An intelligent temperature and humidity regulation method and system for the internal environment of a box-type substation

Abstract

The application discloses a kind of box-type substation internal environment temperature and humidity intelligent regulation and control method and system, it is related to intelligent control technical field, it solves the technical problem that existing technology due to using fixed temperature and humidity threshold value to regulate and control, so that control strategy cannot be adjusted adaptively with load fluctuation and environmental change, leading to equipment response lag in extreme working condition and long-term operation energy consumption is too high;Break through single-point sensing limitation by fusing space temperature field, multipoint humidity, load current and meteorological data;By thermal risk coefficient and condensation probability index, load fluctuation and environmental change are quantified as forward-looking indicators, replacing static threshold;Based on fuzzy rule, temperature and humidity control interval is dynamically generated by index, adaptive adjustment of high-risk strict control and low-risk relaxation is realized;Finally, through enthalpy-humidity analysis and modal coordination matrix, the optimal energy efficiency is selected to execute combination, so as to eliminate lag in advance in extreme working condition, and the interval is relaxed to reduce energy consumption in low load working condition.

Description

Technical Field

[0001] This application belongs to the field of intelligent control technology, specifically a method and system for intelligent control of temperature and humidity in the internal environment of a prefabricated substation. Background Technology

[0002] Prefabricated substations, as a new type of power distribution device widely used in power systems, play an important role in urban and rural power grids, industrial parks, and new energy power plants due to their advantages such as compact structure, convenient installation, and reliable operation. However, because they are mostly enclosed or semi-enclosed structures and are often deployed outdoors or in areas with complex environments, their internal temperature and humidity are easily affected by external climatic conditions, leading to problems such as high temperature, high humidity, and condensation, which seriously threaten the safe and stable operation of electrical equipment.

[0003] Existing technologies use fixed temperature and humidity thresholds for regulation, which prevents the control strategy from adapting to load fluctuations and environmental changes. This results in equipment lag under extreme conditions and excessive energy consumption during long-term operation. Therefore, further improvements are needed for intelligent temperature and humidity control methods within prefabricated substations. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art; to this end, this application proposes an intelligent control method and system for the internal environment temperature and humidity of a prefabricated substation, which solves the technical problem that the control strategy cannot be adaptively adjusted with load fluctuations and environmental changes due to the use of fixed temperature and humidity thresholds in the prior art, resulting in equipment response lag under extreme conditions and excessive energy consumption during long-term operation.

[0005] To achieve the above objectives, the first aspect of this application provides a method for intelligent control of temperature and humidity inside a prefabricated substation, comprising: Acquire multidimensional state data; the multidimensional state data includes spatial temperature field distribution data, multi-point humidity data, real-time load current of equipment, and meteorological environment data; The regulatory impact indicators are generated based on multidimensional state data; these indicators include thermal risk coefficient and condensation probability index. Target ranges for temperature and humidity control are generated based on the indicators of influence of regulation. The control results are generated by multimodal collaborative control of the target range of temperature and humidity.

[0006] This application first integrates spatial temperature field, multi-point humidity, load current, and meteorological data to overcome the limitations of single-point perception; it quantifies load fluctuations and environmental changes into forward-looking indicators by using thermal risk coefficients and condensation probability indices to replace static thresholds; it dynamically generates temperature and humidity control ranges based on fuzzy rules to achieve adaptive adjustment with strict control in high-risk situations and relaxation in low-risk situations; and finally, it selects the most energy-efficient execution combination through enthalpy-humidity analysis and modal coordination matrix to respond in advance under extreme conditions to eliminate lag and relax the range under low-load conditions to reduce energy consumption.

[0007] Furthermore, the generation of regulatory impact indicators based on multidimensional state data includes: Extract spatial temperature field distribution data, multi-point humidity data, and real-time load current of equipment from multi-dimensional state data; the spatial temperature field distribution data refers to the original temperature matrix. The original temperature matrix is ​​sliced ​​into grids, dividing the internal space of the transformer substation into M×N virtual voxel units; the internal space of the transformer substation refers to the space inside the transformer substation; where M and N are integers, and both M and N are greater than 0; Extract the temperature value of each virtual voxel unit and identify the highest and average temperature values ​​inside the transformer substation. Calculate the temperature gradient modulus The formula for calculating the temperature gradient modulus satisfies: Where x, y, and z represent the coordinate axes in three-dimensional space; T represents the temperature value. , and These represent the rates of change of temperature along the three-dimensional spatial coordinate axes, respectively. The hotspot temperature difference is determined by the difference between the highest temperature value and the average temperature value; The thermal risk coefficient is calculated based on the temperature gradient modulus, hot spot temperature difference, and real-time load current of the equipment. The relative humidity and temperature values ​​at several detection points are converted into dew point temperature using the Magnus formula. Select the maximum value among several dew point temperatures as the characteristic dew point temperature of the current environment; The condensation probability index is calculated by using characteristic dew point temperature and surface temperature. The indicators affecting regulation are determined based on the thermal risk coefficient and the condensation probability index.

