An intelligent control system for temperature inside a power distribution cabinet

Abstract

The present invention discloses an intelligent control system for the temperature inside a power distribution cabinet, including: obtaining the structural information of the power distribution cabinet, analyzing the internal heat source, electromagnetic field and gas flow direction, and using digital twin technology to build a digital twin model of the power distribution cabinet; obtaining real-time operation monitoring information, simulating the temperature distribution inside the cabinet, using ELM to build a temperature prediction model and predict the temperature inside the cabinet; generating a temperature prediction map inside the cabinet according to the temperature prediction information, analyzing the potential overheating area, and performing early warning prompts and heat dissipation system regulation; obtaining historical temperature and humidity monitoring information based on big data retrieval and classifying it to form an example data set, building a temperature and humidity prediction model and training the model; extracting real-time temperature and humidity information according to real-time operation monitoring information, predicting through the temperature and humidity prediction model, obtaining temperature and humidity prediction information, and performing condensation judgment, and performing temperature and humidity regulation according to the judgment result. The operation safety and reliability of the power distribution cabinet are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of power distribution cabinets, and in particular to an intelligent control system for the internal temperature of a power distribution cabinet. Background Art

[0002] With the development of modern industry and power systems, the reliability and safety of distribution cabinets, as an important part of the power system, are of vital importance. The distribution cabinet contains a large number of electrical components, which generate a lot of heat during operation. If the heat is not dissipated in a timely and effective manner, the temperature inside the cabinet will rise rapidly, which may cause the components to overheat, affect their normal operation, and even cause safety accidents such as fire. Traditional distribution cabinet temperature control methods mainly rely on simple temperature monitoring and mechanical heat dissipation methods such as fans and air conditioners. However, these methods have problems such as delayed response, high energy consumption and limited heat dissipation effect, and are difficult to cope with complex and changing operating environments.

[0003] In recent years, with the rapid development of sensor technology, computer simulation technology and artificial intelligence technology, digital twin technology has gradually been applied to the field of industrial control. Digital twin technology establishes a virtual model of a physical object to reflect the state and behavior of the physical object in real time, providing a new solution for system operation optimization and fault prediction. In the field of power distribution cabinets, digital twin technology can be used to monitor the internal temperature, electromagnetic field and airflow distribution of the power distribution cabinet in real time, and accurately predict the temperature inside the cabinet, so as to understand the operating status of the power distribution cabinet in advance and adjust it. At the same time, the heat change during the operation of the power distribution cabinet will cause condensation in the power distribution cabinet, which will affect the safety of the power distribution cabinet operation. Therefore, how to better analyze the temperature inside the power distribution cabinet to avoid excessive temperature and condensation is an urgent problem to be solved. Summary of the invention

[0004] The present invention overcomes the defects of the prior art and provides an intelligent control system for the temperature inside a power distribution cabinet, the important purpose of which is to effectively improve the accuracy and response speed of temperature control and improve the operating safety and reliability of the power distribution cabinet.

[0005] To achieve the above-mentioned purpose, the first aspect of the present invention provides a method for intelligently controlling the temperature inside a power distribution cabinet, comprising:

[0006] Obtain the structural information of the distribution cabinet, analyze the internal heat source, internal electromagnetic field and gas flow direction of the target distribution cabinet, build an electromagnetic-thermal model and a temperature and humidity model, and use digital twin technology to build a digital twin model of the distribution cabinet;

[0007] Obtain the real-time operation monitoring information of the target distribution cabinet and perform data preprocessing. According to the preprocessing results, simulate the temperature distribution inside the cabinet. Use ELM to build a temperature prediction model and predict the temperature inside the cabinet to obtain the temperature prediction information inside the cabinet.

[0008] Generate a cabinet temperature prediction map of the target power distribution cabinet according to the cabinet temperature prediction information, perform potential overheating area analysis, and provide early warning prompts and heat dissipation system regulation according to the analysis results;

[0009] Based on big data retrieval, historical temperature and humidity monitoring information of condensation in the target distribution cabinet is obtained and classified to form an instance data set, and a temperature and humidity prediction model is constructed and trained.

[0010] The real-time temperature and humidity monitoring information is extracted according to the real-time operation monitoring information, the temperature and humidity prediction information in the cabinet is obtained by prediction through the temperature and humidity prediction model, and condensation determination is performed, and the temperature and humidity are controlled according to the determination result.

[0011] In this solution, the structure information of the distribution cabinet is obtained, the internal heat source, internal electromagnetic field and gas flow direction of the target distribution cabinet are analyzed, an electromagnetic-thermal model and a temperature and humidity model are constructed, and a digital twin model of the distribution cabinet is constructed using digital twin technology, which specifically includes:

[0012] Acquire the structure information of the power distribution cabinet, build a geometric model of the power distribution cabinet according to the structure information of the power distribution cabinet by using 3D modeling technology, and define material properties, including import coefficient, specific heat capacity and density;

[0013] Extracting internal component information according to the structure information of the power distribution cabinet, performing heat source analysis according to the internal component information, obtaining the power distribution cabinet equipment specification, calculating the calorific value of each component in the power distribution cabinet in combination with the prime number internal component information, and obtaining the component calorific value information;

[0014] According to the heat generation information of the components, the heat source type of each component is defined, including point heat source, surface heat source and body heat source, the cabinet area information of each component is obtained through the structure information of the power distribution cabinet, the heat source area inside the power distribution cabinet is defined, and the heat source analysis information inside the cabinet is obtained;

[0015] Extracting the heat dissipation structure characteristics of the power distribution cabinet according to the structure information of the power distribution cabinet, analyzing the gas flow direction in the internal space of the power distribution cabinet according to the heat dissipation structure characteristics of the power distribution cabinet, and obtaining the gas flow analysis information in the cabinet;

[0016] According to the internal component information and the specification of the power distribution cabinet equipment, an electromagnetic source analysis of the internal components of the power distribution cabinet is performed, and an electromagnetic field simulation is performed in combination with the geometric model of the power distribution cabinet to obtain electromagnetic field analysis information;

[0017] A temperature field model is constructed based on the heat source analysis information in the cabinet and the geometric model of the power distribution cabinet, an electromagnetic field model is constructed based on the electromagnetic field analysis information and the geometric model of the power distribution cabinet, and a temperature and humidity model is constructed in combination with the heat source analysis information in the cabinet and the gas flow analysis information;

[0018] Based on the digital twin technology, the temperature field model and the electromagnetic field model are coupled to form an electromagnetic-thermal model, and the temperature and humidity model is combined to form a digital twin model of the distribution cabinet.

