A fan system and a cooling control method thereof

Abstract

The present application relates to the field of fan technology, and specifically to a fan system and a cooling control method thereof. It uses an infrared detector to monitor and collect the temperature data of the heat dissipated object in real time, and monitor and collect the fan speed of the fan system in real time, and then introduces a data processing and analysis algorithm based on artificial intelligence and deep learning at the back end to perform time series analysis and interactive correlation on the temperature and fan speed, so as to learn and capture the hidden time series dynamic interactive correlation relationship and transfer information between the temperature of the heat dissipated object and the fan speed of the fan system, so as to automatically control the fan speed according to the actual situation. In this way, the fan speed can be adaptively controlled according to the actual temperature change of the heat dissipated object, thereby improving the intelligent level of fan cooling control and avoiding the problems of low efficiency and energy waste caused by traditional manual control methods.

Description

Technical Field

[0001] The present application relates to the field of fan technology, and in particular to a fan system and a temperature reduction control method thereof. Background Art

[0002] Fans are common cooling devices and are widely used in homes, offices and other places. With the rise in energy costs and the increase in people's awareness of environmental protection, reducing unnecessary energy consumption has become an important consideration in the design of fan control systems. However, traditional fan control solutions usually use gear control, and users need to manually select the fan speed gear to adjust the wind speed. This control method requires users to adjust the fan speed according to their own feelings, which lacks intelligence. Not only does it make the adjustment process cumbersome and inefficient, but the fan may still run at a high speed when it does not need to run at high speed, resulting in energy waste.

[0003] Therefore, an optimized fan cooling control solution is desired. Summary of the invention

[0004] This application is made in view of the above problems. One object of this application is to provide a fan system and a temperature reduction control method thereof.

[0005] An embodiment of the present application provides a fan temperature reduction control method, which includes:

[0006] The time series of temperature data of the heat dissipated object is collected by infrared detector;

[0007] Collect the time series of fan speed of the fan system;

[0008] Transmitting the time series of the temperature data and the time series of the fan speed to a fan cooling controller;

[0009] In the fan cooling controller, time series correlation coding is performed on the time series of the fan speed and the time series of the temperature data respectively to obtain a fan speed time series correlation feature vector and a temperature time series correlation feature vector;

[0010] In the fan cooling controller, the fan speed time series associated feature vector and the temperature time series associated feature vector are input into a feature vector dynamic interaction module based on gated response to obtain a fan speed-temperature time series dynamic interaction fusion feature vector;

[0011] In the fan cooling controller, a speed-temperature influence transfer analysis is performed based on the fan speed-temperature time series dynamic interaction fusion feature vector and the temperature time series correlation feature vector to obtain a speed-temperature influence transfer matrix;

[0012] In the fan cooling controller, a control instruction is determined based on the speed-temperature influence transfer matrix, and the control instruction is used to indicate whether to reduce the fan speed.

[0013] For example, according to the fan cooling control method of an embodiment of the present application, in which, in the fan cooling controller, the time series of the fan speed and the time series of the temperature data are respectively time-related encoded to obtain a fan speed time-related feature vector and a temperature time-related feature vector, including: inputting the time series of the fan speed and the time series of the temperature data into a dual-branch structure sequence encoder including a 1DCNN model and a bidirectional gated recurrent unit respectively to obtain the fan speed time-related feature vector and the temperature time-related feature vector.

[0014] For example, according to the fan cooling control method of an embodiment of the present application, in the fan cooling controller, the fan speed timing associated feature vector and the temperature timing associated feature vector are input into a feature vector dynamic interaction module based on a gated response to obtain a fan speed-temperature timing dynamic interaction fusion feature vector, including:

[0015] Inputting the fan speed time series associated feature vector and the temperature time series associated feature vector into a feature combination module for cascade processing to obtain a fan speed-temperature time series combined feature vector;

[0016] Inputting the fan speed-temperature time series joint feature vector into a gated response function to obtain a fan speed-temperature time series dynamic information fusion response gated value;

[0017] The fan speed-temperature timing dynamic information fusion response gate value is used as a weight to calculate the position-weighted sum of the fan speed timing associated feature vector and the temperature timing associated feature vector to obtain the fan speed-temperature timing dynamic interaction fusion feature vector.

[0018] For example, according to the fan cooling control method of an embodiment of the present application, the fan speed-temperature time series joint feature vector is input into the gated response function to obtain the fan speed-temperature time series dynamic information fusion response gated value, including:

[0019] After calculating the matrix multiplication of the fan speed-temperature time series joint eigenvector and the parameter matrix, the obtained eigenvector is added to the bias vector by position to obtain a linear transformation fan speed-temperature time series joint eigenvector;

[0020] The linear transformation fan speed-temperature time series joint feature vector is activated using a sigmoid function to obtain the fan speed-temperature time series dynamic information fusion response gating value.