[0008] Furthermore, the thermal risk coefficient satisfies: ;in, Expressed as thermal risk coefficient; Represented as hotspot temperature difference; This is represented as a reference temperature; This is expressed as the real-time load current of the device. This is expressed as the rated current of the equipment; It represents the equivalent heat dissipation area; xh represents the convective heat transfer coefficient of the box surface; sz represents the specific heat capacity of the equipment material; sz represents the mass of the equipment.

[0009] Furthermore, the condensation probability index satisfies: ;in, It is represented as the condensation probability index; Represented as shape factor, >0; Expressed as surface temperature, This is expressed as the characteristic dew point temperature; It is expressed as the average of several dew point temperatures; It represents the maximum temperature deviation between the dew point temperature and the characteristic dew point temperature at several detection points, satisfying: j represents the number corresponding to the detection point; zq represents the boost weight coefficient; zq∈(0,1).

[0010] This application uses gridded slicing to process infrared thermal imaging data, accurately capturing the internal temperature gradient and hot spot temperature difference of the transformer substation, breaking through the perception blind spot of single-point temperature measurement. At the same time, it couples the square term of the equipment load current with the heat dissipation attenuation factor to construct a nonlinear thermal risk coefficient, so that the risk assessment is no longer limited to the current temperature reading, but combines the dynamic balance of heat source intensity and heat dissipation capacity. In terms of humidity assessment, it uses the Magnus formula to solve the multi-point dew point distribution, selects the extreme value as the characteristic dew point, and introduces a booster term for humidity field non-uniformity to correct the condensation probability, effectively solving the problem of misjudgment caused by the stratification of humid air in the local microenvironment. Thus, the control basis is upgraded from a lagging static threshold to an advanced early warning indicator that integrates the spatiotemporal characteristics of thermal and humidity fields, significantly improving the response speed and accuracy under extreme operating conditions.

[0011] Furthermore, the generation of the temperature and humidity control target range based on the control influence index includes: Extract the indicators affecting regulation; these indicators include the thermal risk coefficient and the condensation probability index. A mapping vector is generated based on the thermal risk coefficient and the condensation probability index; the mapping vector includes a risk vector and a probability vector. Define a fuzzy rule base; the fuzzy rule base includes several fuzzy rules; the fuzzy rules include fuzzy temperature rules and fuzzy humidity rules; the fuzzy rules are constructed from mapping vectors; The activation strength of each fuzzy rule is calculated using the product implication method; The temperature range scaling factor and humidity safety margin are calculated by combining the centroid method with nonlinear transformation. Extract external temperature from meteorological and environmental data; Define a reference temperature comfort range; the reference temperature comfort range includes the minimum reference temperature value and the maximum reference temperature value; The target temperature control range is obtained by correcting the reference temperature comfort range using a temperature range scaling factor. The target upper limit of humidity is calculated using a humidity safety margin; the target upper limit of humidity... ,satisfy: ;in, This is expressed as the characteristic dew point temperature. This is expressed as a humidity safety margin; Set the lower limit of the humidity target to 0; determine the humidity control target range based on the lower and upper limits of the humidity target. The target range for temperature and humidity control is determined based on the target range for temperature control and the target range for humidity control.

[0012] Furthermore, the step of generating a mapping vector based on the thermal risk coefficient and the condensation probability index includes: Extract the thermal risk coefficient and condensation probability index; The thermal risk coefficient and condensation probability index are mapped to several fuzzy subsets; the fuzzy subsets include a risk fuzzy subset and a probability fuzzy subset; the risk fuzzy subset includes low risk, medium risk and high risk; the probability fuzzy subset includes low probability, medium probability and high probability. Construct Gaussian membership functions for several fuzzy subsets; The membership values ​​of the thermal risk coefficient belonging to low risk, medium risk and high risk are calculated by the Gaussian membership function corresponding to the risk fuzzy subset, and several membership values ​​are combined to form a risk vector; The membership values ​​of the condensation probability index belonging to low probability, medium probability, and high probability are calculated by the Gaussian membership function corresponding to the probability fuzzy subset, and several membership values ​​are combined into a probability vector. The mapping vector is determined based on the risk vector and the probability vector.

[0013] Furthermore, the temperature range scaling factor satisfies: ;in, denoted as the temperature range scaling factor; c represents the number corresponding to the fuzzy temperature rule; n represents the total number of fuzzy temperature rules; U represents the scaling factor universe; u represents the integral variable in the scaling factor universe; Represented as a membership function; This is represented by the activation intensity corresponding to the c-th fuzzy temperature rule; The humidity safety margin satisfies: ;in, denoted as humidity safety margin; d represents the number corresponding to the fuzzy humidity rule; m represents the total number of fuzzy humidity rules; V represents the humidity safety universe; v represents the integral variable in the humidity safety universe. Represented as a membership function; This represents the activation intensity corresponding to the d-th fuzzy humidity rule.

