A control method, device and equipment for air-liquid cooling system

Abstract

The present application provides a control method, device and equipment for an air-liquid cooling system, which is applied to the technical field of air-liquid cooling systems. The method includes: obtaining first state information of the air cooling system and second state information of the liquid cooling system. The first state information includes the first working fluid temperature of the working fluid of the air cooling system. The second state information includes the second working fluid temperature of the working fluid of the liquid cooling system. When the first working fluid temperature does not meet the first preset condition and / or the second working fluid temperature does not meet the second preset condition, the first state information and the second state information are input into a preset prediction model to determine the first control parameter of the air cooling system and the second control parameter of the liquid cooling system. The air cooling system is controlled by the first control parameter, and the liquid cooling system is controlled by the second control parameter, so that the difference between the third working fluid temperature of the working fluid of the air cooling system and the fourth working fluid temperature of the working fluid of the liquid cooling system is less than a threshold value. Accurate control of the air-liquid fusion cooling system can be achieved, and the energy efficiency ratio and stability of the system can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of air-liquid cooling systems, and in particular to a control method, device and equipment for an air-liquid cooling system. Background Art

[0002] "Carbon neutrality" has become a global consensus and development trend. In order to achieve this goal, data centers are actively taking measures to reduce energy consumption and improve energy efficiency. Traditional data centers achieve energy conservation and emission reduction by improving the efficiency of components such as UPS (uninterruptible power supply) and air conditioners. With the development of technology, more and more data centers have begun to use intelligent means, especially data analysis and machine learning technology, to finely control the refrigeration system to achieve higher energy saving effects.

[0003] However, the traditional manual control method is often unable to achieve fine management and optimization when facing the air-liquid cooling system due to its complexity. Especially when ensuring the safety of cooling capacity, the traditional method often adopts the maximum cooling capacity management method, which can ensure the safe operation of the system, but will lead to the waste of cooling capacity and cannot achieve true energy-saving synergy. Summary of the invention

[0004] The purpose of the present application is to provide a control method, device and equipment for an air-liquid cooling system, so as to achieve precise control of the air-liquid fusion cooling system and improve the energy efficiency and stability of the system.

[0005] In the first aspect, an embodiment of the present application provides a control method for an air-liquid cooling system, which is applied to an air-liquid cooling system, and the air-liquid cooling system includes an air cooling system and a liquid cooling system. The method includes: obtaining first state information of the air cooling system and second state information of the liquid cooling system. The first state information includes a first working fluid temperature of a working fluid in the air cooling system. The second state information includes a second working fluid temperature of a working fluid in the liquid cooling system. When the first working fluid temperature does not meet a first preset condition and / or the second working fluid temperature does not meet a second preset condition, the first state information and the second state information are input into a trained preset prediction model to determine a first control parameter of the air cooling system and a second control parameter of the liquid cooling system. The air cooling system is controlled using the first control parameter, and the liquid cooling system is controlled using the second control parameter, so that the difference between the third working fluid temperature of the working fluid in the air cooling system and the fourth working fluid temperature of the working fluid in the liquid cooling system is less than a threshold value.

[0006] The control method of the air-liquid cooling system provided in the embodiment of the present application realizes precise control of the third temperature of the working fluid in the air cooling system and the fourth temperature of the working fluid in the liquid cooling system by accurately controlling the first control parameter of the air cooling system and the second control parameter of the liquid cooling system, so that the difference between the third temperature and the fourth temperature is less than a threshold value, thereby reducing the temperature difference between the inlet and outlet working fluids of the air cooling system and the liquid cooling system, which can significantly improve the energy efficiency ratio of the system and ensure stable operation of the system.

[0007] In a possible implementation, the preset prediction model includes: an air cooling feature extraction network, a liquid cooling feature extraction network, and a fusion model. The inputting the first state information and the second state information into the trained preset prediction model to determine the first control parameter of the air cooling system and the second control parameter of the liquid cooling system includes: inputting the first state information into the air cooling feature extraction network to obtain air cooling feature information. Inputting the second state information into the liquid cooling feature extraction network to obtain liquid cooling feature information. Inputting the air cooling feature information and the liquid cooling feature information into the fusion model to determine the first control parameter and the second control parameter.

