A box-type substation moisture-proof and condensation-proof control system

Abstract

This invention relates to the field of intelligent control technology, and more particularly to a moisture-proof and condensation-proof control system for prefabricated substations. The system includes: a thermal imaging analysis module to determine whether to adjust the control analysis based on sensors to one based on hotspot location control analysis; a hotspot location analysis module to determine whether to adjust the setting method of key points from regional adaptive setting to cross-domain collaborative setting based on the thermal zone migration complexity corresponding to the thermal range area, and in the cross-domain collaborative setting, to determine whether to adjust the collaborative setting benchmark from independent extreme points to inter-regional boundary transition points based on the thermal boundary coefficient; a data management module to determine whether to supplement based on anchor points based on the volatility of the hotspot connected domain, and in the anchor point supplementation, to determine whether to adjust the nearest neighbor matching to inverse distance weighted interpolation based on the number of anchor points, and to transmit the final key point data parameters to the cloud; and an execution control module. This invention reduces the risk of condensation and improves the operational reliability of prefabricated substations.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to a moisture-proof and condensation-proof control system for prefabricated substations. Background Technology

[0002] In the operating environment of prefabricated substations, temperature and humidity differences and condensation are key factors affecting the insulation performance and service life of equipment. Traditional moisture-proof and anti-condensation control relies heavily on fixed threshold sensors for start-up and shutdown control, lacking the ability to accurately perceive the non-uniformity of the thermal field distribution and the dynamic nature of hotspot migration within the prefabricated substation. The introduction of thermal imaging analysis technology has provided a new approach to equipment condition monitoring; however, existing thermal imaging-based monitoring methods mostly employ static hotspot location or fixed area division, which is difficult to adapt to the characteristics of heat source distribution in prefabricated substations that migrate with changes in load, ambient temperature, and ventilation conditions. Therefore, constructing a moisture-proof and anti-condensation control system with dynamic thermal imaging analysis, adaptive hotspot location setting, and closed-loop data management correction capabilities has become an urgent need to improve the operational reliability of prefabricated substations.

[0003] Chinese Patent Publication No. CN119756589A discloses a method for arranging temperature measurement points in a new energy prefabricated substation, including: using an infrared thermal imager to detect the test piece to determine the target temperature measurement area and the corresponding reference temperature value; determining the arrangement of temperature measurement points within the target temperature measurement area; using temperature sensors to detect the temperature measurement points based on different arrangement methods to obtain at least three average temperature values ​​of the target temperature measurement area; and determining the final arrangement of the temperature sensors based on the at least three average temperature values ​​and the reference temperature value. It is evident that the above technical solution has the following problems: the temperature measurement points are fixedly arranged, making it impossible to dynamically adjust key points according to the thermal field migration caused by the substation load and environmental disturbances; the measurement points are determined solely based on the regional average temperature, lacking a multi-dimensional thermal stratification judgment mechanism, failing to adaptively switch control strategies, making it difficult for temperature measurement data to accurately reflect dynamic condensation risks, and the arrangement of measurement points is disconnected from moisture control, still exhibiting technical defects such as control blind spots and crude dehumidification. Summary of the Invention

[0004] To address these issues, this invention provides a moisture-proof and anti-condensation control system for prefabricated substations, which overcomes the problems in existing technologies such as static and fixed temperature measurement points, single thermal evaluation dimensions, lack of data supplementation mechanisms leading to delayed thermal response, inaccurate key point settings, and low control accuracy due to control parameter deviations.

[0005] To achieve the above objectives, the present invention provides a moisture-proof and condensation-proof control system for prefabricated substations, comprising: The thermal imaging analysis module is used to determine whether to switch from sensor-based control analysis to hot spot location control analysis based on the thermal stability and thermal uniformity of the target thermal imaging sequence. The hotspot analysis module is used to determine whether to change the setting method of key points from regional adaptive setting to cross-domain collaborative setting based on the heat zone migration complexity corresponding to the heat range area, and to determine whether to change the collaborative setting benchmark from independent extreme point to inter-region boundary transition point based on the thermal boundary coefficient in the cross-domain collaborative setting. The data management module is used to determine whether to supplement based on anchor points based on the volatility of hotspot connected domains, and to determine whether to adjust the nearest matching to inverse distance weighted interpolation based on the number of anchor points during anchor point supplementation, and to transmit the data parameters of the final key points to the cloud. The execution control module is used to generate moisture-proof and anti-condensation control parameters for the prefabricated substation based on the received data parameters.

