A temperature control method, system and storage medium for a heat dissipation device

Abstract

The application relates to the technical field of temperature monitoring, in particular to a temperature control method and system for a heat dissipation device and a storage medium, wherein the method comprises the following steps: collecting environment data in a cabinet and working data of a heat dissipation device; predicting a temperature prediction value in the cabinet by a dynamic prediction model based on the environment data and the working data; and issuing the temperature prediction value to a controller, which controls the heat dissipation device through a multi-stage speed regulation strategy. The application adopts a heat capacity network model and an LSTM residual correction model to construct a dynamic prediction model. The heat capacity network model ensures that the heat conduction logic conforms to the actual structure, has strong interpretability and generalization ability. The LSTM residual correction model adaptively compensates for nonlinear factors such as equipment aging, installation gap and environmental disturbance, thereby obviously improving the short-term temperature trend prediction accuracy and providing a reliable basis for prospective regulation.

Description

Technical Field

[0001] This application relates to the field of temperature monitoring technology, and in particular to a temperature control method, system and storage medium for a heat dissipation device. Background Technology

[0002] Multi-chassis power distribution cabinets are modular electrical cabinets integrating multiple functional modules. They are used to centrally install secondary equipment such as relay protection, measurement and control, power supply, and communication systems. They feature modularity, standardization, high reliability, and ease of maintenance, and are widely used in substations, industrial power distribution, new energy, and rail transportation. Because power distribution cabinets densely house high-power electronic equipment, they generate a significant amount of heat during operation. If not properly cooled, this can easily lead to overheating of components, performance degradation, insulation aging, and even system failure. Therefore, they must be equipped with cooling devices such as fans, air conditioners, or intelligent temperature control systems to ensure safe and stable operation and meet relevant standards for temperature rise limits.

[0003] In related technologies, multi-chassis power distribution cabinets mainly employ forced air cooling, heat exchangers, and industrial air conditioners for heat dissipation, combined with intelligent temperature control and optimized airflow design to cope with the heat generated by high-density equipment and ensure operational safety and reliability. Due to the dense equipment and high heat generation within the power distribution cabinet, the heat dissipation devices must rely on temperature monitoring for intelligent regulation, prevention of localized overheating, timely fault warnings, and compliance with safety standards and maintenance requirements. Therefore, temperature monitoring is an indispensable link in ensuring the reliable operation of the cabinet. Current heat dissipation device monitoring is limited to single-point monitoring, lacks threshold control, and its passive response leads to delayed temperature regulation, resulting in overheating of critical components in the long run. Summary of the Invention

[0004] The main objective of this application is to provide a temperature control method, system, and storage medium for a heat dissipation device, aiming to solve the problems in the background art.

[0005] To achieve the above objectives, one aspect of this application provides a temperature control method for a heat dissipation device, the method comprising: Collect environmental data and operating data of the heat dissipation device inside the cabinet; Based on the environmental and operational data, a dynamic prediction model is used to predict the temperature inside the cabinet. The predicted temperature value is sent to the controller, which controls the heat dissipation device through a multi-level speed regulation strategy.

[0006] In some embodiments, the dynamic prediction model includes a thermal capacity network model and an LSTM residual correction model. Before predicting the temperature forecast value inside the cabinet using the dynamic prediction model, the method further includes: The heat-generating components and the space inside the cabinet are abstracted as heat capacity nodes; Based on the actual heat transfer path, thermal resistance branches are established between heat capacity nodes, and thermal impedance parameters of the thermal resistance branches are set, including thermal resistance value and heat capacity value. A thermal capacity network model is constructed based on the aforementioned thermal capacity nodes and thermal impedance parameters.

[0007] In some embodiments, the prediction of the temperature forecast within the cabinet based on the dynamic prediction model specifically includes: The current environmental and operational data are input into the thermal capacity network model, and the initial temperature prediction sequence of the thermal capacity nodes is output through the thermal capacity network model. The initial temperature prediction sequence is compensated in real time using the LSTM residual correction model, and the real-time compensated temperature prediction sequence is output, which includes multiple temperature prediction values.

