Method, device and system for regulating a heat dissipation fan in a relatively closed space

Abstract

The application relates to an artificial intelligence technology and discloses a control method and equipment of a heat dissipation fan in a relatively closed space and a heat dissipation system, which comprises the following steps: controlling electronic devices in the relatively closed space to run different power consumption modes, controlling multiple heat dissipation fans to run in different parameter combinations of rotating speeds and rotating directions, and collecting temperature data of the electronic devices and wind noise data outside the relatively closed space; inputting the collected data into an artificial intelligence model for training to generate optimal parameter combinations corresponding to the heat dissipation fans under different power consumption modes of the electronic devices; and when the electronic devices are actually applied, the optimal parameter combinations corresponding to the heat dissipation fans are used to perform cooling treatment on the electronic devices according to the current power consumption mode of the electronic devices. The application also discloses a computer readable storage medium. The application aims to reduce wind noise generated by heat dissipation fans as much as possible while cooling the electronic devices in the relatively closed space.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a control method, a control device, a cooling system and a computer readable storage medium for a cooling fan in a relatively closed space. BACKGROUND

[0002] With the rapid development of electronic technology, the integration and power density of electronic devices are continuously improving, and the heat dissipation problem has become one of the key factors restricting the performance and service life of electronic equipment. In particular, in a relatively closed space, such as a server room, a data center, a vehicle-mounted electronic device, an industrial control device, a computer, etc., the heat dissipation problem of electronic devices is particularly prominent.

[0003] As a common heat dissipation means, the cooling fan is often used for heat dissipation and cooling of electronic devices in a relatively closed space. At present, the cooling fan usually relies on operation control of fixed setting parameters. Although this scheme can meet the heat dissipation demand to a certain extent, it is difficult to cope with the dynamic heat dissipation demand of electronic devices under different power consumption modes, and due to the limitation of space closure and air flow, it is easy to cause large running noise, affecting the equipment running environment and user experience.

[0004] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0005] The main purpose of the present application is to provide a control method, a control device, a cooling system and a computer readable storage medium for a cooling fan in a relatively closed space, which aims to use the cooling fan to cool the electronic devices in the relatively closed space, and at the same time ensure the cooling effect and as far as possible reduce the wind noise caused thereby.

[0006] To achieve the above purpose, the present application provides a control method for a cooling fan in a relatively closed space, comprising the following steps:

[0007] Controlling electronic devices in a relatively closed space to run in different power consumption modes, and controlling a plurality of cooling fans to run in different parameter combinations of speed and direction under each power consumption mode;

[0008] Collecting temperature data of the electronic devices and wind noise data outside the relatively closed space when the plurality of cooling fans run in different parameter combinations;

[0009] The relevant collected data is input into the artificial intelligence model for training, so that the artificial intelligence model learns the influence of different parameter combinations between the heat dissipation fans on the temperature data and the wind noise data in different power consumption modes of the electronic device; wherein, the training target of the artificial intelligence model is to optimize the wind noise data on the premise that the temperature data meets the cooling target of the electronic device in different power consumption modes, to obtain the optimal parameter combination of the rotation speed and the rotation direction between the multiple heat dissipation fans;

[0010] According to the training result of the artificial intelligence model, the corresponding optimal parameter combination between the heat dissipation fans in different power consumption modes of the electronic device is generated;

[0011] When the electronic device is actually applied, the corresponding optimal parameter combination between the heat dissipation fans is used to cool the electronic device according to the current power consumption mode of the electronic device.

[0012] To achieve the above-mentioned purpose, the present application also provides a control device, which comprises a memory, a processor and a computer program stored on the memory and executable on the processor, and the computer program implements the steps of the control method of the heat dissipation fan in the relatively closed space when executed by the processor.

[0013] To achieve the above-mentioned purpose, the present application also provides a heat dissipation system, which comprises a control device and multiple heat dissipation fans; each heat dissipation fan is in communication connection with the control device and is controlled by the control device; wherein, the control device is the control device as described above.

[0014] To achieve the above-mentioned purpose, the present application also provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the control method of the heat dissipation fan in the relatively closed space when executed by the processor.

[0015] The control method of the heat dissipation fan in the relatively closed space, the control device, the heat dissipation system and the computer readable storage medium provided by the present application are based on artificial intelligence model learning and optimization, dynamically adjust the rotation speed and the rotation direction of the multiple heat dissipation fans according to the actual power consumption mode of the electronic device, select the optimal fan parameter combination, realize intelligent heat dissipation management of the electronic device in different power consumption modes, and on the premise of ensuring the heat dissipation effect, optimize the wind noise data as much as possible, reduce the operating noise, realize the best balance between the heat dissipation effect and the noise control, and thus improve the user's experience. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 The control method of the heat dissipation fan in the relatively closed space in an embodiment of the present application is shown in the following steps;

[0017] Figure 2Fig. 1 is a schematic diagram of an internal architecture of a control device according to an embodiment of the present application.

[0018] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments in conjunction with the drawings. DETAILED DESCRIPTION

[0019] Embodiments of the present application are described in detail below with reference to examples shown in the accompanying drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by reference to the drawings are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative labor are within the scope of protection of the present application.

[0020] In addition, if the description of "first", "second" and the like is involved in the present application, it is only for the purpose of description (such as for distinguishing the same or similar features), and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first", "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions of various embodiments can be combined with each other, but it must be based on the fact that the technical solutions can be realized by those of ordinary skill in the art. When the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, and is not within the scope of protection required by the present application.

[0021] Reference Figure 1 In an embodiment, the method for controlling the heat dissipation fans in the relatively closed space comprises:

[0022] Step S10, controlling the electronic device in the relatively closed space to run different power consumption modes, and controlling the multiple heat dissipation fans to run at different parameter combinations of rotation speed and rotation direction in each power consumption mode;

[0023] Step S20, collecting temperature data of the electronic device and wind noise data outside the relatively closed space when the multiple heat dissipation fans run at different parameter combinations;

[0024] Step S30, inputting the related collected data into an artificial intelligence model for training, so that the artificial intelligence model learns the influence of different parameter combinations between the heat dissipation fans on the temperature data and the wind noise data under different power consumption modes of the electronic device; wherein the training target of the artificial intelligence model is to optimize the wind noise data under the premise that the temperature data meets the cooling target of the electronic device in different power consumption modes, to obtain the optimal parameter combination of rotation speed and rotation direction between the multiple heat dissipation fans;

[0025] Step S40, according to the training result of the artificial intelligence model, the corresponding optimal parameter combination between the heat dissipation fans under different power consumption modes of the electronic device is generated;

[0026] Step S50, when the electronic device is actually applied, according to the current power consumption mode of the electronic device, the optimal parameter combination between the heat dissipation fans is used to cool the electronic device.

[0027] In this embodiment, the relatively closed space refers to those spaces that have certain physical enclosure. These spaces usually have limited air flow paths and mainly exchange heat through designated ventilation channels (such as fans, vents, etc.). The environmental conditions in such spaces are relatively stable, but due to the space limitations and the fixedness of the air flow path, the heat distribution and transmission are relatively complex.

