Bidirectional convection enhanced heat dissipation fan control method and control system

Abstract

The application relates to the technical field of fan intelligent control, and provides a bidirectional convection enhanced heat dissipation fan control method and a control system, which comprises the following steps: for each group of heat dissipation working condition characteristic data, controlling a bidirectional convection enhanced heat dissipation fan to execute various operation modes, and recording corresponding heat dissipation effect data; the heat dissipation working condition characteristics include device temperature, device load, environment temperature and environment humidity; the heat dissipation effect data include device temperature drop amplitude within a preset time and fan energy consumption; determining the optimal operation mode corresponding to each group of heat dissipation working condition characteristic data based on the heat dissipation effect data; constructing a decision tree model based on the heat dissipation working condition characteristic data and the corresponding optimal operation mode; determining the optimal operation mode of the device under the current working condition by using the decision tree model; and controlling the bidirectional convection enhanced heat dissipation fan to operate according to the optimal operation mode under the current working condition. The application improves the matching degree of the fan operation control mode and the heat dissipation demand, and balances the energy consumption and the heat dissipation effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fan intelligent control, and in particular to a bidirectional convection enhanced heat dissipation fan control method and control system. BACKGROUND

[0002] In the field of electronic devices, with the continuous improvement of chip performance and the increasing integration of devices, heat dissipation has become a key factor affecting the stability and service life of devices. Bidirectional convection enhanced heat dissipation fans can produce different airflows by rotating clockwise and counterclockwise, which can more effectively improve the heat dissipation efficiency compared with traditional unidirectional fans, and are widely used in fields such as servers, high-performance computers, and industrial control devices.

[0003] At present, the control method of bidirectional convection enhanced heat dissipation fans is mainly based on simple threshold setting or fixed operation mode. The threshold control method only compares the single temperature data collected by the temperature sensor with the preset temperature threshold, and adjusts the fan speed when the temperature exceeds the threshold. The control method of fixed operation mode is that the fan always operates in a predetermined mode during device operation. The existing fan operation control method has low matching degree with heat dissipation demand, resulting in poor heat dissipation effect or energy waste, and the balance between energy consumption and heat dissipation effect cannot be achieved. SUMMARY

[0004] In view of the above technical problems, the purpose of the present application is to provide a bidirectional convection enhanced heat dissipation fan control method and control system, which aims to solve the technical problems of low matching degree between the existing fan operation control method and heat dissipation demand, resulting in poor heat dissipation effect or energy waste, and the balance between energy consumption and heat dissipation effect cannot be achieved.

[0005] In a first aspect, the present application provides a bidirectional convection enhanced heat dissipation fan control method, comprising:

[0006] For each group of heat dissipation working condition characteristic data, the bidirectional convection enhanced heat dissipation fan is controlled to execute various operation modes, and the heat dissipation effect data under various operation modes is recorded; wherein the heat dissipation working condition characteristics include device temperature, device load, environment temperature and environment humidity; the heat dissipation effect data includes the device temperature drop amplitude within a preset time and the fan energy consumption;

[0007] Based on the heat dissipation effect data, the optimal operation mode corresponding to each group of heat dissipation working condition characteristic data is determined;

[0008] Based on the heat dissipation working condition characteristic data and the corresponding optimal operation mode, a decision tree model is constructed; wherein each leaf node of the decision tree corresponds to an optimal operation mode;

[0009] The optimal operation mode of the device under the current working condition is determined by using the decision tree model;

[0010] Control the bidirectional convection enhanced heat dissipation fan to run in the optimal operation mode under the current working condition.

[0011] Further, the step of determining the optimal operation mode corresponding to each set of heat dissipation working condition characteristic data based on the heat dissipation effect data comprises:

[0012] Based on the multi-objective optimization algorithm and the heat dissipation effect data, a Pareto optimal solution search is performed between heat dissipation efficiency and energy consumption, and the mode at the heat dissipation efficiency-energy consumption frontier curve and ranked first in the score is selected as the optimal operation mode under the working condition.

[0013] Further, the construction method of the heat dissipation efficiency-energy consumption frontier curve comprises:

[0014] For a set of heat dissipation working condition characteristic data, the heat dissipation efficiency and energy consumption data corresponding to all operation modes are plotted in a two-dimensional coordinate system to form a scatter plot, wherein the horizontal coordinate represents energy consumption and the vertical coordinate represents heat dissipation efficiency.