[0008] In a possible implementation, the inputting the air cooling characteristic information and the liquid cooling characteristic information into the fusion model to determine the first control parameter and the second control parameter includes: using the first weight of the air cooling state information and the second weight of the second characteristic information, fusing the air cooling characteristic information and the liquid cooling characteristic information through a gating mechanism to obtain the load information of the air cooling system and the temperature information of the liquid cooling system. The load information is used to determine the first control parameter, and the temperature information is used to determine the second control parameter.

[0009] In a possible implementation, the process of determining the first weight and the second weight includes: obtaining a data set of the air-liquid cooling system. Using the data set to construct a training set of the air-liquid cooling system. The training set belongs to the data set. The training set includes: first historical state information of the air cooling system, second historical state information of the liquid cooling system, historical load information of the air cooling system corresponding to the first historical state information, and historical temperature information of the liquid cooling system corresponding to the second historical state information. Extracting first feature information from the first historical state information, and extracting second feature information from the second historical state information. Determining a first weight of the first feature information and a second weight of the second feature information based on the historical load information and the historical temperature information.

[0010] In a possible implementation, the method further includes: constructing a test set of the air-liquid cooling system using the data set. The test set belongs to the data set. The test set includes: first test state information of the air cooling system, second test state information of the liquid cooling system, test load information of the air cooling system corresponding to the first test state information, and test temperature information of the liquid cooling system corresponding to the second test state information. Using the first weight of the first feature information and the second weight of the second feature information, the first test state information and the second test state information are fused through a gating mechanism to obtain predicted load information of the air cooling system and predicted temperature information of the liquid cooling system. Using the predicted load information, the predicted temperature information, the test load information, and the test temperature information, the loss value of the fusion model is determined. Using the loss value, the first weight and the second weight are adjusted.

[0011] A possible implementation method, wherein the air cooling system is controlled by the first control parameter and the liquid cooling system is controlled by the second control parameter, includes: adjusting the power of the evaporator fan of the air cooling system by the first control parameter and adjusting the speed of the electronic pump in the liquid cooling system by the second control parameter.

[0012] In a possible implementation manner, the first preset condition includes that the first working fluid temperature does not belong to a first working fluid temperature preset range, and the second preset condition includes that the second working fluid temperature does not belong to a second working fluid temperature preset range.

[0013] In a second aspect, an embodiment of the present application provides a control device for an air-liquid cooling system, which is applied to an air-liquid cooling system, wherein the air-liquid cooling system includes an air cooling system and a liquid cooling system, and the device includes: an acquisition module, a processing module and a control module.

[0014] The acquisition module is used to acquire the first state information of the air cooling system and the second state information of the liquid cooling system. The first state information includes the first working fluid temperature of the working fluid in the air cooling system. The second state information includes the second working fluid temperature of the working fluid in the liquid cooling system.

[0015] A processing module is used to input the first state information and the second state information into a trained preset prediction model to determine the first control parameter of the air cooling system and the second control parameter of the liquid cooling system when the first working fluid temperature does not meet the first preset condition and / or the second working fluid temperature does not meet the second preset condition.

[0016] A control module is used to control the air cooling system using the first control parameter and to control the liquid cooling system using the second control parameter so that the difference between the third working fluid temperature of the working fluid in the air cooling system and the fourth working fluid temperature of the working fluid in the liquid cooling system is less than a threshold value.

[0017] In a third aspect, the present application provides a control device for an air-liquid cooling system, which has the function of implementing the control method for an air-liquid cooling system of the first aspect or any possible implementation method. The function can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0018] In a fourth aspect, a computer-readable storage medium is provided, in which instructions are stored, and when the computer-readable storage medium is run on a computer, the computer can execute the control method of the air-liquid cooling system of the above-mentioned first aspect or any possible implementation method.

[0019] In a fifth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the control method of the air-liquid cooling system of the first aspect or any possible implementation manner.