[0006] Furthermore, the thermal imaging analysis module responds to the condition that the thermal stability is less than the preset thermal stability and the thermal uniformity is less than the preset thermal uniformity, and determines the sensor-based control analysis. The condition that the response thermal stability is greater than or equal to the preset thermal stability or thermal equilibrium is greater than or equal to the preset thermal equilibrium is used to determine the hot spot position control analysis. The thermal stability is determined based on the amount of temperature change, and the thermal uniformity is determined based on the standard deviation of the spatial temperature distribution.

[0007] Furthermore, the hotspot analysis module determines key points based on region adaptive setting when the hotspot migration complexity is less than the preset hotspot migration complexity. The hotspot analysis module sorts the local extreme points within each heat range in descending order to determine a preset number of key points based on regional adaptive settings.

[0008] Furthermore, the key point of the preset quantity is determined based on the area of ​​the heat range region; The preset number of key points is positively correlated with the area of ​​the heat range region.

[0009] Furthermore, the hotspot analysis module determines key points based on cross-domain collaboration when the hotspot migration complexity is greater than or equal to the preset hotspot migration complexity. The complexity of the thermal zone migration is determined based on the displacement of the temperature centroid.

[0010] Furthermore, the hotspot analysis module responds to the conditions set by cross-domain collaboration and the conditions that the thermal boundary coefficient is less than the preset thermal boundary coefficient, and determines the key points based on the independent extreme points. When the thermal boundary coefficient is greater than or equal to the preset thermal boundary coefficient, key points are determined based on the boundary transition points between regions. The thermal boundary coefficient is determined based on the reciprocal of the boundary temperature gradient modulus of two adjacent thermal range regions.

[0011] Furthermore, the hotspot analysis module divides the heat range region based on a preset temperature; The preset temperature includes at least a preset low temperature and a preset high temperature, and the heat range is divided into a low temperature zone, a medium temperature zone, and a high temperature zone by the preset low temperature and the preset high temperature.

[0012] Furthermore, the data management module responds to the condition that the volatility of the hotspot connected domain is greater than or equal to the preset volatility of the hotspot connected domain, determines to supplement based on the anchor point, and uses the supplemented key point as the final key point; The condition that the volatility of the hotspot connected domain is less than the preset volatility of the hotspot connected domain is denoted as the final key point; The volatility of the hotspot connected domains is determined based on the standard deviation and mean of the number of hotspot connected domains.

[0013] Furthermore, the data management module responds to the condition that the stability of the key point distribution is greater than the preset stability of the key point distribution, and records it as an anchor point; The stability of the key point distribution is determined based on the frequency and positional change distance of the key points. The stability of the key point distribution is positively correlated with the frequency, while the stability of the key point distribution is negatively correlated with the positional fluctuation.

[0014] Furthermore, in response to the condition that the number of anchor points is less than the preset number of anchor points, the data management module determines to supplement key point data based on proximity matching. If the number of anchor points is greater than or equal to the preset number of anchor points, key point data supplementation is determined based on inverse distance weighted interpolation.

[0015] Compared with the prior art, the beneficial effects of the present invention are that the thermal imaging analysis module of the present invention reflects the time-varying stability and spatial distribution uniformity of the thermal field inside the substation by the thermal stability and thermal uniformity corresponding to the target thermal imaging sequence. It compares with the preset thermal stability and preset thermal uniformity to determine whether to adjust the sensor-based control analysis to the hot spot position control analysis, thereby improving the response speed and adaptive switching capability to the dynamic evolution of the thermal field. This avoids the control blind spots or excessive dehumidification of the static sensor control method under the conditions of heat source migration or local overheating, effectively reducing the risk of condensation and improving the operational reliability of the box-type substation.

[0016] The hotspot analysis module of this invention reflects the movement trend of the temperature centroid in the thermal field through the thermal zone migration complexity. Based on the thermal zone migration complexity, it determines whether to adjust the setting method of key points from regional adaptive setting to cross-domain collaborative setting, thereby improving the tracking accuracy and response capability of key points to the dynamic migration of heat sources. This avoids key point failure or control blind spots caused by hotspot movement across regions, and enhances the adaptability of the control system to variable operating conditions. The thermal boundary coefficient reflects the continuity and transition strength of the temperature gradient between adjacent thermal range regions. Based on the thermal boundary coefficient, it determines whether to adjust the collaborative setting benchmark from independent extreme points to inter-regional boundary transition points, thereby improving the boundary consistency and thermal field connectivity of key points in cross-domain collaborative setting. This effectively suppresses control benchmark jumps or over-adjustments caused by inter-regional thermal coupling interference, ensuring the smooth output and long-term stability of moisture-proof and anti-condensation control parameters.

