Dehumidification and condensation prevention method and system for indoor full-cabling power distribution station house

Abstract

The invention relates to an indoor full-cable power distribution station house dehumidification and condensation prevention method and system, and the method comprises the steps: collecting temperature and humidity data in a power distribution station house, predicting the temperature and humidity change trend in the station house based on a deep learning model, and building a dynamic temperature and humidity change model; establishing a self-adaptive thermal regulation phase change material anti-condensation unit; according to the easily-condensed area information identified in the dynamic temperature and humidity change model and the operation state data of the ventilation system, the phase-change material anti-condensation unit is arranged at the anti-condensation position of the power distribution station house, and an anti-condensation network and corresponding anti-condensation effect data are obtained; according to the dynamic temperature and humidity change model and the anti-condensation effect data, an active anti-condensation guarantee mechanism based on the PTC heating element is established; and a comprehensive control system is established through a multi-objective optimization algorithm, and dehumidification and condensation prevention are carried out on the power distribution station house through the comprehensive control system. Through dynamic temperature and humidity prediction, phase change material anti-condensation and active heating technologies, the energy consumption is reduced, and the anti-condensation effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and particularly to a method and system for dehumidifying and anti-condensation in an indoor fully-cabled distribution substation building. Background Art

[0002] With the development of power systems, indoor fully-cabled distribution substation buildings have been widely used in urban distribution networks. Such buildings usually adopt a sealed structure, and there are a large number of cable terminals, joints and distribution equipment inside. During use, due to the temperature difference and humidity change between the inside and outside of the building, condensation is likely to occur on the surface of the equipment, posing a serious threat to the safe operation of electrical equipment.

[0003] Traditional anti-condensation and dehumidification technologies mainly include methods such as ventilation dehumidification, heating anti-condensation and desiccant moisture absorption. Ventilation dehumidification reduces the humidity inside the building by introducing dry air; heating anti-condensation keeps the surface temperature of the equipment higher than the dew point temperature through heaters; desiccant moisture absorption uses materials such as silica gel to absorb moisture in the air; in some areas, air conditioners and dehumidifiers are also used for dehumidifying the building.

[0004] However, in the prior art, traditional ventilation systems often lack intelligent control, are difficult to cope with complex and changeable environmental conditions, and sometimes even introduce humid air into the building, exacerbating the condensation problem. Conventional heating anti-condensation methods have high energy consumption, and continuous use will significantly increase the operation cost and carbon emissions of the building. Desiccants need to be replaced frequently, with a large amount of maintenance work, and the dehumidification effect is unstable. Although air conditioners and dehumidifiers have good effects, they have high equipment costs, high energy consumption, and there are risks of noise pollution and refrigerant leakage during operation. In addition, most of the existing anti-condensation and dehumidification technologies are single means, lacking systematic integration and intelligent control strategies, and it is difficult to carry out targeted protection according to the condensation risk characteristics of different areas in the building, resulting in uneven anti-condensation effects, and condensation problems may still occur in some areas. Summary of the Invention

[0005] The present invention provides a method and system for dehumidifying and anti-condensation in an indoor fully-cabled distribution substation building to solve the defects of the prior art.

[0006] The present invention provides a method for dehumidifying and anti-condensation in an indoor fully-cabled distribution substation building, including:

[0007] S1: Collect temperature and humidity data in the distribution substation building to obtain building environment parameter data, and predict the change trend of temperature and humidity in the building based on a deep learning model of time series to establish a dynamic temperature and humidity change model;

[0008] S2: Establish a phase change material anti-condensation unit with adaptive thermal regulation according to the dynamic temperature and humidity change model and the building environment parameter data;

[0009] S3: Based on the information of the easily condensable region identified in the dynamic temperature and humidity change model and the operation status data of the ventilation system, deploy the phase change material anti-condensation unit at the anti-condensation positions in the substation building to obtain an anti-condensation network, and monitor the working status of the anti-condensation network in real time to obtain anti-condensation effect data;

[0010] S4: Based on the dynamic temperature and humidity change model and the anti-condensation effect data, establish an active anti-condensation guarantee mechanism based on PTC heating elements;

[0011] S5: Based on the data flow information of the dynamic temperature and humidity change model, the ventilation system, the anti-condensation network, and the active anti-condensation guarantee mechanism, establish a comprehensive control system through a multi-objective optimization algorithm, and perform dehumidification and anti-condensation on the substation building through the comprehensive control system.

[0012] For a method for dehumidification and anti-condensation of an indoor fully-cabled substation building provided by the present invention, step S1 further includes:

[0013] S11: Monitor key positions including the surface of the power distribution cabinet, the cable joints, the wall condensation risk area, and the corners of the substation building in real time to obtain substation building environment parameter data;

[0014] S12: Store and index the substation building environment parameter data through a time series database to obtain a historical temperature and humidity data set;

[0015] S13: Based on the future meteorological change prediction data and the historical temperature and humidity data set, predict the temperature and humidity change trend to obtain a temperature and humidity change trend prediction result;

[0016] S14: Use a condensation risk assessment algorithm to analyze the temperature and humidity change trend prediction result to obtain dynamic identification information of the easily condensable regions in the substation building, and obtain a complete dynamic temperature and humidity change model.

[0017] For a method for dehumidification and anti-condensation of an indoor fully-cabled substation building provided by the present invention, step S13 further includes:

[0018] S131: Use an LSTM neural network to extract features from the historical temperature and humidity data set to obtain time series features of temperature and humidity changes;

[0019] S132: Obtain future meteorological change prediction data by acquiring weather forecast information through an external meteorological data API;

[0020] S133: Use a multivariate time series analysis method to fuse the time series features and the future meteorological change prediction data to obtain comprehensive prediction input parameters;

[0021] S134: Use the deep learning prediction model to learn the comprehensive prediction input parameters to obtain the prediction result of the temperature and humidity change trend.

[0022] According to a dehumidification and anti-condensation method for indoor fully-cabled distribution substations provided by the present invention, step S2 further includes:

[0023] S21: Select a basic phase change material suitable for the temperature range of the substation according to the dynamic temperature and humidity change model and the substation environment parameter data;

[0024] S22: Add a nano-level modifier to the basic phase change material to optimize its performance to obtain a modified phase change material;

[0025] S23: Perform microcapsule encapsulation with a multi-layer structure design on the modified phase change material to obtain a phase change material anti-condensation unit.

[0026] According to a dehumidification and anti-condensation method for indoor fully-cabled distribution substations provided by the present invention, in step S3, according to the information of the condensation-prone area identified in the dynamic temperature and humidity change model and the operation status data of the ventilation system, the step of arranging the phase change material anti-condensation unit at the anti-condensation position of the distribution substation to obtain an anti-condensation network further includes:

[0027] S31: Perform data mining on the temperature and humidity distribution data in the dynamic temperature and humidity change model to identify the condensation-prone area and obtain a condensation-prone area positioning map;

[0028] S32: Use computational fluid dynamics simulation to process the operation status data of the ventilation system to generate an air flow path and velocity distribution model in the substation to obtain an air circulation dead angle identification result;

[0029] S33: Perform comprehensive overlay analysis on the condensation-prone area positioning map and the air circulation dead angle identification result according to the risk rating method to determine high-risk areas, medium-risk areas, and low-risk areas, and obtain a hierarchical anti-condensation layout plan;

[0030] S34: According to the hierarchical anti-condensation layout plan, arrange the phase change material anti-condensation unit at the anti-condensation position of the distribution substation to obtain an anti-condensation network.

[0031] According to a dehumidification and anti-condensation method for indoor fully-cabled distribution substations provided by the present invention, the step of real-time monitoring of the working state of the anti-condensation network in step S3 specifically includes:

[0032] Monitor the surface temperature of the phase change material anti-condensation unit through a micro temperature sensor to obtain the working temperature of the anti-condensation unit;

[0033] Use infrared thermal imaging technology to scan the temperature distribution of the phase change material anti-condensation unit to obtain heat diffusion effect data;

[0034] Measure the heat transfer between the phase change material anti-condensation unit and the environment through a heat flux sensor to obtain energy exchange information during the phase change process;

[0035] Detect the condensation condition of the protected surface using a surface humidity detector to obtain anti-condensation surface state data.

[0036] According to a dehumidification and anti-condensation method for indoor fully cable-connected substation rooms provided by the present invention, S4 further includes:

[0037] S41: Integrate PTC heating elements in high-risk condensation areas based on the dynamic temperature and humidity change model and the anti-condensation effect data to obtain a basic heating element layout;

[0038] S42: Combine the regional temperature distribution based on thermal imaging technology to optimize the basic heating element layout and obtain an optimized heating element layout;

[0039] S43: Control the power of the PTC heating elements in the optimized heating element layout to form an active anti-condensation guarantee mechanism based on the PTC heating elements.

[0040] According to a dehumidification and anti-condensation method for indoor fully cable-connected substation rooms provided by the present invention, step S5 further includes:

[0041] S51: Integrate the data stream information of the dynamic temperature and humidity change model, the ventilation system, the anti-condensation network, and the active anti-condensation guarantee mechanism through an industrial controller to obtain a system-level control platform;

[0042] S52: Set optimization objectives including minimizing energy consumption, maximizing dehumidification efficiency, and minimizing temperature uniformity, construct an objective function, and obtain an optimal control strategy through a multi-objective optimization algorithm;

[0043] S53: Control the integrated control system through the optimal control strategy to dehumidify and prevent condensation in the substation room.