[0015] In the scatter plot, identify the data point with the lowest energy consumption at a given heat dissipation efficiency level, and generate a heat dissipation efficiency-energy consumption frontier curve using the data point.

[0016] Further, the score is calculated according to the maximum heat dissipation efficiency of all operation modes, the minimum heat dissipation efficiency of all operation modes, the heat dissipation efficiency of the target operation mode, the weight coefficient of heat dissipation efficiency, the maximum energy consumption of all operation modes, the minimum energy consumption of all operation modes, the energy consumption of the target operation mode, and the weight coefficient of energy consumption.

[0017] Further, the step of constructing a decision tree model based on the heat dissipation working condition characteristic data and the corresponding optimal operation mode comprises:

[0018] S31, calculate the information gain rate of each heat dissipation working condition characteristic, select the heat dissipation working condition characteristic with the maximum information gain rate as the root node, and divide the data set into multiple subsets according to different values of the heat dissipation working condition characteristic with the maximum information gain rate.

[0019] S32, for each subset divided by the root node, repeat step S31, i.e. recalculate the information gain rate of the remaining heat dissipation working condition characteristic on the subset, select the heat dissipation working condition characteristic with the maximum information gain rate for division, and generate new subsets;

[0020] S33, check whether each subset meets the stopping condition, if the stopping condition is met, mark the subset as a leaf node and determine the corresponding optimal operation mode; if not, continue recursion.

[0021] S34, repeating step S32 and step S33 until all subsets meet the stopping condition, and constructing a decision tree model for determining the optimal operation mode.

[0022] Further, the step of determining the optimal operation mode of the device under the current working condition by using the decision tree model comprises:

[0023] obtaining heat dissipation working condition characteristic data of the device under the current working condition;

[0024] determining the optimal operation mode of the device under the current working condition by using the decision tree model based on the heat dissipation working condition characteristic data under the current working condition.

[0025] In a second aspect, the embodiments of the present application provide a bidirectional convection enhanced heat dissipation fan control system, which comprises:

[0026] a first control module configured to control the bidirectional convection enhanced heat dissipation fan to perform various operation modes for each set of heat dissipation working condition characteristic data and record heat dissipation effect data under various operation modes, wherein the heat dissipation working condition characteristic data comprises device temperature, device load, environment temperature and environment humidity, and the heat dissipation effect data comprises device temperature drop amplitude within a preset time and fan energy consumption;

[0027] a first determination module configured to determine an optimal operation mode corresponding to each set of heat dissipation working condition characteristic data based on the heat dissipation effect data;

[0028] a decision tree construction module configured to construct a decision tree model based on the heat dissipation working condition characteristic data and the optimal operation mode corresponding thereto, wherein each leaf node of the decision tree corresponds to an optimal operation mode;

[0029] a second determination module configured to determine the optimal operation mode of the device under the current working condition by using the decision tree model;

[0030] a second control module configured to control the bidirectional convection enhanced heat dissipation fan to operate according to the optimal operation mode under the current working condition.

[0031] Further, the first determination module is specifically configured to:

[0032] perform Pareto optimal solution search between heat dissipation efficiency and energy consumption based on a multi-objective optimization algorithm and the heat dissipation effect data, and select a mode on a heat dissipation efficiency-energy consumption frontier curve and ranked first in scoring as the optimal operation mode under the working condition.

[0033] Further, the construction method of the heat dissipation efficiency-energy consumption frontier curve comprises:

[0034] For a set of heat dissipation working condition characteristic data, the heat dissipation efficiency and energy consumption data corresponding to all operating modes are plotted in a two-dimensional coordinate system to form a scatter plot, wherein the abscissa represents energy consumption and the ordinate represents heat dissipation efficiency.

[0035] In the scatter plot, a data point with the lowest energy consumption at a given heat dissipation efficiency level is identified, and a heat dissipation efficiency-energy consumption frontier curve is generated using the data point.

[0036] Further, the score is calculated according to the maximum heat dissipation efficiency of all operating modes, the minimum heat dissipation efficiency of all operating modes, the heat dissipation efficiency of the target operating mode, the weight coefficient of the heat dissipation efficiency, the maximum energy consumption of all operating modes, the minimum energy consumption of all operating modes, the energy consumption of the target operating mode, and the weight coefficient of the energy consumption.