[0020] Among them, the technical effects brought about by any design method in the second to fifth aspects can refer to the technical effects brought about by different possible implementation methods in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 A structural schematic diagram of an air-liquid cooling system provided in an embodiment of the present application;

[0023] Figure 2 A method flow chart of a method for controlling air-liquid cooling provided in an embodiment of the present application;

[0024] Figure 3 A specific schematic diagram of a control method for air-liquid cooling provided in an embodiment of the present application;

[0025] Figure 4 A schematic diagram of the structure of a control device for air-liquid cooling provided in an embodiment of the present application;

[0026] Figure 5 A structural schematic diagram of the control state of air-liquid cooling provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0028] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0029] At present, the traditional manual control method is often unable to achieve fine management and optimization when facing the air-liquid cooling system due to the complexity of the air-liquid cooling system. Especially when ensuring the safety of cooling capacity, the traditional method often adopts the maximum cooling capacity management method, which can ensure the safe operation of the system, but will lead to the waste of cooling capacity and cannot achieve true energy-saving collaborative work.

[0030] Based on this, an embodiment of the present application provides a control method for an air-liquid cooling system, which is applied to a liquid cooling system, wherein the air-liquid cooling system includes an air cooling system and a liquid cooling system. The method includes: obtaining first state information of the air cooling system and second state information of the liquid cooling system. The first state information includes a first temperature of the working fluid in the air cooling system. The second state information includes a second temperature of the working fluid in the liquid cooling system. When the first temperature does not meet the first preset condition and / or the second temperature does not meet the second preset condition, the first state information and the second state information are input into a trained preset prediction model to determine a first control parameter of the air cooling system and a second control parameter of the liquid cooling system. The air cooling system is controlled using the first control parameter, and the liquid cooling system is controlled using the second control parameter, so that the difference between the third temperature of the working fluid in the air cooling system and the fourth temperature of the working fluid in the liquid cooling system is less than a threshold value.

[0031] By accurately controlling the first control parameter of the air cooling system and the second control parameter of the liquid cooling system, the third temperature of the working fluid in the air cooling system and the fourth temperature of the working fluid in the liquid cooling system can be accurately controlled so that the difference between the third temperature and the fourth temperature is less than the threshold value, thereby narrowing the temperature difference between the inlet and outlet working fluids of the air cooling system and the liquid cooling system, which can significantly improve the energy efficiency ratio of the system and ensure stable operation of the system.

[0032] The implementation of the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0033] On the one hand, the embodiments of the present application provide an air-liquid cooling system. Figure 1 As shown, the air-liquid cooling system 100 may include: a dry cooling system 101 , a liquid cooling system 102 and an air cooling system 103 .

[0034] The dry cooling system 101 includes a main circuit, on which a dry cooler and a water pump are deployed.

[0035] The liquid cooling system 102 includes a first branch circuit, a first cooler and a liquid cooling circuit. The liquid cooling circuit is provided with an electronic pump, a liquid cooling server, a first pressure sensor, a second pressure sensor, a third pressure sensor, a fourth pressure sensor, a fifth pressure sensor, a first temperature sensor, a second temperature sensor, a third temperature sensor and a fourth temperature sensor.

[0036] Among them, the first branch circuit is connected to the main circuit, and the working fluid in the main circuit is transferred to the first cooler, so that the working fluid in the first branch circuit can achieve heat exchange with the working fluid in the liquid cooling circuit through the first cooler. The first branch circuit is deployed with a flow control valve for controlling the working state of the liquid cooling system. The electronic pump is used to push the working fluid to flow in the liquid cooling circuit according to the speed of the electronic pump determined by the second control parameter. The liquid cooling server is used to contact the equipment to be cooled, absorb the heat of the equipment to be cooled, and transfer it to the working fluid in the liquid cooling circuit. The first pressure sensor, the second pressure sensor, the third pressure sensor, the fourth pressure sensor and the fifth pressure sensor are used to measure the pressure value of the working fluid in the liquid cooling circuit at different positions in the liquid cooling circuit, and the first temperature sensor, the second temperature sensor, the third temperature sensor and the fourth temperature sensor are used to measure the temperature value of the working fluid in the liquid cooling circuit at different positions.

[0037] The air cooling system 103 includes a second branch circuit, a second cooler and an air cooling circuit. The air cooling circuit is equipped with a compressor, an evaporator, an electronic expansion valve, a liquid-test tube ball valve, a dry filter, a high-pressure sensor and a low-pressure sensor. The compressor, the evaporator, the electronic expansion valve, the liquid-test tube ball valve, the dry filter, the high-pressure sensor and the low-pressure sensor are connected in series.