[0021] For example, according to the fan cooling control method of an embodiment of the present application, the fan speed-temperature time series dynamic information fusion response gate value is used as a weight, and the position-weighted sum of the fan speed time series associated feature vector and the temperature time series associated feature vector is calculated to obtain the fan speed-temperature time series dynamic interaction fusion feature vector, including:

[0022] Calculating the positional product between the fan speed timing associated feature vector and the fan speed-temperature timing dynamic information fusion response gate value to obtain a weighted modulated fan speed timing associated feature vector;

[0023] After calculating one minus the fan speed-temperature time series dynamic information fusion response gate value, the obtained weight value is multiplied by the temperature time series associated feature vector by position to obtain a weight modulated temperature time series associated feature vector;

[0024] The weight-modulated fan speed timing associated feature vector and the weight-modulated temperature timing associated feature vector are added according to the position points to obtain the fan speed-temperature timing dynamic interaction fusion feature vector.

[0025] For example, according to the fan cooling control method of an embodiment of the present application, in which, in the fan cooling controller, a speed-temperature impact transfer analysis is performed based on the fan speed-temperature timing dynamic interaction fusion feature vector and the temperature timing association feature vector to obtain a speed-temperature impact transfer matrix, including: calculating the speed-temperature impact transfer matrix of the fan speed-temperature timing dynamic interaction fusion feature vector relative to the temperature timing association feature vector.

[0026] For example, according to the fan cooling control method of an embodiment of the present application, in the fan cooling controller, a control instruction is determined based on the speed-temperature influence transfer matrix, and the control instruction is used to indicate whether to reduce the fan speed, including: inputting the speed-temperature influence transfer matrix into the classifier-based cooling controller to obtain the control instruction, and the control instruction is used to indicate whether to reduce the fan speed.

[0027] For example, according to the fan cooling control method of an embodiment of the present application, it also includes a training step: used to train the dual-branch structure sequence encoder including the 1DCNN model and the bidirectional gated recurrent unit, the gated response-based feature vector dynamic interaction module, and the classifier-based cooling controller.

[0028] For example, according to the fan cooling control method of an embodiment of the present application, the training step includes:

[0029] Acquire training data, wherein the training data includes a time series of training temperature data of a heat dissipation object collected by an infrared detector, a time series of training fan speed of a fan system, and a real control instruction;

[0030] Transmitting the time series of the training temperature data and the time series of the training fan speed to the fan cooling controller;

[0031] In the fan cooling controller, the time series of the training fan speed and the time series of the training temperature data are respectively input into the dual-branch structure sequence encoder including the 1DCNN model and the bidirectional gated recurrent unit to obtain a training fan speed time series associated feature vector and a training temperature time series associated feature vector;

[0032] In the fan cooling controller, the training fan speed time series associated feature vector and the training temperature time series associated feature vector are input into the feature vector dynamic interaction module based on gated response to obtain the training fan speed-temperature time series dynamic interaction fusion feature vector;

[0033] In the fan cooling controller, a training speed-temperature influence transfer matrix of the training fan speed-temperature time series dynamic interaction fusion feature vector relative to the training temperature time series correlation feature vector is calculated;

[0034] In the fan cooling controller, the training speed-temperature influence transfer matrix is ​​input into the classifier-based cooling controller to obtain a training control instruction;

[0035] Calculating a cross entropy loss function value between the training control instruction and the real control instruction to obtain a classification loss function value;

[0036] Based on the classification loss function value, the dual-branch structure sequence encoder including the 1DCNN model and the bidirectional gated recurrent unit, the gated response-based feature vector dynamic interaction module, and the classifier-based temperature reduction controller are trained.

[0037] An embodiment of the present application further provides a fan system, wherein the fan system is used to execute any of the fan temperature reduction control methods described above.

[0038] According to the fan system and its cooling control method of the embodiments of the present application, the fan speed is adaptively controlled according to the actual temperature changes of the heat dissipated object, thereby improving the intelligence level of the fan cooling control and avoiding the problems of inefficiency and energy waste caused by traditional manual control methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, and are not intended to limit the present application.

[0040] Figure 1 A schematic diagram of the application architecture of the fan cooling control method in an embodiment of the present application is shown;

[0041] Figure 2 A flow chart of a fan cooling control method in an embodiment of the present application is shown;

[0042] Figure 3 A flowchart of sub-step S550 of the fan cooling control method in an embodiment of the present application is shown;

[0043] Figure 4 A schematic diagram of the structure of a fan cooling control system in an embodiment of the present application is shown;

[0044] Figure 5 An application scenario diagram of the fan cooling control method in an embodiment of the present application is shown;

[0045] Figure 6 A schematic diagram of a storage medium according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.

[0047] The terms used in this specification are those common terms currently widely used in the art in consideration of the functions of the present application, but these terms may vary according to the intention of a person of ordinary skill in the art, precedents, or new technologies in the art. In addition, specific terms may be selected by the applicant, and in this case, their detailed meanings will be described in the detailed description of the present application. Therefore, the terms used in the specification should not be understood as simple names, but rather as a general description based on the meaning of the terms and the present application.

[0048] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0049] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0050] Figure 1 A schematic diagram of the application architecture of the fan cooling control method in an embodiment of the present application is shown, including a server 100 and a terminal device 200.