[0014] Furthermore, the temperature control target range includes a lower temperature control limit and a higher temperature control limit; The lower limit of temperature control ,satisfy: ;in, This is represented as the lowest reference temperature. Represented as external temperature; Represented as the temperature coupling coefficient; Represented as a saturation function; The upper limit of temperature control ,satisfy: ;in, This is represented as the highest value of the reference temperature. It is expressed as a temperature range scaling factor.

[0015] This application utilizes Gaussian membership functions to map thermal risk and condensation probability into a risk and probability vector containing multi-dimensional membership. Through product implication and the centroid method, the temperature range scaling factor and humidity safety margin are nonlinearly calculated, thereby transforming abstract risk into concrete control parameters. When constructing the target range, fixed thresholds are abandoned; instead, the scaling factor dynamically narrows or widens the reference temperature range to adapt to the risk level. Furthermore, the lower limit of temperature control is corrected using a saturation function based on external air temperature to prevent overcooling or heating. Simultaneously, the humidity safety margin and characteristic dew point reverse-drive the upper limit of dynamic humidity, achieving adaptive and elastic adjustment of the temperature and humidity range according to the environment and load. This ensures equipment safety under extreme operating conditions while maximizing energy savings under normal conditions.

[0016] Furthermore, the step of generating control results through multimodal collaborative control of the target temperature and humidity control range includes: Extract the target range for temperature and humidity control; the target range for temperature and humidity control includes the target range for temperature control and the target range for humidity control. Acquire external meteorological data, as well as the temperature and humidity inside the transformer substation; Construct a four-dimensional deviation vector; the four-dimensional deviation vector includes the upper temperature limit deviation, the lower temperature limit deviation, the upper humidity limit deviation, and the absolute deviation of the dew point temperature; Modal coding is determined based on the sign combination of the four-dimensional deviation vector; the modal coding includes comfort state, overheating state, overcooling state, and overhumidity state; Calculate the specific enthalpy of the outside air and the inside air; Constructing a feasibility criterion for natural ventilation; the feasibility criterion for natural ventilation ,satisfy: ;in, This is expressed as the efficiency coefficient of the transformer substation duct. Expressed as wind speed; This is represented as an indicator function; the value is 1 if the condition is met, and 0 otherwise. This indicates the allowable temperature difference buffer for the introduction of external air; This represents the upper limit of the humidity target. This refers to external humidity. Represented as external temperature; This refers to the temperature inside the transformer substation. and These are expressed as the specific enthalpy of external air and internal air, respectively. Modal coding, natural ventilation feasibility criteria, external humidity, external temperature, temperature and humidity of the transformer substation interior, and upper limit of humidity target are input into the modal collaborative decision matrix to obtain the control results; the modal collaborative decision matrix consists of modal coding, external air conditions, and control results; the external air conditions refer to the conditions composed of natural ventilation feasibility criteria, external humidity, external temperature, temperature and humidity of the transformer substation interior, and upper limit of humidity target.

[0017] This application constructs a four-dimensional vector encompassing upper and lower temperature limits, upper humidity limits, and dew point deviation to accurately identify concurrent operating conditions such as overheating, overcooling, and overhumidification, overcoming the limitations of traditional single-parameter triggering. It introduces a natural ventilation feasibility criterion based on air specific enthalpy, intelligently distinguishing whether introducing external air is for cooling and dehumidification or for increasing humidity and consuming energy by quantitatively comparing the heat content of internal and external air, thus preventing blind ventilation. Finally, relying on a collaborative decision matrix that integrates modal coding and multiple external air conditions, it automatically matches the optimal combination of execution actions, effectively solving the problems of action conflicts and energy consumption when fans, air conditioners, and heaters operate independently, achieving a balance between precision and high energy efficiency in environmental control.

[0018] Another aspect of the present invention provides a material storage and management system for automotive parts, comprising: a data acquisition module and a data analysis module; the data acquisition module and the data analysis module are connected together; The data acquisition module acquires multi-dimensional status data through data acquisition equipment; the multi-dimensional status data includes spatial temperature field distribution data, multi-point humidity data, real-time load current of the equipment, and meteorological environment data. The data analysis module includes an indicator determination unit, a dynamic adjustment unit, and a result generation unit; The indicator determination unit generates regulation impact indicators based on multidimensional state data; the regulation impact indicators include thermal risk coefficient and condensation probability index. The dynamic adjustment unit generates a target range for temperature and humidity control based on the control impact indicators. The result generation unit generates control results by performing multimodal collaborative control on the target temperature and humidity control range.

[0019] Compared with the prior art, the beneficial effects of this application are: 1. This application first integrates spatial temperature field, multi-point humidity, load current and meteorological data to overcome the limitations of single-point perception; it quantifies load fluctuations and environmental changes into forward-looking indicators by using thermal risk coefficient and condensation probability index to replace static thresholds; it dynamically generates temperature and humidity control ranges based on fuzzy rules to achieve adaptive adjustment with strict control in high-risk situations and relaxation in low-risk situations; and finally, it selects the most energy-efficient execution combination through enthalpy-humidity analysis and modal coordination matrix to respond in advance under extreme conditions to eliminate lag and relax the range under low-load conditions to reduce energy consumption.