[0037] The embodiments of the present application have the following technical effects:

[0038] (1) Compared with the limitations of the traditional method of controlling the fan only according to a single temperature or a fixed mode, the embodiments of the present application consider the device temperature, device load, environmental temperature, and environmental humidity, which are heat dissipation characteristic data, and consider the device temperature drop amplitude within a preset time and fan energy consumption, which are heat dissipation effect data. The optimal operating mode corresponding to each set of heat dissipation working condition characteristic data is determined based on the heat dissipation effect data. The decision tree model for predicting the optimal operating mode is constructed based on the heat dissipation working condition characteristic data and the corresponding optimal operating mode. The optimal operating mode of the device under the current working condition is determined using the decision tree model, which greatly improves the matching degree of the fan operation control mode and the heat dissipation demand, and balances the energy consumption and the heat dissipation effect.

[0039] (2) The relationship between the heat dissipation working condition characteristics (device temperature, device load, environmental temperature, and environmental humidity) of the device and the optimal operating mode of the fan is often nonlinear, and the decision tree used in the present application can automatically discover complex patterns and nonlinear relationships in the data, and can accurately determine the appropriate fan operating mode under various working conditions.

[0040] (3) The training and prediction process of the decision tree is relatively simple and has low computational complexity. When constructing the decision tree, only sorting and comparison operations are required, and the training of the model can be quickly completed for large-scale heat dissipation working condition data. When predicting, only node judgment along the path of the decision tree is required, and the optimal operating mode of the fan under the current working condition can be determined in a short time, meeting the demand of real-time control. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description only relate to some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort.

[0042] Figure 1 is a flowchart of a bidirectional convection enhanced heat dissipation fan control method provided by an embodiment of the present application;

[0043] Figure 2 is a structural diagram of a bidirectional convection enhanced heat dissipation fan control system provided by another embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0045] Those skilled in the art can understand that the singular forms "a", "an" and "the" used herein include plural forms unless specifically stated otherwise. It should be further understood that the phrase "comprises" used in the specification of the present application means that a feature, integer, step, operation, element, module and / or assembly exists, but does not exclude the existence or addition of one or more other features, integers, steps, operations, elements, modules, assemblies and / or groups thereof. It should be understood that when we say that an element is "connected" or "coupled" to another element, it can be directly connected or coupled to the other element, or there can be an intermediate element. In addition, "connected" or "coupled" used herein can include wireless connection or wireless coupling. The phrase "and / or" used herein includes all or any module and all combinations of the associated listed items.

[0046] Those skilled in the art can understand that unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as that generally understood by those skilled in the art to which the present application belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have meanings consistent with those in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as such.

[0047] Please refer to Figure 1 The embodiment of the present application provides a bidirectional convection enhanced heat dissipation fan control method, which comprises:

[0048] S1, for each set of heat dissipation working condition characteristic data, control the bidirectional convection enhanced heat dissipation fan to execute various operation modes, and record the heat dissipation effect data under various operation modes; wherein, the heat dissipation working condition characteristics include device temperature, device load, environment temperature and environment humidity; the heat dissipation effect data includes device temperature drop amplitude within a preset time and fan energy consumption;

[0049] S2, determine the optimal operation mode corresponding to each set of heat dissipation working condition characteristic data based on the heat dissipation effect data;

[0050] S3, construct a decision tree model based on the heat dissipation working condition characteristic data and the corresponding optimal operation mode; wherein, each leaf node of the decision tree corresponds to an optimal operation mode;

[0051] S4, determine the optimal operation mode of the device under the current working condition by using the decision tree model;

[0052] S5, control the bidirectional convection enhanced heat dissipation fan to operate according to the optimal operation mode under the current working condition.

[0053] In the embodiments of the present application, the device temperature is the temperature value detected by the temperature sensor arranged at a specified position in the device, and the device temperature can specifically include CPU temperature and GPU temperature; the environment temperature is the temperature value detected by the temperature sensor arranged at a specified position outside the device; the environment humidity is the temperature value detected by the temperature sensor arranged at a specified position outside the device; and the device load includes CPU usage rate, GPU usage rate, memory occupancy rate and the like. The bidirectional convection enhanced heat dissipation fan includes two fans, which are on the same shaft and face opposite directions, and the operation modes of the bidirectional convection enhanced heat dissipation fan are divided according to the fan speed, the fan rotation direction and the number of working fans. In the embodiments of the present application, for each set of heat dissipation working condition data, specifically, the bidirectional convection enhanced heat dissipation fan is driven to execute various operation modes by the PWM speed regulation module and the H-bridge driving circuit, and the heat dissipation effect data under various modes is recorded; wherein, the PWM speed regulation module is used to control the speed of each fan in the bidirectional convection enhanced heat dissipation fan, the H-bridge driving circuit is used to control the rotation direction of each fan in the bidirectional convection enhanced heat dissipation fan, and the PWM speed regulation module and the H-bridge driving circuit cooperate with each other, so that the bidirectional convection enhanced heat dissipation fan can execute operation modes with different speeds such as clockwise, counterclockwise and bidirectional.

