Heat dissipation self-adaptive adjusting method and device for electrical switch cabinet

Abstract

The invention provides a heat dissipation adaptive adjustment method and device for an electrical switch cabinet, and relates to the technical field of intelligent heat dissipation. Dynamic temperature detection is performed on a predetermined part of the electrical switch cabinet through a sensor to obtain a real-time detection temperature value set; generating an initial temperature visual graph according to the temperature value with the coordinate identifier, obtaining a first position coordinate in the initial temperature visual graph, building a part set of the switch cabinet, matching a first neighborhood part set, and introducing a temperature feedback evaluation integrated fusion model to carry out feedback evaluation on dynamic operation information to obtain a feedback heat generation and dissipation index, the predicted temperature value is rendered to the initial temperature visual graph, heat dissipation self-adaptive adjustment is carried out on the switch cabinet according to the target temperature visual graph, the problem that the heat dissipation efficiency is affected due to the fact that the heat dissipation mode of the electrical switch cabinet lacks flexibility and self-adaptability and heat dissipation adjustment cannot be effectively carried out is solved, and the purposes of effectively carrying out heat dissipation self-adaptive adjustment and improving the heat dissipation efficiency are achieved. The heat dissipation performance is dynamically optimized, and the safety and stability of equipment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent heat dissipation, and in particular to a heat dissipation self-adapting adjustment method and device for an electrical switch cabinet. Background Art

[0002] In power systems and electronic equipment, electrical switchgear is a common electrical equipment widely used in various control and distribution circuits. Since the internal equipment of the switchgear generates a lot of heat energy during operation, if the heat dissipation measures are insufficient, it may cause the equipment to overheat and affect the performance of the equipment and shorten the life of the equipment. In severe cases, it may even cause safety accidents. Therefore, the development of effective heat dissipation control technology is crucial to ensure the stable operation of the electrical switchgear. In the prior art, common heat dissipation methods for electrical switchgear mainly include natural heat dissipation and forced heat dissipation. Natural heat dissipation depends on the design of the cabinet structure and discharges heat through natural convection and thermal radiation, while forced heat dissipation accelerates heat exchange by installing cooling equipment such as fans. However, these traditional heat dissipation methods have many limitations, such as low efficiency of natural heat dissipation and inability to cope with high heat load conditions; although forced heat dissipation is more efficient, it will increase energy consumption and equipment costs, and have a greater impact on environmental noise. In addition, the existing heat dissipation systems mostly adopt fixed heat dissipation strategies, which leads to insufficient optimization of heat dissipation efficiency and energy consumption under different environmental conditions and load changes, and cannot match the actual heat dissipation requirements of the equipment.

[0003] In summary, existing heat dissipation methods for electrical switch cabinets often lack flexibility and adaptability, and are unable to effectively adjust the heat dissipation according to the actual temperature changes inside the electrical switch cabinet, thereby affecting the heat dissipation efficiency and increasing energy consumption and safety risks. Summary of the invention

[0004] The present application provides a method and device for adaptively adjusting heat dissipation for an electrical switch cabinet, which is used to solve the technical problem that the heat dissipation method of the electrical switch cabinet lacks flexibility and adaptability, and cannot effectively adjust the heat dissipation according to the actual temperature changes inside the electrical switch cabinet, thereby affecting the heat dissipation efficiency and increasing energy consumption and safety risks.

[0005] In view of the above problems, the present application provides a method and device for adaptively adjusting heat dissipation of an electrical switch cabinet.

[0006] In a first aspect, the present application provides a heat dissipation adaptive adjustment method for an electrical switch cabinet, the method comprising:

[0007] Dynamic temperature detection is performed on predetermined parts of the electrical switch cabinet by means of a temperature sensor to obtain a real-time detection temperature value set, wherein the real-time detection temperature value set includes a plurality of temperature values ​​with coordinate identifiers; an initial temperature visual graph of the electrical switch cabinet is generated according to the plurality of temperature values ​​with coordinate identifiers, and a first position coordinate in the initial temperature visual graph is obtained, wherein the first position coordinate corresponds to a first position neighborhood; a part set of the electrical switch cabinet is formed, and a first neighborhood part set of the first position neighborhood is matched in the part set; a temperature feedback evaluation integrated fusion model is introduced to perform feedback evaluation on the first dynamic operation information of the first neighborhood part in the first neighborhood part set to obtain a first feedback heat generation and heat dissipation index; a first predicted temperature value of the first position coordinate obtained by analyzing the first feedback heat generation and heat dissipation index is rendered to the initial temperature visual graph to obtain a target temperature visual graph; and heat dissipation of the electrical switch cabinet is adaptively adjusted according to the target temperature visual graph.