[0019] In this solution, the real-time operation monitoring information of the target distribution cabinet is obtained and data preprocessing is performed, the temperature distribution in the cabinet is simulated according to the preprocessing results, and the temperature prediction model is constructed by using ELM to predict the temperature in the cabinet. Specifically, it includes:

[0020] Acquire real-time operation monitoring information of the target power distribution cabinet based on the sensor array, perform data cleaning on the real-time operation monitoring information, and calculate the data standard deviation of the real-time operation monitoring information;

[0021] The calculated data standard deviation is compared with the preset standard deviation range, and the data corresponding to the data standard deviation that is not within the preset standard deviation range is defined as an outlier, and the outlier is eliminated and the difference is compensated to obtain preprocessing information;

[0022] Preset boundary conditions and initial parameters according to the preprocessing information, simulate the temperature distribution in the cabinet in combination with the digital twin model of the power distribution cabinet, solve the temperature based on the finite element analysis method, and obtain real-time temperature analysis information in the cabinet;

[0023] According to the real-time in-cabinet temperature analysis information, a cabinet temperature distribution diagram of the target power distribution cabinet is formed, a time step is preset, and a cabinet temperature change sequence with a time attribute is formed in combination with the in-cabinet temperature distribution diagram;

[0024] A temperature prediction model is built based on ELM, and the PSO algorithm is introduced for model optimization. The input weights and bias parameters of the ELM network are randomly generated. The weights and bias parameters of the ELM are used as the positions of particles in the search space to encode and generate the initial population.

[0025] Preset the fitness function, calculate the fitness value of each particle in the initial population according to the fitness function, and judge it with the preset threshold to determine the individual extreme value and the global extreme value and update the position and speed;

[0026] Iterate according to the above steps until the maximum number of iterations is reached or the stopping criterion is met to obtain the optimal solution, decode the optimal solution to obtain the optimal weight and bias parameters of the ELM network, and optimize the temperature prediction model;

[0027] The temperature change sequence inside the cabinet is input into the optimized temperature prediction model to predict the temperature inside the target distribution cabinet and obtain the cabinet temperature prediction information.

[0028] In this solution, the cabinet temperature prediction map of the target power distribution cabinet is generated according to the cabinet temperature prediction information, potential overheating area analysis is performed, and early warning prompts and heat dissipation system regulation are performed according to the analysis results, specifically including:

[0029] Obtaining cabinet temperature prediction information, generating a cabinet temperature prediction map of a target power distribution cabinet according to the cabinet temperature prediction information, dividing the cabinet area of ​​the target power distribution cabinet into several areas, analyzing the temperature conditions of each sub-area in combination with the cabinet temperature prediction map, and obtaining temperature change condition analysis information;

[0030] According to the results of the area division in the target power distribution cabinet, the regional component information in each sub-area is obtained, the appropriate working temperature corresponding to each component is obtained through data retrieval, and the temperature safety analysis rules for each sub-area are constructed;

[0031] Calculate the temperature change amplitude and change peak value corresponding to each sub-area according to the temperature change status analysis information, perform potential overheating area analysis in combination with the temperature safety analysis rule, and obtain potential overheating area analysis information;

[0032] Determine whether there is a heat source in the potential overheating area according to the potential overheating area analysis information, and if there is a heat source, extract the heat source component information in the target potential overheating area to determine whether there is an abnormal operating condition;

[0033] If the target heat source components have abnormal operating conditions, an early warning will be issued and the cooling system in the target power distribution cabinet will be adjusted for emergency cooling;

[0034] If there is no heat source, the temperature tolerance information of the components in the potential overheating area is obtained to determine whether the temperature tolerance is exceeded, and early warning prompts and heat dissipation system adjustments are performed.

[0035] In this solution, the historical temperature and humidity monitoring information of condensation phenomenon in the target distribution cabinet is obtained based on big data retrieval and classified to form an instance data set, and a temperature and humidity prediction model is constructed and model training is performed, specifically including:

[0036] Based on big data retrieval, historical temperature and humidity monitoring information of condensation in the target distribution cabinet is obtained, wherein the historical temperature and humidity monitoring information includes the temperature and humidity monitoring information inside the cabinet and the ambient temperature and humidity monitoring information;

[0037] The historical temperature and humidity monitoring information is divided into the external control equipment on class and the external control facility off class, and the K-means clustering algorithm is used to cluster the temperature and humidity of the distribution cabinet when condensation occurs, and an instance data set is formed according to the clustering results;

[0038] Based on the Markov algorithm and the example data set, a state space is constructed, and the ambient temperature and humidity and the temperature and humidity inside the cabinet are used as prior conditions to divide the historical temperature and humidity data in the state space;

[0039] According to the division results, the state transition probability of the temperature and humidity of the power distribution cabinet under different external control equipment states is calculated, and a state transition matrix is ​​formed, and a temperature and humidity prediction model is constructed according to the state space, state transition probability and state transition matrix;

[0040] A training data set is constructed according to the example data set to train the temperature and humidity prediction model, and the model is adjusted and optimized to obtain a temperature and humidity prediction model that meets expectations.

[0041] In this solution, the real-time temperature and humidity monitoring information is extracted according to the real-time operation monitoring information, the temperature and humidity prediction information in the cabinet is obtained through prediction by the temperature and humidity prediction model, and condensation determination is performed, and temperature and humidity are controlled according to the determination result, which specifically includes:

[0042] Acquire real-time operation monitoring information of the target distribution cabinet, and extract real-time temperature and humidity monitoring information according to the real-time operation monitoring information, wherein the real-time temperature and humidity monitoring information includes ambient temperature and humidity monitoring information and cabinet temperature and humidity monitoring information;

[0043] The real-time temperature and humidity monitoring information is input into the temperature and humidity prediction model for prediction, the ambient temperature and humidity and the temperature and humidity inside the cabinet are obtained according to the input real-time temperature and humidity monitoring information, and a state transfer matrix is ​​obtained by searching in the state space;

[0044] Predict the changes in temperature and humidity inside the target distribution cabinet at the next moment according to the obtained state transfer matrix, and obtain the prediction information of temperature and humidity inside the cabinet; input the prediction information of temperature and humidity inside the cabinet into the digital twin model of the distribution cabinet for simulation, and generate the temperature and humidity distribution map inside the target distribution cabinet according to the simulation results;

[0045] Taking relative humidity and dew point temperature as the basis for determining condensation phenomenon, an indirect method is used to solve the relative humidity and dew point temperature of the internal area of ​​the target power distribution cabinet through the temperature and humidity distribution diagram in the cabinet, so as to obtain first analysis information;

[0046] A control threshold is preset, and the first analysis information is compared with the control threshold. If the value is greater than the control threshold, a control strategy is formulated to perform anti-condensation control.

