Heat dissipation optimization control method and system suitable for power equipment prefabricated cabin

Abstract

The invention provides a heat dissipation optimization control method and system suitable for a power equipment prefabricated cabin, and relates to the technical field of data processing, and the method comprises the steps: carrying out the arrangement of a temperature sensor for a target power equipment prefabricated cabin according to a preset monitoring point position set; carrying out simultaneous sequence temperature monitoring data acquisition according to a preset monitoring frequency; carrying out double analysis on the temperature monitoring data network sequence; performing risk identification according to a double-item analysis result to obtain a risk monitoring point set and a risk temperature monitoring data set; and taking a preset heat dissipation optimization path as a constraint, and combining the risk monitoring point set and the risk temperature monitoring data set to obtain a heat dissipation optimization control scheme. The technical problems that the temperature in the cabin is still too high and the heat dissipation effect is poor during high-load operation due to the fact that the power equipment prefabricated cabin is difficult to dynamically adjust according to different environmental conditions are solved, and the heat dissipation efficiency of the power equipment prefabricated cabin is improved by introducing two-item analysis and risk identification.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a heat dissipation optimization control method and system applicable to prefabricated cabins of power equipment. Background Art

[0002] A prefabricated cabin of power equipment is a cabin body with a movable, sealed, and modular design, in which various equipment required in the power system (such as transformers, switch cabinets, distribution devices, control systems, etc.) are pre-integrated and installed. It has the characteristics of being movable and quickly deployable on-site. Due to the large number of integrated devices and high operating power inside the cabin, and being in complex environmental conditions such as high temperature and high humidity all year round, a large amount of heat is generated during the operation of the equipment, and heat accumulation is likely to occur inside the cabin. The heat dissipation problem has become a key factor affecting the operation stability and safety of the equipment inside the prefabricated cabin. Traditional heat dissipation control mainly relies on ventilation or natural heat dissipation. However, due to the large amount of heat dissipated during the high-power operation of power equipment and the limited space inside the prefabricated cabin, the heat dissipation effect often fails to meet the thermal management requirements of the equipment.

[0003] Currently, most prefabricated cabins of power equipment adopt simple ventilation heat dissipation or a single air-cooling system, and fail to perform intelligent and dynamic adjustment according to different environmental conditions. The heat dissipation capacity of the ventilation system is limited by factors such as the external environmental temperature and wind speed, and the heat generated by the operation of the equipment usually has strong time-variability. As a result, when operating at high load, the temperature inside the cabin may still be too high, which has an adverse impact on the reliability of the equipment.

[0004] In summary, there is a technical problem in the prior art that due to the difficulty of dynamically adjusting the prefabricated cabin of power equipment according to different environmental conditions, the temperature inside the cabin may still be too high during high-load operation, the heat dissipation effect is poor, and thus the reliability of the equipment operation is affected. Summary of the Invention

[0005] The purpose of this application is to provide a heat dissipation optimization control method and system applicable to prefabricated cabins of power equipment, so as to solve the technical problem in the prior art that due to the difficulty of dynamically adjusting the prefabricated cabin of power equipment according to different environmental conditions, the temperature inside the cabin may still be too high during high-load operation, the heat dissipation effect is poor, and thus the reliability of the equipment operation is affected.

[0006] In view of the above problems, this application provides a heat dissipation optimization control method and system applicable to prefabricated cabins of power equipment.

[0007] In a first aspect, the present application provides a heat dissipation optimization control method applicable to a prefabricated cabin of power equipment. The heat dissipation optimization control method applicable to the prefabricated cabin of power equipment is implemented through a heat dissipation optimization control system applicable to the prefabricated cabin of power equipment. Among them, the heat dissipation optimization control method applicable to the prefabricated cabin of power equipment includes: arranging temperature sensors on a target prefabricated cabin of power equipment according to a preset set of monitoring point positions to construct a temperature monitoring network, where the temperature monitoring network includes a set of temperature monitoring points; collecting simultaneous temperature monitoring data of the temperature monitoring network according to a preset monitoring frequency to obtain a temperature monitoring data network sequence; performing two-way analysis on the temperature monitoring data network sequence to obtain a two-way analysis result; performing risk identification on the set of temperature monitoring points according to the two-way analysis result to obtain a set of risk monitoring points and a set of risk temperature monitoring data; and identifying a heat dissipation optimization control solution by combining the set of risk monitoring points and the set of risk temperature monitoring data with a preset heat dissipation optimization path as a constraint.

[0008] Optionally, mine overheat maintenance logs according to the model of the target prefabricated cabin of power equipment to obtain a set of overheat maintenance logs; retrieve the set of overheat maintenance logs with the maintenance points as indexes to obtain a set of maintenance points; perform position neighbor clustering analysis on the set of maintenance points according to a preset distance bandwidth to determine M sets of clustered maintenance points, where M is a positive integer; and configure monitoring position points based on the M sets of clustered maintenance points to obtain a preset set of monitoring point positions.

[0009] Optionally, determine M risk coefficients according to the number of each set of clustered maintenance points in the M sets of clustered maintenance points; and perform random sampling on the M sets of clustered maintenance points according to the M risk coefficients and a preset number of monitoring points to obtain the preset set of monitoring point positions.

[0010] Optionally, extract data from the temperature monitoring data network sequence with any one monitoring point as an index to obtain a first temperature monitoring data sequence; perform two-dimensional data analysis on the first temperature monitoring data sequence to determine first temperature monitoring data; and so on, perform two-dimensional data analysis at the same monitoring point on the temperature monitoring data network sequence to obtain a temperature monitoring data network; perform multi-scale convolution on the temperature monitoring data network sequence, and perform feature interaction fusion on the multi-scale convolution result to obtain enhanced convolution features; perform convolution analysis on the enhanced convolution features and the temperature monitoring data network at the end of the temperature monitoring data network sequence to determine a temperature monitoring enhanced data network; and perform mapping mean analysis on the temperature monitoring data network and the temperature monitoring enhanced data network to obtain a two-way analysis result.

[0011] Optionally, perform clustering analysis on the first temperature monitoring data sequence from two dimensions of data similarity and data acquisition time to obtain a first clustered temperature monitoring data cluster; respectively count the proportion of each first clustered temperature monitoring data set in the first clustered temperature monitoring data cluster to obtain a first clustered proportion set; perform weighted calculation on the first clustered temperature monitoring data cluster based on the first clustered proportion set to obtain the first temperature monitoring data.