[0008] In a second aspect, the present application provides a heat dissipation adaptive adjustment device for an electrical switch cabinet, the device comprising:

[0009] A temperature detection module is used to perform dynamic temperature detection on a predetermined part of the electrical switch cabinet through a temperature sensor to obtain a real-time detection temperature value set, wherein the real-time detection temperature value set includes a plurality of temperature values ​​with coordinate identifiers; a temperature visual map generation module is used to generate an initial temperature visual map of the electrical switch cabinet according to the plurality of temperature values ​​with coordinate identifiers, and obtain a first position coordinate in the initial temperature visual map, wherein the first position coordinate corresponds to a first position neighborhood; a part position matching module is used to form a part set of the electrical switch cabinet, and match a first neighborhood part set of the first position neighborhood in the part set; a feedback evaluation module is used to introduce a temperature feedback evaluation integrated fusion model to perform feedback evaluation on the first dynamic operation information of the first neighborhood part in the first neighborhood part set, and obtain a first feedback heat generation and heat dissipation index; a temperature rendering module is used to render the first predicted temperature value of the first position coordinate obtained by analyzing the first feedback heat generation and heat dissipation index to the initial temperature visual map, and obtain a target temperature visual map; an intelligent adjustment module is used to perform adaptive heat dissipation adjustment on the electrical switch cabinet according to the target temperature visual map.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] The present application provides a heat dissipation adaptive adjustment method for an electrical switch cabinet. The method performs dynamic temperature detection on a predetermined part of the electrical switch cabinet by a temperature sensor to obtain a real-time detection temperature value set, wherein the real-time detection temperature value set includes a plurality of temperature values ​​with coordinate identifiers; generates an initial temperature visual graph of the electrical switch cabinet according to the plurality of temperature values ​​with coordinate identifiers, and obtains a first position coordinate in the initial temperature visual graph, wherein the first position coordinate corresponds to a first position neighborhood; forms a part set of the electrical switch cabinet, and matches a first neighborhood part set of the first position neighborhood in the part set; introduces a temperature feedback evaluation integrated fusion model to dynamically operate the first neighborhood part of the first neighborhood part set; The information is fed back and evaluated to obtain a first feedback heat dissipation index; the first predicted temperature value of the first position coordinate obtained by analyzing the first feedback heat dissipation index is rendered to the initial temperature visual graph to obtain a target temperature visual graph; the heat dissipation of the electrical switch cabinet is adaptively adjusted according to the target temperature visual graph, which solves the technical problems of lack of flexibility and adaptability in the heat dissipation method of the electrical switch cabinet, inability to effectively adjust the heat dissipation according to the actual temperature changes inside the electrical switch cabinet, thereby affecting the heat dissipation efficiency and increasing energy consumption and safety risks, and achieves the technical effect of effectively performing heat dissipation adaptive adjustment of the electrical switch cabinet, dynamically optimizing the heat dissipation performance, significantly improving the safety and stability of the equipment, and reducing energy consumption and operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic flow chart of a method for adaptively adjusting heat dissipation of an electrical switch cabinet is provided for this application.

[0013] Figure 2 A schematic structural diagram of a heat dissipation adaptive adjustment device for an electrical switch cabinet is provided for this application.

[0014] Explanation of the reference numerals: temperature detection module 11 , temperature visual graph generation module 12 , part position matching module 13 , feedback evaluation module 14 , temperature rendering module 15 , intelligent adjustment module 16 . DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides a heat dissipation adaptive adjustment method for an electrical switch cabinet, the method comprising:

[0017] Dynamic temperature detection is performed on a predetermined part of the electrical switch cabinet by a temperature sensor to obtain a real-time detection temperature value set, wherein the real-time detection temperature value set includes a plurality of temperature values ​​with coordinate identifiers.

[0018] Specifically, dynamic temperature detection of the switchgear is achieved by configuring temperature sensors at key parts of the electrical switchgear, such as busbars, circuit breakers and transformers, as well as heat dissipation equipment, including fans, heat sinks and heat exchangers. These parts are considered to be the key areas with the greatest impact on heat dissipation performance, and their temperature management is crucial to ensuring the overall operation safety and efficiency of the switchgear. In this process, the deployed temperature sensors will continuously collect real-time temperature data from key parts. Subsequently, the real-time detected temperature values ​​are continuously collected and integrated into a data set, and each temperature value has a unique coordinate identifier, which not only includes the temperature reading, but also clearly indicates the specific location of the source of each temperature value, such as a circuit breaker or a specific heat sink. This design makes it possible to accurately track and record the changes in temperature at different locations inside the switchgear, providing precise spatial positioning for subsequent data analysis and heat dissipation adjustment. A real-time temperature value set containing multiple temperature values ​​with coordinate identifiers generated by real-time monitoring can provide an analytical basis for subsequent analysis. For example, if the temperature of a circuit breaker rises abnormally, the sensor can not only detect this change, but also point out the specific abnormal location through the coordinate identifier, which is very helpful for early identification of potential overheating problems, timely heat dissipation adjustment or necessary maintenance and repair. In summary, the temperature monitoring and data collection steps not only enhance the temperature management of key parts in the electrical switchgear, but also support the implementation of more accurate and effective heat dissipation control strategies through detailed coordinate data, ultimately achieving the purpose of optimizing the heat dissipation efficiency of the switchgear, extending the service life of the equipment, and reducing energy consumption and operation and maintenance costs.

[0019] An initial temperature visual graph of the electrical switch cabinet is generated according to the multiple temperature values ​​with coordinate identifiers, and a first position coordinate in the initial temperature visual graph is obtained, where the first position coordinate corresponds to a first position neighborhood.