[0047] A second aspect of the present invention provides an intelligent control system for the temperature inside a power distribution cabinet, the system comprising: a memory and a processor, the memory containing an intelligent control method program for the temperature inside the power distribution cabinet, and the intelligent control method program for the temperature inside the power distribution cabinet when executed by the processor implements the following steps:

[0048] Obtain the structural information of the distribution cabinet, analyze the internal heat source, internal electromagnetic field and gas flow direction of the target distribution cabinet, build an electromagnetic-thermal model and a temperature and humidity model, and use digital twin technology to build a digital twin model of the distribution cabinet;

[0049] Obtain the real-time operation monitoring information of the target distribution cabinet and perform data preprocessing. According to the preprocessing results, simulate the temperature distribution inside the cabinet. Use ELM to build a temperature prediction model and predict the temperature inside the cabinet to obtain the temperature prediction information inside the cabinet.

[0050] Generate a cabinet temperature prediction map of the target power distribution cabinet according to the cabinet temperature prediction information, perform potential overheating area analysis, and provide early warning prompts and heat dissipation system regulation according to the analysis results;

[0051] Based on big data retrieval, historical temperature and humidity monitoring information of condensation in the target distribution cabinet is obtained and classified to form an instance data set, and a temperature and humidity prediction model is constructed and trained.

[0052] The real-time temperature and humidity monitoring information is extracted according to the real-time operation monitoring information, the temperature and humidity prediction information in the cabinet is obtained by prediction through the temperature and humidity prediction model, and condensation determination is performed, and the temperature and humidity are controlled according to the determination result.

[0053] The present invention discloses an intelligent control system for the temperature inside a power distribution cabinet, including: obtaining the structural information of the power distribution cabinet, analyzing the internal heat source, electromagnetic field and gas flow direction, and using digital twin technology to build a digital twin model of the power distribution cabinet; obtaining real-time operation monitoring information, simulating the temperature distribution inside the cabinet, using ELM to build a temperature prediction model and predict the temperature inside the cabinet; generating a temperature prediction map inside the cabinet according to the temperature prediction information, analyzing the potential overheating area, and performing early warning prompts and heat dissipation system regulation; obtaining historical temperature and humidity monitoring information based on big data retrieval and classifying it to form an example data set, building a temperature and humidity prediction model and training the model; extracting real-time temperature and humidity information according to real-time operation monitoring information, predicting through the temperature and humidity prediction model, obtaining temperature and humidity prediction information, and performing condensation judgment, and performing temperature and humidity regulation according to the judgment result. The operation safety and reliability of the power distribution cabinet are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the drawings required for use in the embodiments or exemplary descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to the drawings without paying creative work.

[0055] Figure 1A flow chart of a method for intelligently controlling the temperature inside a power distribution cabinet provided by one embodiment of the present invention;

[0056] Figure 2 A flow chart of temperature monitoring and control in a cabinet provided by an embodiment of the present invention;

[0057] Figure 3 A block diagram of an intelligent control system for temperature inside a power distribution cabinet provided by one embodiment of the present invention;

[0058] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0059] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0061] Figure 1 A flow chart of a method for intelligently controlling the temperature inside a power distribution cabinet provided by one embodiment of the present invention;

[0062] like Figure 1 As shown, the present invention provides a flow chart of a method for intelligently controlling the temperature inside a power distribution cabinet, comprising:

[0063] S102, obtaining the structure information of the distribution cabinet, analyzing the internal heat source, internal electromagnetic field and gas flow direction of the target distribution cabinet, constructing an electromagnetic-thermal model and a temperature and humidity model, and using digital twin technology to construct a digital twin model of the distribution cabinet;

[0064] S104, obtaining real-time operation monitoring information of the target distribution cabinet and performing data preprocessing, simulating the temperature distribution in the cabinet according to the preprocessing result, building a temperature prediction model using ELM and performing cabinet temperature prediction, and obtaining cabinet temperature prediction information;

[0065] S106, generating a cabinet temperature prediction map of the target power distribution cabinet according to the cabinet temperature prediction information, performing potential overheating area analysis, and providing early warning prompts and regulating the cooling system according to the analysis results;

[0066] S108, based on big data retrieval, obtain historical temperature and humidity monitoring information of condensation phenomenon in the target distribution cabinet and classify it into categories to form an instance data set, build a temperature and humidity prediction model and perform model training;

[0067] S110, extracting real-time temperature and humidity monitoring information according to the real-time operation monitoring information, obtaining the temperature and humidity prediction information in the cabinet through prediction by the temperature and humidity prediction model, performing condensation determination, and controlling the temperature and humidity according to the determination result.

[0068] It should be noted that the present invention provides an intelligent control system for the temperature inside the distribution cabinet of the power distribution cabinet. The geometric model of the target distribution cabinet is established through the structural information of the distribution cabinet, the heat source analysis inside the cabinet is performed to define the heat source area inside the distribution cabinet, and the gas flow direction and electromagnetic field inside the distribution cabinet are analyzed to construct a temperature field model, an electromagnetic field model and a temperature and humidity model. The temperature field model and the electromagnetic field model are coupled to form an electromagnetic-thermal model using digital twin technology, and the digital twin model of the distribution cabinet is formed in combination with the temperature and humidity model. Based on the constructed digital twin model of the distribution cabinet, temperature simulation is performed in combination with the collected real-time operation monitoring information to analyze the temperature distribution inside the distribution cabinet. The temperature prediction model is constructed using ELM and the temperature inside the cabinet is predicted. The potential overheating area is analyzed based on the temperature prediction results, and then early warning prompts and heat dissipation system regulation are performed. At the same time, the historical temperature and humidity monitoring information of the condensation phenomenon is obtained and divided, and an instance data set is formed according to the division results. The temperature and humidity prediction model is constructed and the model training is performed through the instance data set. According to the real-time operation monitoring information, the real-time temperature and humidity monitoring information is obtained, the temperature and humidity in the cabinet are predicted, the condensation is determined according to the prediction results, and whether condensation will occur is analyzed, and the temperature and humidity are controlled. The precise control and dynamic adjustment of the internal temperature of the distribution cabinet are realized, which improves the safety and reliability of the operation of the distribution cabinet.