[0012] Optionally, randomly extract a first convolution feature and a second convolution feature from the multi-scale convolution results; perform feature interaction fusion on the first convolution feature and the second convolution feature to obtain a first interaction fusion convolution feature; perform feature interaction fusion on the remaining convolution features in the multi-scale convolution results based on the first interaction fusion convolution feature to obtain an enhanced convolution feature.

[0013] Optionally, determine whether there is risk temperature monitoring data greater than or equal to a preset temperature threshold in the two-way analysis result. If so, add it to the risk temperature monitoring data set and add the corresponding monitoring point to the risk monitoring point set.

[0014] Optionally, pre-construct a control scheme identifier; use the control scheme identifier to identify a preset heat dissipation optimization path, a risk monitoring point set, and a risk temperature monitoring data set to obtain a heat dissipation optimization control scheme.

[0015] Optionally, obtain a feedback monitoring window; monitor the temperature drop gradient of the risk monitoring point set in the feedback monitoring window. If the requirement is not met, generate a warning instruction.

[0016] In a second aspect, the present application further provides a heat dissipation optimization control system applicable to a power equipment prefabricated cabin for executing the heat dissipation optimization control method applicable to a power equipment prefabricated cabin as described in the first aspect. Wherein, the heat dissipation optimization control system applicable to a power equipment prefabricated cabin includes: a sensor layout module for laying out temperature sensors for a target power equipment prefabricated cabin according to a preset monitoring point position set to construct a temperature monitoring network, where the temperature monitoring network includes a temperature monitoring point set; a data acquisition module for simultaneously acquiring temperature monitoring data of the temperature monitoring network at a preset monitoring frequency to obtain a temperature monitoring data network sequence; a two-way analysis module for performing two-way analysis on the temperature monitoring data network sequence to obtain a two-way analysis result; a risk identification module for performing risk identification on the temperature monitoring point set according to the two-way analysis result to obtain a risk monitoring point set and a risk temperature monitoring data set; a control scheme identification module for performing control scheme identification by combining the risk monitoring point set and the risk temperature monitoring data set with a preset heat dissipation optimization path as a constraint to obtain a heat dissipation optimization control scheme.

[0017] One or more technical solutions provided in this application have at least the following beneficial effects: By arranging temperature sensors on the prefabricated cabin of the target power equipment according to a preset set of monitoring point positions, a temperature monitoring network is constructed, where the temperature monitoring network includes a set of temperature monitoring points; collecting simultaneous temperature monitoring data of the temperature monitoring network according to a preset monitoring frequency to obtain a temperature monitoring data network sequence; performing two-way analysis on the temperature monitoring data network sequence to obtain a two-way analysis result; performing risk identification on the set of temperature monitoring points according to the two-way analysis result to obtain a set of risk monitoring points and a set of risk temperature monitoring data; and identifying a control scheme by combining the set of risk monitoring points and the set of risk temperature monitoring data with a preset heat dissipation optimization path as a constraint to obtain a heat dissipation optimization control scheme. That is to say, by arranging temperature sensors at multiple monitoring points, constructing a comprehensively covered monitoring network, collecting the temperature monitoring network sequence according to the monitoring frequency, performing two-way analysis on it, identifying the risk area, and formulating a heat dissipation optimization control scheme for heat dissipation optimization control, the heat dissipation efficiency of the prefabricated cabin of the power equipment is improved, thereby reducing the risk of damage to the power equipment due to high temperature.

[0018] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically illustrates the specific implementation manners of this application. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of this application, nor is it used to limit the scope of this application. Other features of this application will become easily understandable through the following description. Brief Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions in this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0020] Figure 1 It is a schematic flow chart of a heat dissipation optimization control method applicable to the prefabricated cabin of power equipment in this application; Figure 2 It is a schematic structural diagram of a heat dissipation optimization control system applicable to the prefabricated cabin of power equipment in this application.

[0021] Description of the reference numerals: Sensor arrangement module 11, Data acquisition module 12, Two-way analysis module 13, Risk identification module 14, Control scheme identification module 15. Detailed Description of the Embodiments

[0022] By providing a heat dissipation optimization control method and system applicable to prefabricated cabins of power equipment, this application solves the technical problem in the prior art that due to the difficulty of dynamically adjusting the prefabricated cabins of power equipment according to different environmental conditions, the temperature inside the cabin may still be too high during high-load operation, resulting in poor heat dissipation effect and affecting the reliability of equipment operation. By arranging temperature sensors at multiple monitoring points to construct a comprehensively covered monitoring network, collecting the temperature monitoring network sequence according to the monitoring frequency, performing two-way analysis on it, identifying the risk areas, and formulating a heat dissipation optimization control plan for heat dissipation optimization control, the heat dissipation efficiency of the prefabricated cabins of power equipment is improved, thereby reducing the risk of damage to power equipment due to high temperature.

[0023] Next, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited by the example embodiments described here. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application. Additionally, it should be noted that for the sake of description, only parts related to this application are shown in the drawings rather than all.

[0024] Embodiment 1, please refer to the attached Figure 1 , this application provides a heat dissipation optimization control method applicable to prefabricated cabins of power equipment. Among them, the heat dissipation optimization control method applicable to prefabricated cabins of power equipment is executed by a heat dissipation optimization control system applicable to prefabricated cabins of power equipment. The heat dissipation optimization control method applicable to prefabricated cabins of power equipment specifically includes the following steps: S100: According to the preset set of monitoring point positions, arrange temperature sensors for the target prefabricated cabin of power equipment to construct a temperature monitoring network, where the temperature monitoring network includes a set of temperature monitoring points.

[0025] Further, S100 of this application includes: Mine the overheat maintenance logs according to the model of the target prefabricated cabin of power equipment to obtain a set of overheat maintenance logs; retrieve the set of overheat maintenance logs with the maintenance points as the index to obtain a set of maintenance points; perform location nearest neighbor clustering analysis on the set of maintenance points according to the preset distance bandwidth to determine M sets of clustered maintenance points, where M is a positive integer; configure the monitoring position points based on the M sets of clustered maintenance points to obtain the preset set of monitoring point positions.

[0026] Further, this application also includes the following steps: Determine M risk coefficients according to the quantity of each cluster maintenance point set in the M cluster maintenance point sets; perform random sampling on the M cluster maintenance point sets according to the M risk coefficients and the preset number of monitoring points to obtain the preset monitoring point location set.

