Industrial internet of things based device heat dissipation optimization method, system, device and medium

Abstract

The application provides an industrial internet of things-based equipment heat dissipation optimization method, system, device and medium, and relates to the field of industrial internet of things. The method comprises the following steps: obtaining a preset running parameter time sequence set of a target equipment; in the running process of the equipment, performing differentiated heat dissipation control on each hot spot area: collecting real-time temperature and intercepting subsequent running parameter time sequence; analyzing the real-time temperature and the running parameter by using a heat generation predictor corresponding to the hot spot area to generate a temperature change curve; accurately determining a heat dissipation starting time point and a duration period based on the curve, and correspondingly configuring a heat dissipation execution unit; after receiving a heat dissipation completion feedback signal, intelligently starting a next round of prediction and control cycle to realize prospective heat dissipation management. Through the internet of things technology and the prediction of heat dissipation for each hot spot area, the accurate, intelligent and prospective heat dissipation control of each hot spot area of the equipment is realized, the heat dissipation efficiency is improved, and the waste of heat dissipation resources is avoided.

Description

Technical Field

[0001] This application relates to the field of industrial Internet of Things (IIoT), and in particular to a method, system, device, and medium for optimizing device heat dissipation based on IIoT. Background Technology

[0002] For large equipment with multiple hotspot areas, the distribution of these hotspots is often uneven, with significant differences in the heat generation characteristics and cooling requirements of each area. Current technologies for heat dissipation control in large equipment often employ either a holistic passive cooling system or a simple temperature threshold-triggered active cooling solution. These methods typically only activate cooling after the equipment temperature reaches a preset threshold, making intelligent heat management difficult. This often results in some areas experiencing insufficient cooling while others overheat, failing to guarantee stable operation and lifespan, wasting cooling resources, and increasing energy consumption. Summary of the Invention

[0003] The main purpose of this application is to provide a device heat dissipation optimization method, system, device and medium based on the Industrial Internet of Things, which aims to solve the technical problem in the prior art that large equipment with multiple hot spots lacks intelligent heat dissipation control, resulting in insufficient or excessive heat dissipation in some areas, and thus failing to achieve accurate and efficient heat dissipation management.

[0004] To achieve the above objectives, this application provides a device heat dissipation optimization method based on the Industrial Internet of Things (IIoT). This method is applied to a device heat dissipation optimization system, which connects temperature sensing units and heat dissipation execution units located in multiple hotspot areas of a target device via the IoT. The method includes: acquiring a preset operating parameter timing set of the target device; during the operation of the target device, performing heat dissipation control on each of the hotspot areas, the heat dissipation control including: collecting the real-time temperature of the hotspot area through the temperature sensing units, and simultaneously extracting subsequent operating parameter timings based on the preset operating parameter timing set; based on a heat prediction device corresponding to the hotspot area, predicting the heat dissipation of the hotspot area according to the real-time temperature and the subsequent operating parameter timings, obtaining a heat temperature change curve for the hotspot area; determining the heat dissipation start time point and heat dissipation time period based on the heat temperature change curve, and configuring the heat dissipation execution unit based on the heat dissipation start time point and the heat dissipation time period; receiving a heat dissipation completion signal from the heat dissipation execution unit, and initiating the next round of hotspot area heat prediction and heat dissipation control based on the heat dissipation completion signal.

[0005] Optionally, the method further includes: acquiring basic feature information of the target device, constructing device retrieval constraints based on the basic feature information; sending the device retrieval constraints to a cloud server, receiving multiple sample device heating data from the cloud server, wherein each sample device heating data includes a time series set of sample device operating parameters and a sample hotspot temperature change dataset; and constructing a heating predictor for each hotspot region based on the multiple sample device heating data.

[0006] Optionally, the step of constructing a heat prediction device for each hotspot region based on the heat generation data of the multiple sample devices includes: determining a first hotspot region based on the multiple hotspot regions; for the first hotspot region, extracting multiple parameter time series segments from the time series set of operating parameters of each of the sample devices, and extracting corresponding multiple sets of temperature change data from the temperature change dataset of each sample hotspot based on the multiple parameter time series segments; constructing a first training dataset for the first hotspot region based on the multiple parameter time series segments and the multiple sets of temperature change data; training a first heat prediction device based on the first training dataset; and training heat prediction devices for the remaining hotspot regions in the same manner as training the first heat prediction device based on the heat generation data of the multiple sample devices.

[0007] Optionally, training the first heat prediction device based on the first training dataset includes: constructing a digital twin model of the target device and identifying a first hotspot region in the digital twin model to obtain a first regional twin model; sequentially inputting the multiple parameter time-series segments into the first regional twin model to simulate corresponding predicted temperature change data; comparing the predicted temperature change data with the corresponding temperature change data, calculating the prediction error, and adjusting the first regional twin model based on the prediction error; iteratively executing until the prediction error is less than a preset threshold, and using the adjusted first regional twin model as the first heat prediction device.

[0008] Optionally, determining the heat dissipation start time and heat dissipation time period based on the heat generation temperature change curve includes: obtaining the heat dissipation trigger temperature and heat dissipation stop temperature of the hot spot area; determining, based on the heat generation temperature change curve, the first moment when the predicted temperature of the hot spot area equals the heat dissipation trigger temperature, and taking the first moment as the heat dissipation start time; obtaining the heat dissipation characteristic curve of the heat dissipation execution unit corresponding to the hot spot area, and determining the heat dissipation execution duration of the hot spot area based on the heat dissipation characteristic curve; and determining the heat dissipation time period based on the heat dissipation start time and the heat dissipation execution duration.

[0009] Optionally, obtaining the heat dissipation characteristic curve of the heat dissipation execution unit corresponding to the hot spot area includes: obtaining multiple sets of heat dissipation and cooling data of the hot spot area during historical operation; generating a temperature change curve of the heat dissipation execution unit from the heat dissipation trigger temperature to the heat dissipation stop temperature based on each set of heat dissipation and cooling data, thus obtaining multiple temperature change curves; configuring weight coefficients for the multiple temperature change curves in chronological order, wherein the weight coefficient of the temperature change curve closer to the current time is larger; and performing curve fitting on the multiple temperature change curves based on the weight coefficients of each temperature change curve to obtain the heat dissipation characteristic curve of the heat dissipation execution unit.