[0044] According to a dehumidification and anti-condensation method for indoor fully cable-connected substation rooms provided by the present invention, the expression of the optimization objective of the multi-objective optimization algorithm in step S52 is:

[0045]

[0046] Among them, F(x) is the optimization objective, t0 is the starting point of the time range, t fis the end of the time range, λ is the exponential decay coefficient, V(t) is the time series of the ventilation system wind speed adjustment coefficient, Q(t) is the time series of the auxiliary electric heating system power adjustment coefficient, x1 is the decision variable of the ventilation system wind speed adjustment coefficient, x3 is the decision variable of the heating system power adjustment coefficient, H(t) is the humidity time series, P(t) is the temperature distribution time series of the anti-condensation network, x2 is the decision variable of the phase change material layout density, T(t) is the temperature time series, T avg is the average temperature value.

[0047] The present invention also provides an indoor fully-cabled substation building dehumidification and anti-condensation system, including:

[0048] A prediction module: used to collect the temperature and humidity data in the substation building, obtain the substation building environment parameter data, and predict the temperature and humidity change trend in the substation building based on the deep learning model of the time series, and establish a dynamic temperature and humidity change model;

[0049] A first construction module: used to establish a phase change material anti-condensation unit with adaptive heat regulation according to the dynamic temperature and humidity change model and the substation building environment parameter data;

[0050] A monitoring module: used to perform real-time monitoring on the anti-condensation network arranged at the anti-condensation position in the substation building to obtain anti-condensation effect data;

[0051] A second construction module: used to establish an active anti-condensation guarantee mechanism based on PTC heating elements according to the dynamic temperature and humidity change model and the anti-condensation effect data;

[0052] A control module: used to control the integrated control system including the ventilation system, the anti-condensation network and the active anti-condensation guarantee mechanism through a multi-objective optimization algorithm to perform dehumidification and anti-condensation on the substation building.

[0053] A method and system for dehumidifying and anti-condensation in an indoor fully-cabled distribution substation provided by the present invention construct a dynamic temperature and humidity change model by using a time series deep learning model, enabling the system to accurately predict the future temperature and humidity change trends and condensation risk distributions in the substation, solving the problem that traditional methods cannot achieve forward-looking anti-condensation, and at the same time being able to fully explore the temporal characteristics of temperature and humidity data, significantly improving the prediction accuracy, providing a reliable basis for the precise deployment of subsequent anti-condensation measures; secondly, the present invention generates dynamic identification information for easily condensable areas, laying a foundation for the precise deployment of anti-condensation units. By combining data mining technology with computational fluid dynamics simulation, not only the easily condensable areas are accurately identified, but also ventilation dead corners are discovered through the air flow path and flow velocity distribution model. The hierarchical anti-condensation layout scheme formed by comprehensively analyzing these two parts of information by the risk rating method greatly improves the usage efficiency and pertinence of anti-condensation materials; when the anti-condensation network is working, the all-round monitoring of the working state of the anti-condensation network is realized through a multi-dimensional monitoring network, providing rich anti-condensation effect evaluation data. The PTC heating element integration scheme based on data settings combined with the optimized heating element layout by thermal imaging technology realizes the precise control of active anti-condensation and avoids energy waste; finally, the entire system integrates multi-source data streams through an industrial controller, and applies a multi-objective optimization algorithm with triple optimization objectives of minimizing energy consumption, maximizing dehumidification efficiency, and minimizing temperature uniformity to generate an optimal control strategy, balancing various indicators, enabling the control strategy to quickly respond to environmental changes and maintain system stability, showing strong adaptability and stability. The overall solution of the present invention realizes the all-weather, fully automatic, and low-energy consumption operation of dehumidifying and anti-condensation in the distribution substation, significantly improves the safety and reliability of power distribution equipment, and reduces the maintenance cost. Description of the Drawings

[0054] In order to more clearly illustrate the technical solutions in the present invention 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 some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0055] Figure 1 It is a schematic flow chart of a method for dehumidifying and anti-condensation in an indoor fully-cabled distribution substation provided by an embodiment of the present invention;

[0056] Figure 2 It is a schematic structural diagram of a system for dehumidifying and anti-condensation in an indoor fully-cabled distribution substation provided by an embodiment of the present invention.

[0057] Reference Signs:

[0058] 100, prediction module; 200, first construction module; 300, monitoring module; 400, second construction module; 500, control module. Detailed implementation mode

[0059] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments, and they should not be construed as limiting the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention. In the description of the present invention, it should be understood that the terms used are only for the purpose of description and cannot be construed as indicating or implying relative importance.

[0060] The embodiments of the present invention will be described below with reference to the drawings.

[0061] As Figure 1 shown, the present invention provides a method for dehumidifying and anti-condensation in an indoor fully-cabled distribution substation building, including:

[0062] S1: Collect the temperature and humidity data in the distribution substation building to obtain the environmental parameter data of the substation building, and predict the change trend of the temperature and humidity in the substation building based on a deep learning model of time series, and establish a dynamic temperature and humidity change model.

[0063] Further, step S1 mainly includes the collection, storage, processing and predictive analysis of the temperature and humidity data in the distribution substation building, and finally establishes a dynamic temperature and humidity change model. During the operation of the distribution substation building, due to factors such as equipment heating, environmental temperature difference and humidity change, condensation is likely to occur on the surface of electrical equipment, posing a threat to the safe operation of the equipment. To solve this problem, it is necessary to accurately monitor the temperature and humidity in the substation building and predict the change trend, so as to take targeted anti-condensation measures.

[0064] Among them, step S1 further includes:

[0065] S11: Real-time monitor key positions including the surface of the distribution cabinet, cable joints, wall condensation risk areas and corners of the substation building to obtain the environmental parameter data of the substation building.

[0066] Further, in step S11, high-precision temperature and humidity sensors are first installed at positions such as the surface of the power distribution cabinet, cable joints, wall condensation risk areas, and corners of the substation building to collect temperature and humidity data in these areas. The surface of the power distribution cabinet, as the shell of the main electrical equipment, is affected by the heat generated by the internal equipment and the external environment, and it is easy to form a temperature difference; due to the complex structure, cable joints are often the key areas where cold bridges are formed; the wall condensation risk area usually refers to the area close to the exterior wall and greatly affected by the external environment; the corners of the substation building are the positions where the air circulation is poor and moisture is likely to accumulate. SHT3x series temperature and humidity sensors are installed at these positions respectively, with an accuracy of up to ±0.2°C and ±1.5%RH, ensuring the accuracy of the collected data. These sensors transmit the data to the central data collector through the RS485 bus using the ModbusRTU protocol, forming a multi-point real-time monitoring network. The data collection frequency is dynamically adjusted according to the environmental change rate. Usually, it is once every 5 minutes in a stable environment and can be increased to once every 1 minute when the environment changes violently, ensuring that the key change points of temperature and humidity are captured. In addition to temperature and humidity, auxiliary parameters such as surface temperature and air velocity are also collected synchronously for calculating the dew point temperature and air flow distribution. After preliminary screening of these raw data and removing obvious outliers, a standardized dataset of substation building environment parameters is formed.

[0067] S12: Store and index the substation building environment parameter data through a time series database to obtain a historical temperature and humidity dataset.

[0068] Furthermore, different from traditional relational databases, the time series database of the present invention is optimized for time series data and can efficiently process a large amount of timestamp data. The present invention uses InfluxDB as the time series database and stores the station house environment parameter data obtained in step S11 in chronological order. Each data record includes a collection timestamp, a collection location identifier, a temperature value, a humidity value, a calculated dew point temperature value, and other auxiliary data. The data storage uses a compression algorithm to reduce the storage space, and at the same time designs a dynamic downsampling strategy based on a time window, that is, the recent data maintains the original sampling rate, and the earlier data is appropriately downsampled. For example, the data in the most recent 24 hours maintains the original frequency of once every 5 minutes, the data 1-7 days ago is reduced to once every 15 minutes, and the data 7-30 days ago is reduced to once every hour, which not only ensures the fineness of the data in the critical period but also optimizes the storage efficiency. The data index uses a multi-level index structure. First, it is divided according to the station house area, secondly, it is grouped according to the sensor location, and finally, a B+ tree index is established according to the timestamp to achieve millisecond-level data retrieval performance. Through the above design, the system can quickly extract the historical temperature and humidity data at a specific time period and a specific location, providing convenience for subsequent analysis. In addition, the time series database also realizes data integrity check and interpolation processing, and repairs the possible data missing during the collection process through linear interpolation or spline interpolation to ensure data continuity, and finally forms a complete historical temperature and humidity data set.

[0069] S13: Based on the predicted data of future meteorological changes and the historical temperature and humidity data set, predict the change trend of temperature and humidity to obtain the prediction result of the change trend of temperature and humidity.

[0070] Among them, step S13 further includes:

[0071] S131: Use the LSTM neural network to extract features from the historical temperature and humidity data set to obtain the time series features of the temperature and humidity changes.

[0072] Further, in step S131 of the present invention, an LSTM (Long Short-Term Memory) neural network is used to extract features from the historical temperature and humidity data set. LSTM is a variant of the recurrent neural network, specifically designed to handle and predict long-term dependency problems in time series. In the present invention, the input of the LSTM network is the normalized historical temperature and humidity time series, including the temperature, humidity, and calculated dew point temperature of each monitoring point. The network structure includes an LSTM layer with 128 neurons, a dense layer with 64 neurons, and an output layer. The LSTM layer is responsible for capturing time series features, extracting the temperature and humidity change patterns, periodic features, mutation features, etc. from the historical data. Specifically, the historical data is slid and segmented with a 24-hour time window, sliding forward by 1 hour each time, and the data of the past 24 hours is used to predict the value of the next moment. Through training, the network learns the temperature and humidity change rules.