[0008] In some embodiments, after outputting the real-time compensated temperature prediction sequence, the method further includes: When the absolute error between the temperature prediction value and the actual temperature value in the temperature prediction sequence is greater than a threshold, a location heat source or heat dissipation failure alarm is triggered. When the temperature prediction value of the temperature prediction sequence is greater than the safety threshold, the regulation and intervention process is initiated.

[0009] In some embodiments, the step of predicting the temperature prediction value inside the cabinet based on the environmental data and operational data using a dynamic prediction model further includes: The working data is compared with the command values ​​issued by the controller to generate a deviation value; If the deviation value is greater than the threshold, the heat dissipation device is determined to be in an abnormal working state. If the deviation value is less than the threshold, the heat dissipation device is determined to be in normal working condition.

[0010] In some embodiments, the expression of the thermal capacity network model is: ; in Let be the heat capacity value of the i-th heat capacity node. Let be the thermal resistance between the i-th thermal capacity node and the j-th thermal capacity node. Let be the real-time thermal power of the i-th thermal capacity node. Let be the temperature of the i-th heat capacity node. Let be the temperature of the j-th heat capacity node.

[0011] In some embodiments, before collecting environmental data within the cabinet and operational data of the heat dissipation device, the following steps are included: The interior of the cabinet is divided into multiple areas; A three-dimensional temperature field is constructed by placing multiple temperature and humidity sensors in each area; Connect multiple temperature and humidity sensors to the same clock source.

[0012] In some embodiments, the controller directly controls the heat dissipation device via PWM signals or Modbus commands and records the control actions in a log.

[0013] To achieve the above objectives, another aspect of this application provides a temperature control system for a heat dissipation device, the system comprising: The data acquisition module is used to collect environmental data and operating data of the heat dissipation device inside the cabinet; The temperature prediction module is used to predict the temperature inside the cabinet based on the environmental data and working data using a dynamic prediction model. The control module is used to send the temperature prediction value to the heat dissipation device through a multi-level speed regulation strategy.

[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program, characterized in that the computer program implements the above-described method when executed by a processor.

[0015] The embodiments of this application include at least the following beneficial effects: This application provides a temperature control method, system, and storage medium for a heat dissipation device. The present invention uses a thermal capacity network model and an LSTM residual correction model to construct a dynamic prediction model. The thermal capacity network model ensures that the heat conduction logic conforms to the actual structure and has strong interpretability and generalization ability. The LSTM residual correction model adaptively compensates for nonlinear factors such as equipment aging, installation gaps, and environmental disturbances, significantly improving the accuracy of short-term temperature trend prediction and providing a reliable basis for forward-looking regulation. Attached Figure Description Figure 1 A flowchart of a temperature control method for a heat dissipation device provided in an embodiment of this application; Figure 2 This is a schematic diagram of a temperature control method for a heat dissipation device provided in an embodiment of this application; Figure 3 A block diagram of a temperature control system for a heat dissipation device provided in an embodiment of this application. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0017] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0018] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0020] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0021] The thermal capacity network model, a physically simplified model based on the lumped parameter method, is used to describe the dynamic process of heat generation, transfer, and accumulation inside cabinets or electronic equipment. It approximates the real three-dimensional continuous thermal field as a finite number of discrete nodes (thermal capacity nodes) and thermal resistance branches between the nodes, thereby establishing a computable system of ordinary differential equations.

[0022] The LSTM residual correction model is a data-driven temporal error compensation model. It uses a Long Short-Term Memory (LSTM) network to learn the temporal pattern of the residual (error) sequence between the predicted values ​​of the thermal capacity network physical model and the actual temperature. It then uses this pattern to estimate the prediction error of the physical model at future times, thereby correcting the physical prediction results in real time.