[0010] Optionally, the method further includes: acquiring an overall heat detection cycle; when the overall heat detection cycle is triggered, simultaneously sending a temperature synchronization acquisition command to the temperature sensing units of multiple hot spots; receiving multiple area temperature values ​​sent by the temperature sensing units of each hot spot; comparing the multiple area temperature values ​​with the heat dissipation trigger temperature of the corresponding hot spot area to determine the number of overheated areas; obtaining the overheating ratio based on the number of overheated areas and the total number of areas of multiple hot spots; and issuing an audible and visual alarm when the overheating ratio is greater than or equal to a preset ratio.

[0011] Furthermore, to achieve the above objectives, this application provides a device heat dissipation optimization system based on the Industrial Internet of Things (IIoT). The system includes a management platform, a sensor network platform, and an object platform connected sequentially. The object platform includes a target device, which includes a temperature sensing unit and a heat dissipation execution unit, both located in hotspot areas of the target device. The management platform includes: a data acquisition module for acquiring a preset set of operating parameters for the target device; and multiple area heat dissipation control modules for controlling the heat dissipation of each hotspot area during the operation of the target device. Each area heat dissipation control module includes: a parameter extraction submodule for using the temperature sensing unit... The system collects the real-time temperature of the hotspot area and simultaneously extracts the subsequent operating parameter timing based on the preset operating parameter timing set. A heat prediction submodule is used to predict the heat of the hotspot area based on the real-time temperature and the subsequent operating parameter timing, obtaining a heat temperature change curve for the hotspot area. A heat dissipation planning submodule is used to determine the heat dissipation start time and heat dissipation period based on the heat temperature change curve, and configure the heat dissipation execution unit based on the heat dissipation start time and heat dissipation period. A loop triggering submodule receives the heat dissipation completion signal from the heat dissipation execution unit and starts the next round of hotspot area heat prediction and heat dissipation control based on the heat dissipation completion signal.

[0012] Furthermore, to achieve the above objectives, this application also provides an electronic device, including a memory and a processor. The memory is used to store computer software programs; the processor is used to read and execute the computer software programs, thereby implementing the device heat dissipation optimization method based on the Industrial Internet of Things in any of the above possible implementations.

[0013] In addition, this application also provides a non-transitory computer-readable storage medium storing a computer software program, which, when executed by a processor, implements the device heat dissipation optimization method based on the Industrial Internet of Things in any of the above possible implementations.

[0014] The beneficial effects that this application can achieve are as follows: By acquiring the preset operating parameter timing set of the target device, a foundation is laid for subsequent heat dissipation prediction and control. During the operation of the target device, heat dissipation control is performed separately for each hot spot area to achieve differentiated heat dissipation control for each hot spot area, optimize the heat dissipation process of the device, and improve the accuracy and pertinence of heat dissipation control for hot spot areas.

[0015] During the heat dissipation control process in each hotspot area, the real-time temperature of the hotspot area is collected by the temperature sensing unit. Simultaneously, the subsequent operating parameter timing is extracted based on a preset operating parameter timing set, enabling real-time monitoring of the current temperature status of the hotspot area. Combined with the preset operating parameter timing set, the operation sequence to be executed by the device is extracted, providing necessary input data for heat prediction. Based on the heat prediction device corresponding to the hotspot area, heat prediction is performed on the hotspot area according to the real-time temperature and subsequent operating parameter timing, resulting in a heat temperature change curve and future temperature trend. This achieves forward-looking heat dissipation control, avoiding the lag problem of traditional passive heat dissipation control. The heat dissipation start time and heat dissipation period are determined based on the heat temperature change curve. The heat dissipation execution unit is configured based on this start time and period, ensuring that the unit starts at the optimal time and continues for an appropriate duration, achieving precise allocation and efficient utilization of heat dissipation resources. The heat dissipation completion signal from the execution unit is received, and the next round of hotspot area heat prediction and heat dissipation control is initiated based on this signal. This establishes a closed-loop feedback mechanism for heat dissipation control, ensuring that a new round of prediction and control can be initiated promptly after one heat dissipation operation is completed, guaranteeing the continuity and real-time response capability of the heat dissipation process.

[0016] The above technical solution enables intelligent and proactive heat dissipation control for various hotspot areas of the equipment. It allows for precise heat dissipation based on the heat characteristics and future operating conditions of each hotspot area, avoiding insufficient or excessive heat dissipation, improving heat dissipation efficiency, and reducing energy waste. Furthermore, the distributed temperature sensing and heat dissipation execution architecture based on IoT technology enables differentiated heat dissipation strategies for multiple hotspot areas of the equipment, achieving refined heat dissipation management. Attached Figure Description

[0017] Figure 1 A flowchart illustrating the device heat dissipation optimization method based on the Industrial Internet of Things provided in this application; Figure 2 A schematic diagram of the device heat dissipation optimization system based on the Industrial Internet of Things provided in this application; Figure 3 A schematic diagram of the structure of the electronic device provided in this application; Figure 4 This is a schematic diagram of the structure of a computer-readable storage medium provided in this application.

[0018] In the attached diagram, the components represented by each number are as follows: The system includes a data acquisition module 110, a regional heat dissipation control module 120, a parameter extraction submodule 121, a heat generation prediction submodule 122, a heat dissipation planning submodule 123, a cycle triggering submodule 124, an electronic device 200, a memory 210, a processor 220, a computer program 211, and a computer-readable storage medium 300.

[0019] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0021] It should be noted that all directional indicators (such as up, down, left, right, front, back, etc.) in the embodiments of this application are only used to explain the relative positional relationship and movement of each component under a certain preset posture (as shown in the figure). If the preset posture changes, the directional indicator will also change accordingly.