[0020] Optionally, after real-time temperature monitoring, the obtained multiple temperature values ​​with coordinate identifiers are used to generate an initial temperature visualization of the electrical switch cabinet. The visualization is a graphical representation that depicts the temperature distribution of various parts in the electrical switch cabinet in detail, where the position of each temperature point is clearly indicated by its coordinate identifier, so that the spatial distribution of the temperature can be identified at a glance. This visualization not only shows the real-time temperature data of the key parts, but also includes the results of temperature prediction of non-key parts through relevant algorithms. After generating the initial temperature visualization, the system automatically identifies and marks a specific first position coordinate, which represents a non-key part in the electrical switch cabinet. Non-key parts are usually not directly involved in critical operations or heat generation, but their temperature conditions are still important for a comprehensive understanding of the thermal management status of the switch cabinet. The selection of the first position coordinate is based on a series of preset criteria, such as abnormal temperature changes or potential hot spots shown in the prediction results. Once the first position coordinate is determined, the first position neighborhood corresponding to the coordinate is further obtained. This step involves defining the spatial area around the coordinate, usually including several temperature points around the point, forming a regional temperature analysis range. The setting of this neighborhood allows the system to focus on more accurate monitoring and analysis of adjacent parts that may be affected by the temperature of the first location point. In this way, even temperature changes in non-critical parts can be effectively monitored and predicted, thereby ensuring that every part of the switchgear is properly paid attention to and managed in the overall cooling strategy to prevent any heat-related problems that may cause equipment performance degradation or failure. This comprehensive temperature monitoring and visualization further enhances the intelligence and adaptability of the cooling system, ensuring that the electrical switchgear can maintain the optimal temperature state under various operating conditions.

[0021] A part set of the electrical switch cabinet is formed, and a first neighborhood part set of the first position neighborhood is matched in the part set.

[0022] Exemplarily, after generating the initial temperature visualization graph and identifying the first position coordinate, a part set including all parts of the electrical switch cabinet is formed next. This part set includes not only key parts, such as busbars, circuit breakers and transformers, but also non-key parts, that is, those parts that are not directly involved in the main electrical operation but still play an important role in thermal management. This set is established to comprehensively monitor and manage the temperature conditions of various parts in the switch cabinet to ensure the thermal balance of the entire system. After the part set is constructed, the first neighborhood part set of the first position neighborhood is matched in this set. Specifically, all parts located in the neighborhood specified by the first position coordinate are identified and selected to form the first neighborhood part set. This operation involves analyzing the surrounding area of ​​the first position coordinate and determining which parts are located in this neighborhood. For example, if the first position coordinate points to a non-critical heat dissipation part in the switch cabinet, such as the area near the auxiliary heat dissipation fan, the first neighborhood part set may include a cable channel, a small circuit breaker, etc. adjacent to the fan. The purpose of this step is to ensure that each part in the neighborhood can be properly considered in subsequent temperature management and heat dissipation regulation, especially those parts that may be affected by temperature changes in the first position. Through this method, not only can the temperature of key parts be effectively managed and monitored, but also attention can be paid to non-key parts that may be overlooked in routine monitoring. Such comprehensive management ensures that the electrical switchgear can maintain good heat dissipation performance and equipment safety under various operating conditions.

[0023] A temperature feedback evaluation integrated fusion model is introduced to perform feedback evaluation on the first dynamic operation information of the first neighborhood part in the first neighborhood part set to obtain a first feedback heat dissipation index.

[0024] Furthermore, in order to further optimize the heat dissipation management of the electrical switchgear, a temperature feedback evaluation integrated fusion model is introduced. The main purpose of this model is to monitor and feedback the first dynamic operation information of each part of the first neighborhood part set in real time, so as to adjust the heat dissipation measures in time and ensure that the temperature of all relevant parts is kept within a safe range. Specifically, the model integrates advanced data processing technologies, including real-time data collection, dynamic data analysis, and machine learning algorithms, to automatically process and evaluate the temperature data of each neighborhood part. The first dynamic operation information of these parts, including but not limited to real-time temperature, temperature change rate and its historical temperature data, is the key input for evaluation. Real-time tracking and analysis of this information can help the system understand the current heat dissipation effect more accurately and predict possible heat dissipation problems in the future. Then, by applying the feedback evaluation algorithm, the model calculates the first feedback heat dissipation index, which is a quantitative indicator obtained based on the temperature performance and heat dissipation requirements of each part, reflecting the effectiveness of the current heat dissipation strategy and the urgency of possible adjustments. For example, if the feedback heat dissipation index of a part is abnormally high, this may indicate that the heat dissipation of the part is insufficient and additional heat dissipation measures are required. Through this method, the integrated fusion model of temperature feedback evaluation can not only monitor the cooling effect in real time, but also make specific cooling adjustment suggestions based on dynamic data, making the cooling management of the electrical switch cabinet more intelligent and adaptive, greatly improving the operating efficiency and safety of the equipment. At the same time, the automation and intelligence of the entire process reduces the need for human intervention and ensures the continuity and efficiency of cooling management.

[0025] The first predicted temperature value of the first position coordinate obtained by analyzing the first feedback heat dissipation index is rendered to the initial temperature visual graph to obtain a target temperature visual graph.

[0026] The heat dissipation of the electrical switch cabinet is adaptively adjusted according to the target temperature visual map.