[0028] For example, the electronic equipment cabin on a car, an airplane or a ship usually relies on the vehicle-mounted fans and ventilation systems for heat dissipation; the PLC (Programmable Automation Controller) cabinet dissipates heat through the fans inside the cabinet; the personal computer case or the notebook computer has a compact internal structure and relies on the built-in fans for heat dissipation.

[0029] Electronic devices refer to electronic equipment or components that operate in a relatively closed space and generate heat under different workloads. The power consumption and heat generation of these devices usually change with the change of their working mode and load level.

[0030] For example, server CPUs (Central Processing Unit) and personal computer CPUs generate a large amount of heat under high load; GPUs (Graphics Processing Unit) are mainly used for graphics rendering and computing tasks, and usually generate more heat under high load; server power supplies and industrial control power supplies generate heat under high voltage and high current; FPGA (Field Programmable Gate Array) and ASIC (Application Specific Integrated Circuit) chips are used for specific computing tasks and generate significant heat under high load.

[0031] A cooling fan is a device that uses rotating blades to generate airflow, thereby transferring heat from a heat source to the surrounding environment. Installing a cooling fan in a relatively enclosed space enhances airflow and improves heat dissipation efficiency. The number of rotations per minute of a cooling fan directly affects airflow speed and cooling effect. Multiple cooling fans are typically installed in a relatively enclosed space to ensure uniform airflow. The specific number and location of cooling fans can be determined based on the size of the space, the layout of electronic components, and the distribution of heat sources. Typically, cooling fans can be distributed on the top, sides, or bottom of electronic components to ensure air circulation.

[0032] For example, personal computer fans include CPU fans, case fans, and graphics card fans, with multiple types of fans used in combination to optimize heat dissipation; industrial control equipment fans typically use small, high-efficiency fans to fit into compact equipment layouts; and automotive electronic equipment fans are generally high-temperature resistant and vibration-resistant, suitable for use in automotive environments.

[0033] Electronic devices and cooling fans in relatively enclosed spaces can be electrically connected to corresponding control devices to form a corresponding cooling system, and the control devices are responsible for controlling the operation of electronic devices and cooling fans.

[0034] As described in step S10, the electronic devices are controlled to operate in different power consumption modes. For example, these modes may include low-power mode, standard mode, and high-performance mode, to simulate different working scenarios in actual use.

[0035] In low-power mode, electronic devices consume less power and are typically used in standby mode or light-load operation, such as when a laptop is in standby or browsing the web. Standard mode is the normal operating mode of electronic devices, with moderate power consumption, suitable for most daily operations, such as when a laptop is processing documents or watching videos. In high-performance mode, electronic devices consume more power and are typically used for high-load tasks, such as video editing, 3D rendering, or gaming.

[0036] Electronic devices can be switched to different power consumption modes through hardware settings or software control. For example, different power consumption modes can be switched through BIOS settings or power management options in the operating system.

[0037] Furthermore, in each power consumption mode, multiple cooling fans are controlled to operate with different combinations of speed and direction parameters. These parameter combinations can be tested using multiple pre-set combinations.

[0038] In each power consumption mode, the rotation speed of the cooling fans is controlled. The rotation speed can be adjusted by a PWM (Pulse Width Modulation) signal, usually in units of RPM (Revolutions Per Minute). For example, in low power consumption mode, the fan rotation speed can be set to a lower value (such as 1000 RPM), while in high performance mode, the fan rotation speed can be set to a higher value (such as 3000 RPM).

[0039] The rotation direction of the cooling fans usually has two modes: forward rotation and reverse rotation. Different rotation direction modes can affect the direction and speed of air flow.

[0040] In each power consumption mode, test different rotation speed and rotation direction parameter combinations of multiple cooling fans. For example, the following combinations can be tested:

[0041] Combination 1: All fans rotate forward at low speed;

[0042] Combination 2: All fans rotate forward at high speed;

[0043] Combination 3: Part of the fans rotate forward at low speed, part of the fans rotate reverse at high speed;

[0044] Combination 4: Part of the fans rotate reverse at medium speed, part of the fans do not operate.

[0045] Among them, a special controller or software can be used to control the rotation speed and direction of the cooling fans. For example, an intelligent fan controller (such as NCT6798D, Nuvoton, etc.) can be used to achieve precise rotation speed and direction control.

[0046] By controlling the operation of the electronic device in different power consumption modes, and matching different rotation speed and rotation direction parameter combinations of multiple cooling fans, various cooling requirements in actual applications can be simulated. This step provides a basis for subsequent temperature and wind noise data collection, and provides rich data support for the training of artificial intelligence models.

[0047] As described in step S20, when multiple cooling fans operate with different parameter combinations, temperature sensors are used to collect temperature data of the electronic device. These temperature data can include local temperature and overall average temperature of key components.

[0048] At the same time, wind noise data outside the relatively closed space is collected, which mainly refers to the noise generated by the cooling fans during operation, and its impact on users or the surrounding environment. Among them, a sound level meter or digital noise sensor can be used to measure the noise level when the fan is running.

[0049] In order to accurately collect these temperature data, temperature sensors can be installed at key positions of the electronic device. These sensors can be thermistors, thermocouples, or temperature monitoring circuits integrated on chips, etc.

[0050] The control electronics sequentially runs each power consumption mode, and in each power consumption mode, controls the multiple cooling fans to sequentially run various parameter combinations, records the temperature data of the electronic device collected under different parameter combinations, and the wind noise data outside the relatively closed space.

[0051] Through this step, a large amount of temperature data and wind noise data of the electronic device and the cooling fan under different working conditions can be obtained, which will be used to train the artificial intelligence model to learn the relationship between the parameter combination of the cooling fan and the temperature and noise, so as to find the optimal parameter combination that achieves the corresponding cooling effect while minimizing the noise.

[0052] As described in step S30, the operating parameters of the electronic device under different power consumption modes, and the various parameter combinations, temperature data and wind noise data of the cooling fan under each power consumption mode of the electronic device, can be collected as training data related to the artificial intelligence model.

[0053] Before inputting the relevant collected data into the artificial intelligence model, the collected data can be preprocessed to ensure the quality and consistency of the data. The preprocessing steps can include: data cleaning to remove outliers (for example, if the data collected by a certain temperature sensor at a certain time deviates significantly from the normal range, these data need to be removed or corrected), data normalization processing (so that the model can better process data of different dimensions), data segmentation (dividing the data set into training set, validation set and test set).

[0054] The selection of the artificial intelligence model can use a basic network model suitable for processing complex relationship data, such as multilayer perceptron, convolutional neural network, recurrent neural network, etc.

[0055] Based on the causal data division, the model is constructed, wherein the power consumption mode parameters of the electronic device, the rotation speed and direction parameters of the cooling fan are the cause data; the temperature data and the wind noise data are the effect data. Therefore, the input layer of the divided model contains the power consumption mode parameters of the electronic device, the rotation speed and direction parameters of the cooling fan; the hidden layer of the model contains multiple neurons for learning complex relationships; the output layer of the model contains the temperature data and the wind noise data, and the corresponding optimal parameter combination of the cooling fan.