[0017] The data management module of this invention reflects the time-varying dispersion and stability of the number of hotspot connected domains in the thermal field through the hotspot connected domain volatility. Based on the hotspot connected domain volatility, it determines whether to supplement based on anchor points, thereby improving the integrity and continuity of key point data under conditions of severe thermal field fluctuations. This avoids data loss or control signal interruption caused by sudden changes in hotspot morphology, ensuring the accuracy of the moisture-proof and anti-condensation control system. The number of anchor points reflects the sufficiency of stable and reliable key point data. Based on the number of anchor points, it determines whether to adjust neighbor matching to inverse distance weighted interpolation, thereby improving the adaptive selection capability and spatial interpolation accuracy of the data interpolation strategy. When there are sufficient anchor points, inverse distance weighted interpolation is used to achieve more accurate thermal field reconstruction. When there are insufficient anchor points, neighbor matching is used to ensure basic data availability, achieving a balance between data completion effect and computational efficiency. Attached Figure Description

[0018] Figure 1 This is a module connection diagram of the prefabricated substation moisture-proof and anti-condensation control system of the present invention; Figure 2 This is a flowchart illustrating the process of determining whether to switch from sensor-based control analysis to hot spot location control analysis based on thermal stability and thermal uniformity in this invention. Figure 3 This is a flowchart illustrating the present invention's method for determining whether to adjust the setting method of key points from regional adaptive setting to cross-domain collaborative setting based on the complexity of hot zone migration. Figure 4 This is a flowchart illustrating the process of determining whether to supplement based on anchor points according to the volatility of hotspot connected domains in this invention. Detailed Implementation

[0019] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0020] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0021] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0022] Please see Figure 1 The diagram shown is a module connection diagram of the prefabricated substation moisture-proof and anti-condensation control system according to an embodiment of the present invention. The present invention provides a prefabricated substation moisture-proof and anti-condensation control system, comprising: The thermal imaging analysis module is used to determine whether to switch from sensor-based control analysis to hot spot location control analysis based on the thermal stability and thermal uniformity of the target thermal imaging sequence. The hotspot analysis module is used to determine whether to change the setting method of key points from regional adaptive setting to cross-domain collaborative setting based on the heat zone migration complexity corresponding to the heat range area, and to determine whether to change the collaborative setting benchmark from independent extreme point to inter-region boundary transition point based on the thermal boundary coefficient in the cross-domain collaborative setting. The data management module is used to determine whether to supplement based on anchor points based on the volatility of hotspot connected domains, and to determine whether to adjust the nearest matching to inverse distance weighted interpolation based on the number of anchor points during anchor point supplementation, and to transmit the data parameters of the final key points to the cloud. The execution control module is used to generate moisture-proof and anti-condensation control parameters for the prefabricated substation based on the received data parameters.

[0023] This invention is applied to the moisture-proof and anti-condensation control scenario of prefabricated substations. By adaptively switching between sensor control analysis and hot spot location control analysis, dynamically adjusting the setting method and collaborative benchmark of key points, and achieving accurate matching of key point data, it improves the perception ability of non-uniform distribution of thermal field and dynamic migration of hot spots inside the box, thereby improving the accuracy of moisture-proof and anti-condensation control parameters and environmental adaptability, effectively reducing the risk of condensation and improving the reliability of equipment operation.

[0024] In this embodiment of the invention, the method of acquiring the target thermal imaging sequence includes deploying thermal imaging monitoring hardware in the prefabricated substation, using a thermal imaging temperature measurement device installation mechanism to fix the thermal imager in key areas such as transformers, circuit breaker contacts, and cable joints, and configuring thermal imaging monitoring lenses in no less than two directions in the main transformer area to achieve panoramic coverage without blind spots. The thermal imager integrates infrared thermal imaging and high-definition visible light dual-light modules and is deployed by a fixed bullet camera. The acquired images are transmitted to the monitoring center server via Ethernet and arranged in the order of acquisition time to generate a continuous target thermal imaging sequence.

[0025] In this embodiment of the invention, the execution control module generates moisture-proof and anti-condensation control parameters based on the received data parameters. The data parameters of the final key point include the location coordinates of the point in the thermal imaging image and the space of the prefabricated substation, the corresponding measured temperature value, the acquisition timestamp, and the classification of the thermal range area to which it belongs. The moisture-proof and anti-condensation control device of the prefabricated substation includes a dehumidification device, which adopts a rotary dehumidifier and is installed in a well-ventilated area at the bottom or middle of the box; a heating device, which adopts a PTC constant temperature heating plate and is installed in areas prone to condensation, such as the inner wall of the box, the cable inlet, and the bottom of the circuit breaker operating mechanism box; and a ventilation device, which adopts a centrifugal fan and is installed at the air inlets on both sides of the top and bottom of the box to form a bottom-in, top-out circulating air path. Each device is connected to the execution control module via an RS485 bus, and the execution control module generates the control parameters of each device based on the data parameters of the final key point.