[0051] The terminal device 200 and the server 100 can be connected via the Internet to achieve mutual communication. Optionally, the above-mentioned Internet uses standard communication technology and / or protocol. The Internet is usually the Internet, but it can also be any network, including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a dedicated network or a virtual private network. In some embodiments, the data exchanged through the network is represented by technologies and / or formats including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec) can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0052] The server 100 can provide various network services for the terminal device 200, wherein the server 100 can be a single server, a server cluster consisting of several servers, or a cloud computing center. Specifically, the server 100 may include a processor 110 (Center Processing Unit, CPU), a memory 120, an input device 130, and an output device 140, etc. The input device 130 may include a keyboard, a mouse, a touch screen, etc., and the output device 140 may include a display device, such as a liquid crystal display (Liquid Crystal Display, LCD), a cathode ray tube (Cathode Ray Tube, CRT), etc.

[0053] The memory 120 may include a read-only memory (ROM) and a random access memory (RAM), and provides the processor 110 with program instructions and data stored in the memory 120. In the embodiment of the present application, the memory 120 may be used to store the program of the fan cooling control method in the embodiment of the present application.

[0054] The processor 110 calls the program instructions stored in the memory 120, and the processor 110 is used to execute the steps of any fan cooling control method in the embodiments of the present application according to the obtained program instructions.

[0055] In addition, the application architecture diagram in the embodiment of the present application is intended to more clearly illustrate the technical solution in the embodiment of the present application, and does not constitute a limitation on the technical solution provided in the embodiment of the present application. Of course, for other application architectures and business applications, the technical solution provided in the embodiment of the present application is also applicable to similar problems.

[0056] The following is a non-restrictive description of the fan cooling control method provided according to at least one embodiment of the present application through several examples or embodiments. As described below, different features in these specific examples or embodiments can be combined with each other without conflicting with each other to obtain new examples or embodiments, and these new examples or embodiments also fall within the scope of protection of the present application.

[0057] In response to the above technical problems, the technical concept of this application is to monitor and collect the temperature data of the heat dissipated object in real time through an infrared detector, and monitor and collect the fan speed of the fan system in real time, and then introduce a data processing and analysis algorithm based on artificial intelligence and deep learning at the back end to perform time series analysis and interactive correlation on the temperature and fan speed, so as to learn and capture the hidden time series dynamic interactive correlation relationship and transfer information between the temperature of the heat dissipated object and the fan speed of the fan system, so as to automatically control the fan speed according to the actual situation. In this way, the fan speed can be adaptively controlled according to the actual temperature change of the heat dissipated object, thereby improving the intelligent level of fan cooling control and avoiding the problems of inefficiency and energy waste caused by traditional manual control methods.

[0058] Figure 2 1 shows a flow chart of a fan cooling control method in an embodiment of the present application. For example, the fan cooling control method can be executed by a server, which can be Figure 1 The server 100 shown in FIG. Figure 2 As shown, the fan cooling control method according to the embodiment of the present application includes the following steps: S510, collecting the time series of temperature data of the heat dissipated object through an infrared detector; S520, collecting the time series of the fan speed of the fan system; S530, transmitting the time series of the temperature data and the time series of the fan speed to a fan cooling controller; S540, in the fan cooling controller, respectively, performing time series correlation coding on the time series of the fan speed and the time series of the temperature data to obtain a fan speed time series correlation feature vector and a temperature time series correlation feature vector; S550, in the fan cooling controller The fan speed timing associated feature vector and the temperature timing associated feature vector are input into a feature vector dynamic interaction module based on a gated response to obtain a fan speed-temperature timing dynamic interaction fusion feature vector; S560, in the fan cooling controller, a speed-temperature impact transfer analysis is performed based on the fan speed-temperature timing dynamic interaction fusion feature vector and the temperature timing associated feature vector to obtain a speed-temperature impact transfer matrix; S570, in the fan cooling controller, a control instruction is determined based on the speed-temperature impact transfer matrix, and the control instruction is used to indicate whether to reduce the fan speed.

[0059] Specifically, in the technical solution of the present application, first, the time series of temperature data of the heat dissipated object is collected by an infrared detector, and the time series of the fan speed of the fan system is collected. Then, the time series of the temperature data and the time series of the fan speed are transmitted to the fan cooling controller, so that the fan cooling controller performs dynamic interaction and implicit correlation analysis on the time series data of the temperature data and the fan speed, so as to realize the cooling control.

[0060] It should be understood that in the actual process of fan cooling control, the fan speed and the temperature data of the heat dissipated object have dynamic change rules and time series correlation in the time dimension, that is, they have time series continuity and dependency relationship in the time dimension. Based on this, in order to obtain the time series correlation characteristics of the fan speed and temperature in the time dimension respectively, in the fan cooling controller, the time series of the fan speed and the time series of the temperature data are respectively input into the double-branch structure sequence encoder including the 1DCNN model and the bidirectional gated cyclic unit to obtain the fan speed time series correlation feature vector and the temperature time series correlation feature vector. It should be understood that the 1DCNN model can be used to extract the local time series features of the fan speed and temperature data in the time dimension respectively, such as the periodic change of the fan speed, and considering that the captured time series features have local characteristics, in order to more comprehensively understand the context and long-distance correlation relationship of these time series data, in the technical solution of the present application, the bidirectional gated cyclic unit is further used to extract the time series forward and backward long-distance dependency correlation features and information between the local time series features of the fan speed and temperature data in the time dimension. It is worth mentioning that the dual-branch structure allows the model to process two related time series data sets (fan speed and temperature) simultaneously and extract their respective time series correlation features, which helps to better understand the time series characteristics of fan speed and temperature in the time dimension and provide a basis for the subsequent capture of interaction and hidden correlation features.