[0056] Optionally, the training target of the model is set to optimize the wind noise data under the premise of meeting the cooling target of the electronic device under different power consumption modes, to obtain the optimal parameter combination of the rotation speed and direction of the multiple cooling fans.

[0057] Wherein, the temperature target: the temperature of the electronic device should be kept within a safe range, usually a set threshold (such as the threshold value can be 75-85℃ in high power mode, the threshold value can be 55-65℃ in medium power mode, and the threshold value can be 35-45℃ in low power mode).

[0058] Wherein, the wind noise target: under the premise of meeting the cooling target, the wind noise data is as low as possible.

[0059] The final optimization target is to find the fan speed and steering combination that minimizes the wind noise under the premise of meeting the temperature target.

[0060] Based on this, a multi-objective loss function is defined:

[0061] Loss=α×M1+(1-α)×M2;

[0062] Wherein, α is a hyperparameter that balances the temperature and wind noise weights, which needs to be adjusted through the validation set; M1 is the temperature loss, and M2 is the wind noise loss; both the temperature loss and the wind noise loss can use the mean square error (MSE) to calculate the difference between the predicted value and the actual value.

[0063] The preprocessed training set data is input into the selected model for multiple iterations of training. In the forward propagation process of model training, the input data is calculated through the model to obtain the predicted value. According to the predicted value and the actual value, the loss (such as mean square error, cross-entropy loss) is calculated. Then the gradient of the loss function to the model parameters is calculated through the back propagation algorithm to adjust the model parameters. Finally, the model parameters are updated using the optimization algorithm (such as SGD, Adam) to minimize the loss function.

[0064] Wherein, the model hyperparameter tuning can try different speed and steering combinations within the predefined fan parameter range, calculate the corresponding temperature and wind noise predicted values, and select the optimal combination; or, randomly select fan parameter combinations, calculate the predicted values, and select the optimal combination; or, use the Bayesian optimization method to gradually search for the optimal fan parameter combination.

[0065] Further, the performance of the model is evaluated using the validation set data, and the evaluation indicators can be mean square error, root mean square error (RMSE), R 2 Score, etc. The performance gap between the training set and the validation set is used to determine whether the model is overfitting or underfitting. If the training set performance is good but the validation set performance is poor, it indicates that the model is overfitting; if the performance of the training set and the validation set is poor, it indicates that the model is underfitting.

[0066] Wherein, a regularization term (such as L1, L2 regularization) can be added to prevent overfitting; or, the training is stopped in advance when the validation set performance no longer improves, to prevent overfitting.

[0067] Finally, the model is evaluated using the test set data to ensure that it has good generalization ability on unseen data, and the performance indicators of the model on the test set are recorded.

[0068] In this way, through the training of the artificial intelligence model, the optimization of the parameter combination of the cooling fan in different power consumption modes is realized. This step not only improves the cooling efficiency, but also reduces the wind noise and improves the user experience. At the same time, the introduction of the artificial intelligence model makes the entire system have the characteristics of self-adaptation and intelligence, which can better cope with complex working environments and dynamic changes in demand.

[0069] It should be understood that if the deployment environment related hardware conditions of the cooling system are sufficient to support model data collection and training, the model can be trained and deployed directly on the control device of the cooling system; if the deployment environment related hardware conditions of the cooling system are insufficient to support model data collection and training, model data collection and training can be performed during the production design process before the relevant product is shipped, and finally the trained model is deployed to the control device of the cooling system.

[0070] As described in step S40, the trained model is used to predict the optimal parameter combination of the cooling fan, that is, after predicting the optimal temperature data and wind noise data (i.e. the lowest wind noise that can be achieved under the premise that the temperature data meets the cooling target of the corresponding power consumption mode of the electronic device) that can be achieved by the electronic device in different power consumption modes, the optimal parameter combination of the speed and direction of the multiple cooling fans that can achieve optimal cooling and wind noise control is queried in reverse.

[0071] In model application, the optimal parameter combination with the smallest loss can be selected by comparing the comprehensive loss of each parameter combination. Ensure that the selected optimal parameter combination has the smallest wind noise under the premise of meeting the temperature target.

[0072] Optionally, for each power consumption mode, a list containing the optimal parameter combination is generated. Each entry in the list can include: power consumption mode, speed of each cooling fan, direction of each cooling fan, predicted temperature, and predicted wind noise.

[0073] Then, the generated optimal parameter combination list is stored in a database or configuration file for actual application.

[0074] For example, the generated optimal parameter combination is shown in the following table (I):

[0075] Table (I):

[0076]

[0077] In addition, in the low-power mode, the rotation speed of some fans can also be reduced or some fans can be stopped to save energy and reduce wind noise. By precisely controlling the rotation speed and direction of each fan, the wind noise can be minimized while ensuring the heat dissipation effect.

[0078] It should be noted that different rotation directions and speeds of the cooling fans can occur, mainly to optimize the heat dissipation effect and minimize the wind noise as much as possible. In some complex cooling systems, different rotation directions of the fans can generate multi-directional air flow, which helps to more evenly distribute heat; different rotation directions of the fans can generate vortex effect, increasing air turbulence, which helps to more effectively carry away heat on the surface of the device, especially in high heat load areas.

[0079] If all fans run at the same speed and direction, resonance can occur, causing noise to superimpose and increase the overall wind noise; by adjusting the rotation speed and direction of different fans, the resonance effect can be reduced, thereby reducing the wind noise. Of course, different rotation speeds and directions of the fans produce different sound waveforms, and these waveforms mixed together can reduce the noise of a single frequency, making the overall sound softer.

[0080] This also explains why, under the premise that the temperature data meets the cooling target, reducing the rotation speed as much as possible does not necessarily achieve the effect of reducing wind noise. This is because the relationship between wind noise and fan speed is not simply linear, but also involves the design, material, structure of the fan blades, and the fluid mechanics characteristics of air flow. Even if the rotation speed is the same, different designs and configurations of fans can produce significantly different wind noise. The fan at a certain speed can also produce resonance, causing vibration and noise amplification, and simply reducing the speed may not avoid these resonance points, but may make the fan perform worse in some speed range. By finely adjusting the rotation speed and direction of different cooling fans, the air flow can be optimized, and turbulence and noise can be reduced.

[0081] That is, by reasonably configuring the rotation speed and direction of each fan, the noise cancellation effect can be achieved, thereby reducing the overall noise level. Different rotation speeds and directions of the fans produce different sound waveforms, and these waveforms can produce interference effects when mixed, causing some frequencies of noise to be weakened, thereby reducing the overall noise level.