[0026] In this embodiment of the invention, the thermal imaging analysis module responds to conditions where the thermal stability is less than a preset thermal stability and the thermal uniformity is less than a preset thermal uniformity. Based on temperature and humidity sensors, it performs moisture-proof and anti-condensation control. The execution control module compares the data from the fixed-point temperature and humidity sensors with thresholds. When the relative humidity is higher than the first preset humidity and lasts for a first preset duration, dehumidification and ventilation are initiated; when it is lower than the second preset humidity, they are stopped. When the minimum temperature is lower than the first preset temperature, heating is initiated; when it is higher than the second preset temperature, it is stopped. All devices use unified start and stop commands. In this embodiment, the first and second preset humidity are determined based on the critical relative humidity of easily condensing areas. The first preset duration is determined based on the heat exchange time constant inside the chamber and the minimum time window for condensation formation. The first and second preset temperatures are determined based on the critical relationship between the minimum temperature and the dew point temperature. The specific values ​​can be obtained by those skilled in the art based on climatic conditions, the heat and moisture resistance rating of the equipment, and historical condensation data, and will not be elaborated here.

[0027] In this embodiment of the invention, when the response thermal stability is greater than or equal to a preset thermal stability or thermal equilibrium is greater than or equal to a preset thermal equilibrium, the execution control module performs independent zone control based on the final key point data parameters. It extracts the measured temperature values ​​of key points in the low-temperature zone, calculates the difference between each low-temperature point and the current ambient dew point temperature, and linearly determines the power adjustment ratio of the corresponding heating device based on this difference. The smaller the difference, the greater the heating power. The power adjustment ratio continuously changes between a preset minimum power and a preset maximum power. It also extracts the temperature values ​​of key points in the medium-temperature zone, calculates the temperature change rate of each medium-temperature point between two adjacent frames, and dynamically adjusts the speed of the corresponding area's ventilation fan based on the absolute value of the change rate. The greater the change rate, the higher the speed. Finally, it extracts the temperature values ​​of key points in the high-temperature zone, activates enhanced ventilation in the area surrounding high-temperature points where the temperature exceeds a preset tolerance limit, and simultaneously calculates the temperature difference between the high-temperature zone and the low-temperature zone. The average temperature difference at key points in the temperature zone is calculated. When this temperature difference exceeds the preset temperature difference, the output power of the heating device in the low-temperature zone is increased to reduce the temperature difference, thereby achieving active equilibrium of the thermal field distribution. The control parameter cycle of each device is consistent with the data update frequency of the final key point. In this embodiment, the preset minimum power and preset maximum power are determined based on the minimum heating amount for anti-condensation in the low-temperature zone and the upper limit of the equipment's temperature resistance. The preset temperature change rate corresponding to the speed setting is determined based on the critical change rate of switching between natural convection and forced ventilation in the medium-temperature zone. The preset upper limit of tolerance is determined based on the maximum allowable operating temperature of the key equipment and the measurement error of the thermal imager. The preset temperature difference is determined based on the statistical average temperature difference between the high-temperature zone and the low-temperature zone when the thermal field is in equilibrium and the maximum allowable temperature difference for anti-condensation. The specific values ​​of the above parameters can be obtained by those skilled in the art based on equipment parameters, historical operating data, and a limited number of on-site calibration experiments, and will not be elaborated here.

[0028] Please continue reading. Figures 1 to 4 As shown, the thermal imaging analysis module responds to the condition that the thermal stability is less than the preset thermal stability and the thermal uniformity is less than the preset thermal uniformity, and then determines the sensor-based control analysis. The condition that the response thermal stability is greater than or equal to the preset thermal stability or thermal equilibrium is greater than or equal to the preset thermal equilibrium is used to determine the hot spot position control analysis. The thermal stability is determined based on the amount of temperature change, and the thermal uniformity is determined based on the standard deviation of the spatial temperature distribution.

[0029] In this embodiment of the invention, the thermal stability is determined based on the average absolute value of the temperature difference between adjacent frames in the target thermal imaging sequence. It can be understood that thermal stability reflects the intensity of thermal field fluctuations in the time dimension within the prefabricated substation. A smaller thermal stability indicates a smaller average temperature difference between frames, a smoother time-varying thermal field characteristic, and a more stable system operation. Therefore, the higher the user's sensitivity to thermal field fluctuations, the smaller the preset thermal stability value should be. In this embodiment, the thermal stability value when the moisture-proof and anti-condensation control effect meets the standard is collected within a historical operating cycle. After removing outliers, the average value is calculated and recorded as the preset thermal stability. The duration of the historical operating cycle is crucial; a longer historical operating cycle results in a larger amount of data for analyzing the preset value, leading to higher reliability of the statistical analysis. Therefore, the accuracy requirements for the preset value results are higher, and the duration of the historical operating cycle can be increased accordingly. However, it is worth noting that an excessively long historical operating cycle may lead to the collection of data during periods of significant changes in operating conditions, thus affecting the adaptability of the preset value to the current operating state. The aforementioned moisture-proof and anti-condensation control effect meets the standard. It is understood that standards commonly used by those skilled in the art, such as the number of condensation occurrences, can be set as the evaluation criteria for whether the moisture-proof and anti-condensation control effect meets the standard. The above are all contents that are easy for those skilled in the art to understand, and will not be elaborated further.