[0073] S132: Obtain weather forecast information through an external meteorological data API to obtain future meteorological change prediction data.

[0074] In step S132, weather forecast information is obtained through an external meteorological data API. The temperature and humidity changes in the substation building are not only affected by the operating status of internal equipment but also closely related to external meteorological conditions. Therefore, introducing external meteorological data is required to accurately predict the temperature and humidity change trend in the building. In the present invention, the meteorological service API is called to obtain the meteorological forecast data for the next 1-3 days in the area where the substation is located, including elements such as air temperature, humidity, air pressure, precipitation, wind speed, and wind direction. The API interface adopts the RESTful architecture, and structured meteorological data in JSON format is obtained through an HTTP request. The forecast data is automatically updated every 3 hours to obtain the latest meteorological forecast information. The obtained original meteorological data undergoes format conversion and time alignment processing to be consistent with the time stamp of the monitoring data in the substation building, forming a standardized future meteorological change prediction data set for subsequent data fusion.

[0075] S133: Use the multivariate time series analysis method to fuse the time series features with the future meteorological change prediction data to obtain comprehensive prediction input parameters.

[0076] Further, the purpose of step S133 is to combine the features extracted from the historical data inside the station building with the external weather forecast data to form a more comprehensive prediction basis. Specifically, the Dynamic Time Warping (DTW) algorithm is used to analyze the time delay relationship between the internal and external data, and determine the time lag of the impact of external weather changes on the internal environment of the station building. According to the calculated DTW distance matrix, a time series correlation model between external meteorological variables and internal temperature and humidity parameters is established to quantitatively analyze the influence coefficients of external factors such as temperature and humidity on the corresponding parameters inside the station building. At the same time, the distribution load data is introduced as an additional feature to establish a multi-dimensional feature space. The feature space is dimensionally reduced through principal component analysis (PCA) to remove redundant features and retain the main information. Finally, the processed historical feature vectors and the future meteorological prediction data aligned with the time axis are combined according to the determined fusion rule to form the comprehensive prediction input parameters for prediction. The fusion rule adopts the weighted average method, and the contribution degrees of different features are allocated according to the influence weights of various factors in the historical data. The weights are optimized by the gradient descent method.

[0077] S134: Use the deep learning prediction model to learn the comprehensive prediction input parameters to obtain the prediction results of the temperature and humidity change trends.

[0078] Further, in step S134, the deep learning prediction model is used to learn the comprehensive prediction input parameters, and finally the prediction results of the temperature and humidity change trends are obtained. This step uses the Sequence-to-Sequence (Seq2Seq) prediction model, which consists of an encoder-decoder architecture and is specifically used to handle time series prediction problems. The encoder part uses a bidirectional LSTM network, which can consider the context information of the past and the future at the same time; the decoder part uses an LSTM network with an attention mechanism, which can allocate more attention to the important parts in the input sequence. The model input is the comprehensive prediction input parameters generated in step S133, and the output is the temperature and humidity prediction sequences of each monitoring point inside the station building in the next 24 hours. The model training uses the historical data set for supervised learning, uses the mean squared error (MSE) as the loss function, and updates the parameters through the Adam optimizer. To enhance the generalization ability of the model, dropout regularization and early stopping strategies are introduced during the training process to prevent overfitting. After the model training is completed, the prediction accuracy is verified through the test set. The average absolute error of temperature prediction is controlled within 0.5 °C, and the average absolute error of humidity prediction is controlled within 3%. The final output includes the temperature and humidity prediction values of each monitoring point in the next 24 hours and their 95% confidence intervals, forming the prediction results of the temperature and humidity change trends.

[0079] S14: Analyze the predicted results of the temperature and humidity change trend using the condensation risk assessment algorithm to obtain the dynamic identification information of the areas prone to condensation in the station building, and obtain a complete dynamic temperature and humidity change model.

[0080] In step S14, the condensation risk assessment algorithm is used to analyze the predicted results of the temperature and humidity change trend to obtain the dynamic identification information of the areas prone to condensation in the station building, and a complete dynamic temperature and humidity change model is constructed. The condensation risk assessment algorithm is based on the dew point temperature theory. By calculating the difference (temperature difference) between the surface temperature and the air dew point temperature at each monitoring point, the condensation risk is evaluated. When the surface temperature is lower than or close to the dew point temperature, condensation is likely to occur on the surface. The algorithm first calculates the change curve of the dew point temperature for the next 24 hours based on the predicted temperature and humidity data, and then compares it with the predicted surface temperature curve to calculate the minimum value of the temperature difference and the time when it appears. According to the magnitude of the temperature difference, the risk level is divided into four levels: safe (temperature difference > 5°C), attention (2°C < temperature difference ≤ 5°C), warning (0°C < temperature difference ≤ 2°C), and danger (temperature difference ≤ 0°C). For each monitoring point, the algorithm generates a time series diagram of the risk level for the next 24 hours and marks the peak risk period. Through the spatial interpolation algorithm, the risk assessment results of discrete monitoring points are extended to the entire station building space to generate a three-dimensional risk distribution heat map, visually showing the areas prone to condensation and their risk change trends. Finally, based on the risk analysis results and historical condensation event records, a risk prediction model is established using a machine learning classification algorithm (such as random forest) to further improve the accuracy of risk identification. These analysis results together constitute a complete dynamic temperature and humidity change model, including core elements such as the spatio-temporal distribution information of temperature and humidity, change trend prediction, and condensation risk assessment.

[0081] In a specific embodiment taking a certain power distribution station building as an example, the area of the station building is about 40 square meters, which contains 6 groups of high-voltage cable joints, 4 medium-voltage switch cabinets and 2 distribution transformers. First, install temperature and humidity sensors at 20 key positions in the station building and collect data every 5 minutes. Secondly, store the collected data in a time series database. After 30 days of accumulation, a historical temperature and humidity dataset containing 17,280 records (20 points × 12 times / hour × 24 hours × 3 days) is formed. Subsequently, apply the LSTM network in step S131 to extract features from this dataset. During the network training process, after 200 rounds of iteration, the Loss value drops from the initial 0.025 to 0.006, successfully capturing the daily variation law of temperature and humidity (high temperature and low humidity during the day, low temperature and high humidity at night) and the influence mode of equipment load changes on the environment. Obtain the weather forecast for the next 48 hours in this area through step S132. The forecast shows that a cold air mass will pass through, and the external temperature will drop by 8°C within 12 hours, and the relative humidity will increase by 20%. Step S133 fuses the extracted time series features with the weather forecast data. Through DTW algorithm analysis, it is determined that the time lag of the influence of external meteorological changes on the temperature in the station building is about 3 hours, and the time lag of the influence on humidity is about 2 hours. The Seq2Seq model in step S134 predicts the temperature and humidity changes at each point in the station building for the next 24 hours based on the fused data. The prediction results show that under the influence of the cold air, the surface temperature in the cable joint area will drop to 12°C between 2 am and 6 am the next day, while the air humidity in this area will rise to 85% during the same period, resulting in a dew point temperature of about 9.5°C. Finally, through the calculation of the condensation risk assessment algorithm, it is obtained that the minimum difference between the surface temperature and the dew point temperature in the cable joint area is 2.5°C, which appears at 4 am, and the risk level is "Attention", while the minimum surface temperature difference of the distribution cabinet near the outer wall is only 1.3°C, and the risk level is "Warning". The risk distribution heat map generated by spatial interpolation clearly shows that the area near the outer wall in the northeast corner of the station building is the area with the highest condensation risk and needs key protection. The obtained complete dynamic temperature and humidity change model provides an accurate guiding basis for subsequent anti-condensation measures.

[0082] S2: Establish a phase change material anti-condensation unit for adaptive thermal regulation according to the dynamic temperature and humidity change model and the station building environment parameter data.

[0083] Among them, step S2 further includes:

[0084] S21: Select a basic phase change material suitable for the temperature range of the station building according to the dynamic temperature and humidity change model and the station building environment parameter data.

[0085] Furthermore, a phase change material (PCM) is a functional material that can absorb or release a large amount of latent heat within a specific temperature range, and realizes the storage and release of heat through the phase change process. The key to selecting the basic phase change material in step S21 of the present invention lies in determining its phase change temperature, which should match the environmental characteristics of the substation building. Specifically, first, the temperature fluctuation range data of each area in the building are extracted from the dynamic temperature and humidity change model, and the annual minimum temperature, maximum temperature, and average temperature are calculated. Then, the surface temperature and dew point temperature data of the areas prone to condensation in the building are extracted, and the difference distribution between the two is calculated to determine the temperature adjustment range required for anti-condensation. Next, through the analysis of the condensation occurrence frequency, a temperature-condensation risk correlation model is established to determine the optimal phase change temperature range. In addition to the phase change temperature, the selection criteria also consider thermophysical parameters such as latent heat value, density, specific heat capacity, and thermal conductivity. By establishing a material performance-environmental requirement matching degree scoring model, the candidate materials are comprehensively scored, and the most suitable basic phase change material is selected. The scoring model uses the weighted summation method, and the weight distribution during scoring is based on the importance of the indicators. Specifically, in this embodiment, the weight of the phase change temperature matching degree is the highest, accounting for 40%, the latent heat value accounts for 25%, and the other indicators account for 35%. Based on the above data analysis, the present invention selects an organic phase change material with a phase change temperature between 15°C and 30°C as the basic material, and finally selects a fatty acid (palmitic acid) compound as the basic phase change material.

[0086] S22: Add a nano-level modifier to the basic phase change material to optimize its performance and obtain a modified phase change material.