[0069] Furthermore, in a preferred embodiment of the present invention, the structure information of the distribution cabinet is obtained, the internal heat source, internal electromagnetic field and gas flow direction of the target distribution cabinet are analyzed, an electromagnetic-thermal model and a temperature and humidity model are constructed, and a digital twin model of the distribution cabinet is constructed using digital twin technology, which specifically includes:

[0070] Acquire the structure information of the power distribution cabinet, build a geometric model of the power distribution cabinet according to the structure information of the power distribution cabinet by using 3D modeling technology, and define material properties, including import coefficient, specific heat capacity and density;

[0071] Extracting internal component information according to the structure information of the power distribution cabinet, performing heat source analysis according to the internal component information, obtaining the power distribution cabinet equipment specification, calculating the calorific value of each component in the power distribution cabinet in combination with the prime number internal component information, and obtaining the component calorific value information;

[0072] According to the heat generation information of the components, the heat source type of each component is defined, including point heat source, surface heat source and body heat source, the cabinet area information of each component is obtained through the structure information of the power distribution cabinet, the heat source area inside the power distribution cabinet is defined, and the heat source analysis information inside the cabinet is obtained;

[0073] Extracting the heat dissipation structure characteristics of the power distribution cabinet according to the structure information of the power distribution cabinet, analyzing the gas flow direction in the internal space of the power distribution cabinet according to the heat dissipation structure characteristics of the power distribution cabinet, and obtaining the gas flow analysis information in the cabinet;

[0074] According to the internal component information and the specification of the power distribution cabinet equipment, an electromagnetic source analysis of the internal components of the power distribution cabinet is performed, and an electromagnetic field simulation is performed in combination with the geometric model of the power distribution cabinet to obtain electromagnetic field analysis information;

[0075] A temperature field model is constructed based on the heat source analysis information in the cabinet and the geometric model of the power distribution cabinet, an electromagnetic field model is constructed based on the electromagnetic field analysis information and the geometric model of the power distribution cabinet, and a temperature and humidity model is constructed in combination with the heat source analysis information in the cabinet and the gas flow analysis information;

[0076] Based on the digital twin technology, the temperature field model and the electromagnetic field model are coupled to form an electromagnetic-thermal model, and the temperature and humidity model is combined to form a digital twin model of the distribution cabinet.

[0077] It should be noted that the digital twin transmits information through the interaction between the physical model and the physical model to achieve automatic update of the model and parameters. The digital twin model is not limited to the traditional simulation that only analyzes the circuit and the process with large time constants, and can reflect the dynamic change characteristics of the multi-physical field of the equipment with field or field-circuit coupling as comprehensively as possible. The use of data-driven digital twin models can avoid the complex modeling of physical models, and use the input and output data of the distribution cabinet during use as a mathematical model to fit its physical process and realize the reduced-order calculation of the model. By constructing a temperature field model, an electromagnetic field model, and a temperature and humidity model, the relationship between electromagnetics and heat and the relationship between temperature and humidity are further considered, so as to have a more comprehensive understanding of the internal situation of the distribution cabinet. The temperature field model and the electromagnetic field model are coupled using digital twin technology to form an electromagnetic-thermal model, and the temperature and humidity model is combined to form a digital twin model of the distribution cabinet, so as to achieve a comprehensive and accurate simulation of the operating status of the distribution cabinet.

[0078] Further, in a preferred embodiment of the present invention, the real-time operation monitoring information of the target distribution cabinet is obtained and data preprocessing is performed, the temperature distribution simulation in the cabinet is performed according to the preprocessing result, and the temperature prediction model is constructed by using ELM to predict the temperature in the cabinet, which specifically includes:

[0079] Acquire real-time operation monitoring information of the target power distribution cabinet based on the sensor array, perform data cleaning on the real-time operation monitoring information, and calculate the data standard deviation of the real-time operation monitoring information;

[0080] The calculated data standard deviation is compared with the preset standard deviation range, and the data corresponding to the data standard deviation that is not within the preset standard deviation range is defined as an outlier, and the outlier is eliminated and the difference is compensated to obtain preprocessing information;

[0081] Preset boundary conditions and initial parameters according to the preprocessing information, simulate the temperature distribution in the cabinet in combination with the digital twin model of the power distribution cabinet, solve the temperature based on the finite element analysis method, and obtain real-time temperature analysis information in the cabinet;

[0082] According to the real-time in-cabinet temperature analysis information, a cabinet temperature distribution diagram of the target power distribution cabinet is formed, a time step is preset, and a cabinet temperature change sequence with a time attribute is formed in combination with the in-cabinet temperature distribution diagram;

[0083] A temperature prediction model is built based on ELM, and the PSO algorithm is introduced for model optimization. The input weights and bias parameters of the ELM network are randomly generated. The weights and bias parameters of the ELM are used as the positions of particles in the search space to encode and generate the initial population.

[0084] Preset the fitness function, calculate the fitness value of each particle in the initial population according to the fitness function, and judge it with the preset threshold to determine the individual extreme value and the global extreme value and update the position and speed;

[0085] Iterate according to the above steps until the maximum number of iterations is reached or the stopping criterion is met to obtain the optimal solution, decode the optimal solution to obtain the optimal weight and bias parameters of the ELM network, and optimize the temperature prediction model;

[0086] The temperature change sequence inside the cabinet is input into the optimized temperature prediction model to predict the temperature inside the target distribution cabinet and obtain the cabinet temperature prediction information.

[0087] It should be noted that the sensor array deployed on the target distribution cabinet is used to capture the operation monitoring information of the distribution cabinet in real time, including temperature and humidity, voltage, current, etc., and the acquired actual operation monitoring information is preprocessed. The boundary conditions, such as ambient temperature, air flow rate in the cabinet, etc., are set using the preprocessed data. The finite volume method of finite elements is used to solve the three major conservation equations of mass, momentum and energy, thermal boundary conditions, convection heat transfer coefficient and other equations to understand the temperature distribution in the cabinet and construct the cabinet temperature distribution map of the distribution cabinet. At the same time, the time step is preset and combined with the temperature distribution map to generate a cabinet temperature change sequence with time attributes. The temperature prediction model is constructed using the extreme learning machine (ELM). ELM has the advantages of higher accuracy and fast fitting speed. The weights between the input layer and the hidden layer and the threshold of the hidden layer are randomly generated. The learning process does not require adjustment of parameters. The optimal solution can be obtained by setting the number of neurons. In order to solve the problems of large data point offset and parameter randomness of the ELM algorithm, the PSO algorithm is used for optimization. The inverse of the prediction error is taken as the fitness function. The optimal weight and bias parameters of the ELM algorithm are found through iterative updates, and the model is optimized to obtain the optimal network structure. This enables accurate prediction of the temperature inside the distribution cabinet and improves the prediction precision and accuracy.