[0023] refer to Figures 1-2 As shown, one embodiment of this application proposes a temperature control method for a heat dissipation device, including: S1O1: Collects environmental data and operating data of the heat dissipation device inside the cabinet; S1O2: Based on environmental and operational data, a dynamic prediction model is used to predict the temperature inside the cabinet. S1O3: The temperature prediction value is sent to the controller, which controls the heat dissipation device through a multi-level speed regulation strategy.

[0024] The environmental data in S101 includes, but is not limited to, temperature, humidity and pressure difference data inside the cabinet, and the operating data includes the airflow, air volume, fan speed, current and power of the heat dissipation device. This application has multiple temperature and humidity sensors installed inside the cabinet. The temperature and humidity sensors are evenly distributed in the upper, middle and lower areas of the cabinet. Each sensor is horizontally dispersed in each area to construct a three-dimensional temperature field covering the entire space of the cabinet. By constructing a three-dimensional temperature field, the blind spots of single-point monitoring are eliminated. Furthermore, a wind speed sensor and an air volume sensor are integrated at the main air duct outlet to measure the intensity of the effective cooling airflow in real time. Differential pressure sensors are installed on both sides of the inlet air filter to determine the unobstructedness of the filter and air duct. The actual fan speed is obtained in real time through the FG signal line of the heat dissipation equipment. The current and power data of the entire cabinet are collected synchronously through a smart meter as a dynamic heat load input. All sensors and instruments are triggered by the same clock source to sample synchronously, ensuring that multi-dimensional data such as temperature, humidity, wind speed, air volume, pressure difference, speed, current and power are strictly aligned in the time dimension, thereby forming a three-dimensional thermal environment profile with high spatiotemporal resolution.

[0025] Specifically, the heat dissipation device in step S101 includes, but is not limited to, air cooling, liquid cooling, heat pipe or phase change cooling device.

[0026] Specifically, the dynamic prediction model in S1O2 includes a thermal capacity network model and an LSTM residual correction model. The construction of the thermal capacity network model includes: The heat-generating components and the space inside the cabinet are abstracted as heat capacity nodes; Based on the actual heat transfer path, thermal resistance branches are established between heat capacity nodes, and thermal impedance parameters of the thermal resistance branches are set, including thermal resistance value and heat capacity value. A thermal capacity network model is constructed based on the aforementioned thermal capacity nodes and thermal impedance parameters.

[0027] After obtaining the thermal capacity network model, a dynamic prediction model is used to predict the temperature prediction sequence inside the cabinet. This temperature prediction sequence consists of several predicted temperature values, specifically including: Input the current environmental and operational data into the thermal capacity network model, and output the initial temperature prediction sequence of the thermal capacity nodes through the thermal capacity network model; The initial temperature prediction sequence is compensated in real time using an LSTM residual correction model, and the compensated temperature prediction value is output.

[0028] Furthermore, in some other embodiments, a physical heat conduction model is established based on the cabinet structure and equipment layout to reflect the heat transfer path.

[0029] The expression for the heat capacity network model is: ; in Let be the heat capacity value of the i-th heat capacity node. For the first The thermal resistance between the j-th thermal capacity node and the j-th thermal capacity node. , Let be the temperature of the i-th heat capacity node. Let be the temperature of the j-th heat capacity node.

[0030] The LSTM residual correction model learns from historical temperature sequences, current load, and ambient temperature to correct the residual error of the RC model. The expression for the real-time compensated temperature prediction value is: ; in This represents the predicted temperature value after real-time compensation. In the initial predicted temperature sequence Predicted temperature value at time of day This is the data-driven correction term for the LSTM residual correction model, i.e., the real-time compensation amount.

[0031] It should be noted that the thermal capacity network model defines how to calculate the temperature change rate of each node from physical principles, that is, to obtain the curve of the temperature change of each node over time. The curve includes multiple initial temperature prediction values, while the expression of the temperature prediction value after real-time compensation is the predicted temperature value at a specific future time.