[0061] Correspondingly, in step S540, in the fan cooling controller, the time series of the fan speed and the time series of the temperature data are respectively subjected to time series association encoding to obtain a fan speed time series association feature vector and a temperature time series association feature vector, including: respectively inputting the time series of the fan speed and the time series of the temperature data into a dual-branch structure sequence encoder including a 1DCNN model and a bidirectional gated recurrent unit to obtain the fan speed time series association feature vector and the temperature time series association feature vector.

[0062] Then, since the fan speed time series correlation feature vector and the temperature time series correlation feature vector respectively contain the time series correlation features of the fan speed and the temperature of the heat dissipated object in the time dimension, there is a complex correlation relationship and dynamic interaction between the two features. That is to say, the correlation relationship between the fan speed and the temperature is implicit and complex, and will change dynamically with the change of time. Based on this, in order to better understand the time series interaction between the fan speed and the temperature, so as to realize the dynamic interaction and fusion of the time series features between the fan speed and the temperature, in the fan cooling controller, the fan speed time series correlation feature vector and the temperature time series correlation feature vector are input into the feature vector dynamic interaction module based on the gated response to obtain the fan speed-temperature time series dynamic interaction fusion feature vector. Through the processing of the feature vector dynamic interaction module based on the gated response, the complex and implicit correlation features and the time series dynamic interaction information between the fan speed time series features and the heat dissipated object temperature time series features can be automatically learned and captured, and it is identified which of the dynamic interaction information contributes more to the subsequent fan cooling control task and which contributes less. In this way, the gated response mechanism can be used to enhance the expression of these important key semantic features and interactive information during the dynamic interaction and fusion of the fan speed timing characteristics and temperature timing characteristics, thereby better understanding the complex relationship between the fan operating status and the ambient temperature, and providing more accurate and comprehensive information for intelligent fan control decisions.

[0063] Accordingly, in step S550, if Figure 3 As shown, in the fan cooling controller, the fan speed timing associated feature vector and the temperature timing associated feature vector are input into a feature vector dynamic interaction module based on a gated response to obtain a fan speed-temperature timing dynamic interaction fusion feature vector, including: S551, the fan speed timing associated feature vector and the temperature timing associated feature vector are input into a feature union module for cascade processing to obtain a fan speed-temperature timing joint feature vector; S552, the fan speed-temperature timing joint feature vector is input into a gated response function to obtain a fan speed-temperature timing dynamic information fusion response gated value; S553, using the fan speed-temperature timing dynamic information fusion response gated value as a weight, calculating the position-weighted sum of the fan speed timing associated feature vector and the temperature timing associated feature vector to obtain the fan speed-temperature timing dynamic interaction fusion feature vector.

[0064] Among them, in step S552, the fan speed-temperature timing joint feature vector is input into the gated response function to obtain the fan speed-temperature timing dynamic information fusion response gated value, including: calculating the matrix multiplication of the fan speed-temperature timing joint feature vector and the parameter matrix, and then adding the obtained feature vector and the bias vector by position to obtain the linear transformation fan speed-temperature timing joint feature vector; using the sigmoid function to activate the linear transformation fan speed-temperature timing joint feature vector to obtain the fan speed-temperature timing dynamic information fusion response gated value.

[0065] Among them, in step S553, the fan speed-temperature timing dynamic information fusion response gate value is used as a weight, and the position-weighted sum of the fan speed timing association feature vector and the temperature timing association feature vector is calculated to obtain the fan speed-temperature timing dynamic interaction fusion feature vector, including: calculating the position-by-position product between the fan speed timing association feature vector and the fan speed-temperature timing dynamic information fusion response gate value to obtain a weight-modulated fan speed timing association feature vector; calculating one minus the fan speed-temperature timing dynamic information fusion response gate value, and then multiplying the obtained weight value by position with the temperature timing association feature vector to obtain a weight-modulated temperature timing association feature vector; adding the weight-modulated fan speed timing association feature vector and the weight-modulated temperature timing association feature vector by position point to obtain the fan speed-temperature timing dynamic interaction fusion feature vector.

[0066] In a specific example, in the fan cooling controller, the fan speed timing associated feature vector and the temperature timing associated feature vector are input into a feature vector dynamic interaction module based on a gated response to obtain a fan speed-temperature timing dynamic interaction fusion feature vector, including: inputting the fan speed timing associated feature vector and the temperature timing associated feature vector into a feature vector dynamic interaction module based on a gated response to process them using the following dynamic interaction fusion formula to obtain the fan speed-temperature timing dynamic interaction fusion feature vector; wherein the dynamic interaction fusion formula is:

[0067]

[0068] Among them, v 1 and v 2 are the fan speed timing associated feature vector and the temperature timing associated feature vector, respectively. [·,·] represents a vector cascade operation. W is a parameter matrix. b is a bias vector. σ is a sigmoid function. is the fan speed-temperature timing dynamic information fusion response gate value, v fIt is the fan speed-temperature time series dynamic interaction fusion feature vector.