[0054] The embodiments of the present application have the following technical effects:

[0055] (1) Compared with the limitation of only relying on a single temperature or a fixed mode to control the fan in the traditional method, the embodiments of the present application consider the heat dissipation characteristic data of the device temperature, device load, environment temperature and environment humidity, and consider the heat dissipation effect data of the device temperature drop amplitude and fan energy consumption within the preset time, and determine the optimal running mode corresponding to each group of heat dissipation working condition characteristic data based on the heat dissipation effect data, construct a decision tree model for predicting the optimal running mode based on the heat dissipation working condition characteristic data and the corresponding optimal running mode, and use the decision tree model to determine the optimal running mode of the device under the current working condition, which greatly improves the matching degree of the fan running control mode and the heat dissipation demand, and balances the energy consumption and the heat dissipation effect.

[0056] (2) The relationship between the heat dissipation working condition characteristics (device temperature, device load, environment temperature and environment humidity) of the device and the optimal running mode of the fan is often nonlinear, and the decision tree adopted by the present application can automatically discover complex patterns and nonlinear relationships in the data, and can accurately determine the appropriate fan running mode under complex working conditions.

[0057] (3) The training and prediction process of the decision tree is relatively simple, and the computational complexity is low. When constructing the decision tree, only sorting and comparison operations are required for the data, and the training of the model can be quickly completed for large-scale heat dissipation working condition data. When predicting, only node judgment is required along the path of the decision tree, which can determine the optimal running mode of the fan under the current working condition in a short time, meeting the demand of real-time control.

[0058] In an embodiment, the step of determining the optimal running mode corresponding to each group of heat dissipation working condition characteristic data based on the heat dissipation effect data comprises:

[0059] Based on the multi-objective optimization algorithm and the heat dissipation effect data, a Pareto optimal solution search is performed between the heat dissipation efficiency and the energy consumption, and the mode on the heat dissipation efficiency-energy consumption frontier curve and ranked first in the score is selected as the optimal running mode under the working condition.

[0060] In the embodiments of the present application, for each group of heat dissipation working condition characteristic data, the bidirectional convection enhanced heat dissipation fan is controlled to execute various running modes, and the heat dissipation effect data under various running modes is recorded. In order to construct the heat dissipation efficiency-energy consumption frontier curve, the heat dissipation efficiency under different running modes needs to be calculated according to the recorded data. Specifically, the heat dissipation efficiency can be quantified in various ways, for example, the temperature drop rate per unit time is calculated based on the device temperature drop amplitude and the preset time, which is used as an indicator of heat dissipation efficiency. Assuming that the initial temperature of the device is T0, and the temperature drops to T1 after the preset time t, the heat dissipation efficiency is .

[0061] Multi-objective optimization algorithm (such as NSGA-II) is a method for solving optimization problems with multiple conflicting objectives. In the embodiments of the present application, the objectives are to optimize the heat dissipation efficiency and energy consumption simultaneously. For example, increasing the fan speed can improve the heat dissipation efficiency, but at the same time, it will also increase the energy consumption. There is a certain contradiction between the two objectives, and the multi-objective optimization algorithm is to find a balance in this contradiction. The Pareto optimal solution refers to a solution in a multi-objective optimization problem that cannot be improved in at least one objective function value without degrading the other objective function value. In simple terms, it means that under the current conditions, there is no way to improve one objective without compromising the other. The search process is to traverse various fan operation modes, including different speed combinations, forward and reverse combinations, etc., calculate the heat dissipation efficiency and energy consumption under each mode, and then find those modes that cannot be improved in both heat dissipation efficiency and energy consumption by changing the operation mode. The solutions corresponding to these modes are the Pareto optimal solutions.