[0088] Further, in a preferred embodiment of the present invention, the cabinet temperature prediction map of the target distribution cabinet is generated according to the cabinet temperature prediction information, potential overheating area analysis is performed, and early warning prompts and heat dissipation system regulation are performed according to the analysis results, specifically including:

[0089] Acquire cabinet temperature prediction information, generate a cabinet temperature prediction map of the target power distribution cabinet according to the cabinet temperature prediction information, divide the cabinet area of ​​the target power distribution cabinet into several areas, analyze the temperature conditions of each sub-area in combination with the cabinet temperature prediction map, and obtain temperature change condition analysis information;

[0090] According to the results of the area division in the target power distribution cabinet, the regional component information in each sub-area is obtained, the appropriate working temperature corresponding to each component is obtained through data retrieval, and the temperature safety analysis rules for each sub-area are constructed;

[0091] Calculate the temperature change amplitude and change peak value corresponding to each sub-area according to the temperature change status analysis information, and perform potential overheating area analysis in combination with the temperature safety analysis rule to obtain potential overheating area analysis information;

[0092] Determine whether there is a heat source in the potential overheating area according to the potential overheating area analysis information, and if there is a heat source, extract the heat source component information in the target potential overheating area to determine whether there is an abnormal operating condition;

[0093] If the target heat source components have abnormal operating conditions, an early warning will be issued and the cooling system in the target power distribution cabinet will be adjusted for emergency cooling;

[0094] If there is no heat source, the temperature tolerance information of the components in the potential overheating area is obtained to determine whether the temperature tolerance is exceeded, and early warning prompts and heat dissipation system adjustments are performed.

[0095] It should be noted that the temperature prediction map inside the power distribution cabinet is drawn based on the prediction information of the temperature inside the cabinet. The inside of the power distribution cabinet is divided into multiple sub-areas, and the temperature change trend of each sub-area is analyzed based on the temperature prediction map to generate temperature change status analysis information. Next, according to the division results of the internal area of ​​the power distribution cabinet, the specific information of the components in each sub-area is collected, and the appropriate operating temperature range of these components is obtained through data retrieval, and the temperature safety analysis rules are constructed for each sub-area for subsequent evaluation of whether the temperature is within the safe range. The temperature change amplitude and change peak value in each sub-area are calculated, and the areas with potential overheating risks are identified in combination with the temperature safety analysis rules, and the analysis information of the potential overheating area is generated. For the identified potential overheating area, it is determined whether there are heat source components in the area. If so, the system will pay special attention to these heat source components and check whether their operating status is abnormal, because abnormal operation is often the direct cause of the temperature increase. Once an abnormality is found, an early warning is immediately issued, and the heat dissipation system in the power distribution cabinet is started for emergency cooling to prevent damage to the equipment caused by excessive temperature. If there are no direct heat source components in the potential overheating area, the temperature tolerance of the components in the area will be further evaluated. By comparing the actual temperature with the temperature tolerance limit of the components, it is determined whether the temperature has exceeded the safety range of the components. If it exceeds, the system will issue an early warning and adjust the cooling system to reduce the temperature to ensure that all components in the power distribution cabinet can operate in a safe environment. In this way, the internal temperature environment of the power distribution cabinet is fully monitored to ensure operational safety and improve responsiveness.

[0096] Further, in a preferred embodiment of the present invention, the historical temperature and humidity monitoring information of condensation phenomenon in the target distribution cabinet is obtained based on big data retrieval and classified to form an instance data set, a temperature and humidity prediction model is constructed and model training is performed, specifically including:

[0097] Based on big data retrieval, historical temperature and humidity monitoring information of condensation in the target distribution cabinet is obtained, wherein the historical temperature and humidity monitoring information includes the temperature and humidity monitoring information inside the cabinet and the ambient temperature and humidity monitoring information;

[0098] The historical temperature and humidity monitoring information is divided into the external control equipment on class and the external control facility off class, and the K-means clustering algorithm is used to cluster the temperature and humidity of the distribution cabinet when condensation occurs, and an instance data set is formed according to the clustering results;

[0099] Based on the Markov algorithm and the example data set, a state space is constructed, and the ambient temperature and humidity and the temperature and humidity inside the cabinet are used as prior conditions to divide the historical temperature and humidity data in the state space;

[0100] According to the division results, the state transition probability of the temperature and humidity of the power distribution cabinet under different external control equipment states is calculated, and a state transition matrix is ​​formed, and a temperature and humidity prediction model is constructed according to the state space, state transition probability and state transition matrix;

[0101] A training data set is constructed according to the example data set to train the temperature and humidity prediction model, and the model is adjusted and optimized to obtain a temperature and humidity prediction model that meets expectations.

[0102] It should be noted that in the actual operation of the distribution cabinet, due to the differences and changes between the external environment and the internal environment, when the absolute humidity of the air in the distribution cabinet is too high, the air moisture content will be too high. When the water vapor content in the air is saturated, condensation will occur on the solid surface in the cabinet. In the actual operation process, it is within a reasonable range for the distribution cabinet to have a certain degree of condensation. However, due to the hysteresis of the environmental control equipment and the internal control equipment when they are controlled, if the control is performed after the condensation phenomenon occurs, the condensation phenomenon may be aggravated during the time period of the control to the expected range, thereby affecting the safe operation of the distribution cabinet. Therefore, it is necessary to control before the condensation phenomenon occurs, so as to avoid the aggravation of the condensation phenomenon due to the control time during the control process. Using the historical temperature and humidity monitoring information of the condensation phenomenon, it is divided into two categories, one is the external control equipment opening category, and the other is the external control facility closing category. Among them, the external control equipment can be air conditioning equipment or ventilation equipment in the environment, etc. Using the K-means clustering algorithm, the temperature and humidity data of the distribution cabinet when the condensation phenomenon occurs are clustered. Form representative instance data sets that reflect the relationship between different control conditions and condensation phenomena. Use the Markov algorithm to construct the state space. Use the temperature and humidity changes in historical data as prior conditions to divide them, describe the transfer rules of temperature and humidity under different states, and thus predict possible state changes in the future. Use the instance data set to construct a training data set and train the temperature and humidity prediction model.