[0027] Specifically, after the temperature feedback evaluation integrated fusion model evaluates the first dynamic operation information of the first neighborhood part set, the first feedback heat dissipation index is used to predict the first predicted temperature value of the first position coordinate. This predicted temperature value is calculated by an algorithm based on the current heat dissipation status and heat dissipation demand, and reflects the temperature that the location may reach within a certain period of time in the future if no additional heat dissipation measures are taken. This step is crucial for early prevention of overheating problems and can effectively guide the adjustment of the heat dissipation system. This first predicted temperature value is rendered into the initial temperature visualization, and the image is updated to generate a target temperature visualization. In this process, the first predicted temperature value is displayed in different colors or intensities in the visualization, identifying hot spots that may need attention or adjustment. This visualization method not only intuitively displays the current and predicted temperature status of each part, but also helps operation and maintenance personnel to quickly identify problem areas and make decisions. Based on the updated target temperature visualization, the system will perform heat dissipation adaptive adjustment measures, including but not limited to adjusting fan speed, starting additional heat dissipation equipment, or reconfiguring the layout of heat dissipation components. Adaptive adjustment is based on real-time and predicted temperature data to ensure that the temperature of each part can be maintained within a safe and optimal operating range. This intelligent heat dissipation adjustment strategy uses advanced control systems to dynamically adjust heat dissipation parameters based on real-time data and prediction results, optimize heat dissipation effects, reduce energy consumption, and prevent overheating risks. Through this coherent process, highly automated and intelligent heat dissipation management is achieved, significantly improving the reliability and efficiency of electrical switchgear. In addition, the entire process fully considers the dynamic changes and complexity in actual operation to ensure optimal heat dissipation performance under various operating conditions.

[0028] Furthermore, a temperature feedback evaluation integrated fusion model is introduced to perform feedback evaluation on the first dynamic operation information of the first neighborhood part of the first neighborhood part set, including:

[0029] Extract any part from the part set.

[0030] The historical heat generation and heat dissipation records of the same type of the arbitrary part are obtained, and the historical heat generation and heat dissipation records include first historical record data.

[0031] A first training data group is formed based on the first operating characteristic data and the first heat generation and heat dissipation index in the first historical record data.

[0032] The first training data set is subjected to supervised learning, and any feedback evaluation model of the any part is obtained by verification.

[0033] The temperature feedback evaluation integrated fusion model is constructed through the arbitrary feedback evaluation model.

[0034] Further, any part is extracted from the part set of the electrical switch cabinet. The purpose of this step is to ensure that the model can cover the heat dissipation conditions of all critical and non-critical parts in the switch cabinet, so as to achieve comprehensive temperature monitoring and management. The extracted parts can be busbars and circuit breakers with high temperature risks, or fans and heat sinks that are critical for heat dissipation. Subsequently, the historical heat dissipation records of similar parts of the extracted parts are obtained. These historical records include first historical record data, such as past temperature readings, heat dissipation efficiency, equipment operation status, etc., which provide the heat dissipation performance and characteristics of each part under different operating conditions. The analysis of historical heat dissipation records is crucial to understanding the typical heat dissipation behavior patterns of each part. Next, a first training data group is established based on the first operating characteristic data and the first heat dissipation index group in the first historical record data. This data group integrates key operating characteristics and corresponding heat dissipation indexes, and provides necessary input variables for subsequent model training. These variables enable the model to learn the complex relationship from operating status to heat dissipation requirements by accurately describing the heat dissipation performance of the parts under specific conditions. Then, supervised learning is performed on the first training data group, and any feedback evaluation model of the arbitrary part is obtained by verification. The supervised learning process uses algorithms to analyze patterns in the training data and trains a model that can predict heat dissipation requirements. This model has been repeatedly tested and verified to ensure the accuracy and reliability of its predictions. Finally, the temperature feedback evaluation integrated fusion model is built through the arbitrary feedback evaluation model. The integrated fusion model brings together the feedback evaluation models of all individual parts to form a comprehensive heat dissipation evaluation system. This system can receive temperature data from various parts of the switch cabinet in real time, quickly evaluate the current heat dissipation status, and adjust the heat dissipation measures according to the prediction results to achieve adaptive heat dissipation. Through this process, the heat dissipation performance of each part of the electrical switch cabinet can be accurately monitored and efficiently adjusted intelligently, greatly improving the heat dissipation efficiency of the system and the operating safety of the equipment.

[0035] Furthermore, forming a first training data group based on the first operation characteristic data and the first heat generation and heat dissipation index in the first historical record data includes:

[0036] Obtain any heat generation and dissipation type of the any part.

[0037] When the arbitrary heat generation and dissipation type is a heat generation location, the first heat generation and dissipation index is recorded as a positive number.

[0038] When the arbitrary heat generation and heat dissipation type is a heat dissipation location, the first heat generation and heat dissipation index is recorded as a negative number.