[0027] Specifically, there are differences in aspects such as structural layout, equipment density, and heat source distribution among cabin bodies of different models. Therefore, mine the overheat maintenance logs for the specific model of the target power equipment prefabricated cabin that requires heat dissipation optimization monitoring design. Retrieve the corresponding historical overheat faults or maintenance logs according to the model of the prefabricated cabin, which are generally stored in the equipment maintenance management center and include the time of fault occurrence, fault location, fault description, maintenance records, etc., to form an overheat maintenance log set, which contains the maintenance records for overheat problems in the past.

[0028] Using the maintenance points (such as equipment module numbers, cabin location codes) as retrieval indexes, extract the locations where overheat faults occurred from the overheat maintenance log set to form a maintenance point set, which helps to identify which locations have problems in heat dissipation. The maintenance point is the specific location for maintenance in the power equipment prefabricated cabin. Determine the preset distance bandwidth, that is, a distance threshold set according to experience, which is used to define that if the distance between two maintenance points is less than this bandwidth, they are considered to be in a neighboring relationship, controlling the formation range of the cluster.

[0029] Adopt a spatial clustering algorithm to perform location neighboring cluster analysis. Randomly select a maintenance point as the neighborhood center, use the preset distance bandwidth as the neighborhood radius, and continuously find neighboring maintenance points by constantly searching for neighboring maintenance points in the maintenance point set, and classify them into the same cluster. That is to say, continuously search for neighboring maintenance points in the maintenance point set according to the neighborhood center and neighborhood radius, automatically judge the number of clusters according to the given distance bandwidth, and can handle points with different densities at the same time. Set the minimum number of neighbors according to the size of the data set. If the data set is large, the minimum number of neighbors can be set to 3 to 5. For small data sets, 2 or 3 are also acceptable. For each maintenance point, check how many other maintenance points are in its neighborhood. If the number of points in the neighborhood of this maintenance point reaches the minimum number of neighbors, it is considered a core point. For each core point, include all the points in its neighborhood, and recursively add the points that meet the conditions in the neighborhood to the same cluster. For points that do not meet the minimum number of neighbors condition, they are called boundary points. If they overlap with the neighborhood of the core point, they can be added to the cluster where the core point is located. If a point is neither a core point nor has a neighborhood, it is marked as an outlier.

[0030] After performing clustering analysis, the cluster number corresponding to each point is obtained according to the result. The maintenance points with the same number are grouped into one set, that is, one cluster, and all maintenance points are divided into M clusters. The maintenance points within each cluster are spatially concentrated. For the analyzed noise points (outliers), they can be ignored, or monitoring points can be set separately according to actual needs, specifically depending on the heat dissipation requirements of the current target power equipment prefabricated cabin. Each set in the M cluster maintenance point sets represents a specific area in the prefabricated cabin where maintenance problems frequently occur.

[0031] According to the number of maintenance points in each cluster maintenance point set among the M cluster maintenance point sets, the corresponding risk coefficient is determined. Usually, the cluster with more maintenance points represents a higher equipment risk in that area because the equipment is denser or the probability of failure is greater. The number of maintenance points in each cluster can be simply used as its risk coefficient, or it can be normalized to the range of 0 to 1. For example, if there are 5 maintenance points in a certain cluster, the risk coefficient of this cluster is 5; if another cluster has only 2 maintenance points, its risk coefficient is 2.

[0032] According to the calculated risk coefficient and the preset number of monitoring points, random sampling is performed to ensure that each cluster is reasonably allocated monitoring points according to its risk level, and clusters with higher risks will receive more monitoring points. The preset number of monitoring points is the number of monitoring points set in advance, usually obtained from the user side, and it is necessary to ensure that it can cover the entire target power equipment prefabricated cabin for real-time monitoring of the status of maintenance points, especially on important parameters such as temperature and humidity. Random sampling is to randomly select some points as preset monitoring points from the cluster maintenance point sets according to certain rules (such as the risk coefficient) to ensure that key cluster areas can be sufficiently monitored. The risk coefficients of all clusters are added up to obtain the total risk coefficient. According to the proportion of the risk coefficient of each cluster in the total risk coefficient, it is determined how many monitoring points should be allocated to this cluster. In each cluster, according to the number of allocated monitoring points, maintenance points are randomly selected as monitoring points, that is, randomly selected from the maintenance points in the cluster to ensure the uniform distribution of monitoring points.

[0033] After random sampling, a set of preset monitoring point positions is obtained, which is the position where sensors will be deployed during the actual operation and maintenance process. By mining the overheating maintenance logs, the frequently occurring areas of heat dissipation problems in the prefabricated cabin are accurately identified. Through clustering analysis and monitoring position point configuration, the layout of monitoring points is effectively planned to ensure that key areas are fully monitored, improve the pertinence and efficiency of heat dissipation optimization control, and reduce the equipment failure risk caused by overheating problems.

[0034] According to the determined set of preset monitoring point positions, a plurality of rod-shaped temperature sensors are installed at the monitoring points of the target power equipment prefabricated cabin to collect the temperature data of each point in real time. The installed temperature sensors are connected through a communication network to construct a temperature monitoring network, which collects temperature data in real time and transmits it to the control center for processing. All the installed temperature sensors form a complete set of temperature monitoring points, comprehensively covering all areas of the prefabricated cabin and achieving comprehensive monitoring of the temperature of the target power equipment prefabricated cabin. By reasonably arranging the temperature sensors and forming a temperature monitoring network, it is possible to ensure comprehensive temperature monitoring of all important parts inside the power equipment prefabricated cabin, timely detect temperature anomalies and take preventive measures, effectively improving the operation safety and stability of the equipment.

[0035] S200: Collect the temperature monitoring data of the same time series for the temperature monitoring network according to the preset monitoring frequency to obtain a temperature monitoring data network sequence.