[0062] In an embodiment, the method for constructing the heat dissipation efficiency-energy consumption frontier curve includes:

[0063] For a set of heat dissipation condition characteristic data, the heat dissipation efficiency and energy consumption data corresponding to all operation modes are plotted in a two-dimensional coordinate system to form a scatter plot, where the horizontal axis represents energy consumption and the vertical axis represents heat dissipation efficiency.

[0064] In the scatter plot, identify the data point with the lowest energy consumption at a given heat dissipation efficiency level, and use the data point to generate the heat dissipation efficiency-energy consumption frontier curve.

[0065] In the embodiments of the present application, the method for constructing the heat dissipation efficiency-energy consumption frontier curve is as follows: the heat dissipation efficiency and energy consumption data corresponding to all operation modes are plotted in a two-dimensional coordinate system to form a scatter plot, where the horizontal axis represents energy consumption and the vertical axis represents heat dissipation efficiency. In the scatter plot, identify the data point with the lowest energy consumption at a given heat dissipation efficiency level. These points form the heat dissipation efficiency-energy consumption frontier curve, also known as the Pareto frontier. Some mathematical algorithms can be used to identify these frontier points, such as the related techniques in multi-objective optimization algorithms such as the fast non-dominated sorting algorithm (NSGA-II). This algorithm will sort all data points and identify data points that are in a non-dominated position (i.e. there is no other point that is better than it in both heat dissipation efficiency and energy consumption). Connecting these points forms the heat dissipation efficiency-energy consumption frontier curve.

[0066] The embodiments of the present application can achieve a precise dynamic balance between heat dissipation performance and energy consumption by searching for the Pareto optimal solution between heat dissipation efficiency and energy consumption based on multi-objective optimization algorithms and the heat dissipation effect data, and selecting the mode on the heat dissipation efficiency-energy consumption frontier curve with the first ranking score as the optimal operation mode under the condition.

[0067] Further, if there are some discontinuities or large fluctuations between the leading points, the curve can also be further optimized and adjusted according to the actual situation, for example, removing some abnormal points that obviously deviate from the overall trend, or modifying some parts of the curve according to domain knowledge to improve data reliability.

[0068] In an embodiment, the score is calculated according to the maximum heat dissipation efficiency of all operating modes, the minimum heat dissipation efficiency of all operating modes, the heat dissipation efficiency of the target operating mode, the weight coefficient of the heat dissipation efficiency, the maximum energy consumption of all operating modes, the minimum energy consumption of all operating modes, the energy consumption of the target operating mode, and the weight coefficient of the energy consumption.

[0069] In the embodiments of the present application, specifically, the calculation formula of the score is:

[0070] ;

[0071] wherein represents the score, which is used to measure the pros and cons of each operating mode, represents the heat dissipation efficiency of the target operating mode, represents the minimum heat dissipation efficiency of all operating modes, represents the maximum heat dissipation efficiency of all operating modes; represents the minimum energy consumption of all operating modes, represents the maximum energy consumption of all operating modes; represents the energy consumption value of the target operating mode, represents the weight coefficient of the heat dissipation efficiency, represents the weight coefficient of the energy consumption.

[0072] In the embodiments of the present application, by This item normalizes the value of the heat dissipation efficiency to 0-1 to reflect the relative level of the heat dissipation efficiency of the operating mode among all modes. This item normalizes the energy consumption value to 0-1, but uses the relative reduction degree of energy consumption to measure, that is, the lower the energy consumption, the higher the value of this item.

[0073] The embodiments of the present application can better achieve the precise dynamic balance between heat dissipation performance and energy consumption based on the score formula.

[0074] In an embodiment, the step of constructing a decision tree model based on the heat dissipation working condition characteristic data and the corresponding optimal operating mode comprises:

[0075] S31, calculate the information gain rate of each heat dissipation working condition feature, select the heat dissipation working condition feature with the maximum information gain rate as the root node, and divide the data set into multiple subsets according to different values of the heat dissipation working condition feature with the maximum information gain rate;

[0076] S32, for each subset divided by the root node, repeat step S31, i.e. recalculate the information gain rate of the remaining heat dissipation working condition features on the subset, select the heat dissipation working condition feature with the maximum information gain rate for division, and generate new subsets;

[0077] S33, check whether each subset meets the stopping condition, if the stopping condition is met, mark the subset as a leaf node and determine the corresponding optimal operation mode; if not, continue recursion;

[0078] S34, repeat steps S32 and S33 until all subsets meet the stopping condition, and a decision tree model for determining the optimal operation mode is constructed.