[0039] Optionally, each part in the switch cabinet is classified to determine its heat generation and heat dissipation type. The heat generation and heat dissipation types are mainly divided into two categories, namely heat-generating parts and heat-dissipating parts. Heat-generating parts refer to components that generate heat during normal operation, such as transformers and circuit boards, which generate heat due to the passage of current or the operation of equipment; while heat-dissipating parts refer to components that play a cooling role, such as fans and heat sinks, which help cool the entire system by dissipating heat. After determining the heat generation and heat dissipation type of the part, a quantitative value is then assigned, namely the first heat generation and heat dissipation index. For heat-generating parts, the first heat generation and heat dissipation index is recorded as a positive number, and the size of this positive number reflects the intensity of heat generation in the part; for heat-dissipating parts, the first heat generation and heat dissipation index is recorded as a negative number, and the absolute value of the negative number indicates the efficiency of its heat dissipation. In this way, the impact of each part on the temperature of the entire system can be quantified, whether it is heating or cooling. Then, based on the first operating characteristic data in the first historical record data of each part and the corresponding first heat generation and heat dissipation index, a first training data group is constructed. This data group collects all relevant information about the operating status of the part and its impact on the heat dissipation of the system, including but not limited to the current size, operating frequency, historical temperature records, etc. when the equipment is running, and the corresponding heat generation and heat dissipation index. Through this systematic data preparation process, sufficient and accurate training materials are provided for subsequent supervised learning. These training data can not only help the model learn to identify the heat dissipation characteristics of each part, but also predict the heat dissipation requirements under specific operating conditions, and provide scientific data support for the heat dissipation adaptive adjustment of the electrical switch cabinet. This process significantly improves the intelligence level of heat dissipation management and ensures the safe and stable operation of the switch cabinet under various environments and load conditions.

[0040] Furthermore, rendering the first predicted temperature value of the first position coordinate obtained by analyzing the first feedback heat dissipation index to the initial temperature visual graph to obtain a target temperature visual graph includes:

[0041] An average value of the actual detected temperatures of the plurality of temperature values ​​with coordinate identifiers is obtained.

[0042] The first feedback heat dissipation index is used as a weight to weight the actual detected temperature average to obtain the first predicted temperature value.

[0043] Specifically, the actual detected temperature averages of all temperature values ​​with coordinate identifiers in the electrical switch cabinet are collected and calculated. These temperature values ​​come from temperature sensors distributed in key parts of the switch cabinet. The data provided by each sensor contains specific location information (coordinate identifiers), so that each temperature reading can accurately correspond to a specific part of the switch cabinet. The average of these temperature values ​​is calculated to obtain an average temperature level of the switch cabinet from a global perspective, and this average value serves as the basis for subsequent analysis. Next, the above actual detected temperature averages are weighted with the first feedback heat generation and heat dissipation index as the weight, so as to obtain the first predicted temperature value of the first position coordinate. The first feedback heat generation and heat dissipation index reflects the heat dissipation or heat generation performance of the position, where a positive number indicates a heat generation part and a negative number indicates a heat dissipation part. Using this index as a weight for weighting means adjusting the temperature prediction affected by the part according to the heat generation or heat dissipation characteristics of the part to ensure that the prediction is more in line with the actual situation. Finally, the first predicted temperature value calculated by the above method is rendered back to the corresponding first position coordinate in the initial temperature visual graph. This step generates a target temperature visualization by updating the initial temperature visualization. This visualization not only shows the actual temperature of each part at present, but also shows the temperature change trend that may occur in the future through the predicted temperature value. The target temperature visualization provides an intuitive tool for the system to help operation and maintenance personnel identify hot spots that may need extra attention or adjustment, so as to make targeted cooling adjustments. In this way, not only the heat dissipation management is optimized, but also the ability to prevent overheating and optimize the heat dissipation effect is improved, ensuring that the electrical switch cabinet can operate safely and stably under the optimal temperature conditions.

[0044] Furthermore, the first feedback heat dissipation index is used as a weight to weight the actual detected temperature average to obtain the first predicted temperature value, and then the following further includes:

[0045] A first temperature value corresponding to a first coordinate from among the plurality of temperature values ​​with coordinate identifiers is extracted.

[0046] A first spatial distance between the first coordinate and the first position coordinate is obtained.

[0047] The first temperature value is weighted by taking the first spatial distance as a weight to obtain a second predicted temperature value.

[0048] The first predicted temperature value is verified according to the second predicted temperature value.

[0049] Exemplarily, in order to further improve the accuracy and reliability of the prediction, a more detailed verification and optimization step is introduced, including further weighting and verification of the first predicted temperature value. First, the first temperature value corresponding to the first coordinate (i.e., the coordinate of the specific position concerned in the previous analysis) is extracted from the multiple temperature values ​​with coordinate identifiers. This first temperature value is directly obtained from the real-time temperature monitoring data and reflects the temperature state of the specific position at a specific time point. Next, the first spatial distance between the first coordinate and the first position coordinate (i.e., the target position for prediction and analysis) is calculated. The calculation of the spatial distance is based on the actual position relationship between the two coordinate points in the switch cabinet. This distance is an important factor in evaluating the temperature correlation between the two positions, because the temperature propagation is not instantaneously uniform in space and is affected by the layout of components and heat dissipation characteristics. Then, the first temperature value is weighted with the first spatial distance as the weight. The purpose of this step is to adjust the influence of the first temperature value and ensure that the prediction model takes into account the spatial distance factor, so that the prediction result is more in line with the actual situation. The closer the spatial distance is, the greater the influence of its temperature state on the target position. Finally, the first predicted temperature value is verified according to the obtained second predicted temperature value. This verification step is to ensure the accuracy and reliability of the first predicted temperature value. As a corrected prediction result, the second predicted temperature value provides a comparison benchmark to help determine whether the first predicted temperature value needs to be adjusted. If there is a significant difference between the two, it may be necessary to return to the model adjustment step and reconsider the input parameters or weighting logic. Through these steps, the accuracy of the heat dissipation prediction model can be systematically improved, and the temperature management and heat dissipation adaptive adjustment of the electrical switch cabinet can be effectively realized, ensuring that the system can maintain the optimal temperature state under various operating conditions, thereby improving the safety and efficiency of the equipment.