[0020] 2. This application uses gridded slicing to process infrared thermal imaging data, accurately capturing the internal temperature gradient and hot spot temperature difference of the transformer substation, breaking through the perception blind spot of single-point temperature measurement. At the same time, it couples the square term of the equipment load current with the heat dissipation attenuation factor to construct a nonlinear thermal risk coefficient, so that the risk assessment is no longer limited to the current temperature reading, but combines the dynamic balance of heat source intensity and heat dissipation capacity. In terms of humidity assessment, the Magnus formula is used to solve the multi-point dew point distribution, the extreme value is selected as the characteristic dew point, and the boosting term of humidity field non-uniformity is introduced to correct the condensation probability, which effectively solves the problem of misjudgment caused by the stratification of humid air in the local microenvironment. Thus, the control basis is upgraded from the lagging static threshold to the advanced early warning indicator that integrates the spatiotemporal characteristics of thermal and humidity fields, which significantly improves the response speed and accuracy under extreme conditions.

[0021] 3. This application utilizes Gaussian membership functions to map thermal risk and condensation probability into a risk and probability vector containing multi-dimensional membership degrees. Through product implication and centroid method nonlinear calculation of temperature range scaling factor and humidity safety margin, abstract risk is transformed into specific control parameters. When constructing the target range, fixed thresholds are abandoned. The scaling factor is used to dynamically narrow or widen the reference temperature range to adapt to the risk level. Combined with external air temperature, the lower limit of temperature control is corrected through a saturation function to prevent overcooling or heating. At the same time, the upper limit of dynamic humidity is driven by the humidity safety margin and characteristic dew point, realizing the adaptive elastic adjustment of temperature and humidity range with environment and load. This ensures equipment safety under extreme conditions and maximizes energy saving space under normal conditions.

[0022] 4. This application constructs a four-dimensional vector covering upper and lower limits of temperature, upper limit of humidity, and dew point deviation to accurately identify concurrent operating conditions such as overheating, overcooling, and overhumidification, breaking through the limitations of traditional single-parameter triggering. It introduces a natural ventilation feasibility criterion based on air specific enthalpy, and intelligently distinguishes whether the introduction of external air is for cooling and dehumidification or for increasing humidity and consuming energy by quantitatively comparing the heat content of internal and external air, thus eliminating blind ventilation. Finally, relying on a collaborative decision matrix that integrates modal coding and multiple external air conditions, it automatically matches the optimal combination of execution actions, effectively solving the problem of action conflicts and energy consumption when fans, air conditioners, and heaters operate independently, and achieving a balance between precision and high energy efficiency in environmental control. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a method for intelligent control of internal environment temperature and humidity in a prefabricated substation according to this application. Figure 2 This is a flowchart illustrating the generation process of the regulatory impact indicators in this application; Figure 3 This is a flowchart illustrating the generation process of the target temperature and humidity control range in this application. Figure 4 This is a schematic diagram illustrating the principle of an intelligent temperature and humidity control system for the internal environment of a prefabricated substation according to this application. Detailed Implementation

[0025] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0026] Please see Figure 1 The first aspect of this application provides a method for intelligent control of temperature and humidity inside a prefabricated substation, comprising: Acquire multidimensional state data; multidimensional state data includes spatial temperature field distribution data, multi-point humidity data, real-time load current of equipment, and meteorological environment data; The regulatory impact indicators are generated based on multidimensional state data; these indicators include thermal risk coefficient and condensation probability index. Target ranges for temperature and humidity control are generated based on the indicators of influence of regulation. The control results are generated by multimodal collaborative control of the target range of temperature and humidity.

[0027] Please see Figure 2 In this embodiment, the generation of regulatory influence indicators based on multidimensional state data includes: Extract spatial temperature field distribution data, multi-point humidity data, and real-time load current of equipment from multidimensional state data; spatial temperature field distribution data refers to the original temperature matrix. The original temperature matrix is ​​meshed and sliced ​​to divide the internal space of the transformer substation into M×N virtual voxel units; the internal space of the transformer substation refers to the space inside the transformer substation; where M and N are integers, and both M and N are greater than 0; Extract the temperature value of each virtual voxel unit and identify the highest and average temperature values ​​inside the transformer substation. Calculate the temperature gradient modulus The formula for calculating the temperature gradient modulus satisfies: Where x, y, and z represent the coordinate axes in three-dimensional space; T represents the temperature value. , and These represent the rates of change of temperature along the three-dimensional spatial coordinate axes, respectively. The hotspot temperature difference is determined by the difference between the highest temperature value and the average temperature value; The thermal risk coefficient is calculated based on the temperature gradient modulus, hot spot temperature difference, and real-time load current of the equipment. The relative humidity and temperature values ​​at several detection points are converted into dew point temperature using Magnus's formula; in this embodiment, the dew point temperature satisfies: Where i represents the number corresponding to the detection point; Let be the temperature value at the i-th detection point. Let represent the relative humidity at the i-th detection point; a and b represent the Magnus coefficients, where a = 17.27 and b = 237.7℃. Select the maximum value among several dew point temperatures as the characteristic dew point temperature of the current environment; The condensation probability index is calculated by using characteristic dew point temperature and surface temperature. The indicators affecting regulation are determined based on the thermal risk coefficient and the condensation probability index.