[0087] Specifically, in step S22, first add 5-10% of nano-carbon materials to the basic phase change material to obtain a thermally optimized phase change material; then add 3-5% of a cross-linking agent to the thermally optimized phase change material to obtain a structurally stable phase change material; finally, add 1-3% of a flame retardant to the structurally stable phase change material to obtain a modified phase change material.

[0088] Furthermore, the carbon nanomaterials have extremely high thermal conductivity. When added to the phase change material, they can significantly improve its thermal conductivity. A crosslinking agent refers to a compound that can form chemical bonds between molecules and connect molecular chains into a three-dimensional network structure. Commonly used crosslinking agents include polyfunctional alcohols, polyfunctional acids and their anhydrides, epoxy resins, etc. The purpose of adding a crosslinking agent to the thermally optimized phase change material is to enhance the shape stability of the material and prevent material loss in the liquid phase change state. A flame retardant refers to an additive that can inhibit or delay the combustion of materials. Commonly used flame retardants include halogen-based flame retardants, phosphorus-based flame retardants, inorganic flame retardants, etc. Considering the special environment of the substation building, the present invention selects an environment-friendly flame retardant with low smoke, halogen-free, and low toxicity. In this embodiment, a nitrogen-phosphorus synergistic flame retardant is selected to minimize the impact on the phase change performance while ensuring the flame retardant effect.

[0089] S23: Perform microcapsule encapsulation with a multi-layer structure design on the modified phase change material to obtain a phase change material anti-condensation unit.

[0090] In step S23, microcapsule encapsulation with a multi-layer structure design is performed on the modified phase change material to obtain a phase change material anti-condensation unit. Microcapsule encapsulation refers to a technology that wraps the phase change material in tiny capsules to form a core-shell structure, thereby preventing the leakage of liquid phase change materials and improving the stability and service life of the material. The encapsulation process uses the interfacial polymerization method. First, the modified phase change material is dispersed in the continuous phase to form an emulsion, and then a polymerization reaction occurs at the interface between the dispersed phase and the continuous phase to form a polymer shell layer that wraps the phase change material. The selected shell material needs to meet the characteristics of high strength, durability, good sealing performance, and thermal conductivity. The shell material selected in the present invention is polyacrylate, etc.

[0091] The multi-layer structure design mentioned above means that the microcapsule adopts a multi-shell layer structure, which from the inside to the outside is as follows: the inner layer in direct contact with the phase change material uses a high-density polyethylene film to provide basic sealing performance; the middle layer uses an aluminum foil material to improve the heat conduction efficiency and barrier property; the outer layer uses a moisture-proof and flame-retardant engineering plastic to provide mechanical strength and protection function. The multi-layer structure is realized through a layer-by-layer assembly process. The inner layer is formed by the emulsion-solvent evaporation method, the middle layer is prepared by the vacuum aluminizing process, and the outer layer is completed by the dip coating or spraying process.

[0092] S3: According to the information of the condensation-prone area identified in the dynamic temperature and humidity change model and the operation status data of the ventilation system, arrange the phase change material anti-condensation unit at the anti-condensation positions in the substation building to obtain an anti-condensation network, and monitor the working status of the anti-condensation network in real time to obtain anti-condensation effect data.

[0093] In step S3, the step of arranging the phase change material anti-condensation unit at the anti-condensation positions in the substation building to obtain an anti-condensation network according to the information of the condensation-prone area identified in the dynamic temperature and humidity change model and the operation status data of the ventilation system further includes:

[0094] S31: performing data mining on the temperature and humidity distribution data in the dynamic temperature and humidity change model, identifying areas prone to condensation, and obtaining a positioning map of areas prone to condensation.

[0095] Furthermore, in step S31, the condensation-prone area is first identified to obtain a condensation-prone area location map. In this step, the three-dimensional information of each monitoring point and the corresponding temperature, humidity and calculated dew point temperature data are first extracted from the dynamic temperature and humidity change model to form a multidimensional data matrix; secondly, the difference (temperature difference) between the surface temperature and the dew point temperature is calculated, expressed as ΔT. When ΔT is close to or less than zero, it indicates that the condensation risk in the area is high; thirdly, the K-means clustering algorithm is applied to analyze the temperature difference data. The core idea of ​​the algorithm is to divide n data points into k clusters, and each data point belongs to the cluster represented by the cluster center closest to it. The specific calculation process is: randomly select k initial cluster centers; calculate the distance from each data point to each cluster center and assign it to the nearest cluster; recalculate the center point of each cluster; repeat the above steps until the cluster center no longer changes significantly. Through cluster analysis, the area in the station house is divided into different categories according to the condensation risk characteristics.

[0096] After completing the above analysis, the present invention uses spatial interpolation technology, specifically the Kriging interpolation method, to expand the risk assessment results of discrete monitoring points to the entire station space, and finally generates a complete condensation risk distribution heat map in the station, that is, a condensation-prone area positioning map, which can indicate the condensation risk levels of different areas and intuitively display the spatial distribution of condensation-prone areas.

[0097] S32: Use computational fluid dynamics simulation to process the operating status data of the ventilation system, generate the airflow path and flow velocity distribution model in the station building, and obtain the air circulation dead corner identification results.

[0098] Step S32 uses computational fluid dynamics (CFD) simulation to process the operating status data of the ventilation system, generate the airflow path and velocity distribution model in the station house, and obtain the air circulation dead corner identification result. Specifically, in this step, a three-dimensional geometric model of the power distribution station is first established, including information such as the station house structure, equipment layout, and vent location. Then, a computational grid is generated based on the geometric model, using a structured or unstructured grid, and the grid density is encrypted in areas where the flow changes drastically. Then, boundary conditions and initial conditions are set. The boundary conditions include inlet wind speed, outlet pressure, wall no slip, etc. The initial conditions are the initial temperature field and velocity field.

[0099] Through CFD simulation, the three-dimensional air flow field in the station building can be obtained, including the velocity vector field, pressure field, and temperature field. Then, based on the simulation results, the air flow path and velocity distribution are calculated. To identify the dead zones of air circulation, a velocity threshold is defined. In this embodiment, 20% of the average velocity in the station building is taken. When the velocity in a region is lower than the threshold and the flow direction changes frequently, it is determined as a dead zone of air circulation. The mathematical expression is as follows:

[0100]

[0101] where D represents the set of dead zones, (x, y, z) are the coordinates of a spatial point, and v(x, y, z) is the velocity of the spatial point. is the velocity divergence, which represents the expansion or compression rate of the fluid. Being close to zero means that the fluid volume hardly changes, corresponding to a flow stagnation state. The dead zones of air circulation identified by the above method are used to generate a dead zone distribution map, which indicates the areas in the station building where the air flow is blocked. It is difficult for moisture to be discharged from these areas, which are potential high-risk areas for condensation.

[0102] S33: According to the risk rating method, comprehensively superimpose and analyze the condensation-prone area location map and the air circulation dead zone identification result to determine the high-risk area, medium-risk area, and low-risk area, and obtain a hierarchical anti-condensation layout plan.

[0103] In step S33, the condensation-prone area location map and the air circulation dead zone identification result are comprehensively superimposed and analyzed according to the risk rating method to determine the high-risk area, medium-risk area, and low-risk area, and obtain a hierarchical anti-condensation layout plan. Risk rating refers to the process of classifying risks according to the likelihood of risk occurrence and the severity of consequences. In this step, the risk matrix method is used for risk rating. This method locates the risk factors in the matrix according to the occurrence probability and impact degree to determine the risk level.

[0104] S34: According to the hierarchical anti-condensation layout plan, deploy the phase change material anti-condensation unit at the anti-condensation positions in the substation building to obtain an anti-condensation network.

[0105] Furthermore, based on the risk zoning, formulate the layout strategy of the phase change material anti-condensation unit. In the high-risk area, a high-density layout is adopted, with a coverage rate of more than 90%; in the medium-risk area, a medium-density layout is adopted, with a coverage rate of 50 - 70%; in the low-risk area, a low-density layout is adopted, with a coverage rate of about 30%. At the same time, according to the characteristics of different regions, select appropriate forms of anti-condensation units: use plate-shaped units on the wall, flexible wrapped units at the cable joints, and box-shaped units at the bottom of the distribution cabinet, etc., to form a comprehensive and reasonable hierarchical anti-condensation layout plan. Finally, according to the hierarchical anti-condensation layout plan, deploy the phase change material anti-condensation unit at the anti-condensation positions in the substation building.

[0106] During the installation process, it is necessary to ensure good thermal contact between the anti-condensation unit and the protected surface, and fill the contact gap with thermal conductive silicone grease if necessary. For areas that cannot be directly contacted, such as the internal space of the equipment, design a heat conduction channel to conduct the cooling effect of the anti-condensation unit to the target area. After the installation is completed, record and mark the position of the anti-condensation unit for subsequent monitoring and maintenance. Through the above installation steps, an anti-condensation network covering the key areas of the substation building is formed. This network can automatically absorb or release heat according to temperature changes, actively adjust the local environment, and prevent condensation from occurring.

[0107] Among them, the step of real-time monitoring of the working state of the anti-condensation network in step S3 specifically includes:

[0108] Monitor the surface temperature of the phase change material anti-condensation unit through a micro temperature sensor to obtain the working temperature of the anti-condensation unit; use infrared thermal imaging technology to scan the temperature distribution of the phase change material anti-condensation unit to obtain heat diffusion effect data; measure the heat transfer between the phase change material anti-condensation unit and the environment through a heat flux sensor to obtain energy exchange information during the phase change process; use a surface humidity detector to detect the condensation situation on the protected surface to obtain anti-condensation surface state data.