[0030] In this embodiment of the invention, the thermal uniformity is determined based on the spatial standard deviation of the temperature values ​​of all pixels in a single frame of the target thermal imaging sequence. That is, it is the sum of the squares of the differences between the temperature values ​​of each pixel and the average temperature of the whole frame, divided by the arithmetic square root of the total number of pixels. It can be understood that the thermal uniformity reflects the uniformity of the heat field distribution in the box-type substation at the same moment. The smaller the thermal uniformity, the smaller the temperature difference between different areas in the box, the more uniform the temperature distribution, and the more concentrated the risk of condensation is in the global high humidity area rather than the local hot area. Therefore, the higher the user's sensitivity to the risk of misjudging condensation caused by local overheating, the smaller the preset thermal uniformity value should be. In this embodiment, the thermal uniformity value when the moisture-proof and anti-condensation control effect meets the standard during the historical operation cycle is collected, outliers are removed, and the average value is calculated and recorded as the preset thermal uniformity.

[0031] Specifically, the hotspot analysis module determines key points based on region adaptive setting when the hotspot migration complexity is less than the preset hotspot migration complexity. The hotspot analysis module sorts the local extreme points within each heat range in descending order to determine a preset number of key points based on regional adaptive settings.

[0032] In this embodiment of the invention, the hotspot analysis module adaptively sets key points based on regions, extracts local extreme points within each region for each heat range area, merges and sorts the extracted local extreme points from each region in descending order, and selects a preset number of local extreme points at the top of the sorting as initial key points. It can be understood that the local extreme points correspond to the local heat source centers of each region in the box-type substation, such as cable joints, circuit breaker contacts, or local overheating areas of transformer cores. By extracting local extreme points from multiple regions, the key point set can cover multiple dispersed heat source cores, avoiding control blind spots caused by missing secondary hotspot areas due to a single global extreme point.

[0033] Specifically, the key point of the preset quantity is determined based on the area of ​​the heat range region; The preset number of key points is positively correlated with the area of ​​the heat range region.

[0034] In this embodiment of the invention, the preset number of key points is determined based on the area of ​​the thermal range region, which includes a low-temperature zone, a medium-temperature zone, and a high-temperature zone. The area of ​​each region is calculated by multiplying the total number of pixels in the region by the actual physical area corresponding to each pixel. The preset number is positively correlated with the area of ​​the thermal range region, that is, the larger the area, the more key points need to be set to ensure that the key point distribution density is sufficient to characterize the thermal field characteristics of the region. In this embodiment, the number of key points corresponding to the area of ​​the thermal range region when the moisture-proof and anti-condensation control effect meets the standard during the historical operation cycle is collected, and the average value is calculated after removing outliers and recorded as the preset number.

[0035] Specifically, the hotspot analysis module determines key points based on cross-domain collaboration when the hotspot migration complexity is greater than or equal to the preset hotspot migration complexity. The complexity of the thermal zone migration is determined based on the displacement of the temperature centroid.

[0036] In this embodiment of the invention, the thermal migration complexity is based on the planar coordinates of the temperature centroid of each region within each heat range area. The temperature centroid is the weighted average of the temperature value and pixel coordinates of each pixel within the region. The displacement of the temperature centroid in consecutive frames is statistically analyzed, and the average displacement per unit time is calculated. Then, the average displacement of each region is averaged to obtain the thermal migration complexity. It can be understood that the thermal migration complexity reflects the speed and frequency of hot spots moving across regions within the box-type substation. The greater the thermal migration complexity, the more drastic the change in the location of the heat source, requiring a more flexible key point setting strategy. In this embodiment, the thermal migration complexity when the moisture-proof and anti-condensation control effect meets the standard is collected within the historical operating cycle. After removing outliers, the average value is calculated and recorded as the preset thermal migration complexity. The method for removing outliers includes, but is not limited to, the 3σ principle.