[0022] In this application, unless otherwise expressly specified and limited, the terms "connection," "fixed," etc., should be interpreted broadly. For example, "fixed" can mean a fixed connection, a detachable connection, or an integral part; it can mean a mechanical connection or an electrical connection; it can mean a direct connection or an indirect connection through an intermediate medium; it can mean the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0023] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the meaning of "and / or" throughout the text includes three parallel solutions; for example, "A and / or B" includes solution A, solution B, or a solution where both A and B are satisfied simultaneously. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0024] The first embodiment of this application provides a device heat dissipation optimization method based on the Industrial Internet of Things. The method is applied to a device heat dissipation optimization system, which connects temperature sensing units and heat dissipation execution units set in multiple hot spots on the target device through the Internet of Things.

[0025] Specifically, this method is applied to a device heat dissipation optimization system. This system employs an Internet of Things (IoT) architecture, interconnecting temperature sensing units and heat dissipation execution units located in multiple hotspot areas of the target device via wireless or wired network connections. The temperature sensing units monitor temperature changes in each hotspot area, while the heat dissipation execution units implement precise heat dissipation control for their respective hotspot areas. This system achieves integrated management of data acquisition, device control, and information processing through IoT technology, providing the infrastructure support for intelligent heat dissipation optimization of the target device.

[0026] like Figure 1 As shown, the method includes: S1: Obtain the preset operating parameter timing set of the target device; S2: During the operation of the target equipment, heat dissipation control is performed on each hotspot area. The heat dissipation control includes: S21: Collect the real-time temperature of the hot spot area through the temperature sensing unit, and simultaneously extract the subsequent operating parameter timing according to the preset operating parameter timing set; S22: Based on the heat prediction device corresponding to the hot spot area, the heat prediction of the hot spot area is performed according to the real-time temperature and subsequent operating parameter sequence, and the heat temperature change curve of the hot spot area is obtained. S23: Determine the heat dissipation start time and heat dissipation period based on the heat dissipation temperature change curve, and configure the heat dissipation execution unit based on the heat dissipation start time and heat dissipation period; S24: Receive the heat dissipation completion signal from the heat dissipation execution unit, and start the next round of hot spot area heat prediction and heat dissipation control based on the heat dissipation completion signal.

[0027] Specifically, the first step is to acquire the preset operating parameter time series set for the target device. The target device refers to the equipment requiring optimized heat dissipation control, typically a large device that generates significant heat and has multiple hotspot areas during operation. The preset operating parameter time series set contains key operating parameters of the target device at different operating stages and their time-varying data sequences. These operating parameters may include, but are not limited to, parameters such as device power, load status, and operating frequency. Acquiring this data in advance lays the foundation for subsequent intelligent heat dissipation control, enabling proactive management of device heat dissipation.

[0028] After the target equipment is put into normal operation, heat dissipation control is implemented separately for each hotspot area. This strategy of independent control for each area differs from the traditional overall heat dissipation method, enabling precise and differentiated heat dissipation management to address the uneven heat distribution within the equipment. The system formulates and executes corresponding heat dissipation strategies based on the actual temperature status and predicted temperature change trends of each hotspot area, avoiding the problems of insufficient or excessive heat dissipation in some areas due to globally uniform heat dissipation. Furthermore, the heat dissipation control of each hotspot area operates independently yet collaboratively, forming an overall heat dissipation optimization network to ensure that the entire equipment maintains optimal temperature conditions under various operating conditions.

[0029] Specifically, for each hotspot area, firstly, real-time temperature data is collected from the target area using temperature sensing units deployed in the hotspot area. These temperature sensing units can be thermocouples, thermistors, infrared temperature sensors, or other temperature detection devices suitable for the target device's operating environment, capable of continuously monitoring temperature changes in the hotspot area at a preset sampling frequency. Simultaneously with acquiring the real-time temperature, operating parameter time series for a subsequent period is synchronously extracted from the acquired preset operating parameter time series, based on the target device's operating status and time point, and recorded as the subsequent operating parameter time series. The subsequent operating parameter time series includes the target device's expected operating parameters for the future period, such as load changes, power adjustments, and operating mode switching, providing necessary data support for subsequent heat generation prediction. By synchronously acquiring the real-time temperature and the subsequent operating parameter time series, the current state of the device and future operating trends are effectively combined, laying the foundation for accurate prediction of temperature changes in the hotspot area. Then, using the heat generation predictor corresponding to the hotspot area, the collected real-time temperature and the extracted subsequent operating parameter time series are used as input to predict and calculate the temperature changes in the hotspot area over the future period. The heat prediction system is a temperature prediction model built for the hotspot area of ​​the target equipment. Based on the current temperature state of the hotspot area and the future operating parameters of the target equipment, it can accurately predict the temperature change pattern of the hotspot area over a future period, resulting in a heat-temperature change curve reflecting the temperature change of the hotspot area over time. This curve visually presents information such as the temperature rise trend, temperature peak, and possible temperature stability state of the corresponding hotspot area. Through prediction-based heat dissipation control, the limitations of traditional passive response heat dissipation are overcome, enabling proactive judgment of the equipment's heat dissipation needs and providing a basis for timely and efficient implementation of heat dissipation measures.

[0030] Subsequently, the trend characteristics of the heat dissipation curve are analyzed, and combined with preset temperature threshold conditions, the timing of initiating heat dissipation measures and the duration of heat dissipation operation are determined, resulting in the heat dissipation initiation time point and heat dissipation period. This proactive heat dissipation time determination mechanism avoids the lag problem of traditional heat dissipation methods where heat dissipation only begins when the temperature reaches a dangerous level, and also avoids unnecessary premature heat dissipation leading to energy waste. After determining the heat dissipation initiation time point and heat dissipation period, the corresponding heat dissipation execution unit for the hotspot area is configured accordingly. The heat dissipation execution unit initiates the heat dissipation operation at the specified time point according to the configured initiation time point and heat dissipation period, and performs the heat dissipation task for the preset duration, thereby achieving precise temperature control of the hotspot area. Through a prediction-based heat dissipation strategy, heat dissipation efficiency is significantly improved, energy consumption is reduced, and the lifespan of the target equipment is extended. After the heat dissipation execution unit completes heat dissipation according to the configured initiation time point and heat dissipation period, it sends a heat dissipation completion signal to the system. Upon receiving the heat dissipation completion signal, the system uses it as the trigger condition to initiate the next round of heat prediction and heat dissipation control for that hotspot area. Through a closed-loop control mechanism based on the heat dissipation completion signal, the system can form a continuously optimized heat dissipation control process. In this way, the system avoids blind and periodic conflicts in heat dissipation control, ensures that the heat dissipation process in each hot spot area proceeds in an orderly manner, and also enables the optimization of heat dissipation control based on the dynamic changes in the operating status of the target equipment, so as to achieve the best balance between heat dissipation efficiency and equipment performance.