[0036] Specifically, according to the overheating maintenance logs of the same model of the target power equipment prefabricated cabin, a monitoring frequency, that is, the preset monitoring frequency, is determined to ensure that the temperature anomalies of the target power equipment prefabricated cabin can be monitored. For equipment temperature monitoring, the frequency is usually once every few minutes or once every few seconds, depending on the equipment's workload, the rate of environmental change, and safety requirements. According to the preset monitoring frequency, the temperature of the target power equipment prefabricated cabin is monitored through the temperature monitoring network, and the temperature monitoring data of the same time series is obtained, that is, data is collected from each temperature monitoring point (i.e., each temperature sensor) at the same time point, and these data are stored as a sequence. These data are formed into a temperature monitoring data network sequence in chronological order, recording the temperature information of each monitoring point in each acquisition cycle. For example, at 5 minutes, the temperature of monitoring point 1 is 18°C, the temperature of monitoring point 2 is 25°C, and the temperature of monitoring point 3 is 29°C; at 10 minutes, the temperature of monitoring point 1 is 19°C, the temperature of monitoring point 2 is 28°C, and the temperature of monitoring point 3 is 33°C. By collecting the temperature monitoring data of the same time series according to the preset monitoring frequency, it is ensured that continuous and comprehensive data on the temperature changes inside the prefabricated cabin are obtained, so as to timely discover and identify potential hot spots.

[0037] S300: Conduct a two-way analysis on the temperature monitoring data network sequence to obtain a two-way analysis result.

[0038] Furthermore, step S300 of the present application includes: Taking any monitoring point as an index, extract data from the temperature monitoring data network sequence to obtain a first temperature monitoring data sequence; perform two-dimensional data analysis on the first temperature monitoring data sequence to determine the first temperature monitoring data; and so on, perform two-dimensional data analysis on the temperature monitoring data network sequence at the same monitoring point to obtain a temperature monitoring data network; perform multi-scale convolution on the temperature monitoring data network sequence, and perform feature interaction fusion on the multi-scale convolution result to obtain enhanced convolution features; perform convolution analysis on the enhanced convolution features and the temperature monitoring data network at the end of the temperature monitoring data network sequence to determine a temperature monitoring enhanced data network; perform mapping mean analysis on the temperature monitoring data network and the temperature monitoring enhanced data network to obtain a two-way analysis result.

[0039] Furthermore, the present application further includes the following steps: Perform clustering analysis on the first temperature monitoring data sequence from two dimensions of data similarity and data acquisition time to obtain a first clustered temperature monitoring data cluster; respectively count the proportions of each first clustered temperature monitoring data set in the first clustered temperature monitoring data cluster to obtain a first clustered proportion set; perform weighted calculation on the first clustered temperature monitoring data cluster based on the first clustered proportion set to obtain the first temperature monitoring data.

[0040] Specifically, select any monitoring point as an index point, and extract the first temperature monitoring data sequence corresponding to this monitoring point from the temperature monitoring data network sequence, which contains the temperature data of this monitoring point at multiple time points. Perform two-dimensional data analysis on the extracted first temperature monitoring data sequence, that is, analyze from two dimensions.

[0041] Perform clustering analysis on the first temperature monitoring data sequence from two dimensions of data similarity and data acquisition time to obtain a first clustered temperature monitoring data cluster. Data similarity refers to using a distance metric method (such as Euclidean distance) to evaluate the similarity of temperature data between different time points. By calculating the temperature differences between each time point, it is determined which time points have similar temperature data and can be grouped into the same cluster. Data acquisition time is to consider the factor of data acquisition time and analyze whether there are certain periodicities, trends, etc. in the temperature data at different time points. Two-way analysis refers to analyzing the temperature monitoring data from two different dimensions (i.e., data similarity and data acquisition time).

[0042] The first cluster temperature monitoring data cluster is a data cluster divided according to data similarity and data collection time after performing cluster analysis on the first temperature monitoring data sequence from two different dimensions. The proportion of each first cluster temperature monitoring data set in the first cluster temperature monitoring data cluster is statistically analyzed, that is, the proportion of each data point in the cluster, to obtain the first cluster proportion set, which reflects the importance or frequency of a certain data set in the entire cluster. By statistically analyzing the proportions of each data set, the distribution of data in different clusters can be understood.

[0043] According to the first cluster proportion set, a weighted calculation is performed on the first cluster temperature monitoring data cluster. That is to say, according to the proportion of each first cluster temperature monitoring data set, the corresponding weight is determined. The higher the proportion of the data, the higher the weight. A weighted calculation is performed on the first cluster temperature monitoring data cluster to obtain a more representative cluster temperature data, that is, the first temperature monitoring data. For example, assume that the temperature data in the first cluster is: [23°C, 25°C, 28°C], and their proportions are [0.6, 0.2, 0.2], then the calculated first temperature data is 24.4°C.

[0044] Repeat the above process, and perform two-dimensional data analysis on the temperature monitoring data sequences corresponding to all monitoring points in the temperature monitoring data network sequence in turn. Finally, the weighted temperature data of each monitoring point is obtained, that is, multiple temperature monitoring data, which constitute the temperature monitoring data network. Through cluster analysis in two dimensions of data similarity and data collection time, the internal laws of temperature data can be deeply explored, potential trends and periodic changes can be discovered. Through weighted calculation, the temperature representative value of each monitoring point is obtained, which reflects the temperature change of this point during a specific period, and avoids the influence of extreme values on the result.

[0045] Use multi-scale convolution to process the temperature monitoring data network sequence. Multiple convolution kernels of different sizes will be applied to the input data (temperature data). Using convolution kernels of different sizes to process the data can capture different scale features in the data, understand the data from different perspectives, and capture multi-level features from short-term fluctuations to long-term trends. Smaller convolution kernels can capture local details in the data, while larger convolution kernels can identify broader change trends. Feature interaction and fusion refers to merging features from different sources or different levels to obtain a more comprehensive representation. Two convolution features are fused together through a certain interaction method (such as weighted average, concatenation, addition, etc.), thereby enhancing the expression ability of the features. The enhanced convolution feature is the feature after feature interaction and fusion, which contains information from different scales and different feature levels, has a stronger expression ability, and can provide more information than the original convolution feature.

[0046] Perform convolutional analysis on the temperature monitoring data network at the end of the enhanced convolutional feature and temperature monitoring data network sequence. By means of convolutional operation, combine the two data sets (i.e., enhanced convolutional feature and temperature monitoring data network) together, so as to extract their interaction features. Through convolutional operation, the temporal characteristics (such as mutations, fluctuations, etc.) in the device temperature change can be captured, revealing the relationship between the enhanced feature and the latest temperature data, thus obtaining a temperature monitoring enhanced data network containing richer information. After performing convolutional analysis on the temperature monitoring data network through the enhanced convolutional feature, a temperature monitoring enhanced data network is obtained, which combines the original temperature monitoring data and the enhanced convolutional feature, and has richer information and higher expressive ability. For example, if there is a sharp increase in temperature in the temperature monitoring data sequence, and the enhanced convolutional feature contains an effective representation of the high-temperature pattern, the convolutional analysis will extract this pattern and help predict the trend of temperature change.