[0069] Furthermore, considering that the fan speed-temperature timing dynamic interaction fusion feature vector expresses the dynamic interaction fusion information between the fan speed timing characteristics and the temperature timing characteristics, the temperature timing correlation feature vector expresses the timing correlation characteristics of the temperature. Therefore, in order to more specifically quantify the impact of the fan speed on the ambient temperature change, so as to better guide the fan control system to make intelligent adjustment decisions, in the fan cooling controller, the speed-temperature impact transfer matrix of the fan speed-temperature timing dynamic interaction fusion feature vector relative to the temperature timing correlation feature vector is calculated. By calculating the speed-temperature impact transfer matrix, the influence relationship between the fan speed and the ambient temperature can be quantified, which helps the system understand the response mode of the fan operating state to the temperature change, and then better adjust the fan speed to meet the user's needs. In addition, the system can optimize the fan control strategy according to this influence relationship, improve the cooling effect and save energy consumption.

[0070] Correspondingly, in step S560, in the fan cooling controller, a speed-temperature impact transfer analysis is performed based on the fan speed-temperature timing dynamic interaction fusion feature vector and the temperature timing association feature vector to obtain a speed-temperature impact transfer matrix, including: calculating the speed-temperature impact transfer matrix of the fan speed-temperature timing dynamic interaction fusion feature vector relative to the temperature timing association feature vector.

[0071] Then, in the fan cooling controller, the speed-temperature impact transfer matrix is ​​input into the classifier-based cooling controller to obtain a control instruction, and the control instruction is used to indicate whether to reduce the fan speed. In other words, the impact responsiveness transfer feature information between the fan speed timing characteristics and the temperature timing characteristics is used for classification processing, so as to control the fan speed according to the actual situation. In this way, the cooling control can be adaptively performed according to the actual temperature change of the heat dissipated object, thereby improving the intelligent level of the fan cooling control and avoiding the problems of low efficiency and energy waste caused by the traditional manual control method.

[0072] Accordingly, in step S570, the fan cooling controller determines a control instruction based on the speed-temperature influence transfer matrix, and the control instruction is used to indicate whether to reduce the fan speed, including: inputting the speed-temperature influence transfer matrix into the classifier-based cooling controller to obtain the control instruction, and the control instruction is used to indicate whether to reduce the fan speed.

[0073] It should be understood that the role of the classifier is to use the given categories and known training data to learn classification rules and classifiers, and then classify (or predict) unknown data. Logistic regression and SVM are often used to solve binary classification problems. For multi-class classification problems, logistic regression or SVM can also be used, but multiple binary classifications are required to form a multi-classification. However, this is prone to errors and is not efficient. Commonly used multi-classification methods include the Softmax classification function.

[0074] Furthermore, in the technical solution of the present application, the fan cooling control method also includes a training step: used to train the dual-branch structure sequence encoder including the 1DCNN model and the bidirectional gated recurrent unit, the gated response-based feature vector dynamic interaction module, and the classifier-based cooling controller.

[0075] Wherein, the training step includes: obtaining training data, the training data including the time series of training temperature data of the heat dissipated object collected by an infrared detector, the time series of training fan speed of the fan system and the real control instructions; transmitting the time series of the training temperature data and the time series of the training fan speed to the fan cooling controller; in the fan cooling controller, respectively inputting the time series of the training fan speed and the time series of the training temperature data into the dual-branch structure sequence encoder including the 1DCNN model and the bidirectional gated recurrent unit to obtain the training fan speed timing association feature vector and the training temperature timing association feature vector; in the fan cooling controller, inputting the training fan speed timing association feature vector and the training temperature timing association feature vector into the gated response based The corresponding feature vector dynamic interaction module is used to obtain the training fan speed-temperature timing dynamic interaction fusion feature vector; in the fan cooling controller, the training speed-temperature influence transfer matrix of the training fan speed-temperature timing dynamic interaction fusion feature vector relative to the training temperature timing associated feature vector is calculated; in the fan cooling controller, the training speed-temperature influence transfer matrix is ​​input into the classifier-based cooling controller to obtain the training control instruction; the cross entropy loss function value between the training control instruction and the real control instruction is calculated to obtain the classification loss function value; based on the classification loss function value, the dual-branch structure sequence encoder including the 1DCNN model and the bidirectional gated recurrent unit, the feature vector dynamic interaction module based on the gated response and the cooling controller based on the classifier are trained.