[0038] Among them, the second branch circuit is connected to the main circuit, and the working fluid in the main circuit is transferred to the second cooler, so that the working fluid in the second branch circuit can achieve heat exchange with the working fluid in the air-cooled circuit through the second cooler. A second flow control valve is deployed in the second branch circuit to control the working state of the air-cooled system. The compressor is used to compress the gas in the air-cooled circuit into liquid. The evaporator is used to directly contact the heat-generating components (such as CPU, GPU, etc.), and transfer the heat from the heat-generating components to the radiator through heat conduction. The airflow generated by the fan of the evaporator is then used to take away the heat from the surface of the radiator, so that the temperature of the radiator and the heat-generating components is maintained at a lower operating temperature. The electronic expansion valve and the liquid measuring tube ball valve are used to control the flow rate of the working fluid in the air-cooled circuit. The dry filter is used to remove moisture, impurities and other contaminants in the working fluid. The high-pressure sensor and the low-pressure sensor are used to measure the pressure values ​​at both ends of the compressor.

[0039] On the one hand, the embodiment of the present application provides a control method for an air-liquid cooling system, which can be Figure 1 The air-liquid cooling system 100 shown is implemented as Figure 2 As shown, the method may include:

[0040] S201, obtaining first state information of an air cooling system and second state information of a liquid cooling system.

[0041] The first state information includes a first working fluid temperature of a working fluid in an air cooling system, and the second state information includes a second working fluid temperature of a working fluid in a liquid cooling system.

[0042] Exemplarily, a fourth temperature sensor is used to collect a first working fluid temperature of a working fluid in the air cooling system in real time, and the first working fluid temperature is the same as the fourth temperature. The temperature of the evaporator is obtained to obtain a second working fluid temperature.

[0043] S202, when the first working fluid temperature does not satisfy the first preset condition and / or the second working fluid temperature does not satisfy the second preset condition, the first state information and the second state information are input into the trained preset prediction model to determine the first control parameter of the air cooling system and the second control parameter of the liquid cooling system.

[0044] The first preset condition includes that the first working fluid temperature does not belong to the first working fluid temperature preset interval. The second preset condition includes that the second working fluid temperature does not belong to the second working fluid temperature preset interval.

[0045] The preset prediction model includes: an air cooling feature extraction network, a liquid cooling feature extraction network and a fusion model. The fusion model may be a Transformer model.

[0046] A possible implementation method is to input the first state information and the second state information into a pre-set prediction model after training to determine the first control parameter of the air cooling system and the second control parameter of the liquid cooling system, including: inputting the first state information into an air cooling feature extraction network to obtain air cooling feature information. Inputting the second state information into a liquid cooling feature extraction network to obtain liquid cooling feature information. Using the first weight of the first feature information and the second weight of the second feature information, the air cooling feature information and the liquid cooling feature information are fused through a gating mechanism to obtain the load information of the air cooling system and the temperature information of the liquid cooling system. The load information is used to determine the first control parameter, and the temperature information is used to determine the second control parameter.

[0047] For example, Figure 3 As shown, the first working fluid temperature is input into the pre-trained neural network model, so as to use the neural network to extract the air cooling characteristic parameters related to the air cooling system from the first working fluid temperature, including key indicators such as air flow rate, fan speed, and radiator surface temperature. The second working fluid temperature is input into the pre-trained neural network model, so as to use the neural network to extract the liquid cooling characteristic parameters related to the liquid cooling system from the second working fluid temperature, including key indicators such as working fluid flow rate, working state of the electronic pump, and efficiency of the cold plate liquid cooling server.

[0048] Then, the air cooling characteristic parameters and the liquid cooling characteristic parameters are input into the encoder by using the encoder, so as to compress the air cooling characteristic parameters into low-dimensional air cooling codes, and compress the liquid cooling characteristic parameters into low-dimensional liquid cooling codes.