[0047] Map the temperature monitoring data network and the temperature monitoring enhanced data network to the same scale or standard to ensure that these two data networks can be compared and analyzed on the same platform, excluding the deviation caused by different scales or data dimensions. The corresponding values of each data point in the two networks are calculated and then averaged, reflecting the representative temperature of the data point in the two networks. Calculate the mean value of the original temperature data network to obtain the average temperature of each time period. At the same time, calculate the mean value of the temperature monitoring enhanced data network obtained after convolutional analysis. By analyzing the means of these two data networks, obtain their differences, similarities or other statistical features, identify the correlation between the data, and further improve the understanding of temperature changes.

[0048] Two-way analysis is a method for analyzing two related data sets, usually used to measure the relationship, similarity or difference between the two data sets. The two-way analysis result is obtained by analyzing the data of multiple temperature monitoring points, and usually includes information such as the temperature change trend, correlation, similarity, etc. of each monitoring point. By comparing the temperature monitoring data network and the temperature monitoring enhanced data network, the two-way analysis result may reveal that the temperature fluctuations of some monitoring points are relatively large, or that the enhanced data can capture temperature anomalies more accurately during a specific time period. By interpreting the two-way analysis result, evaluate the temperature risk of the device. If the two-way analysis result shows that the change trend of the enhanced data is large or there are obvious abnormal fluctuations, then it may be necessary to check the relevant device or take corresponding heat dissipation optimization measures. Through multi-scale convolution and feature interaction fusion, extract rich temperature change features and improve the prediction accuracy of the device state. By comparing the differences between the temperature monitoring data network and the enhanced data network, temperature anomalies can be detected in a timely manner, thus warning of potential failure risks of the device.

[0049] Further, the present application further includes the following steps: Randomly extract a first convolutional feature and a second convolutional feature from the multi-scale convolutional results; perform feature interaction and fusion on the first convolutional feature and the second convolutional feature to obtain a first interaction and fusion convolutional feature; based on the first interaction and fusion convolutional feature, perform feature interaction and fusion on the remaining convolutional features in the multi-scale convolutional results to obtain an enhanced convolutional feature.

[0050] Specifically, randomly select two convolutional features from the multi-scale convolutional results, which are the first convolutional feature and the second convolutional feature respectively, to ensure that representative features are selected from different convolutional scales. For example, assume that the results of multi-scale convolution contain multiple convolutional features, such as Feature 1 (from a 3×3 convolutional kernel), Feature 2 (from a 5×5 convolutional kernel), Feature 3 (from a 7×7 convolutional kernel), etc. Through random selection, Feature 1 and Feature 2 are selected for fusion.

[0051] Perform feature interaction and fusion on the first convolutional feature and the second convolutional feature, such as addition, etc., to effectively combine these two features, so that the fused feature can contain rich information from two different convolutional scales. For example, if Feature 1 is a short-term fluctuation feature and Feature 2 is a long-term trend feature, a new feature may be obtained after fusion, which contains the comprehensive information of both, including both the details of short-term changes and the overall information of long-term trends. Additive fusion means adding the first convolutional feature and the second convolutional feature element by element. The fused result is called the first interaction and fusion convolutional feature, which combines the feature information of two different convolutional scales to obtain a more comprehensive feature representation.

[0052] The first interaction and fusion convolutional feature contains the information of the first convolutional feature and the second convolutional feature. Using the first interaction and fusion convolutional feature, continue to perform feature interaction and fusion on the remaining convolutional features. The goal is to combine the first interaction and fusion convolutional feature with other convolutional features to obtain the final enhanced convolutional feature. This fusion process is similar to the previous steps, gradually fusing the features in the multi-scale convolutional results to finally obtain an enhanced convolutional feature containing comprehensive information.

[0053] The enhanced convolutional feature contains rich information from multiple convolutional kernels and multi-scale convolution. It not only becomes more complete but also provides more dimensional insights and can more accurately represent the features of the original data. Through multi-scale convolution and feature interaction and fusion, deep features of the temperature monitoring data can be extracted, improving the intelligence and data processing ability of the system.

[0054] S400: Perform risk identification on the temperature monitoring point set according to the dual-item analysis result to obtain a risk monitoring point set and a risk temperature monitoring data set.

[0055] Further, the S400 of the present application includes: Determine whether there is risk temperature monitoring data greater than or equal to a preset temperature threshold in the dual - item analysis result. If so, add it to the risk temperature monitoring data set and add the corresponding monitoring point to the risk monitoring point set.

[0056] Specifically, perform risk identification on the temperature monitoring point set according to the dual - item analysis result to identify which monitoring points may have problems with their temperature data. Set a preset temperature threshold according to the temperature tolerance range of the device. When the temperature data exceeds this threshold, it is considered that there is a risk point, usually set according to the heat dissipation requirements of the prefabricated cabin of the target power equipment.

[0057] According to the dual - item analysis result, check whether the temperature data of each monitoring point exceeds the preset temperature threshold. If there is risk temperature monitoring data greater than or equal to the preset temperature threshold in the dual - item analysis result, perform risk identification on it, consider this monitoring point as a risk monitoring point, and at the same time add the temperature data of this monitoring point to the risk temperature monitoring data set and add this monitoring point to the risk monitoring point set.

[0058] According to the dual - item analysis result of each monitoring point and the actual temperature data of the monitoring point, obtain the final risk monitoring point set and risk temperature monitoring data set. Through risk identification, quickly identify the high - risk areas in the temperature monitoring network, accurately locate the problem areas, which helps to take heat dissipation optimization or other emergency measures in a timely manner to avoid failures caused by overheating of the equipment.

[0059] S500: With the preset heat dissipation optimization path as a constraint, combine the risk monitoring point set and the risk temperature monitoring data set to identify a control scheme and obtain a heat dissipation optimization control scheme.

[0060] Further, the S500 of the present application includes: Pre - construct a control scheme identifier; use the control scheme identifier to identify the preset heat dissipation optimization path, the risk monitoring point set, and the risk temperature monitoring data set to obtain a heat dissipation optimization control scheme.

[0061] Specifically, construct a control scheme identifier to generate an appropriate heat dissipation optimization scheme according to input conditions (such as monitored temperature, risk monitoring points, etc.). The main goal of the identifier is to automatically generate a control scheme that can optimize the device temperature and improve the heat dissipation efficiency according to the input temperature monitoring data, risk data, load conditions, and environmental factors. The inputs received by the identifier include device temperature data, monitoring point information, ambient temperature, device load, etc., and the output is heat dissipation optimization control measures for each device.