[0032] Furthermore, the dynamic prediction model supports online incremental learning. During system operation, the prediction error is continuously collected and compared with actual temperature data. The LSTM weights are fine-tuned periodically. It supports scenarios such as equipment aging, seasonal changes, and load patterns, and automatically triggers model retraining or parameter drift detection.

[0033] Furthermore, step S102 also includes determining the operation of the equipment, specifically: Compare the rotation speed and fan speed of the heat dissipation device (such as a fan) with the command values ​​issued by the controller; If the speed deviation is greater than 10% and lasts for more than 10 seconds, it is determined that the fan performance has degraded or is stalled. If the wind speed is low but the rotation speed is normal and the combined pressure difference is high, it is determined that the filter is clogged or the air duct is deformed.

[0034] Furthermore, following S103, it also includes: When the absolute error between the predicted temperature value and the actual temperature value in the temperature prediction sequence exceeds a threshold, i.e. ,like 5. Triggering an alarm for heat source or heat dissipation failure at the location. This is the actual temperature value; This application uses a fixed step size (e.g., 30 seconds) to push forward to 5 minutes, outputting the complete temperature change trend with an error controlled within ±2℃.

[0035] When the predicted temperature value of the temperature prediction sequence exceeds the safety threshold in the subsequent time period, the regulation and intervention process is initiated.

[0036] If the predicted temperature value will exceed the 60℃ safety threshold within 3 minutes, the control and intervention process will be initiated in advance. Specifically, the control logic of the regulation and intervention process includes feedforward regulation, feedback regulation, and anti-oscillation regulation. When the current suddenly increases by 20% and the preheating heat load rises, it enters feedforward regulation and immediately increases the level to suppress the temperature rise inertia. If the actual temperature rise rate is higher than the prediction, it enters feedback regulation and increases the level again. If the temperature drops steadily, it decreases the level to save energy. The anti-oscillation mechanism avoids frequent switching at the level boundary by setting hysteresis.

[0037] This application employs a multi-level speed control strategy, dividing the fan speed into four levels: 0% (standby), 40% (low speed), 70% (medium speed), and 100% (high speed). When a 20% current surge is detected, the speed is immediately increased by one level via feedforward control to suppress temperature rise inertia. If the actual temperature rise rate is higher than the model prediction, the speed is increased by another level via feedback adjustment. Once the temperature stabilizes and decreases, the speed is automatically reduced to save energy. A hysteresis range is set to avoid oscillations caused by frequent switching at speed boundaries. Finally, the control module directly drives the fan controller via PWM signals or Modbus commands, while recording the time, speed level, temperature status, and energy consumption data of each speed control action for subsequent energy efficiency analysis and model iteration optimization. This achieves a fully closed-loop dynamic monitoring system from sensing, diagnosis, prediction to precise control.

[0038] Furthermore, in some embodiments, this application dynamically optimizes the fan operating power while ensuring that the temperature in critical areas remains below a safe threshold (e.g., 55°C). The hysteresis anti-oscillation mechanism ensures stable control, and the complete control log records support energy efficiency assessment and continuous model iteration. Actual tests show that this strategy can save 20%-70% of energy compared to traditional constant speed operation, while significantly reducing operating noise, achieving safe, stable, efficient, and intelligent closed-loop thermal management.

[0039] Furthermore, the controller of this application directly controls the heat dissipation device through PWM signals or Modbus commands, and records the adjustment action log during the control process.

[0040] refer to Figure 3 As shown, another aspect of this application embodiment also proposes a temperature control system for a heat dissipation device, comprising: The data acquisition module is used to collect environmental data and operating data of the heat dissipation device inside the cabinet; The temperature prediction module is used to predict the temperature inside the cabinet based on environmental and operational data using a dynamic prediction model. The control module is used to send the temperature prediction value to the heat dissipation device for control through a multi-level speed regulation strategy.