[0031] The aforementioned equipment heat dissipation optimization method achieves precise, differentiated, and proactive heat dissipation management for multiple hotspot areas of the equipment. By utilizing IoT technology to connect temperature sensing units and heat dissipation execution units deployed in each hotspot area, and based on the corresponding heat prediction device for each hotspot area, accurate predictions of future temperature changes are made, thereby determining the timing and strategy for heat dissipation. This overcomes the lag and indiscriminate nature of traditional heat dissipation methods. Through the adoption of a closed-loop feedback control mechanism, the heat dissipation strategy can be optimized according to the actual heat generation situation, effectively solving problems such as uneven heat dissipation and waste of heat dissipation resources in large equipment in existing technologies, improving heat dissipation efficiency, reducing energy consumption, and extending equipment lifespan.

[0032] As an optional implementation, embodiments of this application further include: S3: Obtain the basic feature information of the target device and construct device retrieval constraints based on the basic feature information; S4: Send the device retrieval constraints to the cloud server and receive the heat generation data of multiple sample devices from the cloud server. Each sample device heat generation data includes a time series set of sample device operating parameters and a sample hotspot temperature change dataset. S5: Construct a heat prediction device for each hotspot area based on heat data from multiple sample devices.

[0033] Specifically, firstly, basic characteristic information of the target device is obtained, including but not limited to device model, specifications, internal structure, and power characteristics. Based on this basic characteristic information, device retrieval constraints are constructed to form query conditions for retrieving similar devices in the cloud database. Then, the constructed device retrieval constraints are sent to the cloud server. The cloud server, as a centralized data processing platform, stores a large amount of historical operating data from various types of devices. After receiving the device retrieval constraints, the cloud server searches for sample devices with similar characteristics to the target device in the cloud database according to the device retrieval constraints and returns the heat dissipation data of these sample devices, resulting in multiple sample device heat dissipation data sets. The returned sample device heat dissipation data includes two parts: a time series set of sample device operating parameters and a sample hotspot temperature change dataset. The time series set of sample device operating parameters records the sequence of changes in operating parameters of the sample device under various operating conditions, while the sample hotspot temperature change dataset contains the temperature change records of each hotspot area under the corresponding operating conditions.

[0034] Subsequently, using heat dissipation data from multiple sample devices acquired from the cloud, heat dissipation predictors were constructed for various hotspot areas of the target device. Specifically, based on machine learning technology, by mining the operating patterns and thermal characteristics of a large number of similar devices, targeted heat dissipation predictors were established for different hotspot areas of the target device to accurately predict temperature changes in different hotspot areas. This cloud-based predictor construction method effectively solves the problem of lack of historical data for new devices, improves the accuracy and adaptability of heat dissipation prediction, and lays the foundation for achieving precise heat dissipation control.

[0035] As an optional implementation, a heat prediction system is constructed for each hotspot area based on heat generation data from multiple sample devices, including: S51: Based on multiple hotspot areas, determine the primary hotspot area; S52: For the first hot spot area, extract multiple parameter time series segments from the time series set of operating parameters of each sample device, and extract multiple sets of temperature change data corresponding to each sample hot spot temperature change dataset based on the multiple parameter time series segments. S53: Based on multiple parameter time-series segments and multiple sets of temperature change data, construct the first training dataset for the first hotspot region; S54: Train the first heat prediction device based on the first training dataset; S55: Train the heat prediction device for the remaining hotspot areas by training the first heat prediction device based on heat data from multiple sample devices.

[0036] Specifically, firstly, multiple hotspot areas of the target device are traversed, and one hotspot area is selected each time as the first hotspot area. Next, data extraction is performed on the first hotspot area. Specifically, multiple parameter time-series segments are extracted from the acquired time-series sets of operating parameters for each sample device. These parameter time-series segments include parameter sequences such as device power changes, load status, and operating frequency within the corresponding time period. Then, based on these parameter time-series segments, multiple sets of corresponding temperature change data are extracted from the temperature change dataset of each sample hotspot. These temperature change data record the temperature changes in the hotspot area under specific parameter conditions.

[0037] Subsequently, the extracted time-series parameter segments and corresponding sets of temperature change data are matched and integrated to construct the first training dataset for the first hotspot region. This training dataset contains rich mapping relationships between operating parameters and temperature changes, providing ample learning samples for subsequent predictor training. Next, based on the constructed first training dataset, appropriate machine learning algorithms, such as neural networks and long short-term memory networks, are used to train the first heat prediction device. Through iterative learning, the first heat prediction device gradually masters the temperature change patterns of the first hotspot region, forming a mathematical model capable of accurately predicting temperature changes in this region based on operating parameters. Afterward, following the same method and process for constructing the first heat prediction device for the first hotspot region, dedicated heat prediction devices are trained sequentially for the remaining hotspot regions of the target device.

[0038] Through the above methods, an independent and highly targeted heat prediction device was ultimately built for each hot spot area of ​​the target device, thereby achieving accurate temperature prediction and heat dissipation control for multiple hot spot areas of the entire device.

[0039] As an optional implementation, a first heat prediction device is trained based on a first training dataset, including: S541: Construct a digital twin model of the target device, and identify the first hotspot area in the digital twin model to obtain the first area twin model; S542: Input multiple time-series parameter segments sequentially into the first region twin model to simulate and obtain the corresponding predicted temperature change data; S543: Compare the predicted temperature change data with the corresponding temperature change data, calculate the prediction error, and adjust the twin model of the first region based on the prediction error; S544: Iterate until the prediction error is less than the preset threshold, and use the adjusted first region twin model as the first heat prediction device.