[0079] In the embodiments of the present application, first, the information gain rate of each heat dissipation working condition feature (device temperature, device load, environment temperature and environment humidity) is calculated. Then, the information gain rates of all heat dissipation working condition features are compared, and the heat dissipation working condition feature with the maximum information gain rate is selected as the root node of the decision tree. For each subset (subnode) divided by the root node, the above steps are repeated, i.e. the information gain rate of the remaining heat dissipation working condition features on the subset is recalculated, the heat dissipation working condition feature with the maximum information gain rate is selected for division, and new subsets (subnodes) are generated. Subsequently, it is checked whether each subset (subnode) meets the stopping condition, such as whether the number of samples in the node is less than a predetermined threshold, whether the sample purity reaches a certain degree (such as all samples in the node belong to the same category), whether the depth of the tree reaches a predetermined value, etc. If the stopping condition is met, the subnode is marked as a leaf node, and the corresponding optimal operation mode is determined; if not, the recursive division continues. Repeat steps S32 and S33 until all subnodes meet the stopping condition, at which time the complete decision tree is constructed and can be used to determine the optimal operation mode of new data. The embodiments of the present application use the decision tree model to discover the complex relationship between the heat dissipation working condition features (device temperature, device load, environment temperature and environment humidity) and the optimal operation mode of the fan, and can accurately determine the appropriate fan operation mode under various working conditions. Through the decision tree, the optimal operation mode of the fan under the current working condition can be determined in a short time, meeting the needs of real-time control.

[0080] In an embodiment, the step of determining the optimal operation mode of the device under the current working condition by using the decision tree model comprises:

[0081] obtaining heat dissipation working condition feature data of the device under the current working condition;

[0082] Based on the heat dissipation condition characteristic data under the current working condition, the optimal operation mode of the equipment under the current working condition is determined through the decision tree model.

[0083] In the embodiments of the present application, after the decision tree model is constructed, the optimal operation mode of the equipment under the current working condition can be determined by using the decision tree model. Specifically, the heat dissipation condition characteristics of the equipment under the current working condition, including the data of the equipment temperature, the equipment load, the environmental temperature and the environmental humidity, are input into the decision tree model. Starting from the root node, the data is filtered according to the characteristic judgment condition corresponding to the root node. For example, if the root node is the equipment temperature, and the set judgment condition is “whether the equipment temperature is greater than A ℃”, when the input current equipment temperature data meets the condition, the data will enter the next node along the corresponding branch; otherwise, it will enter another branch. At each intermediate node, the model will repeat the above judgment process, and the data will be classified step by step according to the characteristics and judgment conditions corresponding to the nodes. With the continuous downward transmission of the data in the decision tree, the data will finally reach the leaf node. Each leaf node corresponds to an optimal operation mode, which is determined for a specific combination of working condition characteristics after a large amount of historical data training, and can balance the optimization of energy consumption while ensuring the heat dissipation effect. Thus, through the layer-by-layer judgment and filtering of the decision tree model, the optimal operation mode of the equipment under the current working condition is successfully determined.

[0084] In an embodiment, after the step of controlling the bidirectional convection enhanced heat dissipation fan to operate in the optimal operation mode under the current working condition, the method further comprises:

[0085] Periodically collecting new heat dissipation condition characteristic data and corresponding optimal operation mode data, updating and optimizing the decision tree model.

[0086] In the embodiments of the present application, by periodically updating and optimizing the decision tree model, the problem of reduced prediction accuracy caused by the change of the relationship between the heat dissipation condition and the optimal operation mode due to the long-term use of the equipment and the long-term change of the environmental conditions can be avoided.

[0087] In an embodiment, after the step of controlling the bidirectional convection enhanced heat dissipation fan to operate in the optimal operation mode under the current working condition, the method further comprises:

[0088] Sending the heat dissipation effect data of the optimal operation mode under the current working condition to the display screen for display.

[0089] In an embodiment, after the step of controlling the bidirectional convection enhanced heat dissipation fan to operate in the optimal operation mode under the current working condition, the method further comprises:

[0090] Detect whether there is a person in the space where the device is located through the camera based on a target detection algorithm;

[0091] If there is, identify the facial expression of the detected person and detect the noise of the device;

[0092] If the noise of the device is greater than a preset threshold and the expression of the detected person is dissatisfaction, gradually reduce the rotating speed of the bidirectional convection enhanced heat dissipation fan based on the heat dissipation efficiency.