[0028] The thermal risk factor in this embodiment satisfies: ;in, Expressed as thermal risk coefficient; Represented as hotspot temperature difference; This is represented as the reference temperature, which is set to 40°C in this embodiment to normalize the temperature difference. This is expressed as the real-time load current of the device. This is expressed as the rated current of the equipment; It represents the equivalent heat dissipation area; xh represents the convective heat transfer coefficient of the box surface; sz represents the specific heat capacity of the equipment material; sz represents the mass of the equipment; the exponent term in the thermal risk coefficient formula of this embodiment... This is used to simulate the decay of heat dissipation capacity; when the temperature gradient is large and the heat dissipation conditions are poor, A decrease in the value of indicates an increase in the thermal risk coefficient, suggesting that heat dissipation is hindered and the risk is aggravated.

[0029] The condensation probability index in this embodiment satisfies: ;in, It is represented as the condensation probability index; It is represented as a shape coefficient and is used to control the steepness of the probability curve; >0, the specific value is set according to experience, and in this embodiment it is set to 0.8; Expressed as surface temperature, This is expressed as the characteristic dew point temperature; It is expressed as the average of several dew point temperatures; It represents the maximum temperature deviation between the dew point temperature and the characteristic dew point temperature at several detection points, satisfying: j represents the number corresponding to the detection point; zq represents the boosting weight coefficient, which is used to amplify the effect of uneven humidity field causing local preferential condensation; zq∈(0,1); the specific value is set according to experience, and in this embodiment it is set to 0.2.

[0030] Please see Figure 3 In this embodiment, the generation of the temperature and humidity control target range based on the control influence index includes: Extract the indicators affecting regulation; these indicators include the thermal risk coefficient and the condensation probability index. A mapping vector is generated based on the thermal risk coefficient and the condensation probability index; the mapping vector includes a risk vector and a probability vector. Define a fuzzy rule base; the fuzzy rule base includes several fuzzy rules; the fuzzy rules include fuzzy temperature rules and fuzzy humidity rules; fuzzy rules are constructed from mapping vectors; The activation strength of each fuzzy rule is calculated using the product implication method; The temperature range scaling factor and humidity safety margin are calculated by combining the centroid method with nonlinear transformation. Extract external temperature from meteorological and environmental data; Define a reference temperature comfort range; the reference temperature comfort range includes the minimum reference temperature value and the maximum reference temperature value; The target temperature control range is obtained by correcting the reference temperature comfort range using a temperature range scaling factor. Calculate the target upper limit of humidity using the humidity safety margin; target upper limit of humidity. ,satisfy: ;in, This is expressed as the characteristic dew point temperature. This is expressed as a humidity safety margin; Set the lower limit of the humidity target to 0; determine the humidity control target range based on the lower and upper limits of the humidity target. The target range for temperature and humidity control is determined based on the target range for temperature control and the target range for humidity control.

[0031] In this embodiment, the generation of a mapping vector based on the thermal risk coefficient and the condensation probability index includes: Extract the thermal risk coefficient and condensation probability index; The thermal risk coefficient and condensation probability index are mapped to several fuzzy subsets; the fuzzy subsets include risk fuzzy subsets and probability fuzzy subsets; the risk fuzzy subsets include low risk, medium risk and high risk; the probability fuzzy subsets include low probability, medium probability and high probability; Construct Gaussian membership functions for several fuzzy subsets; The membership values ​​of the thermal risk coefficient belonging to low, medium and high risk are calculated by the Gaussian membership function corresponding to the risk fuzzy subset, and several membership values ​​are combined to form a risk vector. The membership values ​​of the condensation probability index belonging to low probability, medium probability, and high probability are calculated by the Gaussian membership function corresponding to the probabilistic fuzzy subset, and several membership values ​​are combined into a probability vector. The mapping vector is determined based on the risk vector and the probability vector.

[0032] The temperature range scaling factor in this embodiment satisfies: ;in, denoted as the temperature range scaling factor; c represents the number corresponding to the fuzzy temperature rule, n represents the total number of fuzzy temperature rules; U represents the scaling factor universe, in this embodiment, U∈[0.5, 2]; u represents the integral variable in the scaling factor universe; Represented as a membership function; This is represented by the activation intensity corresponding to the c-th fuzzy temperature rule; Humidity safety margin, meeting the following requirements: ;in, denoted as humidity safety margin; d represents the number corresponding to the fuzzy humidity rule; m represents the total number of fuzzy humidity rules; V represents the humidity safety domain, in this embodiment, V∈[0,20]℃; v represents the integral variable in the humidity safety domain; Represented as a membership function; This represents the activation intensity corresponding to the d-th fuzzy humidity rule.