[0040] Specifically, when training the first heat prediction device based on the first training dataset, a digital twin model of the target device is first constructed. The digital twin model is a virtual mapping of the physical entity of the target device, accurately replicating its geometry, operating characteristics, etc. After constructing the complete digital twin model, the first hotspot region is further identified within it, forming a first-region twin model. This region twin model retains all the key features of the first hotspot region while simplifying complex factors unrelated to heat dissipation prediction, thereby improving the efficiency of subsequent simulation calculations. Then, multiple parameter time-series segments extracted from the heat dissipation data of the sample device are sequentially input into the first-region twin model. The first-region twin model simulates the operation of the target device based on these parameter time-series segments, simulating the processes of heat generation, conduction, and accumulation during operation, thereby obtaining predicted temperature change data for the hotspot region under specific parameter conditions. This predicted data reflects the current twin model's understanding and expressive ability regarding the temperature change patterns of the hotspot region.

[0041] Subsequently, the simulated predicted temperature change data is compared and analyzed with the corresponding actual temperature change data in the first training dataset to calculate the prediction error. The prediction error can be calculated using mean square error, mean absolute error, or other error calculation methods. Based on the calculated prediction error, the parameters of the first-region twin model are adjusted and optimized, such as correcting the thermal conductivity coefficient, adjusting the heat capacity, and redefining boundary conditions, so that the prediction results of the first-region twin model are closer to the actual temperature changes. The process of model prediction, error calculation, and model adjustment is iteratively executed to continuously optimize the prediction accuracy of the first-region twin model. When the prediction error is less than a preset threshold (e.g., temperature error less than 0.5℃ or relative error less than 3%), the iteration process terminates, and the finally adjusted and optimized first-region twin model is used as the first heat prediction device. This predictor has fully learned the temperature change pattern of the first hot spot region and can accurately predict the temperature change trend under different operating parameter conditions, providing a reliable basis for subsequent precise heat dissipation control.

[0042] As an optional implementation, the heat dissipation start-up time and heat dissipation period are determined based on the heat generation temperature change curve, including: S231: Obtain the heat dissipation trigger temperature and heat dissipation stop temperature of the hotspot area; S232: Based on the heating temperature change curve, determine the first moment when the predicted temperature of the hot spot area equals the heat dissipation trigger temperature, and take the first moment as the heat dissipation start time point; S233: Obtain the heat dissipation characteristic curve of the heat dissipation execution unit corresponding to the hot spot area, and determine the heat dissipation execution time of the hot spot area based on the heat dissipation characteristic curve; S234: Determine the heat dissipation time period based on the heat dissipation start time and heat dissipation execution duration.

[0043] Specifically, when determining the heat dissipation initiation time and duration for a hotspot area based on its temperature change curve, the following steps are taken: First, the heat dissipation trigger temperature and the heat dissipation stop temperature for the hotspot area are obtained. The heat dissipation trigger temperature is the temperature threshold at which heat dissipation measures need to be initiated, typically set within a certain range below the upper limit of the equipment's safe operating temperature to allow sufficient heat dissipation response time. The heat dissipation stop temperature is the temperature threshold at which heat dissipation measures can be stopped, typically set to a temperature level that ensures the safe and stable operation of the equipment. These two temperature thresholds are key parameters for determining the heat dissipation strategy and can be set according to equipment characteristics, operating environment, and performance requirements. Then, the obtained temperature change curve is analyzed to find the point in time where the predicted temperature equals the heat dissipation trigger temperature. This point is defined as the first moment and used as the heat dissipation initiation time. This method of determining the heat dissipation initiation time based on the predicted curve enables advance deployment of heat dissipation measures, avoiding the temperature lag control problem caused by traditional passive heat dissipation where heat dissipation is only initiated when the temperature rises to the trigger point.

[0044] Subsequently, the heat dissipation characteristic curve of the heat dissipation execution unit corresponding to the hot spot area is obtained. The heat dissipation characteristic curve describes the dynamic process of the heat dissipation execution unit from startup to achieving the expected heat dissipation effect, reflecting the heat dissipation capability of the unit. Based on this heat dissipation characteristic curve, the heat dissipation execution time required to reduce the hot spot area from the heat dissipation trigger temperature to the heat dissipation stop temperature is determined. Next, based on the determined heat dissipation startup time and heat dissipation execution time, a complete heat dissipation time period is defined, that is, the time interval from the heat dissipation startup time to the continuous heat dissipation execution time. By determining the heat dissipation time period, a clear working schedule is provided for the heat dissipation execution unit, ensuring that the heat dissipation measures can effectively control the temperature of the hot spot area in a timely manner without wasting energy due to excessive heat dissipation, thus achieving precise and energy-saving heat dissipation control.

[0045] As an optional implementation, the heat dissipation characteristic curve of the heat dissipation execution unit corresponding to the hot spot area is obtained, including: S2331: Obtain multiple sets of heat dissipation and cooling data for hotspot areas during historical operation; S2332: Generate temperature change curves of the heat dissipation execution unit from the heat dissipation trigger temperature to the heat dissipation stop temperature based on each group of heat dissipation and cooling data, and obtain multiple temperature change curves; S2333: Assign weight coefficients to multiple temperature change curves in chronological order, where the weight coefficient of the temperature change curve that is closer to the current time is larger; S2334: Based on the weighting coefficients of each temperature change curve, perform curve fitting on multiple temperature change curves to obtain the heat dissipation characteristic curve of the heat dissipation execution unit.

[0046] Specifically, firstly, multiple sets of heat dissipation and cooling data for the hotspot area during historical operation are acquired. This data records the complete process of temperature change in the hotspot area over time as the heat dissipation execution unit performs heat dissipation tasks at different times. This historical data originates from real-time monitoring records during normal equipment operation, or from data acquisition under specific heat dissipation test scenarios. Then, for each set of heat dissipation and cooling data, the process of the heat dissipation execution unit reducing the temperature of the hotspot area from the heat dissipation trigger temperature to the heat dissipation stop temperature is extracted, and corresponding temperature change curves are generated, resulting in multiple temperature change curves reflecting the historical heat dissipation effect of the heat dissipation execution unit. Due to variations in equipment operating conditions, ambient temperature, and the status of the heat dissipation device, these temperature change curves may differ to some extent, reflecting the changes in the heat dissipation performance of the heat dissipation execution unit under different conditions.