[0049] The air cooling code and liquid cooling code are input into another neural network model (such as a multi-layer perceptron, a recurrent neural network, etc.), which is used to generate air cooling logic and liquid cooling logic. This process can be, for example, to use a multi-layer perceptron to perform nonlinear transformation on the air cooling code and liquid cooling code in the hidden layer through multiple hidden layers, and output the final air cooling logic and liquid cooling logic in the output layer. Or, using a recurrent neural network, at each time step, the RNN receives the air cooling code and liquid cooling code, updates the internal state, and then outputs the air cooling logic and liquid cooling logic of the current time step.

[0050] Use air-cooled logic and liquid-cooled logic for cross-validation. For example, divide the data sets of air-cooled logic and liquid-cooled logic into K subsets (e.g., 5-fold or 10-fold). For each fold, use K-1 subsets for training and the remaining 1 subset for validation. Record the validation results of each fold, such as accuracy, loss, and other indicators. Calculate the average performance indicators of all folds to evaluate the overall performance of the model. And analyze the performance differences between folds to ensure the consistency of the model's performance on different data subsets.

[0051] The cross-validation results are input into the fusion model (Transformer model). The Transformer model captures long-term dependencies in the time series through the self-attention mechanism. The gated (Gate Attention) mechanism (such as GRU, LSTM, or other custom gated mechanisms) is used to fuse the air-cooled logic and the liquid-cooled logic. The air-cooled logic and the liquid-cooled logic are input into the gated mechanism. The gated mechanism dynamically adjusts the air-cooled logic and the liquid-cooled logic according to the weights to generate fused logic information, which combines the air-cooled logic and the liquid-cooled logic.

[0052] Then extract the information related to the air cooling system load from the fused logical information, and extract the information related to the liquid cooling system temperature from the fused logical information. Based on the load information, determine the first control parameters of the air cooling system, including evaporator fan speed, air volume adjustment, evaporator configuration, compressor speed, compressor mode, etc. Based on the temperature information, determine the second control parameters of the liquid cooling system, including working fluid flow, electronic pump working status, liquid cooling server settings, etc.

[0053] The process of determining the first weight and the second weight includes: obtaining a data set of an air-liquid cooling system. Using the data set to construct a training set of an air-liquid cooling system. The training set belongs to the data set. The training set includes: the first historical state information of the air cooling system, the second historical state information of the liquid cooling system, the historical load information of the air cooling system corresponding to the first historical state information, and the historical temperature information of the liquid cooling system corresponding to the second historical state information. The first feature information is extracted from the first historical state information, and the second feature information is extracted from the second historical state information. According to the historical load information and the historical temperature information, the first weight of the first feature information and the second weight of the second feature information are determined. The first feature information is the air cooling state information corresponding to the first historical state information, and the second feature information is the liquid cooling state information corresponding to the second historical state information.

[0054] The data set is then used to construct a test set for the air-liquid cooling system. The test set belongs to the data set. The test set includes: the first test state information of the air cooling system, the second test state information of the liquid cooling system, the test load information of the air cooling system corresponding to the first test state information, and the test temperature information of the liquid cooling system corresponding to the second test state information. Using the first weight of the first feature information and the second weight of the second feature information, the first test state information and the second test state information are fused through a gating mechanism to obtain the predicted load information of the air cooling system and the predicted temperature information of the liquid cooling system. Using the predicted load information, the predicted temperature information, the test load information, and the test temperature information, the loss value of the fusion model is determined. The first weight and the second weight are adjusted using the loss value.

[0055] S203, using the first control parameter to control the air cooling system, and using the second control parameter to control the liquid cooling system, so that the difference between the third working fluid temperature of the working fluid in the air cooling system and the fourth working fluid temperature of the working fluid in the liquid cooling system is less than a threshold value.

[0056] In a possible implementation, the power of the evaporator fan of the air cooling system is adjusted using the first control parameter, and the speed of the electronic pump in the liquid cooling system is adjusted using the second control parameter.

[0057] Exemplarily, when the air-liquid cooling system is started, the water pump runs at high speed, the air cooling system is turned on, and the first flow control valve is closed. At this time, the liquid cooling system works normally. The electronic pump, compressor and evaporator run at full speed.