[0082] Because the generation of wind noise has certain complexity, it is affected by factors such as the characteristics of the heat dissipation fan itself, the operation condition, and the spatial layout of the relatively closed space, and it is difficult to exhaustively calculate various wind noise generation conditions by manpower alone. By applying an artificial intelligence model, the influence of parameter combinations of various heat dissipation fans in a specific relatively closed space on wind noise is explored, without the need to deeply understand the physical mechanism of wind noise generation in a specific relatively closed space. Only the parameter combination that minimizes wind noise needs to be found, thereby simplifying the complexity of the problem. That is, through the artificial intelligence model, the optimal combination can be quickly screened from a large number of possible parameter combinations without the need for detailed physical simulation of each combination.

[0083] Of course, this artificial intelligence model can be applied to the regulation method of heat dissipation fans in various relatively closed spaces. Only by collecting relevant data for model training and updating for a specific relatively closed space based on the training model can the model be trained and updated in different space environments through a data-driven approach, thereby achieving balanced control of temperature and wind noise.

[0084] As described in step S50, when the electronic device is actually applied, the optimal parameter combination corresponding to the heat dissipation fans is used according to the current power consumption mode of the electronic device to perform cooling processing on the electronic device.

[0085] Optionally, the power consumption of the electronic device is monitored in real time, and the current power consumption mode (such as a low power consumption mode, a medium power consumption mode, a high power consumption mode, etc.) is determined according to the power consumption.

[0086] According to the current monitored power consumption mode, the corresponding optimal parameter combination is called from the database. The working of each heat dissipation fan is controlled according to the called parameter combination to achieve the best cooling effect.

[0087] In this way, while ensuring that the electronic device can be effectively cooled in different power consumption modes, the wind noise generated by the heat dissipation fan can be reduced as much as possible.

[0088] In an embodiment, based on artificial intelligence model learning and optimization, the rotation speed and direction of multiple heat dissipation fans are dynamically adjusted according to the actual power consumption mode of the electronic device, the optimal fan parameter combination is selected, intelligent heat dissipation management of the electronic device in different power consumption modes is achieved, and on the premise of ensuring the heat dissipation effect, the wind noise data is optimized as much as possible, the operating noise is reduced, the best balance between heat dissipation effect and noise control is achieved, and the user's use experience is improved. It is suitable for heat dissipation and noise reduction processing of electronic devices in various relatively closed spaces (such as data centers, vehicle-mounted electronics, personal computers, etc.), and has wide application prospects.

[0089] In an embodiment, on the basis of the above-mentioned embodiment, an electrically controlled valve is arranged at the air guide opening of the relatively closed space, and the opening and closing of the air guide opening can be controlled based on the electrically controlled valve.

[0090] When the multiple heat dissipation fans are operated in different parameter combinations, the opening and closing of the air guide opening are adjusted, and the temperature data of the electronic device and the wind noise data outside the relatively closed space are collected.

[0091] The collected data are input into an artificial intelligence model for training, so that the artificial intelligence model learns the influence of different parameter combinations of the heat dissipation fans and different opening and closing of the air guide opening on the temperature data and the wind noise data under different power consumption modes of the electronic device. The training result of the artificial intelligence model includes the corresponding relationship between the optimal parameter combination of the rotation speed and direction of the heat dissipation fans and the opening and closing of the air guide opening.

[0092] When the electronic device is actually applied, the corresponding optimal parameter combination of the heat dissipation fans is used according to the current power consumption mode of the electronic device, and the air guide opening is adjusted to the corresponding opening and closing state, so as to cool the electronic device.

[0093] In the embodiment, an electrically controlled valve is arranged at the air guide opening of the relatively closed space. The electrically controlled valve can control the opening and closing of the air guide opening, so as to adjust the path and speed of air flow. Based on the electrically controlled valve, multiple opening and closing states of the air guide opening can be adjusted, such as completely closed, partially opened, completely opened, and opening direction, etc.

[0094] Optionally, in the process of collecting the training data of the artificial intelligence model, the opening and closing of the air guide opening are adjusted at the same time when the multiple heat dissipation fans are operated in different parameter combinations.

[0095] Optionally, in each power consumption mode, in addition to the different rotation speed and direction combinations of the multiple heat dissipation fans, the different opening and closing of the air guide opening are also adjusted. For example, the air guide opening can be set to 25% opening, 50% opening, 75% opening, and completely opening, and the opening direction can be set to forward, backward, left, right, or center, etc.

[0096] Then, the temperature data of the electronic device and the wind noise data outside the relatively closed space are collected under each parameter combination of the heat dissipation fans and the opening and closing of the air guide opening.

[0097] All the collected data are input into the artificial intelligence model for training. The training target is to optimize the wind noise data and find the best matching between the parameter combination of the heat dissipation fans and the opening and closing of the air guide opening, on the premise that the temperature of the electronic device meets the cooling target under different power consumption modes.

[0098] The goal of training the model is to minimize the wind noise level while ensuring that the electronic device temperature is controlled within a safe range. This can be achieved through multi-objective optimization algorithms such as Pareto optimization.

[0099] Then, according to the training results of the model, the optimal parameter combination of the heat dissipation fan parameter combination and the guide air outlet opening and closing condition under each power consumption mode is generated. That is, the model will output the best combination of the speed and direction of the heat dissipation fan and the opening and closing condition of the guide air outlet under each power consumption mode. A correspondence table of power consumption mode and heat dissipation fan parameter combination and guide air outlet opening and closing condition is established to quickly call in actual application.

[0100] When the electronic device is actually running, the pre-calculated optimal parameter combination is used according to its current power consumption mode, and the opening and closing condition of the guide air outlet is adjusted accordingly to achieve the best cooling effect and the lowest noise level.

[0101] It should be noted that the heat generated by the electronic device under different power output modes is quite different. For example, in some low load conditions, excessive air flow may not be necessary and will increase wind noise and energy consumption. Therefore, in low power consumption mode, a small amount of cooling air can effectively dissipate heat, and appropriate reduction of the opening and closing of the guide air outlet can reduce wind noise and energy consumption.

[0102] In actual application, wind noise and cooling effect need to be balanced. Excessive opening of the guide air outlet may cause excessive wind noise, especially when the fan is running at high speed. By controlling the opening and closing of the guide air outlet, the wind noise can be reduced as much as possible while meeting the cooling demand, improving the user experience.

[0103] Through the above expansion scheme, the system can not only control the operation of the heat dissipation fan more finely, but also further optimize the air flow path by adjusting the opening and closing of the guide air outlet, achieving better cooling effect and lower noise level. This will significantly improve the performance of electronic devices and user experience.

[0104] In an embodiment, on the basis of the above embodiment, the artificial intelligence model further analyzes the influence of the running time of the speed increment value of each heat dissipation fan under each parameter combination on the wind noise data rising curve, obtains the corresponding speed instantaneous increment value of each optimal parameter combination, and the interval control time length of the speed instantaneous increment value; wherein, under the premise that the slope of the wind noise data rising curve meets the preset value, the maximum speed instantaneous increment value is selected; the interval control time length is related to the jump time length of the wind noise data;

[0105] When the electronic device is actually applied, according to the current power consumption mode of the electronic device, the corresponding optimal parameter combination of the heat dissipation fan is used in the process of increasing the rotation speed of each heat dissipation fan by an interval control time length based on the instantaneous increase value of the rotation speed, and then the rotation speed of each heat dissipation fan is reduced to the original value, so as to wait for the arrival of the next interval control time length.