[0076] In the technical solution of the present application, the training fan speed time series association feature vector and the training temperature time series association feature vector respectively represent the training temperature data of the heat dissipation object and the local time series semantic association features of the training fan speed. The training fan speed time series association feature vector and the training temperature time series association feature vector are input into the feature vector dynamic interaction module based on gated response, and the training fan speed-temperature time series dynamic interaction fusion feature vector is calculated relative to the training temperature time series association feature vector, the purpose of which is to construct a model for simulating the influence of fan speed on the temperature data of the heat dissipation object at the data level. However, in the process of fusing the training fan speed timing-related feature vector and the training temperature timing-related feature vector through the feature vector dynamic interaction module based on the gated response, the feature order of the training fan speed-temperature timing dynamic interaction fusion feature vector will be higher than the feature order of the training temperature timing-related feature vector. As a result, the training speed-temperature influence transfer matrix obtained by calculating the transfer matrix of the training fan speed-temperature timing dynamic interaction fusion feature vector relative to the training temperature timing-related feature vector will have the technical problem of insufficient feature distribution aggregation, thereby affecting its convergence effectiveness through the classifier relative to the predetermined class probability label.

[0077] Preferably, in a preferred example of the present application, the training speed-temperature influence transfer matrix is ​​input into the classifier-based cooling controller to obtain training control instructions, including: performing a clustering operation on the training speed-temperature influence transfer matrix, such as performing a clustering operation based on the distance between eigenvalues, and determining the number of in-class features and the number of out-of-class features; dividing the total number of eigenvalues ​​of the training speed-temperature influence transfer matrix by the number of in-class features and the number of out-of-class features respectively to obtain a class importance value and an out-of-class proportion value, and calculating the inverse of the class importance value to obtain a class constraint value; calculating each eigenvalue of the training speed-temperature influence transfer matrix with the class importance value A power function of an exponent is added to an exponential value with a natural function as the base and the class constraint value as the exponent, and then multiplied by the out-of-class proportion value to obtain a training speed-temperature impact transfer modulation matrix; the training speed-temperature impact transfer matrix is ​​point multiplied with the class importance value to obtain a training speed-temperature impact transfer ontology matrix; the weighted sum of the training speed-temperature impact transfer modulation matrix and the training speed-temperature impact transfer ontology matrix is ​​calculated with a weight hyperparameter to obtain an optimized training speed-temperature impact transfer matrix; the optimized training speed-temperature impact transfer matrix is ​​input into the classifier-based cooling controller to obtain the training control instruction.

[0078] That is, in the technical solution of the present application, the training speed-temperature influence transfer matrix is ​​input into the classifier-based cooling controller to obtain the training control instruction, including: clustering optimization of the training speed-temperature influence transfer matrix to obtain the optimized training speed-temperature influence transfer matrix, and the process is expressed by the optimization formula as follows:

[0079]

[0080] Among them, n represents the total number of eigenvalues ​​of the training speed-temperature impact transfer matrix, k represents the number of intra-class features, M represents the training speed-temperature impact transfer matrix, β represents the weight hyperparameter, ⊙ represents the position point multiplication, Add by position, represents exponential operation of each position characteristic value in the vector, M' is the optimized training speed-temperature influence transfer matrix; the optimized training speed-temperature influence transfer matrix is ​​input into the classifier-based cooling controller to obtain the training control instruction.

[0081] Accordingly, in this preferred embodiment, the applicant of the present application, while performing clustering operation on the training speed-temperature effect transfer matrix, further performs responsive modulation with the out-of-class proportional factor by combining the clustering importance measure of the eigenvalue of the training speed-temperature effect transfer matrix with the class constraint measure of the clustering operation, and establishes the simplicity and effectiveness of the overall feature purification of the feature set of the training speed-temperature effect transfer matrix by the clustering operation based on the clustering scaling represented by the feature ontology of the training speed-temperature effect transfer matrix, and suppresses the logical inconsistency of the convergence of the probability density distribution caused by the clustering operation, so as to improve the classification iteration effect of the cooling controller based on the classifier input of the feature set of the training speed-temperature effect transfer matrix, that is, to improve the speed of classification training and the accuracy of classification results. In this way, the fan speed can be controlled more accurately according to the actual temperature change of the heat dissipated object, thereby improving the intelligent level of fan cooling control and avoiding the problems of inefficiency and energy waste caused by traditional manual control methods.

[0082] Furthermore, the present application also provides a fan system, wherein the fan system is used to execute any of the aforementioned fan cooling control methods.

[0083] Based on the above embodiments, see Figure 4The figure is a schematic diagram of the structure of a fan cooling control system 800 in an embodiment of the present application. The fan cooling control system 800 includes: a temperature data acquisition module 810, which is used to collect the time series of temperature data of the heat dissipated object through an infrared detector; a fan speed acquisition module 820, which is used to collect the time series of fan speed of the fan system; a transmission module 830, which is used to transmit the time series of the temperature data and the time series of the fan speed to the fan cooling controller; a timing association encoding module 840, which is used to perform timing association encoding on the time series of the fan speed and the time series of the temperature data in the fan cooling controller to obtain a fan speed timing association feature vector and a temperature timing association feature vector; a dynamic interaction module 850, which is used to A fan cooling controller inputs the fan speed timing associated feature vector and the temperature timing associated feature vector into a feature vector dynamic interaction module based on a gated response to obtain a fan speed-temperature timing dynamic interaction fusion feature vector; a transfer analysis module 860 is used to perform a speed-temperature influence transfer analysis in the fan cooling controller based on the fan speed-temperature timing dynamic interaction fusion feature vector and the temperature timing associated feature vector to obtain a speed-temperature influence transfer matrix; a fan speed control module 870 is used to determine a control instruction in the fan cooling controller based on the speed-temperature influence transfer matrix, and the control instruction is used to indicate whether to reduce the fan speed.