[0058] After the startup process (default 3 minutes) is completed, the first working fluid temperature is obtained by using the fourth temperature sensor, and the first working fluid temperature is compared with the first working fluid temperature range. After the startup process (default 5 minutes) is completed, the second working fluid temperature of the evaporator is obtained, and the second working fluid temperature is compared with the second working fluid temperature range. If the first working fluid temperature does not belong to the first working fluid temperature range, and / or the second working fluid temperature does not belong to the second working fluid temperature range, the first state information and the second state information are used to determine the first control parameter of the air cooling system and the second control parameter of the liquid cooling system. The air cooling system is controlled by the first control parameter, and the liquid cooling system is controlled by the second control parameter, and the third working fluid temperature of the working fluid in the air cooling system and the fourth working fluid temperature of the working fluid in the liquid cooling system are obtained in real time until the difference between the third working fluid temperature and the fourth working fluid temperature is less than the threshold value. If the difference between the third working fluid temperature and the fourth working fluid temperature is greater than or equal to the threshold, the above-mentioned real-time acquisition of new first state information and new second state information is repeated, and the first control parameter of the air cooling system and the second control parameter of the liquid cooling system are determined using the new first state information and the new second state information, until the difference between the third working fluid temperature and the fourth working fluid temperature is less than the threshold. If the difference between the third working fluid temperature and the fourth working fluid temperature still cannot be less than the threshold after the preset time, the equipment fault alarm is activated to prompt the user that the air-liquid cooling system has a fault.

[0059] Exemplarily, during the daily operation of the air-liquid cooling system, the first working fluid temperature is obtained by using the fourth temperature sensor, and the first working fluid temperature is compared with the first working fluid temperature interval. The second working fluid temperature of the evaporator is obtained, and the second working fluid temperature is compared with the second working fluid temperature interval. If the first working fluid temperature does not belong to the first working fluid temperature interval, and / or the second working fluid temperature does not belong to the second working fluid temperature interval, the first state information and the second state information are used to determine the first control parameter of the air cooling system and the second control parameter of the liquid cooling system. The air cooling system is controlled by the first control parameter, and the liquid cooling system is controlled by the second control parameter, and the third working fluid temperature of the working fluid in the air cooling system and the fourth working fluid temperature of the working fluid in the liquid cooling system are obtained in real time until the difference between the third working fluid temperature and the fourth working fluid temperature is less than the threshold. If the difference between the third working fluid temperature and the fourth working fluid temperature is greater than or equal to the threshold, the above-mentioned real-time acquisition of new first state information and new second state information is repeated, and the first control parameter of the air cooling system and the second control parameter of the liquid cooling system are determined by using the new first state information and the new second state information, until the difference between the third working fluid temperature and the fourth working fluid temperature is less than the threshold. If the temperature difference between the third working fluid and the fourth working fluid is still not less than the threshold after the preset time, the equipment fault alarm is activated to prompt the user that the air-liquid cooling system has a fault.

[0060] The air-liquid cooling system provided in the embodiment of the present application achieves precise control of the third temperature of the working fluid in the air cooling system and the fourth temperature of the working fluid in the liquid cooling system by accurately controlling the first control parameter of the air cooling system and the second control parameter of the liquid cooling system, so that the difference between the third temperature and the fourth temperature is less than a threshold value, thereby narrowing the temperature difference between the inlet and outlet working fluids of the air cooling system and the liquid cooling system, which can significantly improve the energy efficiency ratio of the system and ensure stable operation of the system.

[0061] Furthermore, the air-liquid cooling system will also feed back the status information of the air cooling system, the status information of the liquid cooling system, and the control results of the air cooling system and the liquid cooling system, compare them with the output of the prediction model, analyze the deviation between the prediction and the actual, and adjust the parameters of the prediction model. Through continuous learning and adjustment, the air-liquid cooling system can gradually adapt to various status information and improve control accuracy. For example, algorithms such as PID control, fuzzy logic control, or reinforcement learning can be used to optimize the control system in real time.

[0062] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the working principle of the device. It can be understood that in order to realize the above functions, the control device of the air-liquid cooling system includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0063] The embodiment of the present application can divide the control device of the air-liquid cooling system into functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or software functional module.

[0064] It should be noted that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. Figure 4 FIG. 2 shows a possible schematic diagram of the control device of the air-liquid cooling system involved in the above-mentioned embodiments. Figure 4 As shown, the control device 400 of the air-liquid cooling system may include: an acquisition module 401 , a processing module 402 and a control module 403 .