[0103] Further, in a preferred embodiment of the present invention, the real-time temperature and humidity monitoring information is extracted according to the real-time operation monitoring information, the temperature and humidity prediction information in the cabinet is obtained by prediction through the temperature and humidity prediction model, and condensation determination is performed, and temperature and humidity are controlled according to the determination result, specifically including:

[0104] Acquire real-time operation monitoring information of the target distribution cabinet, and extract real-time temperature and humidity monitoring information according to the real-time operation monitoring information, wherein the real-time temperature and humidity monitoring information includes ambient temperature and humidity monitoring information and cabinet temperature and humidity monitoring information;

[0105] The real-time temperature and humidity monitoring information is input into the temperature and humidity prediction model for prediction, the ambient temperature and humidity and the temperature and humidity inside the cabinet are obtained according to the input real-time temperature and humidity monitoring information, and a state transfer matrix is ​​obtained by searching in the state space;

[0106] Predict the changes in temperature and humidity inside the target distribution cabinet at the next moment according to the obtained state transfer matrix, and obtain the prediction information of temperature and humidity inside the cabinet; input the prediction information of temperature and humidity inside the cabinet into the digital twin model of the distribution cabinet for simulation, and generate the temperature and humidity distribution map inside the target distribution cabinet according to the simulation results;

[0107] Taking relative humidity and dew point temperature as the basis for determining condensation phenomenon, an indirect method is used to solve the relative humidity and dew point temperature of the internal area of ​​the target power distribution cabinet through the temperature and humidity distribution diagram in the cabinet, so as to obtain first analysis information;

[0108] A control threshold is preset, and the first analysis information is compared with the control threshold. If the value is greater than the control threshold, a control strategy is formulated to perform anti-condensation control.

[0109] It should be noted that the real-time operation monitoring information of the target distribution cabinet is obtained, and the real-time temperature and humidity monitoring information is extracted, including the temperature and humidity of the environment and the temperature and humidity inside the cabinet. Next, the extracted real-time temperature and humidity monitoring information is input into the previously trained temperature and humidity prediction model. Using the input ambient temperature and humidity and the temperature and humidity inside the cabinet, a search is performed in the state space to find a state transition matrix that matches the current state. Using the obtained state transition matrix, the temperature and humidity changes inside the target distribution cabinet at the next moment are predicted, and the corresponding temperature and humidity prediction information inside the cabinet is generated. The temperature and humidity prediction information inside the cabinet is input into the digital twin model of the distribution cabinet for simulation, and the temperature and humidity distribution map inside the target distribution cabinet is generated, which intuitively displays the temperature and humidity conditions in different areas inside the distribution cabinet. After obtaining the temperature and humidity distribution map inside the cabinet, the indirect method is used to solve the relative humidity and dew point temperature of the internal area of ​​the target distribution cabinet. These two parameters are important bases for judging whether condensation occurs. First, the dry bulb temperature is converted to Kelvin temperature, the saturated water vapor partial pressure is calculated, and the relative humidity and dew point temperature are calculated by the water vapor partial pressure and the saturated water vapor partial pressure. Finally, a control threshold is preset to determine whether the current internal environment of the power distribution cabinet has reached the level that requires control. If the first analysis information is greater than the control threshold, it means that there is a risk of condensation inside the power distribution cabinet, and anti-condensation control is performed according to the preset control strategy to ensure the normal operation of the power distribution cabinet.

[0110] Figure 2 A flow chart of temperature monitoring and control in a cabinet provided by an embodiment of the present invention;

[0111] like Figure 2 As shown, the present invention provides a flow chart of temperature monitoring and control in the cabinet, including:

[0112] S202, obtaining real-time operation monitoring information of the target power distribution cabinet and performing data preprocessing, simulating the temperature distribution in the cabinet according to the preprocessing result, and obtaining real-time temperature analysis information in the cabinet;

[0113] S204, constructing a cabinet temperature distribution diagram of the target power distribution cabinet according to the real-time cabinet temperature analysis information, generating a cabinet temperature change sequence with a time attribute, and inputting it into the optimized temperature prediction model to predict the cabinet temperature of the target power distribution cabinet, and obtaining cabinet temperature prediction information;

[0114] S206, generating a cabinet temperature prediction map of the target power distribution cabinet according to the cabinet temperature prediction information, performing potential overheating area analysis, and providing early warning prompts and cooling system regulation according to the analysis results;

[0115] S208, obtaining real-time temperature and humidity monitoring information, inputting it into the temperature and humidity prediction model for prediction, obtaining the temperature and humidity prediction information inside the cabinet, and inputting it into the digital twin model of the power distribution cabinet for simulation to generate a temperature and humidity distribution map inside the cabinet;

[0116] S210, calculate the relative humidity and dew point temperature of the internal area of ​​the target distribution cabinet to obtain a first analysis information, and judge it with the control threshold. If it is greater than the control threshold, anti-condensation control is performed.

[0117] In addition, the method for intelligently controlling the temperature inside a power distribution cabinet provided by the present invention further includes the following steps:

[0118] Acquire historical operation monitoring instances of normal operation of the target distribution cabinet based on historical data retrieval, perform feature extraction on the historical operation monitoring instances, acquire working state features of the distribution cabinet corresponding to each historical operation monitoring instance, and obtain first feature information;

[0119] Classify each historical operation monitoring instance according to the first characteristic information, and classify each historical operation monitoring instance into different working status categories to obtain first category classification information;

[0120] Extracting the operating environment characteristics of the historical operating monitoring instances under each working state category according to the first category classification information, including environmental climate characteristics, environmental temperature and humidity characteristics, and environmental control equipment operating characteristics, and using a clustering algorithm to classify the historical operating monitoring instances under each working state category into subcategories to obtain second category classification information;

[0121] Perform periodic analysis using the SARIMA model according to the second analog classification information to analyze the internal operating temperature change trend of the power distribution cabinet under various working states during normal operation, and obtain third analysis information;

[0122] According to the third analysis information, the temperature change trend inside the power distribution cabinet in different operating environments under each working state is obtained to construct a normal operating temperature change portrait of the corresponding category, and form a first database;

[0123] Acquire real-time operation monitoring information, extract working state characteristics and operating environment characteristics according to the real-time operation monitoring information, and perform matching in the first database to obtain a corresponding normal operating temperature change portrait;

[0124] A judgment threshold is preset, and a similarity calculation is performed between the obtained normal operating temperature change portrait and the real-time operating environment monitoring information to obtain a similarity value, and a judgment is performed with the judgment threshold to analyze whether the operating temperature of the target distribution cabinet is normal;

[0125] If the similarity value is less than the judgment threshold, it means that there is an abnormality in the environmental control equipment of the target distribution cabinet in the current operating environment. An abnormal warning of the environmental control equipment is issued, and the operating control parameters of the current environmental control equipment are adjusted to cool the target distribution cabinet.