[0033] In this embodiment, the temperature control target range includes a lower limit and an upper limit of temperature control; Temperature control lower limit ,satisfy: ;in, This is represented as the lowest reference temperature. Represented as external temperature; Represented as the temperature coupling coefficient; It is represented as a saturation function, used to restrict the numerical value of the result to the range [-1, 1]; Temperature control upper limit ,satisfy: ;in, This is represented as the highest value of the reference temperature. It is expressed as a temperature range scaling factor.

[0034] In this embodiment, the generation of control results through multimodal collaborative control of the target temperature and humidity range includes: Extract the target range for temperature and humidity control; the target range for temperature and humidity control includes the target range for temperature control and the target range for humidity control. Acquire external meteorological data, as well as the temperature and humidity inside the transformer substation; A four-dimensional deviation vector is constructed. This vector includes the upper temperature limit deviation, lower temperature limit deviation, upper humidity limit deviation, and absolute dew point temperature deviation. In this embodiment, the upper temperature limit deviation refers to the difference between the temperature inside the transformer substation and the upper temperature control limit within the target temperature control range. The lower temperature limit deviation refers to the difference between the lower temperature control limit within the target temperature control range and the temperature inside the transformer substation. The upper humidity limit deviation refers to the difference between the humidity inside the transformer substation and the upper humidity target within the target humidity control range. The absolute dew point temperature deviation refers to the difference between the surface temperature and the characteristic dew point temperature. Modal coding is determined based on the sign combination of the four-dimensional deviation vector; modal coding includes comfortable state, overheated state, overcooled state, and overhumid state; in this embodiment, comfortable state refers to the upper limit deviation of temperature, the lower limit deviation of temperature, and the upper limit deviation of humidity all being less than 0; overheated state refers to the lower limit deviation of temperature being greater than 0; overcooled state refers to the upper limit deviation of temperature being greater than 0; and overhumid state refers to the upper limit deviation of humidity being greater than 0. Calculate the specific enthalpy of the outside air and the inside air; in this embodiment, the specific enthalpy of the outside air is... ,satisfy: ;in, Represented as external temperature; This refers to external humidity. Expressed as atmospheric pressure; "2501" represents the saturated vapor pressure; "2501" represents the latent heat of vaporization of water. Specific enthalpy of internal air ,satisfy: ;in, This refers to the temperature inside the transformer substation. This refers to the humidity inside the transformer substation. Expressed as saturated vapor pressure; Constructing feasibility criteria for natural ventilation; feasibility criteria for natural ventilation ,satisfy: ;in, This is expressed as the efficiency coefficient of the transformer substation's ventilation duct. The specific value is determined by the structure of the transformer substation. In this embodiment, the efficiency coefficient of the transformer substation's ventilation duct is in the range of 0.3 to 0.8. Expressed as wind speed; This is represented as an indicator function; the value is 1 if the condition is met, and 0 otherwise. This represents the allowable temperature difference buffer for the introduction of external air. In this embodiment, the allowable temperature difference buffer for the introduction of external air is set to 2°C. This represents the upper limit of the humidity target. This refers to external humidity. Modal coding, natural ventilation feasibility criteria, external humidity, external temperature, temperature and humidity inside the transformer substation, and upper limit of humidity target are input into the modal collaborative decision matrix to obtain the control results. The modal collaborative decision matrix consists of modal coding, external air conditions, and control results. External air conditions refer to the conditions composed of natural ventilation feasibility criteria, external humidity, external temperature, temperature and humidity inside the transformer substation, and upper limit of humidity target.

[0035] Please see Figure 4 Another embodiment of this application provides a material storage management system for automotive parts, including: a data acquisition module and a data analysis module; the data acquisition module and the data analysis module are connected. Data acquisition module: Acquires multidimensional status data through data acquisition equipment; multidimensional status data includes spatial temperature field distribution data, multi-point humidity data, real-time load current of equipment, and meteorological environment data; The data analysis module includes an indicator determination unit, a dynamic adjustment unit, and a result generation unit; Indicator determination unit: Generates regulation impact indicators based on multidimensional state data; regulation impact indicators include thermal risk coefficient and condensation probability index; Dynamic adjustment unit: Generates target ranges for temperature and humidity control based on the indicators affecting regulation; Result generation unit: Generates control results by performing multimodal collaborative control on the target range of temperature and humidity.

[0036] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0037] The working principle of this application is as follows: By integrating spatial temperature field, multi-point humidity, load current, and meteorological data, it overcomes the limitations of single-point perception; by using thermal risk coefficient and condensation probability index, it quantifies load fluctuations and environmental changes into forward-looking indicators, replacing static thresholds; based on fuzzy rules, it dynamically generates temperature and humidity control ranges from the indicators, achieving adaptive adjustment with strict control in high-risk situations and relaxation in low-risk situations; finally, by using enthalpy-humidity analysis and modal coordination matrix to select the most energy-efficient execution combination, it can respond in advance under extreme conditions to eliminate lag, and relax the range under low-load conditions to reduce energy consumption. This avoids the problem in existing technologies where fixed temperature and humidity thresholds prevent the control strategy from adaptively adjusting to load fluctuations and environmental changes, resulting in delayed response and excessively high energy consumption during long-term operation under extreme conditions.