[0062] Generate an overheating maintenance log based on the model of the target power equipment prefabricated cabin, and obtain historical temperature monitoring data, risk points, corresponding heat dissipation solutions, and heat dissipation effect data. Clean the collected data, remove invalid and abnormal data, and fill in missing values using a filling method based on neighboring values to fill in the missing values caused by faults or lost data. Standardize or normalize the data to eliminate the influence of dimensions. Convert each eigenvalue into a form with a mean of 0 and a standard deviation of 1 to eliminate the influence of different dimensions on the data analysis results. Scale the data to a certain range (such as 0 to 1) so that the influence of different features is maintained at the same level.

[0063] Select a suitable machine learning model, such as a support vector machine, to generate a heat dissipation optimization control scheme under different input conditions. Support vector machines are good at processing data with high-dimensional features and can effectively learn the relationship between equipment overheating and heat dissipation solutions from historical data. Train the support vector machine model using the cleaned and preprocessed dataset. The goal of training is to enable the model to predict a suitable heat dissipation solution based on input features such as temperature and load in historical data. Divide the dataset into a training set and a test set, and use cross-validation to evaluate the accuracy and generalization ability of the model. Use the training set to train the model, continuously adjust the parameters, and at the same time use the validation set to evaluate the performance of the model. Set the convergence conditions of the model, such as the validation set loss changing less than 0.01 for 5 consecutive rounds or the training set accuracy reaching 95%.

[0064] Through the trained support vector machine model, generate a control scheme recognizer that automatically identifies a suitable heat dissipation control scheme based on real-time data such as the equipment temperature and monitoring points input. Utilize the control scheme recognizer, combine the risk monitoring point set and the risk temperature monitoring data set, and perform control scheme recognition with a preset heat dissipation optimization path as a constraint. The preset heat dissipation optimization path will be adjusted according to the heat dissipation requirements of the equipment, the ambient temperature, and the load conditions, determining the selection and switching method of the heat dissipation solution.

[0065] Using a control scheme recognizer, combining a set of risk monitoring points and a set of risk temperature monitoring data, and taking a preset heat dissipation optimization path as a constraint, a control scheme is recognized. This means that the recognizer will generate an optimal heat dissipation optimization control scheme based on the current risk situation and the preset control path. This scheme will take specific control measures for the risk monitoring points to reduce the overheating risk. For example, assume that the set of risk monitoring points includes monitoring points A and B, and the set of risk temperature monitoring data shows that the temperatures of these two points exceed the preset threshold. The preset heat dissipation optimization path includes increasing the fan speed, adjusting the air conditioner settings, etc. The control scheme recognizer generates a control scheme based on this information, such as increasing the fan speed near monitoring points A and B and adjusting the air conditioner settings to lower the temperatures in these areas. By pre-building a control scheme recognizer, a heat dissipation optimization control scheme for the current risk situation is generated to ensure the effectiveness and pertinence of the control measures, thereby improving the efficiency and effect of heat dissipation optimization.

[0066] Furthermore, the present application further includes the following steps: Obtain a feedback monitoring window; monitor the temperature drop gradient of the set of risk monitoring points within the feedback monitoring window, and if the requirement is not met, generate a warning instruction.

[0067] Specifically, obtain a feedback monitoring window for continuously tracking the temperature change of the target device or monitoring point. Monitor the temperature in real time within the feedback monitoring window and compare it with a predetermined heat dissipation target or threshold to ensure that the operating temperature of the device is always within a safe range. The time range of the feedback monitoring window is usually a preset time period, such as 10 minutes, 30 minutes, etc.

[0068] During the feedback monitoring window, monitor the temperature change of each risk monitoring point in real time and calculate the temperature drop gradient of each monitoring point. That is, record the temperature change of each monitoring point within the feedback window and calculate the rate of temperature change per unit time. The temperature drop gradient refers to the rate of temperature change per unit time, that is, the speed at which the temperature of the monitoring point decreases.

[0069] According to the heat dissipation requirements of the device and historical temperature data, set a reasonable temperature drop gradient threshold, usually adjusted based on the device's workload and environmental conditions. Within the feedback monitoring window, calculate the temperature drop gradient of each monitoring point based on the collected temperature data. If the temperature drop speed of a certain point within a time period is lower than the preset threshold, it means that the heat dissipation effect of this point is not ideal and measures need to be taken.

[0070] Compare the temperature drop gradient of each risk monitoring point with the preset requirements. If the temperature drop gradient of a certain monitoring point fails to meet the preset requirements (i.e., the cooling rate is too slow), it is considered that there is a risk at this point, which may cause the equipment to overheat or fail to cool down in time. Once it is detected that the temperature drop gradient does not meet the expectation, a warning instruction is generated to remind the maintenance personnel or the automatic system to respond. The warning instruction usually contains relevant information, such as the location of the monitoring point, the temperature anomaly, the temperature change gradient, etc., to help the maintenance personnel locate the problem in time and take measures.

[0071] Through real-time monitoring and temperature gradient analysis, a warning is issued in a timely manner when the temperature change does not meet the requirements, avoiding overheating faults of the equipment and ensuring the long-term stable operation of the equipment. By monitoring the feedback monitoring window and the real-time temperature drop gradient, the area with insufficient heat dissipation can be effectively identified and warning measures can be taken to ensure that the temperature of the prefabricated cabin of the target power equipment is always within the safe range.

[0072] In summary, the heat dissipation optimization control method for the prefabricated cabin of power equipment provided by this application has the following beneficial effects: By arranging temperature sensors on the prefabricated cabin of the target power equipment according to the preset set of monitoring point positions, a temperature monitoring network is constructed, where the temperature monitoring network includes a set of temperature monitoring points; the temperature monitoring network is simultaneously monitored for temperature monitoring data acquisition according to the preset monitoring frequency to obtain a temperature monitoring data network sequence; a two-way analysis is performed on the temperature monitoring data network sequence to obtain a two-way analysis result; risk identification is performed on the set of temperature monitoring points according to the two-way analysis result to obtain a set of risk monitoring points and a set of risk temperature monitoring data; with the preset heat dissipation optimization path as a constraint, a control scheme is identified in combination with the set of risk monitoring points and the set of risk temperature monitoring data to obtain a heat dissipation optimization control scheme. That is to say, by arranging temperature sensors at multiple monitoring points, constructing a comprehensively covered monitoring network, collecting the temperature monitoring network sequence according to the monitoring frequency, performing a two-way analysis on it, identifying the risk area, and formulating a heat dissipation optimization control scheme for heat dissipation optimization control, the heat dissipation efficiency of the prefabricated cabin of power equipment is improved, thereby reducing the risk of damage to power equipment due to high temperature.