[0126] It should be noted that in the operating environment of the power distribution cabinet, the environmental control equipment includes external control equipment and internal control equipment, such as air conditioners, fans, etc. When the environmental control equipment is working normally, there is a certain regularity in the temperature change inside the power distribution cabinet under different working conditions, that is, the temperature inside the power distribution cabinet under different working conditions and different working environments can be effectively controlled, thus showing a normal working trend. Therefore, when the temperature inside the power distribution cabinet conforms to the normal working trend, the control parameters of the corresponding environmental control equipment are also the same, that is, the temperature change control strategy for the power distribution cabinet is the same. Furthermore, through historical data analysis, the corresponding temperature change trend of the power distribution cabinet under different working conditions and different working environments can be obtained, and this change trend inside the cabinet represents the control parameters of the corresponding environmental control equipment that can control the optimal parameters of the current temperature. Therefore, according to the temperature change trend inside the cabinet, it is possible to judge whether the corresponding environmental control equipment is operating normally in one step, improve the precise control of the temperature inside the power distribution cabinet, and ensure the safe operation of the power distribution cabinet.

[0127] Figure 3 An embodiment of the present invention provides an intelligent control system 3 for the temperature inside a power distribution cabinet, the system comprising: a memory 31 and a processor 32, wherein the memory 31 contains an intelligent control method program for the temperature inside the power distribution cabinet, and when the intelligent control method program for the temperature inside the power distribution cabinet is executed by the processor 32, the following steps are implemented:

[0128] Obtain the structural information of the distribution cabinet, analyze the internal heat source, internal electromagnetic field and gas flow direction of the target distribution cabinet, build an electromagnetic-thermal model and a temperature and humidity model, and use digital twin technology to build a digital twin model of the distribution cabinet;

[0129] Obtain the real-time operation monitoring information of the target distribution cabinet and perform data preprocessing. According to the preprocessing results, simulate the temperature distribution inside the cabinet. Use ELM to build a temperature prediction model and predict the temperature inside the cabinet to obtain the temperature prediction information inside the cabinet.

[0130] Generate a cabinet temperature prediction map of the target power distribution cabinet according to the cabinet temperature prediction information, perform potential overheating area analysis, and provide early warning prompts and heat dissipation system regulation according to the analysis results;

[0131] Based on big data retrieval, historical temperature and humidity monitoring information of condensation in the target distribution cabinet is obtained and classified into categories to form an instance data set, and a temperature and humidity prediction model is constructed and trained.

[0132] The real-time temperature and humidity monitoring information is extracted according to the real-time operation monitoring information, the temperature and humidity prediction information in the cabinet is obtained by prediction through the temperature and humidity prediction model, and condensation determination is performed, and the temperature and humidity are controlled according to the determination result.

[0133] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0134] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0135] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0136] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0137] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0138] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for intelligently controlling the temperature inside a power distribution cabinet, characterized in that: include: Obtain the structural information of the distribution cabinet, analyze the internal heat source, internal electromagnetic field and gas flow direction of the target distribution cabinet, build an electromagnetic-thermal model and a temperature and humidity model, and use digital twin technology to build a digital twin model of the distribution cabinet; Obtain the real-time operation monitoring information of the target distribution cabinet and perform data preprocessing. According to the preprocessing results, simulate the temperature distribution inside the cabinet. Use ELM to build a temperature prediction model and predict the temperature inside the cabinet to obtain the temperature prediction information inside the cabinet. Generate a cabinet temperature prediction map of the target power distribution cabinet according to the cabinet temperature prediction information, perform potential overheating area analysis, and provide early warning prompts and heat dissipation system regulation according to the analysis results; Based on big data retrieval, historical temperature and humidity monitoring information of condensation in the target distribution cabinet is obtained and classified to form an instance data set, and a temperature and humidity prediction model is constructed and trained. Extracting real-time temperature and humidity monitoring information according to the real-time operation monitoring information, obtaining the temperature and humidity prediction information in the cabinet through the temperature and humidity prediction model, and making a condensation determination, and adjusting the temperature and humidity according to the determination result; The acquisition of real-time operation monitoring information of the target distribution cabinet and data preprocessing, the simulation of the temperature distribution in the cabinet according to the preprocessing result, the use of ELM to build a temperature prediction model and predict the temperature in the cabinet, specifically includes: Acquire real-time operation monitoring information of the target power distribution cabinet based on the sensor array, perform data cleaning on the real-time operation monitoring information, and calculate the data standard deviation of the real-time operation monitoring information; The calculated data standard deviation is compared with the preset standard deviation range, and the data corresponding to the data standard deviation that is not within the preset standard deviation range is defined as an outlier, and the outlier is eliminated and the difference is compensated to obtain preprocessing information; Preset boundary conditions and initial parameters according to the preprocessing information, simulate the temperature distribution in the cabinet in combination with the digital twin model of the power distribution cabinet, solve the temperature based on the finite element analysis method, and obtain real-time temperature analysis information in the cabinet; According to the real-time in-cabinet temperature analysis information, a cabinet temperature distribution diagram of the target power distribution cabinet is formed, a time step is preset, and a cabinet temperature change sequence with a time attribute is formed in combination with the in-cabinet temperature distribution diagram; A temperature prediction model is built based on ELM, and the PSO algorithm is introduced for model optimization. The input weights and bias parameters of the ELM network are randomly generated. The weights and bias parameters of the ELM are used as the positions of particles in the search space to encode and generate the initial population. Preset the fitness function, calculate the fitness value of each particle in the initial population according to the fitness function, and judge it with the preset threshold to determine the individual extreme value and the global extreme value and update the position and speed; Iterate according to the above steps until the maximum number of iterations is reached or the stopping criterion is met to obtain the optimal solution, decode the optimal solution to obtain the optimal weight and bias parameters of the ELM network, and optimize the temperature prediction model; The temperature change sequence inside the cabinet is input into the optimized temperature prediction model to predict the temperature inside the target distribution cabinet and obtain the cabinet temperature prediction information.