[0106] The interval time length of the two interval control time lengths is related to the recovery time length of the wind noise data after the speed reduction.

[0107] In some high power consumption modes in the embodiment, the heat dissipation demand will increase sharply, and the fan rotation speed may need to be instantaneously increased to quickly cool down. The instantaneous increase value of the rotation speed will cause the wind noise data to rapidly rise. In this case, the influence of the running time of the fan rotation speed after the increase value on the wind noise data rising curve can be further analyzed by the artificial intelligence model under different parameter combinations, so as to determine the trend of the wind noise data.

[0108] Then, under the premise that the slope of the wind noise data rising curve meets the preset value (that is, the rate of wind noise data rising is within an acceptable range), the maximum instantaneous increase value of the rotation speed is selected. In this way, the heat dissipation efficiency can be maximized, while the rapid rise of the wind noise data is avoided.

[0109] The time required for the wind noise data to jump from the value before the increase of the rotation speed to the noise fluctuation extreme value acceptable to the human ear (that is, once the extreme value is exceeded, the change of the noise can be obviously felt) is called the jump time length. When the noise level suddenly rises above a certain threshold, the human ear will obviously feel the change of the noise, which may cause discomfort or distraction. The noise fluctuation extreme value refers to the maximum fluctuation range of the noise level that can be accepted without causing obvious discomfort to the user.

[0110] The interval control time length is related to the jump time length of the wind noise data, and needs to ensure that the interval control time length ends before the wind noise data rises to the noise fluctuation extreme value. The interval control time length can be set to be less than the jump time length of the wind noise data.

[0111] According to the analysis result of the artificial intelligence model, the instantaneous increase value of the rotation speed corresponding to each fan rotation speed in each optimal parameter combination is obtained. These values are the optimized parameters according to the power consumption mode and the wind noise data rising curve.

[0112] When the electronic device is actually applied, according to the current power consumption mode, the optimal parameter combination of the heat dissipation fan is used. In the high power consumption mode requiring rapid cooling, according to the instantaneous increase value of the rotation speed, the rotation speed of each heat dissipation fan is increased intermittently. After the rotation speed is increased, the fan needs to run at high speed for a period of time (that is, the interval control time length) to complete the heat dissipation task. After the interval control time length ends, the rotation speed of each heat dissipation fan is reduced to the original value to reduce the wind noise data and restore to a lower noise level.

[0113] After the speed drops back to the original value, the wind noise data needs some time to recover to the normal level. The interval duration between the two interval control durations is related to the recovery duration of the wind noise data. For example, if the recovery duration of the wind noise data is 15 seconds, the interval duration can be set to 15 seconds, ensuring that the wind noise data has recovered to the normal level before the next speed increase.

[0114] On the basis of an embodiment, each optimal parameter combination is equipped with a corresponding speed instantaneous increment, and when necessary, the speed instantaneous increment can quickly increase the heat dissipation efficiency, ensuring that the temperature of the electronic device is within a safe range. At the same time, by dropping back to the original speed after the interval control duration ends, long-term high-speed operation is avoided, and the sustained rise of the wind noise data is reduced. Moreover, the interval duration is related to the recovery duration of the wind noise data, ensuring that the next speed increase is performed only after the wind noise data recovers to the normal level, thereby achieving smooth noise control.

[0115] In this way, the speed increment of the fan, the interval control duration, and the interval duration can be dynamically adjusted according to the needs of different power consumption modes, achieving intelligent heat dissipation management.

[0116] Actual application scenario example: The electronic device operates in high-performance mode, and the power consumption increases sharply, causing the temperature to rise rapidly. The control process starts the optimal parameter combination control according to the current power consumption mode to control multiple cooling fans for cooling. On this basis, the speed of the fan is intermittently increased based on the speed instantaneous increment, ensuring rapid cooling while avoiding causing a large fluctuation in the wind noise data.

[0117] In an embodiment, by further analyzing the influence of the operation duration of the fan speed increment on the wind noise data rise curve, the dynamic control strategy of the cooling fan is optimized. By setting the speed instantaneous increment, the interval control duration, and the interval duration, the rapid response to the heat dissipation demand in the high-power consumption mode is achieved while effectively controlling the rise and recovery of the wind noise data. This method not only improves the intelligent level of the heat dissipation system, but also further optimizes the user experience.

[0118] In an embodiment, on the basis of the above-mentioned embodiment, after the step of using the corresponding optimal parameter combination between the cooling fans according to the current power consumption mode of the electronic device to cool the electronic device when the electronic device is actually applied, the method further comprises:

[0119] After the cooling processing operation is executed for a preset duration, if it is detected that the current temperature of the electronic device exceeds the warning temperature, the speed of the cooling fan is gradually increased until the current temperature drops below the warning temperature;

[0120] The rotation speed of each stage of the cooling fan, the operation of the electronic device, the temperature change data, and the optimal parameter combination used in the current power consumption mode are fed back to the artificial intelligence model to update the artificial intelligence model.

[0121] The optimal parameter combination is regenerated based on the updated artificial intelligence model.

[0122] In this embodiment, when the electronic device is actually applied, the system uses the optimal parameter combination between the corresponding cooling fans to perform cooling processing according to the current power consumption mode. This operation needs to be performed for a period of time (i.e., a "preset time length") to ensure stable cooling effect.

[0123] The preset time length can be set according to actual cooling requirements, such as 30 seconds to 1 minute.

[0124] Optionally, after the cooling processing operation is performed for the preset time length, the system continuously monitors the current temperature of the electronic device and determines whether the current temperature exceeds a warning temperature.

[0125] The warning temperature is a pre-set temperature threshold for determining whether the electronic device is in an overheating state. The setting of the warning temperature needs to be determined according to the specifications of the electronic device, the characteristics of the working load, and the temperature range for safe operation.

[0126] Optionally, if it is detected that the current temperature of the electronic device exceeds the warning temperature, it means that the initial cooling processing does not completely meet the cooling requirements, and therefore the cooling capacity needs to be further enhanced.

[0127] Optionally, when the temperature exceeds the warning temperature, the system gradually increases the rotation speed of the cooling fan. Here, "gradually" means that the increase in the rotation speed of the fan is performed in stages, rather than a one-time large increase. In this way, the impact of wind noise and unnecessary energy consumption caused by a sudden increase in the rotation speed of the fan can be avoided.

[0128] Optionally, the magnitude and frequency of the increase in the rotation speed can be optimized according to the balance between the cooling requirements of the system and the control of wind noise. For example, the magnitude of the increase in the rotation speed can be 5% or 10%, and after each increase, the next adjustment is performed after a period of time (such as 10 seconds).