[0065] The acquisition module 401 is used to support the control device 400 of the air-liquid cooling system provided in the embodiment of the present application to execute Figure 2 S201 in the control method of the air-liquid cooling system shown.

[0066] The processing module 402 is used to support the control device 400 of the air-liquid cooling system provided in the embodiment of the present application to execute Figure 2 S202 in the control method of the air-liquid cooling system shown.

[0067] The control module 403 is used to support the control device 400 of the air-liquid cooling system provided in the embodiment of the present application to execute Figure 2 S203 in the control method of the air-liquid cooling system shown.

[0068] It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0069] The control device 400 of the air-liquid cooling system provided in the embodiment of the present application is used to execute the above Figure 2 or Figure 3 The control method of the air-liquid cooling system shown can therefore achieve the same effect as the control method of the air-liquid cooling system described above.

[0070] The embodiment of the present application also provides a control device for an air-liquid cooling system, which can execute the control method and related steps of the air-liquid cooling system in the above method embodiment.

[0071] The embodiment of the present application also provides a computer-readable storage medium on which instructions are stored. When the instructions are executed, the control method and related steps of the air-liquid cooling system in the above method embodiment are executed.

[0072] The embodiment of the present application also provides a computer program product. When the computer program product is run on a computer, the computer executes the control method and related steps of the air-liquid cooling system in the above method embodiment.

[0073] In some embodiments, the methods described herein may be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or encoded on other non-transitory media or articles of manufacture.

[0074] The present application also provides a control system 500 for an air-liquid cooling system. Figure 5 As shown, the control system 500 of the air-liquid cooling system includes at least one processor 501 and at least one interface circuit 502 .

[0075] As an example, when the control system 500 of the air-liquid cooling system includes a processor and an interface circuit, the processor may be Figure 5 The processor 501 shown in the solid line frame (or the processor 501 shown in the dotted line frame) may be Figure 5 The interface circuit 502 shown in the solid line frame (or the interface circuit 502 shown in the dotted line frame). When the control system 500 of the air-liquid cooling system includes two processors and two interface circuits, the two processors include Figure 5 The processor 501 shown in the solid line frame and the processor 501 shown in the dotted line frame, the two interface circuits include Figure 5 The interface circuit 502 shown in the solid line frame and the interface circuit 502 shown in the dotted line frame are not limited to this.

[0076] The processor 501 and the interface circuit 502 may be interconnected via a line. For example, the interface circuit 502 may be used to receive a signal. In another example, the interface circuit 502 may be used to send a signal to another device (e.g., the processor 501). For example, the interface circuit 502 may read a computer instruction stored in a memory and send the computer instruction to the processor 501. The processor 501 executes the instruction and implements the various steps in the above embodiments in combination with the input and output devices, such as implementing Figure 2 or Figure 3 The various steps performed in the method embodiment shown. Of course, the control system of the air-liquid cooling system may also include other discrete components, which are not specifically limited in the embodiment of the present application.

[0077] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0078] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0079] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0080] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0081] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0082] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A control method for an air-liquid cooling system, characterized in that: Applied to an air-liquid cooling system, the air-liquid cooling system includes an air cooling system and a liquid cooling system, and the method includes: Acquire first state information of the air cooling system and second state information of the liquid cooling system; the first state information includes a first working fluid temperature of the working fluid in the air cooling system; the second state information includes a second working fluid temperature of the working fluid in the liquid cooling system; When the first working fluid temperature does not satisfy a first preset condition and / or the second working fluid temperature does not satisfy a second preset condition, the first state information and the second state information are input into a trained preset prediction model to determine a first control parameter of the air cooling system and a second control parameter of the liquid cooling system; the preset prediction model includes: an air cooling feature extraction network, a liquid cooling feature extraction network and a fusion model; Controlling the air cooling system using the first control parameter, and controlling the liquid cooling system using the second control parameter, so that a difference between a third working fluid temperature of the working fluid in the air cooling system and a fourth working fluid temperature of the working fluid in the liquid cooling system is less than a threshold value; The inputting the first state information and the second state information into the trained preset prediction model to determine the first control parameter of the air cooling system and the second control parameter of the liquid cooling system comprises: inputting the first state information into the air cooling feature extraction network to obtain air cooling feature information; Inputting the second state information into the liquid cooling feature extraction network to obtain liquid cooling feature information; Using the first weight of the air cooling characteristic information and the second weight of the liquid cooling characteristic information, the air cooling characteristic information and the liquid cooling characteristic information are fused through a gating mechanism to obtain the load information of the air cooling system and the temperature information of the liquid cooling system; The first control parameter is determined using the load information, and the second control parameter is determined using the temperature information.