[0037] In this embodiment of the invention, the hot spot analysis module responds to the condition that the hot zone migration complexity is greater than or equal to the preset hot zone migration complexity, which reflects that the location of the heat source inside the box-type substation changes drastically or migrates frequently. If the key point is set using regional adaptive setting, problems such as the key point lagging behind the heat source movement and cross-regional thermal coupling not being effectively captured will easily occur, resulting in control blind spots or dehumidification response delays. Therefore, the hot spot analysis module determines to adjust the setting method of the key point from regional adaptive setting to cross-domain collaborative setting.

[0038] Specifically, the hotspot analysis module responds to the conditions set by cross-domain collaboration and the conditions that the thermal boundary coefficient is less than the preset thermal boundary coefficient, and determines key points based on independent extreme points. When the thermal boundary coefficient is greater than or equal to the preset thermal boundary coefficient, key points are determined based on the boundary transition points between regions. The thermal boundary coefficient is determined based on the reciprocal of the boundary temperature gradient modulus of two adjacent thermal range regions.

[0039] In this embodiment of the invention, the thermal boundary coefficient is based on adjacent low-temperature and medium-temperature zones, and medium-temperature and high-temperature zones. The temperature values ​​of pixels on the boundary lines are extracted, the temperature gradient magnitude in the normal direction of the boundary lines is calculated, and the reciprocal of the magnitude is taken as the thermal boundary coefficient of the pair of regions. The average value of the thermal boundary coefficients of all adjacent region pairs is taken as the final thermal boundary coefficient. It can be understood that the smaller the thermal boundary coefficient, the more intense the temperature transition between adjacent regions, and the existence of obvious temperature boundaries. In this case, independent extreme points are used as collaborative setting benchmarks. The larger the thermal boundary coefficient, the smoother the temperature transition, and the existence of fuzzy boundaries between regions. In this case, using the boundary transition points between regions as benchmarks can better reflect the true thermal field connectivity. In this embodiment, the thermal boundary coefficients when the moisture-proof and anti-condensation control effects are met during historical operating cycles are collected, outliers are removed, and the average value is calculated and recorded as the preset thermal boundary coefficient.

[0040] In this embodiment of the invention, when the hot spot analysis module responds to the condition that the heat zone migration complexity is greater than or equal to the preset heat zone migration complexity, and the thermal boundary coefficient is less than the preset thermal boundary coefficient, the hot spot analysis module performs global extreme point detection on the temperature distribution matrix corresponding to the entire frame of thermal imaging image. It uses a non-maximum suppression algorithm to constrain the independence of each candidate extreme point, ensuring that the Euclidean distance between any two selected independent extreme points is not less than the preset spacing, so as to avoid multiple extreme points from clustering in the same heat source center. After independence screening, the remaining candidate extreme points are sorted in descending order of temperature value from high to low, and a preset number of points at the top of the sort are selected as key points. It can be understood that the independent extreme point setting method is suitable for working conditions where the temperature gradient between regions is steep and the centers of each heat source are far apart. It can ensure the uniformity of the spatial distribution of key points and the comprehensiveness of heat source coverage without being constrained by the boundary of the heat range region.

[0041] In this embodiment of the invention, when the hotspot analysis module responds to the condition that the hotspot migration complexity is greater than or equal to the preset hotspot migration complexity, and the thermal boundary coefficient is greater than or equal to the preset thermal boundary coefficient, the hotspot analysis module samples along the boundary lines of two adjacent heat range regions at equal arc length intervals to obtain several candidate points. It calculates the arithmetic mean of the temperature values ​​of all pixels within the two regions and uses the average temperature of the two regions as the reference temperature. It selects the point whose temperature value is closest to the reference temperature from the candidate points of the corresponding boundary line as the key point of the boundary position. It merges the key points selected from each boundary. If the total number of key points exceeds the preset number, it filters them in descending order of temperature value until the preset number is reached. If it is insufficient, it supplements the local extreme points within each region until the preset number is reached.

[0042] Specifically, the hotspot analysis module divides the heat range region based on a preset temperature; The preset temperature includes at least a preset low temperature and a preset high temperature, and the heat range is divided into a low temperature zone, a medium temperature zone, and a high temperature zone by the preset low temperature and the preset high temperature.

[0043] In this embodiment of the invention, the hotspot analysis module divides the thermal range region based on a preset temperature. The preset temperature includes a preset low temperature and a preset high temperature. The hotspot analysis module classifies pixels in the thermal imaging image of the prefabricated substation with a temperature value lower than the preset low temperature as a low temperature region, pixels with a temperature value greater than or equal to the preset low temperature and less than or equal to the preset high temperature as a medium temperature region, and pixels with a temperature value higher than the preset high temperature as a high temperature region. In this embodiment, the preset temperature is set through simulation to obtain the temperature field simulation data of the target prefabricated substation under multi-physics coupling conditions. The continuity of the thermal range region division and the completeness of key point coverage are used as evaluation indicators. After iterative fine-tuning, the temperature critical value with the best comprehensive performance is selected as the preset temperature. The specific value of the preset temperature is calibrated by those skilled in the art based on actual equipment parameters and operating environment, and will not be elaborated here.