[0129] The goal of gradually increasing the rotation speed of the fan is to reduce the current temperature of the electronic device to below the warning temperature. Once the temperature of the electronic device is reduced to below the warning temperature, the system stops further increasing the rotation speed of the fan and maintains the current rotation speed to maintain temperature stability.

[0130] During the process of increasing the rotation speed of the fan when the temperature exceeds the warning temperature, the system records the rotation speed of the fan at each stage. These rotation speed data reflect the running state of the fan under different cooling requirements.

[0131] Optionally, the fan's stage speed is associated with the following data:

[0132] Operation status of the electronic device: can include the current power consumption mode, load status, running time, etc.

[0133] Temperature change data: can include the magnitude of temperature exceeding the warning temperature, the speed of temperature drop, the final stable temperature value, etc.

[0134] Optimal parameter combination used in the current power consumption mode: records the optimal fan parameter combination used in the cooling process in the current power consumption mode.

[0135] The above-mentioned associated data is fed back to the artificial intelligence model. These data provide the model with dynamic cooling effect and fan adjustment behavior in actual operation, which helps the model further optimize its learning and prediction ability.

[0136] The artificial intelligence model is updated and trained based on the latest feedback data. By analyzing the relationship between fan speed, temperature change and operation status, the model can learn more cooling strategies, especially the response mode when the temperature exceeds the warning temperature. The updated model aims to further optimize the dynamic adjustment strategy of fan speed while meeting the cooling demand, optimizing the balance between cooling and wind noise.

[0137] Based on the updated artificial intelligence model, the optimal fan parameter combination of the electronic device in different power consumption modes is regenerated. The new parameter combination will more accurately match the actual cooling demand and optimize the dynamic regulation strategy of the fan.

[0138] In future practical applications, the system will use the updated optimal parameter combination for cooling treatment to ensure that the electronic device can obtain the best cooling effect in different working states.

[0139] In this way, through the temperature warning mechanism and dynamic fan speed adjustment, the dynamic nature and response ability of the cooling regulation are enhanced. At the same time, by feeding real-time data to the artificial intelligence model, the updated model can more intelligently generate optimal parameter combinations to optimize cooling effect and wind noise control. This scheme not only improves the reliability and intelligence level of the cooling system, but also provides strong support for the stable operation of electronic devices in complex working environments.

[0140] In an embodiment, on the basis of the above-mentioned embodiment, after the step of using the corresponding optimal parameter combination between the cooling fans to cool the electronic device according to the current power consumption mode of the electronic device when the electronic device is actually applied, it further includes:

[0141] After performing the cooling treatment operation and controlling the current temperature of the electronic device below the pre-warning temperature, the current temperature of the electronic device is continuously monitored and the duration of maintaining the current rotation speed is recorded;

[0142] If the current temperature is monitored to show a temperature rising trend, the rotation speed of the cooling fan is gradually increased until the temperature rising trend is suppressed and the current temperature is controlled below the pre-warning temperature;

[0143] The rotation speed and the duration of maintaining at each stage of the cooling fan are associated with the operation condition of the electronic device, the temperature change data, and the optimal parameter combination used under the current power consumption mode, and are fed back to the artificial intelligence model to update the artificial intelligence model;

[0144] Based on the updated artificial intelligence model, the optimal parameter combination of the time-sharing regulation strategy with multiple rotation speeds is generated.

[0145] In the embodiment, when the electronic device is actually applied, the system performs cooling treatment using the corresponding optimal parameter combination of the fan according to the current power consumption mode, and ensures that the current temperature of the electronic device is controlled below the pre-warning temperature.

[0146] After the cooling treatment operation is performed, the system continuously monitors the current temperature of the electronic device so as to timely find any temperature change trend. At the same time, the duration of maintaining the current rotation speed of the fan, i.e. the time that the fan continuously runs at a certain rotation speed, is recorded, which helps to analyze the stability and continuity of the cooling effect at a certain rotation speed.

[0147] If the current temperature of the electronic device is monitored to show a temperature rising trend, i.e. the temperature continuously rises in a period of time, it indicates that the current cooling effect may be insufficient to cope with the current cooling demand.

[0148] In order to suppress the temperature rising trend, the system gradually increases the rotation speed of the cooling fan. This gradual increase can avoid sudden increase of wind noise and energy consumption, while effectively enhancing the cooling capacity. The rotation speed is adjusted until the temperature rising trend is suppressed and the current temperature is controlled below the pre-warning temperature again.

[0149] Among them, the rotation speed of the fan at each stage and the corresponding duration of maintaining are recorded, and these data are associated with the following information:

[0150] Operation condition of the electronic device: which can include power consumption mode, load condition, running time, etc.;

[0151] Temperature change data: which can record the trend of temperature change, temperature rising rate, temperature falling rate, etc.;

[0152] Optimal parameter combination used under the current power consumption mode: which is the fan parameter combination used under the current power consumption mode of the electronic device, i.e. the optimal parameter combination recommended by the previous artificial intelligence model.

[0153] The collected data is fed back to the artificial intelligence model for further training and optimization. Through learning from these real-time data, the artificial intelligence model optimizes its prediction ability of temperature change trends and improves the fan speed regulation strategy to more effectively cope with temperature fluctuations.

[0154] At this stage, the artificial intelligence model has received feedback data from actual operation, including the duration of fan at different speeds, the operation of electronic devices, temperature change data, and the optimal parameter combination used at the time. These data are used as the training set of the model to help the model learn how to more effectively regulate fan speed under different conditions to cope with temperature changes.

[0155] The training goal of the model at this stage is to learn how to dynamically adjust the fan speed under different time and temperature conditions to achieve the best heat dissipation effect and the lowest wind noise level. This involves predicting temperature change trends and making adjustments to fan speed in advance accordingly.

[0156] Based on the trained model, a time-division, multi-segment speed regulation strategy can be generated. This strategy takes into account time series and temperature changes, dividing the entire operation period into multiple time segments and setting different fan speeds in each time segment.

[0157] According to the usage patterns and historical data of electronic devices, the time is divided into different segments. In each time segment, according to the model's prediction of temperature change trends, the corresponding fan speed is set. If the predicted temperature will rise, the speed is increased in advance; if the predicted temperature will fall, the speed is appropriately reduced to save energy and reduce noise.

[0158] Finally, based on the learning results of the artificial intelligence model, an optimal parameter combination containing multiple time segments and corresponding fan speeds is generated. This combination needs to meet the following conditions:

[0159] (1) Temperature control: Ensure that the temperature of the electronic device remains within a safe range and does not exceed the warning temperature in all time segments;

[0160] (2) Energy consumption and noise optimization: On the premise of ensuring temperature control, try to reduce the energy consumption and noise generated by the fan to improve user experience.

[0161] The generated optimal parameter combination will be implemented in actual application and its effect will be continuously monitored. By collecting actual operation data, it is evaluated whether the temperature control meets the expectations and whether the wind noise and energy consumption are optimized. According to the evaluation results, the model parameters can be further adjusted to iteratively optimize the regulation strategy.

