.

[0136] Radiant system cooling capacity Q RAD It can be expressed by formula (3):

[0137] Q RAD =q*A (3);

[0138] Where A is the area of the radiation panel.

[0139] The conversion rate between energy and heat of the radiation system COP RAD It can be expressed by formula (4):

[0140] COP RAD =Q RAD / W RAD (4);

[0141] Among them, W RAD Refers to the energy consumption of the radiation system.

[0142] In the embodiment of the present application, as shown in the above formula (2), the surface temperature of the radiation plate (which can be obtained by T op and T w to obtain) and indoor environmental parameters (T op and T w ) can be used to know the total heat flux density of the radiation system, and further calculate the cooling capacity of the radiation air-conditioning system; in order to avoid the complexity and inconvenience of thermal resistance calculation, the calculation process of the radiation panel surface temperature can be simplified to the correlation between the ambient temperature and the water supply temperature as shown in formula (1). The specific correlation coefficients a, b, m, and n can be determined by the product performance characteristic parameters or identified by real-time measurement parameters; the cooling capacity required by the radiation system unit has been obtained, and the radiation system COP has been determined. RAD Then calculate its energy consumption. Among them, the cooling capacity of the radiation air conditioning system is equivalent to the energy prepared by the radiation system in the above embodiment, and the COP of the radiation system is RADIt is equivalent to the first performance parameter in the above embodiment, and the energy consumption is equivalent to the predicted radiation system energy consumption in the above embodiment.

[0143] In some embodiments, the performance prediction model of the fresh air system is as follows: Figure 8 As shown, the cooling capacity 801 required to be provided by the fresh air unit is theoretically the load minus the cooling capacity provided by the radiant air conditioning system, where the load is output by the load forecasting module; after the cooling capacity demand of the fresh air unit has been obtained, the COP of the fresh air unit is determined. OAP 802, then calculate the energy consumption 803; in the calculation of the COP of the fresh air unit OAP 802 requires the characteristic parameters of the unit, which can be determined by product performance characteristic parameters or identified (updated) by real-time measurement parameters. Among them, the cooling capacity 801 that the fresh air unit needs to provide is equivalent to the energy prepared by the fresh air system in the above embodiment, and the COP of the fresh air unit is OAP 802 is equivalent to the second performance parameter in the above embodiment, and energy consumption 803 is equivalent to the predicted energy consumption of the fresh air system in the above embodiment.

[0144] refer to Figure 8 , cooling capacity of fresh air unit Q OAP It can be expressed by formula (5):

[0145] Q OAP =Load-Q RAD (5);

[0146] Among them, Load is the load, Q RAD is the cooling capacity of the radiant system.

[0147] The conversion rate COP between energy and heat of the fresh air unit OAP It can be expressed by formula (6):

[0148] COP OAP =Q OAP / W OAP (6);

[0149] Among them, W OAP Refers to the energy consumption of the fresh air unit system.

[0150] In the embodiment of the present application, the system optimization method proposed in the embodiment of the present application can be used to improve the comprehensive energy efficiency of the radiation air conditioning and fresh air system, thereby reducing the energy consumption of the system; the embodiment of the present application utilizes a real-time optimization method, fully considering the characteristics of the two parts in the system, ensuring that the system can operate in a high-efficiency zone for a long time, and eliminating the problem of the two parts acting independently and poorly matched; because the radiation system has been set as a constraint condition for no condensation during the optimization process, the system will not have condensation, thereby improving user experience and equipment safety; the potential of the fresh air unit is fully utilized, and in the transition season it may even be possible to handle all indoor loads only through the fresh air unit, without turning on the radiation air conditioning refrigeration unit, thereby achieving better indoor air quality and better energy-saving effects; the proposed system optimization method can also be used in the heating mode, in which case the constraint of condensation risk can be removed, and the method has good versatility.