[0050] Furthermore, adaptively adjusting the heat dissipation of the electrical switch cabinet according to the target temperature visual map includes:

[0051] The color saliency strategy is called to perform color saliency analysis on the target temperature visual graph to obtain the target saliency position.

[0052] The mobile temperature sensing probe is activated to perform dynamic temperature detection on a prominent position of the target to obtain a target temperature value.

[0053] When the target temperature value exceeds a predetermined temperature threshold, an abnormal heat generation and dissipation warning is issued to the electrical switch cabinet.

[0054] Furthermore, the color significance strategy is implemented on the target temperature visual map to perform color significance analysis. In this step, the color distribution in the target temperature visual map is analyzed to identify those areas with high color significance, which usually indicates that the temperature in these areas is relatively high or there is a significant temperature change. Color significance analysis is an effective visual processing technology that highlights important temperature information by enhancing color contrast and saturation, so that operation and maintenance personnel can quickly identify hot spots that need attention. Next, the mobile temperature sensor probes are activated to perform dynamic temperature detection on the identified target significant positions. These mobile sensor probes are specially designed to move flexibly in the switch cabinet, directly contact or approach the target significant positions to obtain more accurate temperature readings. Dynamic temperature detection can monitor the real-time temperature status of each key part in real time, providing more accurate and real-time data than static sensors. Finally, when the detected target temperature value exceeds the predetermined temperature threshold, an abnormal heat dissipation warning will be automatically issued. This warning mechanism is based on a pre-set safety temperature standard. Once the temperature of a certain part exceeds this standard, it means that there may be problems such as insufficient heat dissipation or equipment overload. The system will immediately notify the maintenance personnel to check and intervene through sound, light signals or message push. This step ensures that the electrical switchgear can operate safely and stably at the optimal operating temperature, significantly improving the reliability and safety of the system while reducing equipment failures and maintenance costs caused by heat dissipation problems.

[0055] Furthermore, calling a color saliency strategy to perform color saliency analysis on the target temperature visual graph to obtain a target saliency position includes:

[0056] A target red channel visual image of the target temperature visual image is obtained according to the color saliency strategy.

[0057] A target green channel visual image of the target temperature visual image is obtained according to the color saliency strategy.

[0058] A target blue channel visual graph of the target temperature visual graph is obtained according to the color saliency strategy.

[0059] Obtain target repeated significant areas of the target red channel visible image, the target green channel visible image, and the target blue channel visible image.

[0060] The target repeated significant area is used as the target significant position of the target temperature visual map.

[0061] Specifically, the visual graphs of the red, green and blue channels in the target temperature visual graph are obtained respectively according to the color saliency strategy. This step is based on the color separation technology in image processing to decompose the composite color image into its basic color components. Each color channel independently represents the intensity distribution of the image on the corresponding color spectrum, which is crucial for the subsequent color saliency analysis. Then, the saliency of the three color channel visual graphs will be analyzed separately. By applying advanced image processing algorithms, such as those based on color contrast, edge detection or color clustering technology, it is possible to evaluate which areas in each channel have the most significant color changes, which usually correspond to abnormal or critical changes in temperature. Then, the salient areas of the three color channels are compared to determine the repeated salient areas that exist in all three channels. This step is achieved by cross-comparing the saliency results of the three color channels, with the aim of finding the areas that are commonly identified as salient by all channels, which are considered to be the most likely locations to represent true temperature anomalies. Finally, these cross-validated salient areas are marked as target salient locations of the target temperature visual graph. At this point, these locations will be used as key focus areas for subsequent dynamic temperature detection and heat dissipation regulation. This method not only improves the accuracy of heat anomaly detection, but also optimizes the heat management process, ensuring that the electrical switch cabinet can maintain a safe temperature range under any operating conditions. This comprehensive method of color significance analysis provides a highly accurate and responsive solution for the temperature management of electrical switch cabinets, significantly improving the operating efficiency and safety of the system.

[0062] Through the technical solutions of the above-mentioned embodiments, the method for adaptively adjusting heat dissipation for an electrical switch cabinet provided in the present application solves the technical problems of lack of flexibility and adaptability in the heat dissipation method of the electrical switch cabinet, and inability to perform effective heat dissipation adjustment according to the actual temperature changes inside the electrical switch cabinet, thereby affecting the heat dissipation efficiency and increasing energy consumption and safety risks. The method achieves the technical effect of effectively performing adaptive heat dissipation adjustment of the electrical switch cabinet, dynamically optimizing heat dissipation performance, significantly improving equipment safety and stability, and reducing energy consumption and operating costs.