[0047] Subsequently, weighting coefficients were assigned to the acquired multiple temperature change curves in chronological order. The principle was that the more recent the temperature change curve, the higher its weighting coefficient. This strategy is based on the consideration that the current state of the heat dissipation execution unit is more correlated with its recent state. For example, an exponential decay function was used to assign weights to historical curves, ensuring that the most recent heat dissipation record has the highest reference value, while earlier records have a smaller weighting in the overall evaluation. Then, based on the weighting coefficients of each temperature change curve, a weighted fitting process was performed on the multiple temperature change curves to synthesize the information from them, forming a comprehensive curve that accurately reflects the current heat dissipation characteristics of the heat dissipation execution unit. This comprehensive curve serves as the heat dissipation characteristic curve, providing a reliable basis for determining the heat dissipation time period.

[0048] By constructing a dynamically updated heat dissipation characteristic curve, the system can adapt to changes in the performance of the heat dissipation execution unit over time and under usage conditions, ensuring that the heat dissipation control strategy is always based on the actual heat dissipation capacity of the equipment, thereby achieving the optimal balance between heat dissipation effect and energy utilization.

[0049] As an optional implementation method, embodiments of this application include: S61: Obtain the overall heat detection cycle; S62: When the overall heating detection cycle is triggered, a temperature synchronization acquisition command is sent simultaneously to the temperature sensing units of multiple hot spots. S63: Receive multiple temperature values ​​from the temperature sensing units of each hot spot area; S64: Compare the temperature values ​​of multiple regions with the heat dissipation trigger temperature of the corresponding hot spot region to determine the number of overheated regions; S65: The overheating ratio is obtained based on the number of overheated areas and the total number of multiple hotspot areas; S66: When the over-temperature ratio is greater than or equal to the preset ratio, an audible and visual alarm will be issued.

[0050] Specifically, by regularly monitoring the temperature of various hot spots in the equipment, comprehensive monitoring and early warning of abnormalities in the overall thermal state of the equipment can be achieved.

[0051] First, the system acquires the preset overall thermal detection cycle. This cycle is the time interval at which the system performs comprehensive temperature detection. It can be reasonably set according to equipment characteristics, operating environment, and safety requirements, typically ranging from a few minutes to tens of minutes. A shorter detection cycle is beneficial for timely detection of temperature anomalies but increases the system load; a longer detection cycle can reduce the system load but may delay the anomaly detection time. When the system clock reaches the trigger time of the overall thermal detection cycle, the system simultaneously sends a temperature synchronization acquisition command to the temperature sensing units deployed in multiple hotspot areas. This synchronization acquisition mechanism ensures the time consistency of the acquired temperature data, providing a foundation for accurately assessing the overall thermal state of the equipment. Subsequently, the system receives multiple temperature values ​​returned by the temperature sensing units in each hotspot area after responding to the synchronization acquisition command. These temperature values ​​together constitute a temperature distribution map of the current thermal state of the equipment, reflecting the real-time temperature status of each hotspot area.

[0052] Subsequently, the acquired temperature values ​​from multiple areas are compared and analyzed with the heat dissipation trigger temperature of their respective hot spots. The number of hot spots whose current temperature exceeds the heat dissipation trigger temperature is counted, i.e., the number of over-temperature areas. This statistical result intuitively reflects the distribution of areas with abnormal temperatures within the equipment. Based on the calculated number of over-temperature areas and the total number of hot spots in the target equipment, the over-temperature ratio of the current equipment is calculated. The over-temperature ratio is a percentage value, representing the proportion of hot spots with abnormal temperatures among all hot spots, and is an indicator for assessing the overall thermal state of the equipment. Then, the calculated over-temperature ratio is compared with a preset ratio. When the over-temperature ratio is greater than or equal to the preset ratio, it indicates that the overall thermal state of the equipment has reached or exceeded the safety warning line, and the system immediately issues an audible and visual alarm to remind maintenance personnel to pay attention to the abnormal temperature condition of the equipment and take necessary intervention measures.

[0053] Through the overall thermal status monitoring and alarm mechanism, early detection and warning of abnormal equipment temperature are achieved, effectively preventing the risk of overall equipment overheating caused by local heat dissipation control failure, and providing additional protection for the safe and stable operation of the equipment.

[0054] The second embodiment of this application provides a device heat dissipation optimization system based on the Industrial Internet of Things, such as Figure 2As shown, the industrial IoT-based device heat dissipation optimization system 100 includes a management platform 101, a sensor network platform 102, and an object platform 103 connected in sequence. The object platform 103 includes a target device, which includes a temperature sensing unit and a heat dissipation execution unit. The temperature sensing unit and the heat dissipation execution unit are located in the hotspot area of ​​the target device. The management platform 101 includes a data acquisition module 110 and multiple area heat dissipation control modules 120. The data acquisition module 110 is used to acquire a preset operating parameter time series set of the target device. The multiple area heat dissipation control modules 120 are used to perform heat dissipation control on each of the hotspot areas during the operation of the target device. Each area heat dissipation control module 120 includes a parameter interception submodule 121, a heat generation prediction submodule 122, a heat dissipation planning submodule 123, and a cycle triggering submodule 124. The parameter extraction submodule 121 is used to collect the real-time temperature of the hot spot area through the temperature sensing unit, and simultaneously extract the subsequent operating parameter timing according to the preset operating parameter timing set; the heat prediction submodule 122 is used to predict the heat of the hot spot area based on the heat predictor corresponding to the hot spot area, according to the real-time temperature and the subsequent operating parameter timing, to obtain the heat temperature change curve of the hot spot area; the heat dissipation planning submodule 123 is used to determine the heat dissipation start time point and heat dissipation time period according to the heat temperature change curve, and configure the heat dissipation execution unit based on the heat dissipation start time point and heat dissipation time period; the loop triggering submodule 124 receives the heat dissipation completion signal from the heat dissipation execution unit, and starts the next round of hot spot area heat prediction and heat dissipation control according to the heat dissipation completion signal.