[0162] In this way, the artificial intelligence model can learn and adapt to the heat dissipation needs of the electronic device under different working conditions, generating a dynamic and time-sharing fan speed regulation strategy, thereby achieving more intelligent and efficient heat dissipation management.

[0163] Based on the updated artificial intelligence model, the optimal parameter combination of the time-sharing regulation strategy with multiple speed segments is generated. According to different time stages and temperature change trends, different fan speeds are set to achieve more refined temperature control and energy management.

[0164] In future practical applications, the system will adopt the new optimal parameter combination, adjust the fan speed in stages according to the time sequence and temperature change, to keep the temperature of the electronic device within a safe range, while minimizing wind noise and energy consumption.

[0165] In an embodiment, by continuously monitoring the temperature change of the electronic device and dynamically adjusting the fan speed according to the temperature trend, more intelligent and refined heat dissipation management is achieved. By feeding back the actual running data to the artificial intelligence model, the fan regulation strategy is continuously optimized, so that the system can maintain the best heat dissipation effect and the lowest wind noise level under different working conditions, thereby improving the reliability and user experience of the electronic device.

[0166] In an embodiment, based on the above embodiment, if the current temperature is found to be showing a rising trend, the speed of the heat dissipation fan is gradually increased until the rising trend is suppressed and the current temperature is controlled below the warning temperature, and then the steps further include:

[0167] If the current temperature is found to be lower than the temperature value when the rising trend is shown, the speed of the heat dissipation fan is reduced;

[0168] If the current temperature does not show a rising trend after the speed of the heat dissipation fan is reduced, the current speed is maintained;

[0169] If the current temperature shows a rising trend after the speed of the heat dissipation fan is reduced, the previous speed is restored.

[0170] In this embodiment, when the current temperature of the electronic device is found to be showing a rising trend, the system gradually increases the speed of the heat dissipation fan until the rising trend is suppressed and the temperature is controlled below the warning temperature.

[0171] If the current temperature is found to be lower than the temperature value when the rising trend is shown after increasing the speed of the fan, the system gradually reduces the speed of the fan to save energy and reduce noise.

[0172] After reducing the speed of the fan, the system continues to monitor the change of the temperature to observe whether the temperature starts to rise.

[0173] Optionally, if the temperature does not show a rising trend, the current fan speed is maintained.

[0174] Optionally, if the temperature again shows a rising trend, the previous speed is restored to ensure that the temperature does not exceed the warning range.

[0175] Through this dynamic adjustment of fan speed method, the system can more effectively manage the temperature, while optimizing energy use and user experience.

[0176] Of course, if the speed of the cooling fan is reduced, and the current temperature does not show a rising trend, the current speed is maintained, and the related data of this speed reduction stage can also be fed back to the artificial intelligence model together with the speed of the cooling fan in previous stages, the maintenance time, the operation of the electronic device, the temperature change data and the optimal parameter combination used in the current power consumption mode, to update the artificial intelligence model; based on the updated artificial intelligence model, the optimal parameter combination of the time-sharing control strategy with multiple speed segments is generated.

[0177] This process not only ensures the optimization of fan speed when the temperature does not show a rising trend, but also further improves the intelligent level and efficiency of heat dissipation management of the system through data feedback and model updating. Through continuous optimization, the system can achieve the best heat dissipation effect and wind noise balance management under different operating conditions.

[0178] In an embodiment, on the basis of the above-mentioned embodiment, the control method of the cooling fan in the relatively closed space further comprises:

[0179] When the electronic device is actually applied, if the temperature control and wind noise balance strategy is selected, the optimal parameter combination corresponding to the cooling fan is used according to the current power consumption mode of the electronic device to perform cooling treatment on the electronic device;

[0180] Or, when the electronic device is actually applied, if the cooling priority strategy is selected, the speed of each cooling fan is adjusted in real time according to the current temperature of the electronic device.

[0181] In this embodiment, the system can provide a related setting interface to allow users to select different cooling strategies according to actual needs, including the temperature control and wind noise balance strategy and the cooling priority strategy.

[0182] Under the temperature control and wind noise balance strategy, the goal of the system is to meet the cooling demand of the electronic device while trying to reduce the wind noise generated by the operation of the cooling fan; under the cooling priority strategy, the primary goal of the system is to ensure that the temperature of the electronic device always remains within a safe range, and the optimization of wind noise is in a secondary position.

[0183] Optionally, the current power consumption mode of the electronic device is detected in real time when the electronic device is actually applied.

[0184] Optionally, if the temperature control and wind noise balance strategy is selected, the optimal parameter combination corresponding to the current power consumption mode is called according to the training result of the artificial intelligence model, which can minimize the wind noise while meeting the cooling target. While meeting the cooling demand, the wind noise is optimized as much as possible to improve the user experience.

[0185] Optionally, if the cooling priority strategy is selected, the speed of each cooling fan is dynamically adjusted according to the current temperature. If the temperature is close to or exceeds the safety range, the system will quickly increase the speed of the cooling fan to enhance the cooling effect; if the temperature drops to the safety range, the system can gradually reduce the fan speed to reduce energy consumption and wind noise. By dynamically adjusting the speed of the cooling fan, the temperature of the electronic device is always controlled within the safety range. In this way, the temperature of the electronic device is always within the safety range, providing higher cooling efficiency.

[0186] In addition, an embodiment of the present application also provides a control device, the internal architecture of which can be as shown in Figure 2 The control device includes a processor, a memory, a communication interface and an input interface connected by a system bus. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database is used to store data called by the computer program. The communication interface is used for data communication with an external terminal. The input interface is used to receive signals input by an external device. The computer program is executed by the processor to implement a cooling fan regulation method in a relatively closed space as described in the above embodiments.

[0187] Those skilled in the art can understand that Figure 2 the structure shown in the above embodiments is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the control device to which the scheme of the present application is applied. For example, in some optional embodiments, the control device can also include an output interface (not shown in the figure), and the output interface is also connected to the system bus and is used to output corresponding signals to an external device.

[0188] In addition, the present application also proposes a cooling system, which includes a control device and a plurality of cooling fans; each cooling fan is in communication connection with the control device and is controlled by the control device; the specific structure of the control device is referred to the above embodiments. Since the cooling system adopts all the technical solutions of the above embodiments, it at least has all the technical effects brought by the technical solutions of the above embodiments, which will not be described one by one.

[0189] In addition, the application further provides a computer readable storage medium including a computer program, which, when executed by a processor, implements the steps of the method for regulating the heat dissipation fan in the relatively closed space as described in the above embodiments. It can be understood that the computer readable storage medium in the embodiments can be a volatile readable storage medium or a non-volatile readable storage medium.