2. The method for intelligently controlling the temperature inside a power distribution cabinet according to claim 1, characterized in that: The method of obtaining the structure information of the distribution cabinet, analyzing the internal heat source, internal electromagnetic field and gas flow direction of the target distribution cabinet, constructing an electromagnetic-thermal model and a temperature and humidity model, and constructing a digital twin model of the distribution cabinet using digital twin technology specifically includes: Acquire the structure information of the power distribution cabinet, build a geometric model of the power distribution cabinet according to the structure information of the power distribution cabinet by using 3D modeling technology, and define material properties, including thermal conductivity, specific heat capacity and density; Extracting internal component information according to the structure information of the power distribution cabinet, performing heat source analysis according to the internal component information, obtaining the power distribution cabinet equipment specification, calculating the calorific value of each component in the power distribution cabinet in combination with the internal component information, and obtaining component calorific value information; According to the heat generation information of the components, the heat source type of each component is defined, including point heat source, surface heat source and body heat source, the cabinet area information of each component is obtained through the structure information of the power distribution cabinet, the heat source area inside the power distribution cabinet is defined, and the heat source analysis information inside the cabinet is obtained; Extracting the heat dissipation structure characteristics of the power distribution cabinet according to the structure information of the power distribution cabinet, analyzing the gas flow direction in the internal space of the power distribution cabinet according to the heat dissipation structure characteristics of the power distribution cabinet, and obtaining the gas flow analysis information in the cabinet; According to the internal component information and the specification of the power distribution cabinet equipment, an electromagnetic source analysis of the internal components of the power distribution cabinet is performed, and an electromagnetic field simulation is performed in combination with the geometric model of the power distribution cabinet to obtain electromagnetic field analysis information; A temperature field model is constructed based on the heat source analysis information in the cabinet and the geometric model of the power distribution cabinet, an electromagnetic field model is constructed based on the electromagnetic field analysis information and the geometric model of the power distribution cabinet, and a temperature and humidity model is constructed in combination with the heat source analysis information in the cabinet and the gas flow analysis information; Based on the digital twin technology, the temperature field model and the electromagnetic field model are coupled to form an electromagnetic-thermal model, and the temperature and humidity model is combined to form a digital twin model of the distribution cabinet.

3. The method for intelligently controlling the temperature inside a power distribution cabinet according to claim 1, characterized in that: The step of generating a cabinet temperature prediction map of a target power distribution cabinet according to the cabinet temperature prediction information, analyzing potential overheating areas, and providing early warning prompts and regulating the heat dissipation system according to the analysis results specifically includes: Obtaining cabinet temperature prediction information, generating a cabinet temperature prediction map of a target power distribution cabinet according to the cabinet temperature prediction information, dividing the cabinet area of ​​the target power distribution cabinet into several areas, analyzing the temperature conditions of each sub-area in combination with the cabinet temperature prediction map, and obtaining temperature change condition analysis information; According to the results of the area division in the target power distribution cabinet, the regional component information in each sub-area is obtained, the appropriate working temperature corresponding to each component is obtained through data retrieval, and the temperature safety analysis rules for each sub-area are constructed; Calculate the temperature change amplitude and change peak value corresponding to each sub-area according to the temperature change status analysis information, perform potential overheating area analysis in combination with the temperature safety analysis rule, and obtain potential overheating area analysis information; Determine whether there is a heat source in the potential overheating area according to the potential overheating area analysis information, and if there is a heat source, extract the heat source component information in the target potential overheating area to determine whether there is an abnormal operating condition; If the target heat source components have abnormal operating conditions, an early warning will be issued and the cooling system in the target power distribution cabinet will be adjusted for emergency cooling; If there is no heat source, the temperature tolerance information of the components in the potential overheating area is obtained to determine whether the temperature tolerance is exceeded, and early warning prompts and heat dissipation system adjustments are performed.

4. The method for intelligently controlling the temperature inside a power distribution cabinet according to claim 1, characterized in that: The method of obtaining historical temperature and humidity monitoring information of condensation phenomenon in the target distribution cabinet based on big data retrieval and classifying it into categories to form an instance data set, building a temperature and humidity prediction model and performing model training specifically includes: Based on big data retrieval, historical temperature and humidity monitoring information of condensation in the target distribution cabinet is obtained, wherein the historical temperature and humidity monitoring information includes the temperature and humidity monitoring information inside the cabinet and the ambient temperature and humidity monitoring information; The historical temperature and humidity monitoring information is divided into the external control equipment on class and the external control facility off class, and the K-means clustering algorithm is used to cluster the temperature and humidity of the distribution cabinet when condensation occurs, and an instance data set is formed according to the clustering results; Based on the Markov algorithm and the example data set, a state space is constructed, and the ambient temperature and humidity and the temperature and humidity inside the cabinet are used as prior conditions to divide the historical temperature and humidity data in the state space; According to the division results, the state transition probability of the temperature and humidity of the power distribution cabinet under different external control equipment states is calculated, and a state transition matrix is ​​formed, and a temperature and humidity prediction model is constructed according to the state space, state transition probability and state transition matrix; A training data set is constructed according to the example data set to train the temperature and humidity prediction model, and the model is adjusted and optimized to obtain a temperature and humidity prediction model that meets expectations.

5. The method for intelligently controlling the temperature inside a power distribution cabinet according to claim 1, characterized in that: The extracting of real-time temperature and humidity monitoring information according to the real-time operation monitoring information, obtaining the temperature and humidity prediction information in the cabinet through the prediction of the temperature and humidity prediction model, and performing condensation determination, and performing temperature and humidity control according to the determination result, specifically includes: Acquire real-time operation monitoring information of the target distribution cabinet, and extract real-time temperature and humidity monitoring information according to the real-time operation monitoring information, wherein the real-time temperature and humidity monitoring information includes ambient temperature and humidity monitoring information and cabinet temperature and humidity monitoring information; The real-time temperature and humidity monitoring information is input into the temperature and humidity prediction model for prediction, the ambient temperature and humidity and the temperature and humidity inside the cabinet are obtained according to the input real-time temperature and humidity monitoring information, and a state transfer matrix is ​​obtained by searching in the state space; Predict the changes in temperature and humidity inside the target distribution cabinet at the next moment according to the obtained state transfer matrix, and obtain the prediction information of temperature and humidity inside the cabinet; input the prediction information of temperature and humidity inside the cabinet into the digital twin model of the distribution cabinet for simulation, and generate the temperature and humidity distribution map inside the target distribution cabinet according to the simulation results; Taking relative humidity and dew point temperature as the basis for determining condensation phenomenon, an indirect method is used to solve the relative humidity and dew point temperature of the internal area of ​​the target power distribution cabinet through the temperature and humidity distribution diagram in the cabinet, so as to obtain first analysis information; A control threshold is preset, and the first analysis information is compared with the control threshold. If the value is greater than the control threshold, a control strategy is formulated to perform anti-condensation control.

6. An intelligent control system for the temperature inside a power distribution cabinet, characterized in that: The system includes: a memory and a processor, wherein the memory contains a method program for intelligently controlling the temperature inside a distribution cabinet, and when the method program for intelligently controlling the temperature inside a distribution cabinet is executed by the processor, the steps of a method for intelligently controlling the temperature inside a distribution cabinet as described in any one of claims 1 to 5 are implemented.

Images