[0084] Here, those skilled in the art will appreciate that the specific functions and operations of each module in the fan cooling control system 800 have been described in detail above. Figure 2 to Figure 3 It has been described in detail in the description of the fan cooling control method, and therefore, its repeated description will be omitted.

[0085] Figure 5 FIG. 1 is an application scenario diagram of the fan cooling control method according to an embodiment of the present application. Figure 5 As shown, in this application scenario, first, the time series of temperature data of the heat dissipated object is collected by an infrared detector (for example, Figure 5 D1 as shown in FIG) and collects the time series of the fan speed of the fan system (for example, Figure 5 Then, the time series of the temperature data and the time series of the fan speed are input to a server (for example, Figure 5 In S) shown in , the server can use the fan cooling control algorithm to process the time series of the temperature data and the time series of the fan speed to obtain a control instruction indicating whether to reduce the fan speed.

[0086] Based on the above embodiments, another exemplary embodiment of an electronic device is also provided in the embodiments of the present application. In some possible implementations, the electronic device in the embodiments of the present application may include a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the steps of the fan cooling control method in the above embodiments when executing the program.

[0087] For example, in the case of electronic equipment Figure 1 Taking the server 100 in the example as an example, the processor in the electronic device is the processor 110 in the server 100, and the memory in the electronic device is the memory 120 in the server 100.

[0088] An embodiment of the present application also provides a computer-readable storage medium. Figure 6 1 shows a schematic diagram of a computer-readable storage medium 1000 according to an embodiment of the present application. Figure 6 As shown, the computer-readable storage medium 1000 stores computer-executable instructions 1001. When the computer-executable instructions 1001 are executed by the processor, the fan cooling control method according to the embodiment of the present application described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc.

[0089] The embodiment of the present application also provides a computer program product or a computer program, which includes computer executable instructions, and the computer executable instructions are stored in a computer readable storage medium. The processor of the computer device reads the computer executable instructions from the computer readable storage medium, and the processor executes the computer executable instructions, so that the computer device executes the fan cooling control method according to the embodiment of the present application.

[0090] Those skilled in the art will appreciate that the contents disclosed in this application may be subject to various variations and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.

[0091] In addition, although the present application makes various references to certain units in the system according to embodiments of the present application, any number of different units can be used and run on the client and / or server. The units are only illustrative, and different aspects of the system and method can use different units.

[0092] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of software function modules. The present application is not limited to any particular form of combination of hardware and software.

[0093] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined as such herein.

[0094] The above is an explanation of the present application and should not be considered as a limitation thereof. Although several exemplary embodiments of the present application have been described, it will be readily understood by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present application. Therefore, all of these modifications are intended to be included within the scope of the present application as defined by the claims. It should be understood that the above is an explanation of the present application and should not be considered to be limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present application is defined by the claims and their equivalents.