[0151] Based on the foregoing embodiments, an embodiment of the present application provides a system optimization device, wherein the modules included in the device and the units included in each module can be implemented by a processor in a computer device; of course, they can also be implemented by corresponding logic circuits; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

[0152] The present application further provides a system optimization device, Figure 9 A schematic diagram of the structure of the system optimization device provided in the embodiment of the present application is shown in FIG. Figure 9 As shown, the system optimization device 900 includes:

[0153] Acquisition module 901, used to acquire environmental parameters, trained spatial characteristic prediction model and system performance prediction model;

[0154] A first prediction module 902 is configured to predict spatial characteristics using the trained spatial characteristic prediction model and the environmental parameters to obtain predicted load and predicted dew point temperature;

[0155] The second prediction module 903 is configured to predict the system performance using the system performance prediction model, the predicted load, and the environmental parameters to obtain predicted system energy consumption;

[0156] An optimization module 904 is configured to optimize current system parameters based on the predicted dew point temperature and the predicted system energy consumption to obtain target system parameters;

[0157] The control module 905 is used to control the system to operate based on the target system parameters.

[0158] In some embodiments, the system includes a radiation system and a fresh air system, the system performance prediction model includes a radiation system prediction sub-model and a fresh air system prediction sub-model, and the second prediction module 903 includes:

[0159] A first prediction submodule is configured to perform prediction processing on the radiation system using the radiation system prediction submodel and the environmental parameters to obtain predicted radiation system energy consumption;

[0160] A second prediction submodule is configured to perform prediction processing on the fresh air system using the fresh air system prediction submodel, the predicted radiation system energy consumption, and the predicted load to obtain predicted fresh air system energy consumption;

[0161] The first determining submodule is configured to determine the sum of the predicted radiation system energy consumption and the predicted fresh air system energy consumption as the predicted system energy consumption.

[0162] In some embodiments, the acquisition module 901 is further configured to acquire a first structural parameter corresponding to the radiation system and a first performance parameter corresponding to the radiation system; and acquire a second structural parameter corresponding to the fresh air system and a second performance parameter corresponding to the fresh air system.

[0163] The system optimization device 900 further includes:

[0164] A first building module, configured to build the radiation system prediction sub-model based on the first structural parameter and the first performance parameter;

[0165] The second construction module is used to construct the fresh air system prediction sub-model based on the second structural parameter and the second performance parameter.

[0166] In some embodiments, the first prediction submodule includes:

[0167] a first determining unit, configured to determine a surface temperature of a radiation panel of the radiation system based on the environmental parameter;

[0168] a second determining unit, configured to determine a total heat flux density of the radiation system based on a surface temperature of the radiation panel;

[0169] a third determining unit, configured to determine energy generated by the radiation system based on the total heat flux density;

[0170] A fourth determining unit is configured to determine the predicted radiation system energy consumption based on the first performance parameter and the radiation system preparation energy.

[0171] In some embodiments, the second prediction submodule includes:

[0172] a fifth determining unit, configured to determine energy prepared by a fresh air system based on the predicted radiation system energy consumption and the predicted load;

[0173] A sixth determining unit is configured to determine the predicted energy consumption of the fresh air system based on the energy prepared by the fresh air system and the second performance parameter.

[0174] In some embodiments, the trained spatial characteristic prediction model includes a load prediction sub-model and a temperature prediction sub-model, the spatial characteristics include load and dew point temperature, and the first prediction module 902 includes:

[0175] A third prediction submodule is configured to predict the load using the load prediction submodel and the environmental parameters to obtain the predicted load;

[0176] The fourth prediction submodule is used to predict the dew point temperature using the temperature prediction submodel and the environmental parameters to obtain the predicted dew point temperature.