[0044] Specifically, the data management module responds to the condition that the volatility of the hotspot connected domain is greater than or equal to the preset volatility of the hotspot connected domain, determines to supplement based on the anchor point, and uses the supplemented key point as the final key point; The condition that the volatility of the hotspot connected domain is less than the preset volatility of the hotspot connected domain is denoted as the final key point; The volatility of the hotspot connected domains is determined based on the standard deviation and mean of the number of hotspot connected domains.

[0045] In this embodiment of the invention, the hotspot connectivity volatility is determined based on the standard deviation and mean of the number of hotspot connected regions. The hotspot connectivity volatility is the ratio of the standard deviation of the number of hotspot connected regions in each frame of a continuous frame to the mean of the number of hotspot connected regions in that frame. It can be understood that the hotspot connectivity volatility reflects the dynamic dispersion of the spatial splitting, merging, and expansion and contraction of areas within a prefabricated substation. The greater the volatility, the more unstable the thermal field morphology. A single static key point setting method is difficult to cover the dynamically changing thermal zone distribution. Therefore, it is necessary to supplement key points based on anchor points. In this embodiment, the hotspot connectivity volatility is collected when the moisture-proof and anti-condensation control effect meets the standard during the historical operating cycle. After removing outliers, the average value is calculated and recorded as the preset hotspot connectivity volatility.

[0046] Specifically, the data management module responds to a condition where the stability of the key point distribution is greater than the preset stability of the key point distribution, and this condition is denoted as an anchor point. The stability of the key point distribution is determined based on the frequency and positional change distance of the key points. The stability of the key point distribution is positively correlated with the frequency, while the stability of the key point distribution is negatively correlated with the positional fluctuation.

[0047] In this embodiment of the invention, the key point distribution stability is determined based on the ratio of the frequency of key point occurrence to the ratio of the distance of position change. For any key point location, the total number of times it is set as a key point by the system within a continuous monitoring period is counted and recorded as the frequency. The Euclidean distance between the actual spatial coordinates and the historical average coordinates of the point in each period is calculated, and the standard deviation of the distance sequence is counted and recorded as the distance of position change. It can be understood that the key point distribution stability reflects the reliability of the location point as a stable thermal feature center. The larger the value, the more frequently the point appears and the smaller the position change, and the more suitable it is as an anchor point for data supplementation. In this embodiment, the key point distribution stability when the moisture-proof and anti-condensation control effect meets the standard is collected within the historical operating period. After removing outliers, the average value is calculated and recorded as the preset key point distribution stability.

[0048] Specifically, the data management module responds to the condition that the number of anchor points is less than the preset number of anchor points and determines to supplement key point data based on proximity matching; If the number of anchor points is greater than or equal to the preset number of anchor points, key point data supplementation is determined based on inverse distance weighted interpolation.

[0049] In this embodiment of the invention, when the number of anchor points is less than the preset number of anchor points, the data management module responds to the condition that the number of anchor points is less than the preset number of anchor points. The data management module uses the nearest neighbor matching method to supplement the key point data. For each key point location with missing temperature data, the spatial Euclidean distance between it and each anchor point is calculated with reference to the existing anchor points. The anchor point with the smallest distance is selected, and the temperature value of the anchor point is directly assigned to the missing key point. All missing key points are traversed in turn until the preset number of key point data is completely supplemented.

[0050] In this embodiment of the invention, the data management module responds to the condition that the number of anchor points is greater than or equal to the preset number of anchor points, and uses inverse distance weighted interpolation to supplement key point data. For each key point location with missing temperature data, the nearest anchor point is selected, and the inverse square of the spatial Euclidean distance between the missing point and each selected anchor point is calculated as a weight. The estimated temperature value of the missing point is obtained by weighted averaging of the temperature values ​​of each anchor point. After weight normalization, the weighted sum is calculated. The inverse distance weighted interpolation method utilizes the spatial correlation of multiple anchor points, which can provide more accurate thermal field reconstruction results when there are sufficient anchor points. In this embodiment, the preset number of anchor points is set through simulation. The key point distribution dataset and anchor point supplementation simulation results of the target system under the preset thermal field fluctuation condition set are obtained. The accuracy of thermal field reconstruction after data supplementation and the consumption of computing resources are used as evaluation indicators, and the number of anchor points with the best comprehensive performance is selected as the preset number of anchor points.