Claims

1. A fan cooling control method, characterized in that: include: The time series of temperature data of the heat dissipated object is collected by infrared detector; Collect the time series of fan speed of the fan system; Transmitting the time series of the temperature data and the time series of the fan speed to a fan cooling controller; In the fan cooling controller, time series correlation coding is performed on the time series of the fan speed and the time series of the temperature data respectively to obtain a fan speed time series correlation feature vector and a temperature time series correlation feature vector; In the fan cooling controller, the fan speed time series associated feature vector and the temperature time series associated feature vector are input into a feature vector dynamic interaction module based on gated response to obtain a fan speed-temperature time series dynamic interaction fusion feature vector; In the fan cooling controller, a speed-temperature influence transfer analysis is performed based on the fan speed-temperature time series dynamic interaction fusion feature vector and the temperature time series correlation feature vector to obtain a speed-temperature influence transfer matrix; In the fan cooling controller, a control instruction is determined based on the speed-temperature influence transfer matrix, wherein the control instruction is used to indicate whether to reduce the fan speed; In the fan cooling controller, respectively performing time series correlation coding on the time series of the fan speed and the time series of the temperature data to obtain a fan speed time series correlation feature vector and a temperature time series correlation feature vector, including: respectively inputting the time series of the fan speed and the time series of the temperature data into a two-branch structure sequence encoder including a 1DCNN model and a bidirectional gated recurrent unit to obtain the fan speed time series correlation feature vector and the temperature time series correlation feature vector; In the fan cooling controller, the fan speed timing associated feature vector and the temperature timing associated feature vector are input into a feature vector dynamic interaction module based on gated response to obtain a fan speed-temperature timing dynamic interaction fusion feature vector, including: Inputting the fan speed time series associated feature vector and the temperature time series associated feature vector into a feature combination module for cascade processing to obtain a fan speed-temperature time series combined feature vector; Inputting the fan speed-temperature time series joint feature vector into a gated response function to obtain a fan speed-temperature time series dynamic information fusion response gated value; Taking the fan speed-temperature time series dynamic information fusion response gate value as a weight, calculating the position-weighted sum of the fan speed time series associated feature vector and the temperature time series associated feature vector to obtain the fan speed-temperature time series dynamic interaction fusion feature vector; The fan speed-temperature time series joint feature vector is input into a gated response function to obtain a fan speed-temperature time series dynamic information fusion response gated value, including: After calculating the matrix multiplication of the fan speed-temperature time series joint eigenvector and the parameter matrix, the obtained eigenvector is added to the bias vector by position to obtain a linear transformation fan speed-temperature time series joint eigenvector; Using a sigmoid function to activate the linear transformation fan speed-temperature time series joint feature vector to obtain the fan speed-temperature time series dynamic information fusion response gating value; Taking the fan speed-temperature time series dynamic information fusion response gate value as a weight, calculating the position-weighted sum of the fan speed time series associated feature vector and the temperature time series associated feature vector to obtain the fan speed-temperature time series dynamic interaction fusion feature vector, including: Calculating the positional product between the fan speed timing associated feature vector and the fan speed-temperature timing dynamic information fusion response gate value to obtain a weighted modulated fan speed timing associated feature vector; After calculating one minus the fan speed-temperature time series dynamic information fusion response gate value, the obtained weight value is multiplied by the temperature time series associated feature vector by position to obtain a weight modulated temperature time series associated feature vector; The weight-modulated fan speed time series associated feature vector and the weight-modulated temperature time series associated feature vector are combined according to the position points to obtain the fan speed-temperature time series dynamic interaction fusion feature vector; In the fan cooling controller, a speed-temperature impact transfer analysis is performed based on the fan speed-temperature timing dynamic interaction fusion feature vector and the temperature timing correlation feature vector to obtain a speed-temperature impact transfer matrix, including: calculating the speed-temperature impact transfer matrix of the fan speed-temperature timing dynamic interaction fusion feature vector relative to the temperature timing correlation feature vector; In the fan cooling controller, based on the speed-temperature influence transfer matrix, determining a control instruction, the control instruction is used to indicate whether to reduce the fan speed, including: inputting the speed-temperature influence transfer matrix into the classifier-based cooling controller to obtain the control instruction, the control instruction is used to indicate whether to reduce the fan speed; In the fan cooling controller, the fan speed timing associated feature vector and the temperature timing associated feature vector are input into a feature vector dynamic interaction module based on a gated response to obtain a fan speed-temperature timing dynamic interaction fusion feature vector, including: the fan speed timing associated feature vector and the temperature timing associated feature vector are input into a feature vector dynamic interaction module based on a gated response to process them using the following dynamic interaction fusion formula to obtain the fan speed-temperature timing dynamic interaction fusion feature vector; wherein the dynamic interaction fusion formula is: Wherein, v1 and v2 are the fan speed timing associated feature vector and the temperature timing associated feature vector, respectively, [·,·] represents a vector cascade operation, W is a parameter matrix, b is a bias vector, σ is a sigmoid function, is the fan speed-temperature timing dynamic information fusion response gate value, v f It is the fan speed-temperature time series dynamic interaction fusion feature vector.

2. The fan cooling control method according to claim 1, characterized in that: The method also includes a training step for training the dual-branch structure sequence encoder including the 1DCNN model and the bidirectional gated recurrent unit, the gated response-based feature vector dynamic interaction module, and the classifier-based temperature reduction controller.

3. The fan cooling control method according to claim 2, characterized in that: The training step comprises: Acquire training data, wherein the training data includes a time series of training temperature data of a heat dissipation object collected by an infrared detector, a time series of training fan speed of a fan system, and a real control instruction; Transmitting the time series of the training temperature data and the time series of the training fan speed to the fan cooling controller; In the fan cooling controller, the time series of the training fan speed and the time series of the training temperature data are respectively input into the dual-branch structure sequence encoder including the 1DCNN model and the bidirectional gated recurrent unit to obtain a training fan speed time series associated feature vector and a training temperature time series associated feature vector; In the fan cooling controller, the training fan speed time series associated feature vector and the training temperature time series associated feature vector are input into the feature vector dynamic interaction module based on gated response to obtain the training fan speed-temperature time series dynamic interaction fusion feature vector; In the fan cooling controller, a training speed-temperature influence transfer matrix of the training fan speed-temperature time series dynamic interaction fusion feature vector relative to the training temperature time series correlation feature vector is calculated; In the fan cooling controller, the training speed-temperature influence transfer matrix is ​​input into the classifier-based cooling controller to obtain a training control instruction; Calculating a cross entropy loss function value between the training control instruction and the real control instruction to obtain a classification loss function value; Based on the classification loss function value, the dual-branch structure sequence encoder including the 1DCNN model and the bidirectional gated recurrent unit, the gated response-based feature vector dynamic interaction module, and the classifier-based temperature reduction controller are trained.

4. A fan system, characterized in that: The fan system is used to execute the fan cooling control method described in any one of claims 1 to 3.

Images