[0041] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0042] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0043] The methods provided in this application relate to the field of information technology. The methods provided in this application can be applied to terminals, servers, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the method, but is not limited to the above forms.

[0044] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0045] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0046] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0047] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0048] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0049] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0050] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0051] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0052] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0053] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0054] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0055] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0056] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A temperature control method for a heat dissipation device, characterized in that, The method includes: Collect environmental data and operating data of the heat dissipation device inside the cabinet; Based on the environmental and operational data, a dynamic prediction model is used to predict the temperature inside the cabinet. The predicted temperature value is sent to the controller, which controls the heat dissipation device through a multi-level speed regulation strategy.

2. The temperature control method for a heat dissipation device according to claim 1, characterized in that, The dynamic prediction model includes a thermal capacity network model and an LSTM residual correction model. Before predicting the temperature inside the cabinet using the dynamic prediction model, the following steps are also included: The heat-generating components inside the cabinet and the space inside the cabinet are mapped as thermal capacity nodes; Based on the actual heat transfer path, thermal resistance branches are established between heat capacity nodes, and thermal impedance parameters of the thermal resistance branches are set, including thermal resistance value and heat capacity value. A thermal capacity network model is constructed based on the aforementioned thermal capacity nodes and thermal impedance parameters.

3. The temperature control method for a heat dissipation device according to claim 2, characterized in that, The prediction of the temperature inside the cabinet based on the dynamic prediction model specifically includes: The current environmental and operational data are input into the thermal capacity network model, and the initial temperature prediction sequence of the thermal capacity nodes is output through the thermal capacity network model. The initial temperature prediction sequence is compensated in real time using the LSTM residual correction model, and the real-time compensated temperature prediction sequence is output, which includes multiple temperature prediction values.

4. The temperature control method for a heat dissipation device according to claim 3, characterized in that, After outputting the real-time compensated temperature prediction sequence, the system further includes: When the absolute error between the temperature prediction value and the actual temperature value in the temperature prediction sequence is greater than a threshold, a location heat source or heat dissipation failure alarm is triggered. When the temperature prediction value of the temperature prediction sequence is greater than the safety threshold, the regulation and intervention process is initiated.

5. The temperature control method for a heat dissipation device according to claim 1, characterized in that, The method of predicting the temperature inside the cabinet using a dynamic prediction model based on the environmental and operational data further includes: The working data is compared with the command values ​​issued by the controller to generate a deviation value; If the deviation value is greater than the threshold, the heat dissipation device is determined to be in an abnormal working state. If the deviation value is less than the threshold, the heat dissipation device is determined to be in normal working condition.

6. The temperature control method for a heat dissipation device according to claim 3, characterized in that, The expression for the heat capacity network model is: ； in Let be the heat capacity value of the i-th heat capacity node. For the first The thermal resistance between the j-th thermal capacity node and the j-th thermal capacity node. Let be the real-time thermal power of the i-th thermal capacity node. Let be the temperature of the i-th heat capacity node. Let be the temperature of the j-th heat capacity node.

7. The temperature control method for a heat dissipation device according to claim 1, characterized in that, Before collecting environmental data within the cabinet and operational data from the heat dissipation device, the following is included: The interior of the cabinet is divided into multiple areas; A three-dimensional temperature field is constructed by placing multiple temperature and humidity sensors in each area; Connect multiple temperature and humidity sensors to the same clock source.

8. The temperature control method for a heat dissipation device according to claim 1, characterized in that, The controller directly controls the heat dissipation device via PWM signals or Modbus commands and records the control actions in a log.

9. A temperature control system for a heat dissipation device, characterized in that, The system includes: The data acquisition module is used to collect environmental data and operating data of the heat dissipation device inside the cabinet; The temperature prediction module is used to predict the temperature inside the cabinet based on the environmental data and working data using a dynamic prediction model. The control module is used to send the temperature prediction value to the heat dissipation device through a multi-level speed regulation strategy.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 8.

Images