[0051] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0052] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A moisture-proof and condensation-proof control system for a box-type substation, characterized by, include: The thermal imaging analysis module is used to determine whether to switch from sensor-based control analysis to hot spot location control analysis based on the thermal stability and thermal uniformity of the target thermal imaging sequence. The hotspot analysis module is used to determine whether to change the setting method of key points from regional adaptive setting to cross-domain collaborative setting based on the heat zone migration complexity corresponding to the heat range area, and to determine whether to change the collaborative setting benchmark from independent extreme point to inter-region boundary transition point based on the thermal boundary coefficient in the cross-domain collaborative setting. The data management module is used to determine whether to supplement based on anchor points based on the volatility of hotspot connected domains, and to determine whether to adjust the nearest matching to inverse distance weighted interpolation based on the number of anchor points during anchor point supplementation, and to transmit the data parameters of the final key points to the cloud. The execution control module is used to generate moisture-proof and anti-condensation control parameters for the prefabricated substation based on the received data parameters.

2. The moisture-proof and anti-condensation control system for prefabricated substations according to claim 1, characterized in that, The thermal imaging analysis module responds to the condition that the thermal stability is less than the preset thermal stability and the thermal uniformity is less than the preset thermal uniformity, and determines the sensor-based control analysis. The condition that the response thermal stability is greater than or equal to the preset thermal stability or thermal equilibrium is greater than or equal to the preset thermal equilibrium is used to determine the hot spot position control analysis. The thermal stability is determined based on the amount of temperature change, and the thermal uniformity is determined based on the standard deviation of the spatial temperature distribution.

3. The moisture-proof and anti-condensation control system for prefabricated substations according to claim 2, characterized in that, The hotspot analysis module determines key points based on region adaptive setting when the hotspot migration complexity is less than the preset hotspot migration complexity. The hotspot analysis module sorts the local extreme points within each heat range in descending order to determine a preset number of key points based on regional adaptive settings.

4. The moisture-proof and anti-condensation control system for prefabricated substations according to claim 3, characterized in that, The key point of the preset quantity is determined based on the area of ​​the heat range region; The preset number of key points is positively correlated with the area of ​​the heat range region.

5. The moisture-proof and anti-condensation control system for prefabricated substations according to claim 4, characterized in that, The hotspot analysis module determines key points based on cross-domain collaboration when the hotspot migration complexity is greater than or equal to the preset hotspot migration complexity. The complexity of the thermal zone migration is determined based on the displacement of the temperature centroid.

6. The moisture-proof and anti-condensation control system for prefabricated substations according to claim 5, characterized in that, The hotspot analysis module responds to the conditions set by cross-domain collaboration and the condition that the thermal boundary coefficient is less than the preset thermal boundary coefficient, and determines the key points based on the independent extreme points. When the thermal boundary coefficient is greater than or equal to the preset thermal boundary coefficient, key points are determined based on the boundary transition points between regions. The thermal boundary coefficient is determined based on the reciprocal of the boundary temperature gradient modulus of two adjacent thermal range regions.

7. The moisture-proof and anti-condensation control system for prefabricated substations according to claim 6, characterized in that, The hotspot analysis module divides the heat range region based on a preset temperature. The preset temperature includes at least a preset low temperature and a preset high temperature, and the heat range is divided into a low temperature zone, a medium temperature zone, and a high temperature zone by the preset low temperature and the preset high temperature.

8. The moisture-proof and condensation-proof control system for prefabricated substations according to claim 7, characterized in that, The data management module responds to the condition that the volatility of the hotspot connected domain is greater than or equal to the preset volatility of the hotspot connected domain, determines to supplement based on the anchor point, and uses the supplemented key point as the final key point; The condition that the volatility of the hotspot connected domain is less than the preset volatility of the hotspot connected domain is denoted as the final key point; The volatility of the hotspot connected domains is determined based on the standard deviation and mean of the number of hotspot connected domains.

9. The moisture-proof and anti-condensation control system for prefabricated substations according to claim 8, characterized in that, The data management module responds to a key point distribution stability condition that is greater than the preset key point distribution stability, and this condition is denoted as an anchor point. The stability of the key point distribution is determined based on the frequency and positional change distance of the key points. The stability of the key point distribution is positively correlated with the frequency, while the stability of the key point distribution is negatively correlated with the positional fluctuation.

10. The moisture-proof and anti-condensation control system for prefabricated substations according to claim 9, characterized in that, The data management module responds to the condition that the number of anchor points is less than the preset number of anchor points and determines to supplement key point data based on proximity matching. If the number of anchor points is greater than or equal to the preset number of anchor points, key point data supplementation is determined based on inverse distance weighted interpolation.

Images