[0093] In the embodiments of the present application, a camera is installed on the device to clearly capture the picture of the space where the device is located, and a noise detection sensor is installed to accurately measure the noise generated when the device is running. The facial expression of the detected person can be identified using a facial expression recognition model, such as an expression recognition network based on deep learning, which can be trained using a public facial expression dataset. In the embodiments of the present application, when the device noise is detected to be greater than a preset threshold and the expression of the person is dissatisfaction, the fan rotating speed is gradually reduced based on the heat dissipation efficiency under the premise of meeting the heat dissipation demand, which can meet the heat dissipation demand and effectively reduce the interference of noise on the person. During the process of gradually reducing the fan rotating speed, the facial expression of the detected person is monitored in real time to determine whether the emotion of the detected person has improved. The embodiments of the present application gradually reduce the fan rotating speed by comprehensively considering the heat dissipation efficiency and the emotion of the detected person, which can meet the heat dissipation demand and effectively reduce the interference of noise on the person.

[0094] The embodiments of the present application also provide a bidirectional convection enhanced heat dissipation fan control system, which comprises:

[0095] A first control module 1 is configured to control the bidirectional convection enhanced heat dissipation fan to execute various operating modes for each set of heat dissipation working condition characteristic data and record heat dissipation effect data under various operating modes; wherein the heat dissipation working condition characteristics include device temperature, device load, environment temperature and environment humidity; and the heat dissipation effect data includes the device temperature drop amplitude within a preset time and fan energy consumption;

[0096] A first determination module 2 is configured to determine the optimal operating mode corresponding to each set of heat dissipation working condition characteristic data based on the heat dissipation effect data;

[0097] A decision tree construction module 3 is configured to construct a decision tree model based on the heat dissipation working condition characteristic data and the corresponding optimal operating mode; wherein each leaf node of the decision tree corresponds to an optimal operating mode;

[0098] A second determination module 4 is configured to determine the optimal operating mode of the device under the current working condition by using the decision tree model;

[0099] A second control module 5 is configured to control the bidirectional convection enhanced heat dissipation fan to operate in the optimal operation mode under the current working condition.

[0100] In an embodiment, the first determining module is specifically configured to:

[0101] Based on the multi-objective optimization algorithm and the heat dissipation effect data, a Pareto optimal solution search is performed between heat dissipation efficiency and energy consumption, and a mode on a heat dissipation efficiency-energy consumption frontier curve and ranked first in scoring is selected as the optimal operation mode under the working condition.

[0102] In an embodiment, the method for constructing the heat dissipation efficiency-energy consumption frontier curve comprises:

[0103] For a set of heat dissipation working condition characteristic data, heat dissipation efficiency and energy consumption data corresponding to all operation modes are plotted in a two-dimensional coordinate system to form a scatter plot, wherein the abscissa represents energy consumption and the ordinate represents heat dissipation efficiency.

[0104] In the scatter plot, a data point with the lowest energy consumption at a given heat dissipation efficiency level is identified, and a heat dissipation efficiency-energy consumption frontier curve is generated using the data point.

[0105] In an embodiment, the score is calculated according to the maximum heat dissipation efficiency of all operation modes, the minimum heat dissipation efficiency of all operation modes, the heat dissipation efficiency of the target operation mode, the weight coefficient of heat dissipation efficiency, the maximum energy consumption of all operation modes, the minimum energy consumption of all operation modes, the energy consumption of the target operation mode, and the weight coefficient of energy consumption.

[0106] In an embodiment, the method for constructing the decision tree model based on the heat dissipation working condition characteristic data and the corresponding optimal operation mode comprises:

[0107] S31, calculate the information gain rate of each heat dissipation working condition characteristic, select the heat dissipation working condition characteristic with the maximum information gain rate as the root node, and divide the data set into multiple subsets according to different values of the heat dissipation working condition characteristic with the maximum information gain rate;

[0108] S32, for each subset divided by the root node, repeat step S31, i.e. recalculate the information gain rate of the remaining heat dissipation working condition characteristic on the subset, select the heat dissipation working condition characteristic with the maximum information gain rate for division, and generate new subsets;

[0109] S33, check whether each subset meets the stopping condition, if the stopping condition is met, mark the subset as a leaf node and determine the corresponding optimal operation mode; if not, continue to recurse;

[0110] S34, repeating step S32 and step S33 until all subsets meet the stop condition, and constructing a decision tree model for determining the optimal operation mode.