[0109] The micro temperature sensor is used to monitor the surface temperature of the phase change material anti-condensation unit to obtain the working temperature of the anti-condensation unit. Select a thermistor or thermocouple temperature sensor with a size less than 5mm×5mm and install it at key positions on the surface of the anti-condensation unit. The number and position of the sensors are determined according to the size and importance of the anti-condensation unit. Usually, 2-3 sensors are installed on the anti-condensation unit in each high-risk area, 1-2 in the medium-risk area, and appropriately reduced in the low-risk area. The sensor acquisition frequency is set to once every 5 minutes. When a rapid temperature change is detected (change rate exceeds 0.5℃ / min), the acquisition frequency is automatically increased to once every 1 minute. The temperature data is sent to the central monitoring system through a wireless transmission module to record the temperature change curve of the anti-condensation unit in real time. According to the phase change temperature characteristics of the phase change material, judge whether the unit is in the phase change state: if the unit temperature remains near the phase change temperature (±0.5℃) for a period of time, it indicates that the unit is absorbing or releasing latent heat and is in an active working state.

[0110] Specifically, in the present invention, an infrared thermal imager is used to scan the anti-condensation network regularly. The resolution of the thermal imager is not less than 320×240 pixels, the temperature sensitivity is better than 0.05℃, and the scanning frequency is once per hour, increasing to once every 30 minutes when the ambient temperature changes rapidly. After the thermal image data is radiometrically corrected and geometrically corrected, it is converted into a temperature distribution map. Analyze the characteristics of the temperature distribution map through an image processing algorithm, and finally compare the temperature distribution maps of two consecutive scans to calculate the temperature change rate field and evaluate the dynamic response performance of the anti-condensation unit.

[0111] The heat flux sensor is used to measure the heat transfer between the phase change material anti-condensation unit and the environment, and obtain the energy exchange information during the phase change process. The heat flux sensor is a device for measuring the heat flux density (heat flux rate per unit area), and the common types include thermoelectric type and thermal gradient type. Heat flux sensors are respectively installed on the inner surface (close to the protected equipment) and the outer surface (facing the environment) of the anti-condensation unit. The size of the sensor is 10mm×10mm, and the sensitivity is better than 0.01W / (m 2 ·K). The data acquisition frequency of the sensor is synchronized with that of the temperature sensor. By measuring the obtained heat flux density value and combining it with the sensor area, the heat flux rate is calculated. The difference in the heat flux rates between the inner and outer surfaces is the heat stored or released by the anti-condensation unit. A positive value indicates that the unit is absorbing heat (during the stage of rising ambient temperature), and a negative value indicates that the unit is releasing heat (during the stage of falling ambient temperature). Finally, the total amount of heat exchange in a complete cycle is calculated by integration to evaluate the energy regulation ability of the anti-condensation unit.

[0112] The surface humidity detector is a sensing device that can directly detect the surface condensation state. In the present invention, a small surface humidity detector is installed on the surface of the equipment prone to condensation. The size of the detector is less than 10mm×10mm to reduce the interference with the operation of the equipment. The output of the detector is a continuous value signal (surface humidity percentage), and the acquisition frequency is set to once every 10 minutes. When a humidity change trend is detected, the frequency is automatically increased to once every 2 minutes. Through the surface humidity data, the anti-condensation effect is directly verified, and the areas with insufficient anti-condensation are found.

[0113] In a specific embodiment, the area of the substation building is 60 square meters, and there are 8 sets of high-voltage cable joints, 6 medium-voltage switchgear cabinets and 3 distribution transformers inside. First, through data mining of the dynamic temperature and humidity change model, three main areas prone to condensation are identified: the northeast corner near the outer wall, where the minimum temperature difference is 0.8 °C, and the occurrence frequency is from 3 to 5 o'clock in the early morning every day; the cable inlet and outlet, where the minimum temperature difference is 1.5 °C, and the occurrence frequency is from 4 to 6 o'clock in the early morning every day and on rainy days; the bottom area of the distribution cabinet, where the minimum temperature difference is 2.2 °C, and the occurrence frequency is irregular, mainly related to the change of equipment load. The location map of the condensation-prone area generated by Kriging interpolation shows that about 15% of the area of the substation building belongs to the high condensation risk area. Then, under the ventilation condition with a CFD simulated wind speed of 0.5 m / s in step S32, the air flow situation in the substation building is simulated. The simulation results show that an obvious air flow dead angle is formed in the northeast corner, with a flow velocity lower than 0.1 m / s; there is also a problem of poor air circulation in the narrow space between the back of the equipment and the distribution cabinet, with an average flow velocity of 0.15 m / s; while the air flow in the central passage of the substation building is smooth, with a flow velocity reaching 0.4 - 0.5 m / s. Subsequently, the condensation risk and ventilation risk are comprehensively scored, and the weights are set to 0.6 and 0.4 respectively. The calculation results show that the comprehensive risk score of the northeast corner area is 8.5 points, belonging to the high-risk area; the score at the cable inlet and outlet is 7.2 points, also belonging to the high-risk area; the score at the bottom of the distribution cabinet is 5.8 points, belonging to the medium-risk area; the score of the central passage of the substation building is 2.1 points, belonging to the low-risk area. According to this classification result, an anti-condensation layout plan is formulated: the total area of the high-risk area is 12 square meters, and 24 plate-shaped anti-condensation units of 500 mm × 500 mm are arranged, with a coverage rate of 95%; the total area of the medium-risk area is 20 square meters, and 28 anti-condensation units of the same specification are arranged, with a coverage rate of 70%; the total area of the low-risk area is 28 square meters, and 14 anti-condensation units of the same specification are arranged, with a coverage rate of 30%. In step S34, the anti-condensation units are installed according to the plan. For the northeast corner wall, light steel keels are used to fix the plate-shaped units; for the cable joints, flexible wrapping units are used to closely adhere to the joints; for the bottom of the distribution cabinet, box-shaped units are placed. After installation, 60 micro temperature sensors, 2 infrared thermal imagers, 24 heat flux sensors and 30 surface humidity detectors are arranged to form an all-round monitoring network. The operation data shows that during a cold air intrusion process, when the ambient temperature drops from 25 °C to 12 °C, the surface temperature of the anti-condensation unit drops to 18.2 °C and then stabilizes for about 3 hours, proving that the phase change material is releasing latent heat; the peak heat release power measured by the heat flux sensor is 45 W per square meter; the surface humidity detector does not detect any condensation phenomenon throughout the process, verifying the effectiveness of the anti-condensation network.

[0114] S4: Based on the dynamic temperature and humidity change model and the anti-condensation effect data, establish an active anti-condensation guarantee mechanism based on PTC heating elements.

[0115] Step S4 mainly establishes an active anti-condensation guarantee mechanism based on the PTC heating element as a supplement to the passive anti-condensation network to ensure effective prevention of condensation even under extreme conditions. The PTC (Positive Temperature Coefficient) heating element is a positive temperature coefficient thermistor element. Its characteristic that the resistance value increases with the increase of temperature enables it to have a self-limiting temperature function, which can prevent overheating and achieve precise temperature control, and is particularly suitable for anti-condensation and dehumidification occasions.

[0116] Among them, S4 further includes:

[0117] S41: Integrate PTC heating elements in high-risk condensation areas according to the dynamic temperature and humidity change model and the anti-condensation effect data to obtain the basic heating element layout.

[0118] In step S41, according to the dynamic temperature and humidity change model and the anti-condensation effect data, PTC heating elements are integrated in high-risk condensation areas to obtain the basic heating element layout. First, key data are extracted from the dynamic temperature and humidity change model, especially the difference between the surface temperature and the dew point temperature (abbreviated as temperature difference) data. The temperature difference is a direct indicator for judging the condensation risk. When the temperature difference is less than or equal to zero, condensation will occur on the surface. The data processing process statistically analyzes the temperature difference data of all monitoring points in the substation building, including the minimum temperature difference value, the frequency of the temperature difference below the threshold, and the time distribution characteristics of the temperature difference. Usually, a temperature difference of 2°C is set as the risk threshold, and values below this are considered to have an obvious condensation risk.

[0119] Calculate the risk index RI for each monitoring point. The risk index is a composite indicator that comprehensively considers the temperature difference value and the duration. In the calculation, the reciprocal of the temperature difference value at each time point is multiplied by the weight coefficient at that time point and then summed. When the temperature difference approaches or is less than zero, the risk index value increases rapidly. Key periods such as the early morning low-temperature period will be given a higher weight to reflect their greater condensation risk. According to the calculated risk index, all areas in the substation building are sorted to determine the area with the highest condensation risk.

[0120] Then, analyze the anti-condensation effect data to evaluate the matching degree between the working state of the existing phase change material anti-condensation unit and the anti-condensation demand. The anti-condensation effect data includes the working temperature of the anti-condensation unit, the heat diffusion effect data, the energy exchange information during the phase change process, and the anti-condensation surface state data. Through the energy exchange data measured by the heat flux sensor, calculate the anti-condensation capacity gap for each area. The calculation method is to perform a time integral on the difference between the heat flux required to maintain the surface temperature above the dew point temperature and the actual heat flux provided by the phase change material during the period of insufficient anti-condensation to obtain the energy gap value, with the unit of joule.