[0177] In some embodiments, the acquisition module 901 is further configured to acquire a preset load prediction sub-model, a preset temperature prediction sub-model, and sample environment parameters, wherein the sample environment parameters include training environment parameters and test environment parameters; if the evaluation index value is less than a preset index threshold, the training environment parameters are acquired again;

[0178] The system optimization device 900 further includes:

[0179] A first training module is used to train the preset load prediction sub-model and the preset temperature prediction sub-model respectively using the training environment parameters to obtain a preliminarily trained load prediction sub-model and a preliminarily trained temperature prediction sub-model;

[0180] A testing module, using the test environment parameters to evaluate the preliminarily trained load prediction sub-model and the preliminarily trained temperature prediction sub-model respectively to obtain evaluation index values;

[0181] The second training module is used to continue training the preliminarily trained load prediction sub-model and the preliminarily trained temperature prediction sub-model using the training environment parameters acquired again until the evaluation index value reaches the index threshold, thereby obtaining the trained load prediction sub-model and the trained temperature prediction sub-model.

[0182] It should be noted that the description of the system optimization device in the embodiment of the present application is similar to the description of the above-mentioned method embodiment and has similar beneficial effects as the method embodiment. For technical details not disclosed in the embodiment of the present device, please refer to the description of the method embodiment of the present application for understanding.

[0183] It should be noted that, in the embodiment of the present application, if the above-mentioned system optimization method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0184] Accordingly, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the system optimization method provided in the above embodiment.

[0185] The embodiment of the present application provides a system optimization device, Figure 10 A schematic diagram of the structure of the system optimization device provided in the embodiment of the present application is shown in FIG. Figure 10 As shown, the system optimization device 1000 includes: a processor 1001, at least one communication bus 1002, a user interface 1003, at least one external communication interface 1004, and a memory 1005. The communication bus 1002 is configured to enable communication between these components. The user interface 1003 may include a display screen, and the external communication interface 1004 may include a standard wired interface and a wireless interface. The processor 1001 is configured to execute the system optimization method program stored in the memory to implement the system optimization method provided in the above embodiment.

[0186] The description of the above system optimization device and storage medium embodiments is similar to the description of the above method embodiments and has similar beneficial effects as the method embodiments. For technical details not disclosed in the system optimization device and storage medium embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0187] It should be noted that the descriptions of the above storage medium and system optimization device embodiments are similar to the descriptions of the above method embodiments and have similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and system optimization device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0188] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments.

[0189] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0190] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0191] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present application.

[0192] In addition, all functional units in the embodiments of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the above-mentioned integrated units can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0193] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiments; and the aforementioned storage medium includes: mobile storage devices, ROM, disks or optical disks, and other media that can store program codes.

[0194] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application, or the part that contributes to the relevant technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling an AC to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks or optical disks.

[0195] The above is merely an embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A system optimization method, characterized in that: The method comprises: Obtaining environmental parameters, a trained spatial characteristic prediction model, and a system performance prediction model, wherein the system includes a radiation system and a fresh air system, and the system performance prediction model includes a radiation system prediction sub-model and a fresh air system prediction sub-model; Predicting spatial characteristics using the trained spatial characteristic prediction model and the environmental parameters to obtain predicted load and predicted dew point temperature; Performing prediction processing on the radiation system using the radiation system prediction sub-model and the environmental parameters to obtain predicted radiation system energy consumption; Performing prediction processing on the fresh air system using the fresh air system prediction sub-model, the predicted radiation system energy consumption, and the predicted load to obtain predicted fresh air system energy consumption; Determining the sum of the predicted radiation system energy consumption and the predicted fresh air system energy consumption as the predicted system energy consumption; On the premise that the surface temperature of the system radiation panel is higher than the predicted dew point temperature, optimizing the predicted system energy consumption based on the predicted dew point temperature to obtain target system parameters; The control system operates based on the target system parameters.

2. The method according to claim 1, wherein The method further comprises: Acquiring a first structural parameter corresponding to the radiation system and a first performance parameter corresponding to the radiation system; Obtaining a second structural parameter corresponding to the fresh air system and a second performance parameter corresponding to the fresh air system; constructing the radiation system prediction sub-model based on the first structural parameter and the first performance parameter; Based on the second structural parameter and the second performance parameter, the fresh air system prediction sub-model is constructed.