[0111] In an embodiment, the step of determining the optimal operation mode of the device under the current working condition by using the decision tree model comprises:

[0112] obtaining heat dissipation working condition characteristic data of the device under the current working condition;

[0113] determining the optimal operation mode of the device under the current working condition by using the decision tree model based on the heat dissipation working condition characteristic data under the current working condition.

[0114] A person of ordinary skill in the art can understand 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, the processes of the above-mentioned embodiments can be included. Any reference to memory, storage, database or other medium provided in the present 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.

[0115] It should be noted that, in this document, the terms "comprise", "contain" or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, device, article or method comprising a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, device, article or method. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of another identical element in the process, device, article or method comprising the element.

[0116] The above merely describes the preferred embodiments of the present application, and is not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, which is made according to the content of the present application specification and drawings, is also included in the patent protection scope of the present application.

Claims

1. A bidirectional convection-enhanced heat-dissipation fan control method, characterized in that, The method comprises: For each set of heat dissipation working condition characteristic data, control the bidirectional convection enhanced heat dissipation fan to execute various operation modes, and record the heat dissipation effect data under various operation modes; wherein the heat dissipation working condition characteristics include device temperature, device load, environment temperature and environment humidity; the heat dissipation effect data includes the device temperature drop amplitude within a preset time and the fan energy consumption; Determine the optimal operation mode corresponding to each set of heat dissipation working condition characteristic data based on the heat dissipation effect data; Based on the heat dissipation working condition characteristic data and the corresponding optimal operation mode, a decision tree model is constructed; wherein each leaf node of the decision tree corresponds to an optimal operation mode; Determine the optimal operation mode of the device under the current working condition by using the decision tree model; Control the bidirectional convection enhanced heat dissipation fan to operate according to the optimal operation mode under the current working condition; The step of determining the optimal operation mode corresponding to each set of heat dissipation working condition characteristic data based on the heat dissipation effect data comprises: Based on the multi-objective optimization algorithm and the heat dissipation effect data, search for the Pareto optimal solution between the heat dissipation efficiency and the energy consumption, and select the mode on the heat dissipation efficiency-energy consumption frontier curve and ranked first in the score as the optimal operation mode under the working condition; The step of constructing a decision tree model based on the heat dissipation working condition characteristic data and the corresponding optimal operation mode comprises: S31, calculate the information gain rate of each heat dissipation working condition characteristic, select the heat dissipation working condition characteristic with the maximum information gain rate as the root node, and divide the data set into multiple subsets according to different values of the heat dissipation working condition characteristic with the maximum information gain rate; S32, for each subset divided by the root node, repeat step S31, i.e. recalculate the information gain rate of the remaining heat dissipation working condition characteristic on the subset, select the heat dissipation working condition characteristic with the maximum information gain rate for division, and generate new subsets; S33, check whether each subset meets the stopping condition, if the stopping condition is met, mark the subset as a leaf node and determine the corresponding optimal operation mode; if not, continue to recurse; S34, repeat steps S32 and S33 until all subsets meet the stopping condition, and a decision tree model for determining the optimal operation mode is constructed.

2. The bidirectional convection-enhanced heat-dissipation fan control method according to claim 1, wherein, The construction method of the heat dissipation efficiency-energy consumption frontier curve comprises: For a set of heat dissipation working condition characteristic data, plot the heat dissipation efficiency and energy consumption data corresponding to all operation modes in a two-dimensional coordinate system to form a scatter plot, wherein the horizontal coordinate represents the energy consumption and the vertical coordinate represents the heat dissipation efficiency; In the scatter plot, identify the data point with the lowest energy consumption at a given heat dissipation efficiency level, and generate a heat dissipation efficiency-energy consumption frontier curve using the data point.

3. The bidirectional convection-enhanced heat-dissipation fan control method according to claim 1, wherein, The score is calculated according to the maximum heat dissipation efficiency of all operation modes, the minimum heat dissipation efficiency of all operation modes, the heat dissipation efficiency of the target operation mode, the weight coefficient of the heat dissipation efficiency, the maximum energy consumption of all operation modes, the minimum energy consumption of all operation modes, the energy consumption of the target operation mode and the weight coefficient of the energy consumption.

Images