[0073] Embodiment 2, based on the same inventive concept as the heat dissipation optimization control method for the prefabricated cabin of power equipment in the foregoing Embodiment 1, this application also provides a heat dissipation optimization control system for the prefabricated cabin of power equipment. Please refer to the appendix Figure 2 , the heat dissipation optimization control system for the prefabricated cabin of power equipment includes: The sensor layout module 11 is used to layout temperature sensors for the prefabricated cabin of the target power equipment according to the preset monitoring point position set, and construct a temperature monitoring network. Among them, the temperature monitoring network includes a temperature monitoring point set; the data acquisition module 12 is used to collect simultaneous temperature monitoring data of the temperature monitoring network according to the preset monitoring frequency, and obtain a temperature monitoring data network sequence; the dual - item analysis module 13 is used to perform dual - item analysis on the temperature monitoring data network sequence to obtain a dual - item analysis result; the risk identification module 14 is used to perform risk identification on the temperature monitoring point set according to the dual - item analysis result, and obtain a risk monitoring point set and a risk temperature monitoring data set; the control scheme identification module 15 is used to identify a heat dissipation optimization control scheme by combining the risk monitoring point set and the risk temperature monitoring data set with the constraint of the preset heat dissipation optimization path.

[0074] Furthermore, the sensor layout module 11 in the heat dissipation optimization control system applicable to the prefabricated cabin of power equipment is further used for: Mining overheat maintenance logs according to the model of the prefabricated cabin of the target power equipment to obtain an overheat maintenance log set; retrieving the overheat maintenance log set with the maintenance points as indexes to obtain a maintenance point set; performing position - near neighbor clustering analysis on the maintenance point set according to the preset distance bandwidth to determine M clustered maintenance point sets, where M is a positive integer; configuring monitoring position points based on the M clustered maintenance point sets to obtain a preset monitoring point position set.

[0075] Furthermore, the sensor layout module 11 in the heat dissipation optimization control system applicable to the prefabricated cabin of power equipment is further used for: Determining M risk coefficients according to the number of each clustered maintenance point set in the M clustered maintenance point sets; randomly sampling the M clustered maintenance point sets according to the M risk coefficients and the preset number of monitoring points to obtain the preset monitoring point position set.

[0076] Furthermore, the dual - item analysis module 13 in the heat dissipation optimization control system applicable to the prefabricated cabin of power equipment is further used for: Taking any monitoring point as an index, extract data from the temperature monitoring data network sequence to obtain a first temperature monitoring data sequence; perform two-dimensional data analysis on the first temperature monitoring data sequence to determine the first temperature monitoring data; and so on, perform two-dimensional data analysis on the temperature monitoring data network sequence at the same monitoring point to obtain a temperature monitoring data network; perform multi-scale convolution on the temperature monitoring data network sequence, and perform feature interaction fusion on the multi-scale convolution results to obtain enhanced convolution features; perform convolution analysis on the enhanced convolution features and the temperature monitoring data network at the end of the temperature monitoring data network sequence to determine a temperature monitoring enhanced data network; perform mapping mean analysis on the temperature monitoring data network and the temperature monitoring enhanced data network to obtain a two-way analysis result.

[0077] Furthermore, the two-way analysis module 13 in the heat dissipation optimization control system applicable to the prefabricated cabin of power equipment is further configured to: Perform clustering analysis on the first temperature monitoring data sequence from two dimensions of data similarity and data acquisition time to obtain a first clustered temperature monitoring data cluster; respectively count the proportions of each first clustered temperature monitoring data set in the first clustered temperature monitoring data cluster to obtain a first clustered proportion set; perform weighted calculation on the first clustered temperature monitoring data cluster based on the first clustered proportion set to obtain the first temperature monitoring data.

[0078] Furthermore, the two-way analysis module 13 in the heat dissipation optimization control system applicable to the prefabricated cabin of power equipment is further configured to: Randomly extract a first convolution feature and a second convolution feature from the multi-scale convolution results; perform feature interaction fusion on the first convolution feature and the second convolution feature to obtain a first interaction fusion convolution feature; perform feature interaction fusion on the remaining convolution features in the multi-scale convolution results based on the first interaction fusion convolution feature to obtain enhanced convolution features.

[0079] Furthermore, the risk identification module 14 in the heat dissipation optimization control system applicable to the prefabricated cabin of power equipment is further configured to: Judge whether there is risk temperature monitoring data greater than or equal to a preset temperature threshold in the two-way analysis result. If so, add it to the risk temperature monitoring data set and add the corresponding monitoring point to the risk monitoring point set.

[0080] Furthermore, the control scheme identification module 15 in the heat dissipation optimization control system applicable to the prefabricated cabin of power equipment is further configured to: Pre-construct a control scheme identifier; use the control scheme identifier to identify a preset heat dissipation optimization path, a risk monitoring point set, and a risk temperature monitoring data set to obtain a heat dissipation optimization control scheme.

[0081] Furthermore, the heat dissipation optimization control system applicable to the prefabricated cabin of power equipment further includes a feedback warning module, and the feedback warning module is further configured to: Obtain a feedback monitoring window; monitor the temperature drop gradient of the risk monitoring point set in the feedback monitoring window, and generate a warning instruction if the requirement is not met.

[0082] The various embodiments in this specification are described in a progressive manner, and the key point of each embodiment is to illustrate the differences from other embodiments. The Figure 1 Heat dissipation optimization control method and specific examples in Embodiment 1 are equally applicable to the heat dissipation optimization control system applicable to the prefabricated cabin of power equipment in this embodiment. Through the detailed description of the heat dissipation optimization control method applicable to the prefabricated cabin of power equipment above, those skilled in the art can clearly know the heat dissipation optimization control system applicable to the prefabricated cabin of power equipment in this embodiment. Therefore, for the sake of simplicity of the specification, it will not be elaborated here.