[0121] Based on the risk index and energy gap data, determine the areas where PTC heating elements need to be installed. Priority should be given to areas that meet the following conditions: areas with a risk index in the top 30% within the substation building, obvious energy gaps, high equipment importance, or serious condensation consequences. For each selected area, calculate the required power density of the PTC heating element, that is, divide the energy gap by the area of the region and the cumulative time when the gap occurs, and then multiply by a safety factor (usually taken as 1.2 - 1.5) to obtain the required power value per unit area (W / m 2 ²). Select PTC heating elements with appropriate specifications according to the calculation results, considering factors such as rated power, operating voltage, size and shape, protection level, etc.

[0122] Next, the present invention designs the basic heating element layout, and the layout design follows the following principles: matching the heat load distribution, with a higher heating density in high-risk areas; maintaining heating uniformity to avoid local overheating or insufficient heating; avoiding sensitive parts of electrical equipment to reduce electromagnetic interference; facilitating installation and maintenance; optimizing cable layout to reduce the amount of wire used. After the layout design is completed, verify the heating effect through numerical thermal simulation to ensure that the anti-condensation requirements are met. The numerical simulation uses the finite element analysis method to establish a composite heat conduction model including the substrate, phase change material, and PTC element, solve the temperature field distribution, and check for areas with too low temperature or temperature non-uniformity.

[0123] S42: Combine the regional temperature distribution based on thermal imaging technology to optimize the basic heating element layout and obtain an optimized heating element layout.

[0124] In step S42, the basic heating element layout is optimized by combining the regional temperature distribution based on thermal imaging technology to obtain an optimized heating element layout. Thermal imaging technology is a non-contact temperature measurement method that can visualize the temperature distribution on the surface of an object. In this step, an infrared thermal imager is used to scan the substation building equipped with the anti-condensation network to obtain the temperature distribution image under the actual operating conditions. The original data collected by the thermal imager is an infrared radiation intensity matrix, which needs to be converted into an accurate temperature matrix through a series of processes.

[0125] The data processing process first performs geometric correction to eliminate the influence of lens distortion and shooting angle, ensuring that the spatial position in the image is consistent with the actual position. Geometric correction uses the reference point matching method, marks reference points with known coordinates in the thermal image, and corrects the image through a coordinate transformation matrix. Secondly, radiation correction is performed to compensate for the influence of environmental radiation and material emissivity differences. When performing radiation correction, the surface emissivity values of different materials need to be considered: usually 0.1 - 0.3 for metal surfaces and 0.8 - 0.95 for insulating material surfaces.

[0126] Then, the corrected thermal image is analyzed and processed to extract key features. The processing steps include: image filtering, using Gaussian filtering or median filtering to reduce noise; temperature gradient calculation, using Sobel or Prewitt operator to calculate the temperature gradient field; region segmentation, using threshold segmentation or watershed algorithm to segment the image into different temperature zones; feature point extraction, identifying temperature extreme points, rapid change areas and temperature stable areas.

[0127] For thermal images collected at multiple time points, time series analysis is performed, including: calculating the temperature-time curve of each pixel; Fourier analysis to extract the periodic characteristics of temperature changes; trend analysis to identify areas with rising or falling temperature trends; anomaly detection to find areas with abnormal temperature fluctuations. The purpose of time series analysis is to identify dynamic thermal characteristics, distinguish areas with different thermal inertia, and provide a basis for optimizing heating control strategies.

[0128] Compare the thermal imaging analysis results with the basic heating element layout in step S41 to find mismatches. Common mismatches include: hot spots, that is, areas where the temperature in the thermal map is significantly higher than the surrounding area. Such areas may have too many heat sources and the heating elements are arranged too densely; cold spots, that is, areas with continuously low temperatures, where the heating elements are not covered enough; areas with large temperature gradients, where unreasonable element spacing leads to uneven heat distribution; areas with drastic temperature changes, which may require special control strategies.

[0129] Based on the comparative analysis, the basic heating element layout is optimized and adjusted. The adjustment methods include: reducing the number of heating elements or lowering the power density in the hot spot area; increasing the element density or selecting higher power elements in the cold spot area; adjusting the element spacing in the area with large temperature gradient to achieve a more uniform heat distribution; and using special layouts in areas with drastic temperature changes, such as gradient layout or layered layout. The optimization process adopts an iterative method, and the effect is verified by thermal simulation after each adjustment until the best layout is achieved.

[0130] The optimized layout not only considers the spatial distribution, but also the control partition. Areas with similar thermal characteristics are divided into the same control partition, and each partition is equipped with an independent temperature sensor and control loop to achieve refined control. The control partition division is based on cluster analysis, using K-means or hierarchical clustering algorithms to group areas with similar temperature feature vectors into one category. The temperature feature vector contains multi-dimensional features such as average temperature, temperature fluctuation range, heating rate, and cooling rate.

[0131] S43: Power control is performed on the PTC heating element in the optimized heating element layout to form an active anti-condensation protection mechanism based on the PTC heating element.

[0132] Step S43 performs power control on the PTC heating elements in the optimized heating element layout to form an active anti-condensation guarantee mechanism based on the PTC heating elements. Power control is the key to ensuring the efficient and precise operation of the heating system, involving control strategy design, regulation method selection, and safety protection mechanism establishment.

[0133] First, clarify the control objective: maintain the temperature of the protected surface higher than the dew point temperature by a certain margin (usually 2 - 3 °C), while minimizing energy consumption. This can be expressed as a mathematical optimization problem, that is, minimizing the time integral of the power function under the constraint that the surface temperature is always higher than the dew point temperature plus the safety margin.

[0134] The control strategy adopts a hierarchical structure, including three levels: prediction, decision-making, and execution. The prediction layer uses a dynamic temperature and humidity change model to predict the trends of environmental temperature and humidity and surface temperature changes in the future for a period of time (usually 1 - 6 hours). The decision-making layer formulates an optimal control plan based on the prediction results and the current state, including start / stop timing, power curve, and control mode, etc. The execution layer is responsible for implementing the control plan and adjusting the heating power in real time to respond to environmental changes.

[0135] The specific control algorithm adopts the Model Predictive Control (MPC) framework. MPC is an advanced control strategy that can handle multivariable systems, meet constraint conditions, and optimize control objectives. The core idea of MPC is that in each control cycle, use the system model to predict the system response in the future for a period of time, solve the optimal control sequence, but only execute the first control action in the sequence, and then slide the prediction window and repeat the above process. The control objective function includes two weight terms: temperature tracking accuracy and energy consumption, and the anti-condensation effect and energy consumption are balanced by adjusting the weight coefficients.

[0136] To achieve precise power control, PWM (Pulse Width Modulation) technology is adopted. PWM controls the average power output by adjusting the on / off time ratio (duty cycle) of the voltage. The basic parameters of PWM control include the carrier frequency and duty cycle resolution. The carrier frequency is selected in the range of 20 - 40 kHz to avoid the audible range of the human ear and reduce electromagnetic interference; the duty cycle resolution is set to 10 bits (0.1%) to ensure the accuracy of power regulation. The PWM control signal is output to the PTC heating element through a solid-state relay or MOSFET drive circuit.

[0137] Based on power control, a multi-level safety protection mechanism is established: over-temperature protection, when the temperature of the PTC element or the protected surface exceeds the preset safety threshold, the power is automatically reduced or cut off; over-current protection, the working current of the PTC element is monitored in real time through a current sensor, and when an abnormal current is detected, the power is immediately cut off and an alarm is issued; leakage protection, a leakage protector is configured, and when the system grounding current exceeds the safety value (usually 30 mA), the power supply is cut off within 30 ms; abnormal operation detection, by comparing the actual temperature rise with the theoretical temperature rise, it is judged whether the PTC element is working normally.

[0138] The PTC heating system forms a collaborative working mechanism with the passive anti-condensation network and the ventilation system. The control strategy sets a three-level anti-condensation plan: the first level is ventilation and dehumidification, which is applicable to the situation where the external air humidity is lower than the air humidity in the substation building; the second level is passive temperature regulation by phase change materials, which is applicable to the situation where the temperature fluctuation range is within the working range of the phase change materials; the third level is PTC active heating, which is only activated when the first two levels of measures cannot meet the anti-condensation requirements. The above-mentioned cascade strategy realizes intelligent switching through a control algorithm, and the algorithm decision is based on real-time environmental data and a prediction model, comprehensively considering the anti-condensation effect and energy consumption.

[0139] In a specific embodiment, the area of the substation building is 70 square meters, and there are 10 groups of high-voltage cable joints, 8 medium-voltage switchgear cabinets and 4 distribution transformers inside. In step S41, by analyzing the data of the dynamic temperature and humidity change model, it is found that the minimum temperature difference in the cable joint area has dropped to 0.6 °C, and the risk exposure time ratio is 25%; the minimum temperature difference in the bottom area of the switchgear cabinet is 1.2 °C, and the risk exposure time ratio is 18%; while the temperature difference in the area near the outer wall is frequently lower than 2 °C, and the risk exposure time ratio is as high as 32%. These data are obtained through the temperature and humidity sensor data collected every 5 minutes and through continuous statistical analysis for 30 days. By analyzing the anti-condensation effect data and calculating the energy gap, it is found that the energy gap in the cable joint area reaches 35 watt-hours per square meter under extreme weather conditions, 22 watt-hours per square meter at the bottom of the switchgear cabinet, and 42 watt-hours per square meter in the area near the outer wall. These energy gap data are the difference between the actual heat flow measured by the heat flow sensor and the theoretically required heat flow, and are integrated within the time period when the temperature difference is lower than 2 °C.