[0063] Embodiment 2 is based on the same inventive concept as the heat dissipation adaptive adjustment method for an electrical switch cabinet in the above embodiment. Figure 2 As shown, the present application provides a heat dissipation adaptive adjustment device for an electrical switch cabinet, the device comprising:

[0064] The temperature detection module 11 is used to perform dynamic temperature detection on a predetermined part of the electrical switch cabinet through a temperature sensor to obtain a real-time detection temperature value set, wherein the real-time detection temperature value set includes a plurality of temperature values ​​with coordinate identifiers.

[0065] The temperature visual map generating module 12 is used to generate an initial temperature visual map of the electrical switch cabinet according to the multiple temperature values ​​with coordinate identifiers, and obtain a first position coordinate in the initial temperature visual map, where the first position coordinate corresponds to a first position neighborhood.

[0066] The part position matching module 13 is used to form a part set of the electrical switch cabinet and match a first neighborhood part set of the first position neighborhood in the part set.

[0067] The feedback evaluation module 14 is used to introduce a temperature feedback evaluation integrated fusion model to perform feedback evaluation on the first dynamic operation information of the first neighborhood part in the first neighborhood part set to obtain a first feedback heat dissipation index.

[0068] The temperature rendering module 15 is used to render the first predicted temperature value of the first position coordinate obtained by analyzing the first feedback heat generation index to the initial temperature visual graph to obtain a target temperature visual graph.

[0069] The intelligent adjustment module 16 is used to perform adaptive heat dissipation adjustment on the electrical switch cabinet according to the target temperature visual map.

[0070] Furthermore, the feedback evaluation module 14 is further configured to perform the following steps:

[0071] Extract any part from the part set.

[0072] The historical heat generation and heat dissipation records of the same type of the arbitrary part are obtained, and the historical heat generation and heat dissipation records include first historical record data.

[0073] A first training data group is formed based on the first operating characteristic data and the first heat generation and heat dissipation index in the first historical record data.

[0074] The first training data set is subjected to supervised learning, and any feedback evaluation model of the any part is obtained by verification.

[0075] The temperature feedback evaluation integrated fusion model is constructed through the arbitrary feedback evaluation model.

[0076] Furthermore, the feedback evaluation module 14 is further configured to perform the following steps:

[0077] Obtain any heat generation and dissipation type of the any part.

[0078] When the arbitrary heat generation and dissipation type is a heat generation location, the first heat generation and dissipation index is recorded as a positive number.

[0079] When the arbitrary heat generation and heat dissipation type is a heat dissipation location, the first heat generation and heat dissipation index is recorded as a negative number.

[0080] Furthermore, the temperature rendering module 15 is further configured to perform the following steps:

[0081] An average value of the actual detected temperatures of the plurality of temperature values ​​with coordinate identifiers is obtained.

[0082] The first feedback heat dissipation index is used as a weight to weight the actual detected temperature average to obtain the first predicted temperature value.

[0083] Furthermore, the temperature rendering module 15 is further configured to perform the following steps:

[0084] A first temperature value corresponding to a first coordinate from among the plurality of temperature values ​​with coordinate identifiers is extracted.

[0085] A first spatial distance between the first coordinate and the first position coordinate is obtained.

[0086] The first temperature value is weighted by taking the first spatial distance as a weight to obtain a second predicted temperature value.

[0087] The first predicted temperature value is verified according to the second predicted temperature value.

[0088] Furthermore, the intelligent adjustment module 16 is further configured to perform the following steps:

[0089] The color saliency strategy is called to perform color saliency analysis on the target temperature visual graph to obtain the target saliency position.

[0090] The mobile temperature sensing probe is activated to perform dynamic temperature detection on a prominent position of the target to obtain a target temperature value.

[0091] When the target temperature value exceeds a predetermined temperature threshold, an abnormal heat generation and dissipation warning is issued to the electrical switch cabinet.

[0092] Furthermore, the intelligent adjustment module 16 is further configured to perform the following steps:

[0093] A target red channel visual image of the target temperature visual image is obtained according to the color saliency strategy.

[0094] A target green channel visual image of the target temperature visual image is obtained according to the color saliency strategy.

[0095] A target blue channel visual graph of the target temperature visual graph is obtained according to the color saliency strategy.

[0096] Obtain target repeated significant areas of the target red channel visible image, the target green channel visible image, and the target blue channel visible image.

[0097] The target repeated significant area is used as the target significant position of the target temperature visual map.

[0098] Through the above-mentioned detailed description of the heat dissipation adaptive adjustment method for an electrical switch cabinet, those skilled in the art can clearly understand the heat dissipation adaptive adjustment device for an electrical switch cabinet in this embodiment. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0099] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A heat dissipation adaptive adjustment method for an electrical switch cabinet, characterized in that: include: Performing dynamic temperature detection on a predetermined part of the electrical switch cabinet by a temperature sensor to obtain a real-time detection temperature value set, wherein the real-time detection temperature value set includes a plurality of temperature values ​​with coordinate identifiers; Generate an initial temperature visual map of the electrical switch cabinet according to the plurality of temperature values ​​with coordinate identifiers, and obtain a first position coordinate in the initial temperature visual map, where the first position coordinate corresponds to a first position neighborhood; assembling a part set of the electrical switch cabinet, and matching a first neighborhood part set of the first location neighborhood in the part set; Introducing a temperature feedback evaluation integrated fusion model to perform feedback evaluation on the first dynamic operation information of the first neighborhood part of the first neighborhood part set to obtain a first feedback heat dissipation index; Rendering the first predicted temperature value of the first position coordinate obtained by analyzing the first feedback heat generation and heat dissipation index to the initial temperature visual graph to obtain a target temperature visual graph; The heat dissipation of the electrical switch cabinet is adaptively adjusted according to the target temperature visual map.