[0038] The above embodiments are only used to illustrate the technical methods of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of this application without departing from the spirit and scope of the technical methods of this application.

Claims

1. A method for intelligent control of temperature and humidity inside a prefabricated substation, characterized in that, include: Obtain multidimensional state data; The multidimensional state data includes spatial temperature field distribution data, multi-point humidity data, real-time equipment load current, and meteorological environment data. The regulatory impact indicators are generated based on multidimensional state data; these indicators include thermal risk coefficient and condensation probability index. Target ranges for temperature and humidity control are generated based on the indicators of influence of regulation. The control results are generated by multimodal collaborative control of the target range of temperature and humidity.

2. The intelligent temperature and humidity control method for the internal environment of a prefabricated substation according to claim 1, characterized in that, The generation of regulatory impact indicators based on multidimensional state data includes: Extract spatial temperature field distribution data, multi-point humidity data, and real-time load current of equipment from multi-dimensional state data; the spatial temperature field distribution data refers to the original temperature matrix. The original temperature matrix is ​​processed by meshing and slicing to divide the internal space of the transformer substation into M×N virtual voxel units; the internal space of the transformer substation refers to the space inside the transformer substation; where M and N are integers, and both M and N are greater than 0; Extract the temperature value of each virtual voxel unit and identify the highest and average temperature values ​​inside the transformer substation. Calculate the temperature gradient modulus The formula for calculating the temperature gradient modulus satisfies: Where x, y, and z represent the coordinate axes in three-dimensional space; T represents the temperature value. , and These represent the rates of change of temperature along the three-dimensional spatial coordinate axes, respectively. The hotspot temperature difference is determined by the difference between the highest temperature value and the average temperature value; The thermal risk coefficient is calculated based on the temperature gradient modulus, hot spot temperature difference, and real-time load current of the equipment. The relative humidity and temperature values ​​at several detection points are converted into dew point temperature using the Magnus formula. Select the maximum value among several dew point temperatures as the characteristic dew point temperature of the current environment; The condensation probability index is calculated by using characteristic dew point temperature and surface temperature. The indicators affecting regulation are determined based on the thermal risk coefficient and the condensation probability index.

3. The intelligent temperature and humidity control method for the internal environment of a prefabricated substation according to claim 2, characterized in that, The thermal risk coefficient satisfies: ;in, Expressed as thermal risk coefficient; Represented as hotspot temperature difference; Indicated as reference temperature; This is expressed as the real-time load current of the device. This is expressed as the rated current of the equipment; It represents the equivalent heat dissipation area; xh represents the convective heat transfer coefficient of the box surface; sz represents the specific heat capacity of the equipment material; sz represents the mass of the equipment.

4. The intelligent temperature and humidity control method for the internal environment of a prefabricated substation according to claim 2, characterized in that, The condensation probability index satisfies: ;in, Represented as the condensation probability index; Represented as shape factor, >0; Expressed as surface temperature, This is expressed as the characteristic dew point temperature; It is expressed as the average of several dew point temperatures; It represents the maximum temperature deviation between the dew point temperature and the characteristic dew point temperature at several detection points, satisfying: j represents the number corresponding to the detection point; zq represents the boost weight coefficient; zq∈(0,1).

5. The intelligent temperature and humidity control method for the internal environment of a prefabricated substation according to claim 1, characterized in that, The generation of temperature and humidity control target ranges based on control impact indicators includes: Extract the indicators affecting regulation; these indicators include the thermal risk coefficient and the condensation probability index. A mapping vector is generated based on the thermal risk coefficient and the condensation probability index; the mapping vector includes a risk vector and a probability vector. Define a fuzzy rule base; the fuzzy rule base includes several fuzzy rules; the fuzzy rules include fuzzy temperature rules and fuzzy humidity rules; the fuzzy rules are constructed from mapping vectors; The activation strength of each fuzzy rule is calculated using the product implication method; The temperature range scaling factor and humidity safety margin are calculated by combining the centroid method with nonlinear transformation. Extract external temperature from meteorological and environmental data; Define a reference temperature comfort range; the reference temperature comfort range includes the minimum reference temperature value and the maximum reference temperature value; The target temperature control range is obtained by correcting the reference temperature comfort range using a temperature range scaling factor. The target upper limit of humidity is calculated using a humidity safety margin; the target upper limit of humidity... ,satisfy: ;in, This is expressed as the characteristic dew point temperature. This is expressed as a humidity safety margin; Set the lower limit of the humidity target to 0; determine the humidity control target range based on the lower and upper limits of the humidity target. The target range for temperature and humidity control is determined based on the target range for temperature control and the target range for humidity control.