[0140] Calculate the power required for the PTC heating element based on the above data: 200 W / m² is required for the cable joint area, 150 W / m² is required for the bottom of the power distribution cabinet, and 250 W / m² is required for the exterior wall area. Select PTC heating sheets with a rated power of 50 W and a size of 100 mm × 200 mm. Design the initial layout according to the area shape. A total of 48 PTC heating elements are arranged, covering a total area of about 15 m². In step S42, through thermal imaging analysis, it is found that there are three uneven heat distributions in the initial layout: there is a cold spot of about 2°C at the exterior wall corner; a heat bridge is formed between two adjacent cable joints, and the temperature is 3.5°C higher than the surrounding area; the temperature gradient in the bottom area of the power distribution cabinet is large, with a maximum difference of 4°C. These thermal imaging data are obtained by an infrared thermal imager with a resolution of 640 × 480 pixels at three time points: 6 am, 12 noon, and 10 pm, and are the results after geometric correction and radiation correction processing.

[0141] For the problems found, adjust the layout: add 2 heating elements at the exterior wall corner; reduce the number of elements in the heat bridge area from the original 4 to 2, and adjust them to be arranged at intervals; adopt a variable density layout for the bottom of the power distribution cabinet, increase the element density in the cold area, and adjust the original evenly distributed 10 elements to 8 in the cold area and 2 in the hot area. The optimized layout uses a total of 50 PTC heating elements. Through verification by the finite element thermal analysis model, the temperature uniformity is significantly improved. The simulation results show that the maximum temperature difference is reduced from the original 4°C to about 1.5°C. In step S43, design a three-zone independent control system, configure 2 temperature sensors and 2 humidity sensors in each zone, adopt an improved PID control algorithm, and obtain the optimal parameter combination through genetic algorithm optimization. The control system uses PWM modulation technology with a carrier frequency of 25 kHz to achieve power regulation with an accuracy of 0.1%.

[0142] In the actual operation test, under the extreme working condition that the outdoor temperature drops suddenly from 15°C to -5°C, the PTC system successfully maintains the surface temperature of the key area above the dew point temperature by 2.5°C, there is no condensation throughout the process, and the average power consumption is 3.2 kWh / day, and it only starts between 2 and 6 am when the temperature is the lowest. The test results verify the effectiveness of the active anti-condensation protection mechanism and the design goal of energy efficiency optimization, providing a reliable guarantee for the safe operation of the fully cabled indoor substation building.

[0143] S5: Based on the data flow information of the dynamic temperature and humidity change model, the ventilation system, the anti-condensation network, and the active anti-condensation protection mechanism, establish a comprehensive control system through a multi-objective optimization algorithm, and dehumidify and prevent condensation in the substation building through the comprehensive control system.

[0144] Among them, step S5 further includes:

[0145] S51: Integrate the data stream information of the dynamic temperature and humidity change model, the ventilation system, the anti-condensation network, and the active anti-condensation guarantee mechanism through an industrial controller to obtain a system-level control platform.

[0146] In step S51, integrate the data stream information of the dynamic temperature and humidity change model, the ventilation system, the anti-condensation network, and the active anti-condensation guarantee mechanism through an industrial controller to obtain a system-level control platform. The industrial controller has the characteristics of strong anti-interference ability, high reliability, and good real-time performance. In the present invention, a Siemens S7-1500 series PLC is selected as the core controller, and with the cooperation of an industrial Ethernet communication network and a SCADA (Supervisory Control and Data Acquisition) system, a system-level control platform is constructed. Through the data stream integration process, a unified system-level control platform is formed, providing a data basis and an execution environment for the next multi-objective optimal control.

[0147] S52: Set optimization objectives including minimizing energy consumption, maximizing dehumidification efficiency, and minimizing temperature uniformity, and construct an objective function. Obtain the optimal control strategy through a multi-objective optimization algorithm.

[0148] Among them, the expression of the optimization objective of the multi-objective optimization algorithm in step S52 is:

[0149]

[0150] Among them, F(x) is the optimization objective, t0 is the starting point of the time range, t f is the end point of the time range, λ is the exponential decay coefficient, V(t) is the time series of the ventilation system wind speed adjustment coefficient, Q(t) is the time series of the auxiliary electric heating system power adjustment coefficient, x1 is the decision variable of the ventilation system wind speed adjustment coefficient, x3 is the decision variable of the heating system power adjustment coefficient, H(t) is the humidity time series, P(t) is the temperature distribution time series of the anti-condensation network, x2 is the decision variable of the phase change material layout density, T(t) is the temperature time series, T avg is the average temperature value.

[0151] Furthermore, the objective function includes an energy consumption minimization objective function, a dehumidification efficiency maximization objective function, and a temperature uniformity minimization objective function. For the expression of the objective function, the control system needs to simultaneously satisfy the constraint conditions:

[0152]

[0153] Among them, G(x) is the set of constraint conditions, T max is the temperature upper limit, H min is the humidity lower limit, P max is the energy consumption upper limit.

[0154] The present invention uses the NSGA-II algorithm to solve the above multi-objective optimization problem. NSGA-II is an efficient multi-objective optimization algorithm that can generate a well-distributed set of Pareto optimal solutions in a single run and is suitable for dealing with complex optimization problems with multiple objectives and multiple constraints. The finally output control strategies include: the control timing sequence of the ventilation system (the time function of the fan speed and valve opening), the control timing sequence of the PTC heating system (the time function of the heating power in each area), and the distribution density map of the phase change material arrangement. These control strategies are input as instructions for the next control execution.

[0155] S53: Control the integrated control system through the optimal control strategy to dehumidify and prevent condensation in the substation building.

[0156] In a specific embodiment, the area of the substation building is 80 square meters, and there are 12 groups of high-voltage cable joints, 10 medium-voltage switchgears, and 5 distribution transformers inside. First, based on step S51, use Siemens S7-1515PLC as the central controller, cooperate with ET200SP distributed I / O station and TP1200 touch screen to build a system-level control platform. Set 64 data acquisition points, including 32 temperature and humidity acquisition points, 16 heat flow acquisition points, 8 air flow acquisition points, and 8 electrical parameter acquisition points, to form a comprehensive data acquisition network. The data acquisition period is set as follows: temperature and humidity data once every 5 minutes, fan speed and valve opening once every 1 minute, and PTC heating power once every 30 seconds. The collected original data is stored in the time series database after preprocessing, forming about 28,800 data records per day. Through data analysis, establish a temperature and humidity distribution model in the substation building, and identify three typical condensation risk areas: the cable joint area (minimum temperature difference 0.8°C), the bottom area of the distribution cabinet (minimum temperature difference 1.5°C), and the area near the outer wall (minimum temperature difference 0.6°C).

[0157] Secondly, set the optimization objective weights as follows: minimum energy consumption w1 = 0.4, maximum dehumidification efficiency w2 = 0.35, and minimum temperature uniformity w3 = 0.25. Through the NSGA-II algorithm, set the population size to 100, the maximum number of iterations to 500, the crossover probability to 0.8, and the mutation probability to 0.1, and run the optimization calculation. After about 300 iterations, the algorithm converges and 20 Pareto optimal solutions are obtained. These solutions have different emphases on the three objectives. For example, solution A is the best in terms of energy consumption (saving 25% energy consumption) but has poor temperature uniformity; solution B is the best in terms of dehumidification efficiency but has slightly higher energy consumption; solution C makes a balanced trade-off among the three objectives. Considering the humid climate environment where the substation building is located, select solution B that pays more attention to dehumidification efficiency as the final control strategy.

[0158] Subsequently, the optimized control strategy will be converted into device control instructions. For the ventilation system, the calculated optimal operating speed of the fan is 1200 rpm, which is 75% of the rated speed; the opening degrees of the inlet valve and the exhaust valve are 60% and 80% respectively. For the PTC heating system, the heating powers of the three risk areas are determined as follows: 180 W / m for the cable joint area 2 , 120 W / m for the bottom area of the distribution cabinet 2 , and 220 W / m for the area near the outer wall 2 . Through the PWM modulation technology, the carrier frequency is set to 25 kHz, and the PWM duty cycle of each area is calculated according to the power demand. During the execution of the supervision process, the temperature and humidity changes and the device response in the station house are monitored in real time to ensure that the system operates according to the optimized strategy.

[0159] In a complete day-night operation cycle, the system automatically adjusts the control strategy according to the external environment changes: when the external humidity is low during the day, the ventilation volume is increased to make full use of natural ventilation for dehumidification; when the temperature drops in the evening, the ventilation volume is gradually reduced to increase the temperature regulation effect of the phase change material; when the temperature is the lowest in the early morning, PTC heating is started in the high-risk areas to ensure that the surface temperature is always higher than the dew point temperature. Through the above intelligent coordinated control, the temperature in the station house is maintained within the range of 18 - 25 °C, the relative humidity is controlled between 50 - 65%, no condensation occurs, and at the same time, the average daily energy consumption is only 4.5 kWh, saving 65% of energy compared with the traditional full-time heating method. This example verifies the effectiveness and efficiency of the comprehensive control strategy based on multi-objective optimization of the present invention in dehumidification and anti-condensation of indoor fully-cabled distribution station houses.

[0160] As Figure 2 shown, the present invention also provides a dehumidification and anti-condensation system for an indoor fully-cabled distribution station house, including:

[0161] A prediction module 100: used to collect the temperature and humidity data in the distribution station house, obtain the station house environment parameter data, and predict the temperature and humidity change trend in the station house based on a deep learning model of time series, and establish a dynamic temperature and humidity change model;

[0162] A first construction module 200: used to establish a phase change material anti-condensation unit for adaptive heat regulation according to the dynamic temperature and humidity change model and the station house environment parameter data;

[0163] A monitoring module 300: used to perform real-time monitoring on the anti-condensation network at the anti-condensation positions arranged in the distribution station house to obtain anti-condensation effect data;

[0164] A second construction module 400: used to establish an active anti-condensation guarantee mechanism based on PTC heating elements according to the dynamic temperature and humidity change model and the anti-condensation effect data;

[0165] Control module 500: It is used to control the integrated control system including the ventilation system, the anti-condensation network, and the active anti-condensation guarantee mechanism through a multi-objective optimization algorithm to dehumidify and prevent condensation in the distribution substation building.