[0190] In summary, the method for regulating the heat dissipation fan in the relatively closed space, the control device, the heat dissipation system and the computer readable storage medium provided in the embodiments of the application are based on artificial intelligence model learning and optimization, dynamically adjust the rotation speed and rotation direction of the multiple heat dissipation fans according to the actual power consumption mode of the electronic device, select the optimal fan parameter combination, realize intelligent heat dissipation management of different power consumption modes of the electronic device, and on the premise of ensuring the heat dissipation effect, optimize the wind noise data as much as possible, reduce the operating noise, realize the best balance of heat dissipation effect and noise control, and thus improve the user experience. It is suitable for heat dissipation and noise reduction processing of electronic devices in various relatively closed spaces (such as data centers, vehicle-mounted electronics, personal computers, etc.), and has a wide application prospect.

[0191] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium provided by the application and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM) and the like.

[0192] It should be noted that, in the present document, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises a", "comprising", or "comprises" does not, without further restriction, exclude the existence of additional elements of the process, method, article, or apparatus that comprises the element.

[0193] The preferred embodiments of the present application have been described above with the intent to enable those skilled in the art to make and use it. Various modifications to these embodiments will occur to those skilled in the art and are intended to be encompassed by the present application. Therefore, it is to be understood that, within the scope of the present application, the application can be practiced otherwise than as specifically described. For example, the order of steps can be varied, or some steps can be omitted or adapted; the use of some reagents can be tailored or made redundant, and other suitable terrestrial or extraterrestrial elements shown and described individually can be used in combination. The scope of the present application is, therefore, indicated and limited only by the following claims.

Claims

1. A method for controlling a cooling fan in a relatively enclosed space, characterized in that, include: Control the electronic devices in a relatively enclosed space to operate in different power consumption modes, and in each power consumption mode, control multiple cooling fans to operate with different combinations of parameters such as speed and direction; When multiple cooling fans are operating with different parameter combinations, temperature data of electronic components and wind noise data outside a relatively enclosed space are collected. Relevant collected data is input into an artificial intelligence model for training. This model learns the impact of different parameter combinations among cooling fans on temperature and wind noise data under various power consumption modes of electronic devices. The training objective of the AI ​​model is to optimize wind noise data while ensuring that the temperature data meets the cooling target under different power consumption modes of the electronic device, thereby obtaining the optimal parameter combination for the speed and direction of multiple cooling fans. The AI ​​model also analyzes the impact of the operating time of each cooling fan speed increment under each parameter combination on the wind noise data rise curve, obtaining the instantaneous speed increment corresponding to each optimal parameter combination, as well as the interval adjustment time for the instantaneous speed increment. The largest instantaneous speed increment is selected provided that the slope of the wind noise data rise curve meets a preset value; the interval adjustment time is related to the jump duration of the wind noise data. Based on the training results of the artificial intelligence model, the optimal parameter combination between the cooling fans of electronic devices under different power consumption modes is generated. When electronic devices are actually used, the optimal parameter combination between cooling fans is used to cool the electronic devices according to the current power consumption mode of the electronic devices. In particular, based on the instantaneous increase of the rotation speed, the rotation speed of each cooling fan is increased at intervals for the interval control time, and then the rotation speed of each cooling fan is reduced back to the original value to wait for the next interval control time. The interval between the two interval control times is related to the recovery time of the wind noise data after the speed reduction.

2. The method for controlling a cooling fan in a relatively enclosed space as described in claim 1, characterized in that, An electrically controlled valve is installed at the air vent of the relatively enclosed space, which can control the opening and closing of the air vent. When multiple cooling fans are operating with different parameter combinations, the opening and closing of the air vents are adjusted, and temperature data of electronic components and wind noise data outside the relatively enclosed space are collected. The relevant collected data is input into the artificial intelligence model for training, so that the artificial intelligence model learns the impact of different parameter combinations between cooling fans and different opening and closing states of air vents on temperature data and wind noise data under different power consumption modes of electronic devices; the training results of the artificial intelligence model include the correspondence between the optimal parameter combination of speed and direction of cooling fans and the opening and closing state of air vents. When electronic devices are actually used, the optimal parameter combination between cooling fans is used according to the current power consumption mode of the electronic devices, and the air vents are opened and closed accordingly to cool the electronic devices.

3. The method for controlling a cooling fan in a relatively enclosed space as described in claim 1 or 2, characterized in that, After the step of cooling the electronic device by using the optimal parameter combination between cooling fans according to the current power consumption mode of the electronic device in actual application, the method further includes: After the cooling process has been running for a preset time, if the current temperature of the electronic device is detected to exceed the warning temperature, the speed of the cooling fan will be gradually increased until the current temperature drops below the warning temperature. The speed of the cooling fan at each stage, along with the operation of electronic devices, temperature change data, and the optimal parameter combination used in the current power consumption mode, are fed back to the artificial intelligence model to update the model. The optimal parameter combination is regenerated based on the updated artificial intelligence model.

4. The method for controlling a cooling fan in a relatively enclosed space as described in claim 1 or 2, characterized in that, After the step of cooling the electronic device by using the optimal parameter combination between cooling fans according to the current power consumption mode of the electronic device in actual application, the method further includes: After performing the cooling operation and controlling the current temperature of the electronic components below the warning temperature, the current temperature of the electronic components is continuously monitored and updated, and the duration of the current rotation speed is recorded. If the current temperature is detected to be rising, the speed of the cooling fan will be gradually increased until the rising trend is stopped and the current temperature is kept below the warning temperature. The speed and duration of the cooling fan at each stage, along with the operating status of electronic devices, temperature change data, and the optimal parameter combination used in the current power consumption mode, are fed back to the artificial intelligence model to update the model. Based on the updated artificial intelligence model, the optimal parameter combination for a time-sharing control strategy with multiple speed ranges is generated.

5. The method for controlling a cooling fan in a relatively enclosed space as described in claim 4, characterized in that, The step of gradually increasing the speed of the cooling fan until the rising temperature is detected and the current temperature is kept below the warning temperature, after which the following steps are also included: If the current temperature is detected to be lower than the temperature value when the temperature showed an upward trend, reduce the speed of the cooling fan; If the temperature does not rise after the cooling fan speed is reduced, then maintain the current speed. If the current temperature shows an upward trend after the cooling fan speed is reduced, the previous speed will be restored.

6. The method for controlling a cooling fan in a relatively enclosed space as described in claim 1, characterized in that, The method for controlling the cooling fan in the relatively enclosed space also includes: When electronic devices are used in actual applications, if a temperature control and fan noise balance strategy is selected, then the optimal parameter combination between the cooling fans is used to cool the electronic devices according to the current power consumption mode of the electronic devices. Alternatively, when electronic devices are actually used, if a cooling-first strategy is selected, the speed of each cooling fan is adjusted in real time according to the current temperature of the electronic device.

7. A control device, characterized in that, The control device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When executed by the processor, the computer program implements the steps of the method for regulating a cooling fan in a relatively enclosed space as described in any one of claims 1 to 6.

8. A heat dissipation system, characterized in that, It includes control equipment and multiple cooling fans; each cooling fan establishes a communication connection with the control equipment and is controlled by the control equipment. The control device is the control device as described in claim 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for controlling a cooling fan in a relatively enclosed space as described in any one of claims 1 to 6.

Images