2. The method according to claim 1, characterized in that The process of determining the first weight and the second weight includes: Acquire a data set of the air-liquid cooling system; A training set of the air-liquid cooling system is constructed using the data set; the training set belongs to the data set; the training set includes: first historical state information of the air cooling system, second historical state information of the liquid cooling system, historical load information of the air cooling system corresponding to the first historical state information, and historical temperature information of the liquid cooling system corresponding to the second historical state information; extracting first characteristic information from the first historical state information, and extracting second characteristic information from the second historical state information; A first weight of the first feature information and a second weight of the second feature information are determined according to the historical load information and the historical temperature information.

3. The method according to claim 2, characterized in that The method further comprises: A test set of the air-liquid cooling system is constructed using the data set; the test set belongs to the data set; the test set includes: first test state information of the air cooling system, second test state information of the liquid cooling system, test load information of the air cooling system corresponding to the first test state information, and test temperature information of the liquid cooling system corresponding to the second test state information; Using a first weight of the first feature information and a second weight of the second feature information, the first test state information and the second test state information are fused through a gating mechanism to obtain predicted load information of the air cooling system and predicted temperature information of the liquid cooling system; Determining a loss value of the fusion model using the predicted load information, the predicted temperature information, the test load information, and the test temperature information; The first weight and the second weight are adjusted using the loss value.

4. The method according to claim 1, characterized in that: The controlling the air cooling system by using the first control parameter and the controlling the liquid cooling system by using the second control parameter includes: The first control parameter is used to adjust the power of the evaporator fan of the air cooling system, and the second control parameter is used to adjust the speed of the electronic pump in the liquid cooling system.

5. The method according to claim 1, characterized in that The first preset condition includes that the first working fluid temperature does not belong to a first working fluid temperature preset range, and the second preset condition includes that the second working fluid temperature does not belong to a second working fluid temperature preset range.

6. A control device for an air-liquid cooling system, characterized in that: Applied to an air-liquid cooling system, the air-liquid cooling system includes an air cooling system and a liquid cooling system, and the device includes: An acquisition module, used to acquire first state information of the air cooling system and second state information of the liquid cooling system; the first state information includes a first working fluid temperature of the working fluid in the air cooling system; the second state information includes a second working fluid temperature of the working fluid in the liquid cooling system; a processing module, configured to input the first state information and the second state information into a trained preset prediction model to determine a first control parameter of the air cooling system and a second control parameter of the liquid cooling system when the first working fluid temperature does not satisfy a first preset condition and / or the second working fluid temperature does not satisfy a second preset condition; the preset prediction model comprises: an air cooling feature extraction network, a liquid cooling feature extraction network and a fusion model; a control module, configured to control the air cooling system using the first control parameter, and control the liquid cooling system using the second control parameter, so that a difference between a third working fluid temperature of the working fluid in the air cooling system and a fourth working fluid temperature of the working fluid in the liquid cooling system is less than a threshold value; The processing module is specifically used to input the first state information into the air cooling feature extraction network to obtain air cooling feature information; input the second state information into the liquid cooling feature extraction network to obtain liquid cooling feature information; use the first weight of the air cooling feature information and the second weight of the liquid cooling feature information to fuse the air cooling feature information and the liquid cooling feature information through a gating mechanism to obtain the load information of the air cooling system and the temperature information of the liquid cooling system; use the load information to determine the first control parameter, and use the temperature information to determine the second control parameter.

7. A control device for an air-liquid cooling system, characterized in that: The control device of the air-to-liquid cooling system includes a processor and a memory, the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the control method of the air-to-liquid cooling system according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to implement the control method of the air-liquid cooling system according to any one of claims 1 to 5.

Images