[0166] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative labor.

[0167] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0168] The present invention aims to solve the problems that air conditioners and traditional dehumidifiers consume a large amount of electric energy continuously during operation, especially in high-humidity seasons, with high operating costs, which increases the economic burden on power enterprises; traditional equipment is difficult to accurately adjust according to changes in environmental humidity, easily causing over-dehumidification or insufficient dehumidification. Over-dehumidification will lead to energy waste, while insufficient dehumidification cannot meet the strict requirements of the fully-cabled distribution substation building for environmental humidity, posing a safety hazard; traditional dehumidification methods are difficult to balance the spatial temperature and humidity uniformity, easily forming condensation in local areas, such as areas with lower temperatures like cable trenches and equipment surfaces, posing a potential threat to the insulation performance and service life of equipment; traditional equipment lacks intelligent control means and cannot achieve functions such as humidity monitoring, early warning, and automatic adjustment, requiring frequent manual operations, increasing the operation and maintenance burden, and it is difficult to achieve refined management. The present invention comprehensively applies dynamic temperature and humidity prediction, phase change material anti-condensation, and active heating technologies, and realizes all-weather accurate anti-condensation and dehumidification in the distribution substation building through a multi-objective optimization algorithm, significantly improving the anti-condensation effect, reducing energy consumption, and extending the service life of equipment.

[0169] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for dehumidification and anti-condensation of an indoor fully cabled distribution station, characterized in that: include: S1: Collect temperature and humidity data in the distribution station, obtain station environmental parameter data, and predict the temperature and humidity change trend in the station based on the deep learning model of time series, and establish a dynamic temperature and humidity change model; S2: establishing a phase change material anti-condensation unit for adaptive thermal regulation according to the dynamic temperature and humidity change model and the station environment parameter data; S3: According to the condensation-prone area information identified in the dynamic temperature and humidity change model and the operating status data of the ventilation system, the phase change material anti-condensation unit is arranged at the anti-condensation position of the power distribution station to obtain an anti-condensation network, and the working status of the anti-condensation network is monitored in real time to obtain anti-condensation effect data; S4: establishing an active anti-condensation protection mechanism based on a PTC heating element according to the dynamic temperature and humidity change model and the anti-condensation effect data; S5: Based on the data flow information of the dynamic temperature and humidity change model, the ventilation system, the anti-condensation network and the active anti-condensation guarantee mechanism, a comprehensive control system is established through a multi-objective optimization algorithm, and the distribution station room is dehumidified and anti-condensed through the comprehensive control system.

2. A method for dehumidifying and preventing condensation in an indoor fully cabled distribution station according to claim 1, characterized in that: Step S1 further comprises: S11: Real-time monitoring of key locations including the surface of the distribution cabinet, cable joints, wall condensation risk areas and station building corners to obtain station building environmental parameter data; S12: Storing and indexing the station room environmental parameter data through a time series database to obtain a historical temperature and humidity data set; S13: Based on the future meteorological change prediction data and the historical temperature and humidity data set, predict the temperature and humidity change trend to obtain the temperature and humidity change trend prediction result; S14: Analyze the temperature and humidity change trend prediction results using a condensation risk assessment algorithm to obtain dynamic identification information of condensation-prone areas in the station building and obtain a complete dynamic temperature and humidity change model.

3. A method for dehumidification and anti-condensation of an indoor fully cabled distribution station according to claim 2, characterized in that: Step S13 further comprises: S131: Using an LSTM neural network to extract features from the historical temperature and humidity data set to obtain time series features of temperature and humidity changes; S132: Obtain weather forecast information through an external meteorological data API to obtain future meteorological change prediction data; S133: using a multivariate time series analysis method to fuse the time series features with the future meteorological change prediction data to obtain comprehensive prediction input parameters; S134: The comprehensive prediction input parameters are learned through a deep learning prediction model to obtain a prediction result of the temperature and humidity change trend.

4. The method for dehumidifying and preventing condensation in an indoor fully cabled distribution station according to claim 1, characterized in that: Step S2 further comprises: S21: selecting a basic phase change material suitable for the temperature range of the station building according to the dynamic temperature and humidity change model and the station building environmental parameter data; S22: adding a nano-scale modifier to the basic phase change material to optimize performance, thereby obtaining a modified phase change material; S23: encapsulating the modified phase change material in a microcapsule with a multi-layer structure to obtain a phase change material anti-coagulation unit.

5. The method for dehumidifying and preventing condensation in an indoor fully cabled distribution station according to claim 1, characterized in that: In step S3, according to the condensation-prone area information identified in the dynamic temperature and humidity change model and the operation status data of the ventilation system, the phase change material anti-condensation unit is arranged at the anti-condensation position of the distribution station room, and the step of obtaining the anti-condensation network further includes: S31: performing data mining on the temperature and humidity distribution data in the dynamic temperature and humidity change model, identifying areas prone to condensation, and obtaining a positioning map of areas prone to condensation; S32: Processing the operation status data of the ventilation system by using computational fluid dynamics simulation, generating the airflow path and flow velocity distribution model in the station building, and obtaining the air circulation dead corner identification result; S33: Comprehensively superimpose and analyze the condensation-prone area location map and the air circulation dead-angle identification result according to the risk rating method, determine high-risk areas, medium-risk areas and low-risk areas, and obtain a graded anti-condensation layout plan; S34: According to the hierarchical anti-condensation arrangement scheme, the phase change material anti-condensation unit is arranged at the anti-condensation position of the power distribution station to obtain an anti-condensation network.

6. The method for dehumidifying and preventing condensation in an indoor fully cabled distribution station according to claim 1, characterized in that: The step of real-time monitoring of the working status of the anti-coagulation network in step S3 specifically includes: The surface temperature of the phase change material anti-coagulation unit is monitored by a micro temperature sensor to obtain the working temperature of the anti-coagulation unit; Use infrared thermal imaging technology to scan the temperature distribution of the phase change material anti-coagulation unit to obtain heat diffusion effect data; The heat transfer between the phase change material anti-condensation unit and the environment is measured by a heat flow sensor to obtain the energy exchange information of the phase change process; The surface humidity detector is used to detect the condensation situation of the protected surface and obtain the anti-condensation surface status data.

7. The method for dehumidifying and preventing condensation in an indoor fully cabled distribution station according to claim 1, characterized in that: S4 further includes: S41: Integrate PTC heating elements in high-risk condensation areas according to the dynamic temperature and humidity change model and the anti-condensation effect data to obtain a basic heating element layout; S42: Optimizing the basic heating element layout based on the regional temperature distribution based on the thermal imaging technology to obtain an optimized heating element layout; S43: Power control is performed on the PTC heating element in the optimized heating element layout to form an active anti-condensation protection mechanism based on the PTC heating element.

8. The method for dehumidifying and preventing condensation in an indoor fully cabled distribution station according to claim 1, characterized in that: Step S5 further comprises: S51: Integrate the data flow information of the dynamic temperature and humidity change model, the ventilation system, the anti-condensation network and the active anti-condensation guarantee mechanism through an industrial controller to obtain a system-level control platform; S52: Setting optimization objectives including minimizing energy consumption, maximizing dehumidification efficiency, and minimizing temperature uniformity and constructing objective functions, and obtaining the optimal control strategy through a multi-objective optimization algorithm; S53: Controlling the integrated control system through the optimal control strategy to dehumidify and prevent condensation in the power distribution station.

9. A method for dehumidifying and preventing condensation in an indoor fully cabled distribution station according to claim 8, characterized in that: The expression of the optimization objective of the multi-objective optimization algorithm in step S52 is: Among them, F(x) is the optimization target, t0 is the starting point of the time range, and t f is the end point of the time range, λ is the exponential decay coefficient, V(t) is the time series of the wind speed regulation coefficient of the ventilation system, Q(t) is the time series of the power regulation coefficient of the auxiliary electric heating system, x1 is the decision variable of the wind speed regulation coefficient of the ventilation system, x3 is the decision variable of the power regulation coefficient of the heating system, H(t) is the humidity time series, P(t) is the temperature distribution time series of the anti-condensation network, x2 is the decision variable of the phase change material layout density, T(t) is the temperature time series, T avg is the average temperature value.

10. An indoor fully cabled distribution station dehumidification and anti-condensation system, characterized in that: include: Prediction module: used to collect temperature and humidity data in the distribution station, obtain station environmental parameter data, and predict the temperature and humidity change trend in the station based on the deep learning model of time series, and establish a dynamic temperature and humidity change model; The first building module is used to establish a phase change material anti-condensation unit for adaptive thermal regulation according to the dynamic temperature and humidity change model and the station environment parameter data; Monitoring module: used to monitor the working status of the anti-condensation network arranged at the anti-condensation position of the distribution station in real time and obtain the anti-condensation effect data; The second building module is used to establish an active anti-condensation guarantee mechanism based on the PTC heating element according to the dynamic temperature and humidity change model and the anti-condensation effect data; Control module: used to control the integrated control system including the ventilation system, the anti-condensation network and the active anti-condensation guarantee mechanism through a multi-objective optimization algorithm, so as to dehumidify and prevent condensation in the distribution station room.

Images