[0055] As an optional implementation, the system further includes a retrieval constraint construction module, a data retrieval module, and a predictor construction module. The retrieval constraint construction module is used to acquire basic feature information of the target device and construct device retrieval constraints based on this basic feature information. The data retrieval module is used to send the device retrieval constraints to a cloud server and receive multiple sample device heating data from the cloud server, wherein each sample device heating data includes a time series set of sample device operating parameters and a sample hotspot temperature change dataset. The predictor construction module is used to construct a heating predictor for each hotspot region based on the multiple sample device heating data.

[0056] As an optional implementation, the predictor construction module includes a first region determination submodule, a data extraction submodule, a training data construction submodule, a first predictor training submodule, and other predictor construction submodules. Specifically, the first region determination submodule determines a first hotspot region based on the plurality of hotspot regions; the data extraction submodule extracts multiple parameter time-series segments from the time-series sets of operating parameters of each of the sample devices for the first hotspot region, and extracts corresponding multiple sets of temperature change data from the temperature change datasets of each sample hotspot based on the multiple parameter time-series segments; the training data construction submodule constructs a first training dataset for the first hotspot region based on the multiple parameter time-series segments and the multiple sets of temperature change data; the first predictor training submodule trains a first heat prediction device based on the first training dataset; and the other predictor construction submodules train heat prediction devices for the other hotspot regions in the same manner as training the first heat prediction device based on the heat data of the plurality of sample devices.

[0057] As an optional implementation, the first predictor training submodule includes a first twin model construction unit, a simulation prediction unit, a model adjustment unit, and an iterative training unit. Specifically, the first twin model construction unit constructs a digital twin model of the target device and identifies a first hotspot region within the digital twin model to obtain a first region twin model; the simulation prediction unit sequentially inputs multiple parameter time-series segments into the first region twin model to simulate corresponding predicted temperature change data; the model adjustment unit compares the predicted temperature change data with the corresponding temperature change data, calculates the prediction error, and adjusts the first region twin model based on the prediction error; the iterative training unit iteratively executes the training until the prediction error is less than a preset threshold, and uses the adjusted first region twin model as the first heat prediction device.

[0058] As an optional implementation, the heat dissipation planning submodule 123 includes a relevant temperature acquisition unit, a start-up time determination unit, a heat dissipation duration determination unit, and a heat dissipation time period determination unit. Specifically, the relevant temperature acquisition unit acquires the heat dissipation trigger temperature and heat dissipation stop temperature of the hotspot area; the start-up time determination unit determines, based on the heat generation temperature change curve, the first moment when the predicted temperature of the hotspot area equals the heat dissipation trigger temperature, and uses this first moment as the heat dissipation start-up time point; the heat dissipation duration determination unit acquires the heat dissipation characteristic curve of the heat dissipation execution unit corresponding to the hotspot area, and determines the heat dissipation execution duration of the hotspot area based on the heat dissipation characteristic curve; and the heat dissipation time period determination unit determines the heat dissipation time period based on the heat dissipation start-up time point and the heat dissipation execution duration.

[0059] As an optional implementation, the heat dissipation duration determination unit includes a historical data acquisition subunit, a curve acquisition subunit, a weight configuration subunit, and a curve fitting subunit. The historical data acquisition subunit acquires multiple sets of heat dissipation and cooling data for the hotspot area during historical operation. The curve acquisition subunit generates multiple temperature change curves for the heat dissipation execution unit, based on each set of heat dissipation and cooling data, representing the temperature change from the heat dissipation trigger temperature to the heat dissipation stop temperature. The weight configuration subunit assigns weight coefficients to the multiple temperature change curves in chronological order, with the weight coefficient of the temperature change curve closer to the current time being larger. The curve fitting subunit performs curve fitting on the multiple temperature change curves based on their weight coefficients to obtain the heat dissipation characteristic curve of the heat dissipation execution unit.

[0060] As an optional implementation, the system also includes a heat dissipation alarm module. This alarm module comprises a detection cycle acquisition submodule, a command sending submodule, a temperature value receiving submodule, an over-temperature determination submodule, an over-temperature ratio submodule, and an audible and visual alarm submodule. Specifically, the detection cycle acquisition submodule acquires the overall heat dissipation detection cycle; the command sending submodule sends a temperature synchronization acquisition command to the temperature sensing units of multiple hotspot areas simultaneously when the overall heat dissipation detection cycle is triggered; the temperature value receiving submodule receives multiple area temperature values ​​sent by the temperature sensing units of each hotspot area; the over-temperature determination submodule compares the multiple area temperature values ​​with the heat dissipation trigger temperature of the corresponding hotspot area to determine the number of over-temperature areas; the over-temperature ratio submodule calculates the over-temperature ratio based on the number of over-temperature areas and the total number of areas in the multiple hotspot areas; and the audible and visual alarm submodule issues an audible and visual alarm when the over-temperature ratio is greater than or equal to a preset ratio.

[0061] The third embodiment of this application provides an electronic device, such as... Figure 3 As shown, the electronic device includes a memory 210, a processor 220, and a computer program 211 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the computer program 211, it implements the device heat dissipation optimization method based on the Industrial Internet of Things in any possible implementation of the first embodiment.

[0062] The fourth embodiment of this application provides a computer-readable storage medium, such as... Figure 4 As shown, a computer program 211 is stored on a computer-readable storage medium 300. When executed by a processor, the computer program 211 implements the device heat dissipation optimization method based on the Industrial Internet of Things in any possible implementation of the first embodiment.