2. The heat dissipation adaptive adjustment method for an electrical switch cabinet according to claim 1, characterized in that: Introducing a temperature feedback evaluation integrated fusion model to perform feedback evaluation on the first dynamic operation information of the first neighborhood part in the first neighborhood part set, including: Extracting any part from the part set; Acquire a historical heat generation and heat dissipation record of a similar part of the arbitrary part, wherein the historical heat generation and heat dissipation record includes first historical record data; forming a first training data group based on the first operation characteristic data and the first heat generation and heat dissipation index in the first historical record data; Performing supervised learning on the first training data group, and verifying and obtaining any feedback evaluation model of the any part; The temperature feedback evaluation integrated fusion model is constructed through the arbitrary feedback evaluation model.

3. The heat dissipation adaptive adjustment method for an electrical switch cabinet according to claim 2, characterized in that: A first training data group is formed based on the first operation characteristic data and the first heat generation and heat dissipation index in the first historical record data, including: Obtaining any heat generation and heat dissipation type of any part; When the arbitrary heat generation and dissipation type is a heat generation part, the first heat generation and dissipation index is recorded as a positive number; When the arbitrary heat generation and heat dissipation type is a heat dissipation location, the first heat generation and heat dissipation index is recorded as a negative number.

4. The heat dissipation adaptive adjustment method for an electrical switch cabinet according to claim 1, characterized in that: Rendering the first predicted temperature value of the first position coordinate obtained by analyzing the first feedback heat generation and heat dissipation index to the initial temperature visual graph to obtain a target temperature visual graph includes: Obtaining an average of the actual detected temperatures of the plurality of temperature values ​​with coordinate identifiers; The first feedback heat dissipation index is used as a weight to weight the actual detected temperature average to obtain the first predicted temperature value.

5. The heat dissipation adaptive adjustment method for an electrical switch cabinet according to claim 4, characterized in that: The first feedback heat dissipation index is used as a weight to weight the actual detected temperature average to obtain the first predicted temperature value, and then the following further includes: Extracting a first temperature value corresponding to a first coordinate from the plurality of temperature values ​​with coordinate identifiers; Acquire a first spatial distance between the first coordinate and the first position coordinate; Taking the first spatial distance as a weight, weighting the first temperature value to obtain a second predicted temperature value; The first predicted temperature value is verified according to the second predicted temperature value.

6. The heat dissipation adaptive adjustment method for an electrical switch cabinet according to claim 1, characterized in that: Adaptively adjusting the heat dissipation of the electrical switch cabinet according to the target temperature visual map includes: Calling a color saliency strategy to perform color saliency analysis on the target temperature visual graph to obtain a target saliency position; Activate the mobile temperature sensing probe to perform dynamic temperature detection on the target prominent position to obtain the target temperature value; When the target temperature value exceeds a predetermined temperature threshold, an abnormal heat generation and dissipation warning is issued to the electrical switch cabinet.

7. The heat dissipation adaptive adjustment method for an electrical switch cabinet according to claim 6, characterized in that: Calling a color saliency strategy to perform color saliency analysis on the target temperature visual graph to obtain a target saliency position includes: Acquire a target red channel visual image of the target temperature visual image according to the color saliency strategy; Acquire a target green channel visual image of the target temperature visual image according to the color saliency strategy; Acquire a target blue channel visual graph of the target temperature visual graph according to the color saliency strategy; Acquire target repeated significant areas of the target red channel visible image, the target green channel visible image, and the target blue channel visible image; The target repeated significant area is used as the target significant position of the target temperature visual map.

8. A heat dissipation adaptive adjustment device for an electrical switch cabinet, characterized in that: The device is used to implement the heat dissipation adaptive adjustment method for an electrical switch cabinet according to any one of claims 1 to 7, the device comprising: A temperature detection module, used to perform dynamic temperature detection on a predetermined part of the electrical switch cabinet through a temperature sensor to obtain a real-time detection temperature value set, wherein the real-time detection temperature value set includes a plurality of temperature values ​​with coordinate identifiers; A temperature visual map generating module, configured to generate an initial temperature visual map of the electrical switch cabinet according to the plurality of temperature values ​​with coordinate identifiers, and obtain a first position coordinate in the initial temperature visual map, wherein the first position coordinate corresponds to a first position neighborhood; A part position matching module, used for forming a part set of the electrical switch cabinet, and matching a first neighborhood part set of the first position neighborhood in the part set; A feedback evaluation module, used for introducing a temperature feedback evaluation integrated fusion model to perform feedback evaluation on the first dynamic operation information of the first neighborhood part of the first neighborhood part set to obtain a first feedback heat generation and heat dissipation index; A temperature rendering module, configured to render the first predicted temperature value of the first position coordinate obtained by analyzing the first feedback heat generation and heat dissipation index to the initial temperature visual graph, to obtain a target temperature visual graph; The intelligent adjustment module is used to perform adaptive heat dissipation adjustment on the electrical switch cabinet according to the target temperature visual map.

Images