[0083] 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 obvious to those skilled in the art, and the general principles defined herein can 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 be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0084] Obviously, those skilled in the art can make several improvements and modifications to the present application without departing from the principle of the present application, and these improvements and modifications also fall within the protection scope of the present application.

Claims

1. A heat dissipation optimization control method applicable to a prefabricated cabin of power equipment, characterized in that, Including: According to a preset set of monitoring point positions, temperature sensors are arranged on the prefabricated cabin of the target power equipment to construct a temperature monitoring network, where the temperature monitoring network includes a set of temperature monitoring points; Simultaneous temperature monitoring data of the temperature monitoring network is collected according to a preset monitoring frequency to obtain a temperature monitoring data network sequence; Two-way analysis is performed on the temperature monitoring data network sequence to obtain a two-way analysis result; Risk identification is performed on the set of temperature monitoring points according to the two-way analysis result to obtain a set of risk monitoring points and a set of risk temperature monitoring data; Constrained by a preset heat dissipation optimization path, a control scheme is identified by combining the set of risk monitoring points and the set of risk temperature monitoring data to obtain a heat dissipation optimization control scheme.

2. The heat dissipation optimization control method applicable to the prefabricated cabin of power equipment according to claim 1, characterized in that The preset set of monitoring point positions includes: Overheating repair logs of the prefabricated cabin of the target power equipment are mined according to its model to obtain a set of overheating repair logs; Indexed by repair points, the set of overheating repair logs is retrieved to obtain a set of repair points; Position near-neighbor clustering analysis is performed on the set of repair points according to a preset distance bandwidth to determine M sets of clustered repair points, where M is a positive integer; Based on the M sets of clustered repair points, monitoring position points are configured to obtain a preset set of monitoring point positions.

3. The heat dissipation optimization control method applicable to the prefabricated cabin of power equipment according to claim 2, characterized in that Based on the M sets of clustered repair points, configuring monitoring position points to obtain a preset set of monitoring point positions includes: According to the number of each set of clustered repair points in the M sets of clustered repair points, M risk coefficients are determined; According to the M risk coefficients and the preset number of monitoring points, random sampling is performed on the M sets of clustered repair points to obtain the preset set of monitoring point positions.

4. The heat dissipation optimization control method applicable to the prefabricated cabin of power equipment according to claim 1, characterized in that, Performing two-way analysis on the temperature monitoring data network sequence to obtain a two-way analysis result includes: Indexed by any one monitoring point, data is extracted from the temperature monitoring data network sequence to obtain a first temperature monitoring data sequence; Two-dimensional data analysis is performed on the first temperature monitoring data sequence to determine the first temperature monitoring data; And so on, two-dimensional data analysis of the same monitoring point is performed on the temperature monitoring data network sequence to obtain a temperature monitoring data network; Multi-scale convolution is performed on the temperature monitoring data network sequence, and feature interaction fusion is performed on the multi-scale convolution result to obtain enhanced convolution features; The enhanced convolution features are subjected to convolution analysis with the temperature monitoring data network at the end of the temperature monitoring data network sequence to determine a temperature monitoring enhanced data network; Mapping mean analysis is performed on the temperature monitoring data network and the temperature monitoring enhanced data network to obtain a two-way analysis result.

5. The heat dissipation optimization control method applicable to the prefabricated cabin of power equipment according to claim 4, characterized in that Performing two-dimensional data analysis on the first temperature monitoring data sequence to determine the first temperature monitoring data includes: Clustering analysis is performed on the first temperature monitoring data sequence from two dimensions of data similarity and data acquisition time to obtain a first clustered temperature monitoring data cluster; The proportion of each first clustered temperature monitoring data set in the first clustered temperature monitoring data cluster is statistically calculated respectively to obtain a first clustered proportion set; Perform weighted calculation on the first cluster temperature monitoring data cluster based on the first cluster occupancy ratio set to obtain the first temperature monitoring data.

6. The heat dissipation optimization control method applicable to the prefabricated cabin of power equipment according to claim 4, wherein Perform feature interaction fusion on the multi-scale convolution results to obtain enhanced convolution features, including: Randomly extract a first convolution feature and a second convolution feature from the multi-scale convolution results; Perform feature interaction fusion on the first convolution feature and the second convolution feature to obtain a first interaction fusion convolution feature; Based on the first interaction fusion convolution feature, perform feature interaction fusion on the remaining convolution features in the multi-scale convolution results to obtain enhanced convolution features.

7. The heat dissipation optimization control method applicable to the prefabricated cabin of power equipment according to claim 1, wherein Judge whether there is risk temperature monitoring data greater than or equal to a preset temperature threshold in the two-way analysis result. If so, add it to the risk temperature monitoring data set and add the corresponding monitoring point to the risk monitoring point set.

8. The heat dissipation optimization control method applicable to the prefabricated cabin of power equipment according to claim 1, characterized in that, Obtain a heat dissipation optimization control scheme, including: Pre-build a control scheme recognizer; Use the control scheme recognizer to recognize a preset heat dissipation optimization path, a risk monitoring point set, and a risk temperature monitoring data set to obtain a heat dissipation optimization control scheme.

9. The heat dissipation optimization control method applicable to the prefabricated cabin of power equipment according to claim 1, wherein, Further include: Obtain a feedback monitoring window; Monitor the temperature drop gradient of the risk monitoring point set in the feedback monitoring window. If the requirement is not met, generate a warning instruction.

10. A heat dissipation optimization control system applicable to a prefabricated cabin of power equipment, characterized in that, For implementing the steps of the heat dissipation optimization control method applicable to a prefabricated cabin of power equipment according to any one of claims 1 to 9, the heat dissipation optimization control system applicable to a prefabricated cabin of power equipment includes: A sensor layout module for laying temperature sensors on a target prefabricated cabin of power equipment according to a preset monitoring point position set to construct a temperature monitoring network, where the temperature monitoring network includes a temperature monitoring point set; A data acquisition module for simultaneously acquiring temperature monitoring data of the temperature monitoring network at a preset monitoring frequency to obtain a temperature monitoring data network sequence; A two-way analysis module for performing two-way analysis on the temperature monitoring data network sequence to obtain a two-way analysis result; A risk identification module for performing risk identification on the temperature monitoring point set according to the two-way analysis result to obtain a risk monitoring point set and a risk temperature monitoring data set; A control scheme recognition module for performing control scheme recognition by combining the risk monitoring point set and the risk temperature monitoring data set with a preset heat dissipation optimization path as a constraint to obtain a heat dissipation optimization control scheme.

Images