[0063] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for optimizing device heat dissipation based on the Industrial Internet of Things, characterized in that, The method is applied to a device heat dissipation optimization system. The system includes a management platform, a sensor network platform, and an object platform that are sequentially and communicatively connected. The object platform includes a target device, which includes a temperature sensing unit and a heat dissipation execution unit. The temperature sensing unit and the heat dissipation execution unit are located in the hotspot area of ​​the target device. The method includes: Obtain the preset operating parameter timing set of the target device; During the operation of the target device, heat dissipation control is performed on each of the hot spots, and the heat dissipation control includes: The temperature sensing unit collects the real-time temperature of the hot spot area and simultaneously extracts the subsequent operating parameter timing according to the preset operating parameter timing set. Based on the heat prediction device corresponding to the hot spot area, the heat prediction of the hot spot area is performed according to the real-time temperature and the subsequent operating parameter sequence to obtain the heat temperature change curve of the hot spot area. The heat dissipation start time and heat dissipation period are determined based on the heat dissipation temperature change curve, and the heat dissipation execution unit is configured based on the heat dissipation start time and the heat dissipation period. The system receives a heat dissipation completion signal from the heat dissipation execution unit and initiates the next round of hot spot area heat prediction and heat dissipation control based on the heat dissipation completion signal. The heat prediction device is obtained through training a digital twin model. The iterative training of the digital twin model terminates when the prediction error between the predicted temperature change data and the actual temperature change data is less than a preset threshold. When the prediction error is less than the preset threshold, the iterative process terminates. The method further includes: Obtain the overall fever detection cycle; When the overall heating detection cycle is triggered, a temperature synchronization acquisition command is sent simultaneously to the temperature sensing units of multiple hot spot areas. Receive temperature values ​​from multiple areas sent by temperature sensing units in each hotspot area; The number of overheated areas is determined by comparing the temperature values ​​of multiple regions with the heat dissipation trigger temperature of the corresponding hot spot areas. The overheating ratio is obtained based on the number of overheated areas and the total number of multiple hotspot areas. When the over-temperature ratio is greater than or equal to the preset ratio, an audible and visual alarm will be issued.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the basic feature information of the target device, and construct device retrieval constraints based on the basic feature information; The device retrieval constraints are sent to the cloud server, and multiple sample device heat dissipation data are received from the cloud server. Each sample device heat dissipation data includes a time series set of sample device operating parameters and a sample hot spot temperature change dataset. A heat prediction device is constructed for each hotspot area based on the heat generation data of the multiple sample devices.

3. The method according to claim 2, characterized in that, The step of constructing a heat prediction device for each hotspot area based on the heat data from the multiple sample devices includes: Based on the multiple hotspot areas, a first hotspot area is determined; For the first hotspot area, multiple parameter time series segments are extracted from the time series set of operating parameters of each of the sample devices, and based on the multiple parameter time series segments, multiple sets of temperature change data are extracted from the temperature change dataset of each sample hotspot. Based on the time-series segments of the multiple parameters and the multiple sets of temperature change data, a first training dataset is constructed for the first hotspot region. Based on the first training dataset, train the first heat prediction device; The same method is used to train the first heat prediction device based on the heat data of the multiple sample devices, and then train heat prediction devices for the remaining hotspot areas.

4. The method according to claim 3, characterized in that, The step of training the first heat prediction device based on the first training dataset includes: A digital twin model of the target device is constructed, and a first hotspot area is identified in the digital twin model to obtain a first region twin model; The time-series segments of the multiple parameters are sequentially input into the twin model of the first region to simulate and obtain the corresponding predicted temperature change data. The predicted temperature change data is compared with the corresponding temperature change data to calculate the prediction error, and the twin model of the first region is adjusted based on the prediction error. The process is iteratively executed until the prediction error is less than a preset threshold, and the adjusted first region twin model is used as the first heat prediction device.

5. The method according to claim 1, characterized in that, The step of determining the heat dissipation start time and heat dissipation time period based on the heat generation temperature change curve includes: Obtain the heat dissipation trigger temperature and heat dissipation stop temperature of the hotspot area; Based on the heating temperature change curve, determine the first moment when the predicted temperature of the hot spot area is equal to the heat dissipation trigger temperature, and take the first moment as the heat dissipation start time point. Obtain the heat dissipation characteristic curve of the heat dissipation execution unit corresponding to the hot spot area, and determine the heat dissipation execution time of the hot spot area based on the heat dissipation characteristic curve; The heat dissipation time period is determined based on the heat dissipation start time and the heat dissipation execution duration.

6. The method according to claim 5, characterized in that, The step of obtaining the heat dissipation characteristic curve of the heat dissipation execution unit corresponding to the hot spot area includes: Obtain multiple sets of heat dissipation and cooling data for the hotspot area during historical operation; Based on each set of heat dissipation and cooling data, the heat dissipation execution unit generates a temperature change curve from the heat dissipation trigger temperature to the heat dissipation stop temperature, resulting in multiple temperature change curves. The multiple temperature change curves are assigned weight coefficients in chronological order, with the weight coefficient of the temperature change curve that is closer to the current time being larger. Based on the weighting coefficients of each temperature change curve, curve fitting is performed on multiple temperature change curves to obtain the heat dissipation characteristic curve of the heat dissipation execution unit.

7. A device heat dissipation optimization system based on the Industrial Internet of Things, characterized in that, The system includes a management platform, a sensor network platform, and an object platform that are connected in sequence. The object platform includes a target device, and the target device includes a temperature sensing unit and a heat dissipation execution unit. The temperature sensing unit and the heat dissipation execution unit are located in the hot spot area of ​​the target device. The management platform includes: The data acquisition module is used to acquire the preset operating parameter time series set of the target device; Multiple area heat dissipation control modules are used to control the heat dissipation of each hot spot area during the operation of the target device; The heat dissipation control modules for each area include: The parameter extraction submodule is used to collect the real-time temperature of the hot spot area through the temperature sensing unit, and simultaneously extract the subsequent operating parameter timing according to the preset operating parameter timing set. The heat prediction submodule is used to predict the heat of the hot spot area based on the heat predictor corresponding to the hot spot area, according to the real-time temperature and the timing of the subsequent operating parameters, and to obtain the heat temperature change curve of the hot spot area. The heat dissipation planning submodule is used to determine the heat dissipation start time and heat dissipation period based on the heat generation temperature change curve, and to configure the heat dissipation execution unit based on the heat dissipation start time and the heat dissipation period. The loop trigger submodule receives the heat dissipation completion signal from the heat dissipation execution unit and starts the next round of hot spot area heat prediction and heat dissipation control based on the heat dissipation completion signal.

8. An electronic device, characterized in that, include: Memory, used to store computer software programs; A processor for reading and executing the computer software program to implement the method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, characterized in that, The storage medium stores a computer software program, which, when executed by a processor, implements the method as described in any one of claims 1 to 6.

Images