6. The intelligent temperature and humidity control method for the internal environment of a prefabricated substation according to claim 5, characterized in that, The process of generating a mapping vector based on the thermal risk coefficient and the condensation probability index includes: Extract the thermal risk coefficient and condensation probability index; The thermal risk coefficient and condensation probability index are mapped to several fuzzy subsets; the fuzzy subsets include a risk fuzzy subset and a probability fuzzy subset; the risk fuzzy subset includes low risk, medium risk and high risk; the probability fuzzy subset includes low probability, medium probability and high probability. Construct Gaussian membership functions for several fuzzy subsets; The membership values ​​of the thermal risk coefficient belonging to low risk, medium risk and high risk are calculated by the Gaussian membership function corresponding to the risk fuzzy subset, and several membership values ​​are combined to form a risk vector; The membership values ​​of the condensation probability index belonging to low probability, medium probability, and high probability are calculated by the Gaussian membership function corresponding to the probability fuzzy subset, and several membership values ​​are combined into a probability vector. The mapping vector is determined based on the risk vector and the probability vector.

7. The intelligent temperature and humidity control method for the internal environment of a prefabricated substation according to claim 5, characterized in that, The temperature range scaling factor satisfies: ;in, denoted as the temperature range scaling factor; c represents the number corresponding to the fuzzy temperature rule; n represents the total number of fuzzy temperature rules; U represents the scaling factor universe; u represents the integral variable in the scaling factor universe; Represented as a membership function; This is represented by the activation intensity corresponding to the c-th fuzzy temperature rule; The humidity safety margin satisfies: ;in, denoted as humidity safety margin; d represents the number corresponding to the fuzzy humidity rule; m represents the total number of fuzzy humidity rules; V represents the humidity safety universe; v represents the integral variable in the humidity safety universe. Represented as a membership function; This represents the activation intensity corresponding to the d-th fuzzy humidity rule.

8. The intelligent temperature and humidity control method for the internal environment of a prefabricated substation according to claim 5, characterized in that, The temperature control target range includes a lower limit and an upper limit for temperature control. The lower limit of temperature control ,satisfy: ;in, This is represented as the lowest reference temperature. Represented as external temperature; Represented as the temperature coupling coefficient; Represented as a saturation function; The upper limit of temperature control ,satisfy: ;in, This is represented as the highest value of the reference temperature. It is expressed as a temperature range scaling factor.

9. The intelligent temperature and humidity control method for the internal environment of a prefabricated substation according to claim 1, characterized in that, The process of generating control results through multimodal collaborative control of the target temperature and humidity range includes: Extract the target range for temperature and humidity control; the target range for temperature and humidity control includes the target range for temperature control and the target range for humidity control. Acquire external meteorological data, as well as the temperature and humidity inside the transformer substation; Construct a four-dimensional deviation vector; the four-dimensional deviation vector includes the upper temperature limit deviation, the lower temperature limit deviation, the upper humidity limit deviation, and the absolute deviation of the dew point temperature; Modal coding is determined based on the sign combination of the four-dimensional deviation vector; the modal coding includes comfort state, overheating state, overcooling state, and overhumidity state; Calculate the specific enthalpy of the outside air and the inside air; Constructing a feasibility criterion for natural ventilation; the feasibility criterion for natural ventilation ,satisfy: ;in, This is expressed as the efficiency coefficient of the transformer substation duct. Expressed as wind speed; This is represented as an indicator function; the value is 1 if the condition is met, and 0 otherwise. This indicates the allowable temperature difference buffer for the introduction of external air; This represents the upper limit of the humidity target. This refers to external humidity. Represented as external temperature; This refers to the temperature inside the transformer substation. and These are expressed as the specific enthalpy of external air and internal air, respectively. Modal coding, natural ventilation feasibility criteria, external humidity, external temperature, temperature and humidity of the transformer substation interior, and upper limit of humidity target are input into the modal collaborative decision matrix to obtain the control results; the modal collaborative decision matrix consists of modal coding, external air conditions and control results; the external air conditions refer to the conditions composed of natural ventilation feasibility criteria, external humidity, external temperature, temperature and humidity of the transformer substation interior, and upper limit of humidity target.

10. A smart temperature and humidity control system for the internal environment of a prefabricated substation, applied to the smart temperature and humidity control method for the internal environment of a prefabricated substation as described in any one of claims 1-9, characterized in that, include: Data acquisition module and data analysis module; The data acquisition module and the data analysis module are connected; The data acquisition module acquires multidimensional status data through a data acquisition device. The multidimensional state data includes spatial temperature field distribution data, multi-point humidity data, real-time equipment load current, and meteorological environment data. The data analysis module includes an indicator determination unit, a dynamic adjustment unit, and a result generation unit; The indicator determination unit generates regulation impact indicators based on multidimensional state data; the regulation impact indicators include thermal risk coefficient and condensation probability index. The dynamic adjustment unit generates a target range for temperature and humidity control based on the control impact indicators. The result generation unit generates control results by performing multimodal collaborative control on the target temperature and humidity control range.

Images