3. The method according to claim 2, characterized in that The using the radiation system prediction sub-model and the environmental parameters to perform prediction processing on the radiation system to obtain predicted radiation system energy consumption includes: determining a surface temperature of a radiation panel of the radiation system based on the environmental parameters; determining a total heat flux density of the radiation system based on the surface temperature of the radiation panel; determining a radiation system production energy based on the total heat flux; The predicted radiation system energy consumption is determined based on the first performance parameter and the radiation system production energy.

4. The method according to claim 2, characterized in that The method of performing prediction processing on the fresh air system by using the fresh air system prediction sub-model, the predicted radiation system energy consumption, and the predicted load to obtain the predicted fresh air system energy consumption includes: Determining the energy prepared by the fresh air system based on the predicted radiation system energy consumption and the predicted load; The predicted energy consumption of the fresh air system is determined based on the energy prepared by the fresh air system and the second performance parameter.

5. The method according to claim 1, wherein The trained spatial characteristic prediction model includes a load prediction sub-model and a temperature prediction sub-model, the spatial characteristics include load and dew point temperature, and the spatial characteristics are predicted using the trained spatial characteristic prediction model and the environmental parameters to obtain predicted load and predicted dew point temperature, including: Predicting the load using the load prediction sub-model and the environmental parameters to obtain the predicted load; The dew point temperature is predicted using the temperature prediction sub-model and the environmental parameters to obtain the predicted dew point temperature.

6. The method according to claim 5, characterized in that The method further comprises: Obtaining a preset load prediction sub-model, a preset temperature prediction sub-model, and sample environmental parameters, wherein the sample environmental parameters include training environment parameters and test environment parameters; Using the training environment parameters to train the preset load prediction sub-model and the preset temperature prediction sub-model respectively, to obtain a preliminarily trained load prediction sub-model and a preliminarily trained temperature prediction sub-model; Using the test environment parameters, respectively evaluating the preliminarily trained load prediction sub-model and the preliminarily trained temperature prediction sub-model to obtain evaluation index values; If the evaluation index value is less than the preset index threshold, obtaining the training environment parameters again; The preliminarily trained load prediction sub-model and the preliminarily trained temperature prediction sub-model are continued to be trained using the training environment parameters acquired again until the evaluation index value reaches the index threshold, thereby obtaining a trained load prediction sub-model and a trained temperature prediction sub-model.

7. A system optimization device, characterized in that: The system optimization device comprises: An acquisition module is used to acquire environmental parameters, a trained spatial characteristic prediction model, and a system performance prediction model, wherein the system includes a radiation system and a fresh air system, and the system performance prediction model includes a radiation system prediction sub-model and a fresh air system prediction sub-model; A first prediction module is used to predict the spatial characteristics by using the trained spatial characteristics prediction model and the environmental parameters to obtain the predicted load and the predicted dew point temperature; a second prediction module, configured to perform prediction processing on the radiation system using the radiation system prediction sub-model and the environmental parameters to obtain predicted radiation system energy consumption, perform prediction processing on the fresh air system using the fresh air system prediction sub-model, the predicted radiation system energy consumption, and the predicted load to obtain predicted fresh air system energy consumption, and determine the sum of the predicted radiation system energy consumption and the predicted fresh air system energy consumption as the predicted system energy consumption; an optimization module, configured to optimize the predicted system energy consumption based on the predicted dew point temperature to obtain target system parameters, provided that the surface temperature of the system radiation panel is higher than the predicted dew point temperature; A control module is used to control the system to operate based on the target system parameters.

8. A system optimization device, characterized in that: The system optimization device includes: processor; and a memory for storing a computer program executable on the processor; Wherein, when the computer program is executed by a processor, the system optimization method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are configured to execute the system optimization method according to any one of claims 1 to 6.

Images