Intelligent prefabricated cabin type substation evaluation method and system based on digital twinning

Abstract

This invention discloses an evaluation method and system for intelligent prefabricated substations based on digital twins, belonging to the field of digital twin technology for substations. The method includes the following steps: constructing a digital twin of the enclosure structure of the intelligent prefabricated substation, the digital twin including structural parameters to be identified; using the measured internal temperature as a calibration target, iteratively optimizing the structural parameters to obtain a deduced parameter vector; performing trend decomposition on the deduced parameter vector to obtain an irreversible aging trend term; and evaluating the thermal insulation and sealing performance of the prefabricated enclosure based on the drift of the irreversible aging trend term relative to the enclosure's baseline parameters. This invention addresses the problem of limited evaluation accuracy of intelligent prefabricated substations under complex weather conditions.

Description

Technical Field

[0001] This invention relates to the field of digital twin technology for substations, and more specifically, to an evaluation method and system for intelligent prefabricated substations based on digital twins. Background Technology

[0002] With the construction of the Global Energy Internet and the rapid development of smart grid technology, the construction mode of power infrastructure is undergoing profound changes. As a key node connecting the transmission and distribution networks, the construction form of substations has shifted from the traditional on-site civil engineering model to a delivery-type model of factory prefabrication and modular assembly. Intelligent prefabricated substations, with their significant advantages such as small footprint, short construction period, strong environmental adaptability, and high degree of standardization, have become the preferred solution for modern urban distribution networks and new energy grid integration. While this new type of infrastructure brings construction convenience, it also presents new technical challenges for subsequent operation, maintenance, and full life-cycle management, especially the increasingly prominent issues of thermal performance and airtightness management of its core protective barrier and enclosure structure.

[0003] The existing technology has at least the following problems: Existing technologies mainly rely on threshold alarms based on environmental monitoring data, lacking online quantitative assessment methods for the physical performance of prefabricated cabin enclosure structures. Conventional digital twin applications are mostly limited to three-dimensional visualization, lacking deep computing capabilities based on physical mechanisms, making it difficult to effectively distinguish between reversible environmental fluctuations and irreversible material aging under complex working conditions, resulting in lag and misjudgment in the diagnosis of equipment health status.

[0004] To address the above problems, this invention proposes a solution. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide an evaluation method and system for intelligent prefabricated substations based on digital twins. By constructing a digital twin, parameter inversion is performed to reconstruct and deduce parameter vectors, irreversible aging characteristics are extracted from them, and the performance of the prefabricated module is evaluated based on the drift degree, thereby solving the problem of limited evaluation accuracy of intelligent prefabricated substations under complex weather conditions.

[0006] To achieve the above objectives, the present invention provides the following technical solution: The evaluation method for intelligent prefabricated substations based on digital twins includes the following steps: constructing a digital twin of the enclosure structure of the intelligent prefabricated substation, the digital twin including the structural parameters to be identified; using the measured internal temperature as the calibration target, iteratively optimizing the structural parameters to be identified to obtain a deduced parameter vector; performing trend decomposition on the deduced parameter vector to obtain an irreversible aging trend term; and evaluating the thermal insulation and sealing performance of the prefabricated substation based on the drift of the irreversible aging trend term relative to the reference parameters of the substation.

[0007] In a preferred embodiment, constructing a digital twin of the enclosure structure of the intelligent prefabricated substation includes: discretizing the enclosure structure of the intelligent prefabricated substation into outer wall, core layer, inner wall, and indoor air nodes using the lumped parameter method; constructing an equivalent thermal resistance-capacitance network topology, wherein the network topology includes structural parameters to be identified; the structural parameters to be identified include the equivalent thermal resistance between the nodes, the equivalent thermal capacity of the nodes, and airtightness parameters; establishing dynamic thermal balance differential equations for each node based on the law of conservation of energy; and integrating the equivalent thermal resistance-capacitance network topology and the dynamic thermal balance differential equations for each node to construct a digital twin of the enclosure structure of the intelligent prefabricated substation.

[0008] In a preferred embodiment, the construction of the equivalent thermal resistance-capacitance network topology specifically involves: using equivalent thermal resistance, sequentially connecting the outer wall, core layer, inner wall, and indoor air nodes to form a main heat conduction loop; connecting geothermal capacity in parallel at the outer wall and core layer nodes to construct energy storage branches; converting solar radiation intensity into an equivalent heat flow source acting on the outer wall nodes, and superimposing the heat generated by the equipment inside the cabin as a power source onto the indoor air nodes; and coupling the main heat conduction loop and the energy storage branches to construct the equivalent thermal resistance-capacitance network topology.

[0009] In a preferred embodiment, the process of establishing the dynamic thermal balance differential equations for each node includes calculating the infiltration sensible heat power of the indoor air nodes. Specifically, this involves: calculating the static pressure difference between the inside and outside of the prefabricated cabin based on the ambient wind speed and the fresh air supply of the air conditioning system; calculating the instantaneous infiltration air mass flow rate through the gaps in the prefabricated cabin enclosure structure based on a preset orifice outflow model, airtightness parameters, and the static pressure difference; and converting the instantaneous infiltration air mass flow rate into infiltration sensible heat power by combining the air specific heat capacity and the real-time temperature difference between the inside and outside of the cabin.

[0010] In a preferred embodiment, the iterative optimization of the structural parameters to be identified to obtain the deduced parameter vector specifically involves: setting physical constraints on the structural parameters to be identified, and constructing a multi-dimensional optimization space based on the physical constraints; solving the dynamic thermal balance differential equations of each node to obtain the theoretical response sequence of the cabin temperature of the digital twin; calculating the fitting residual between the theoretical response sequence and the measured cabin temperature based on the root mean square error criterion, and constructing an optimization objective function based on the approximation degree of the residual value; iterating the structural parameters to be identified in the multi-dimensional optimization space based on the optimization objective function until the fitting residual converges to a preset approximation threshold to obtain the deduced parameters at the current time; and arranging the time-series deduced parameters into a deduced parameter vector.

[0011] In a preferred embodiment, the step of performing trend decomposition on the inferred parameter vector to obtain the irreversible aging trend term specifically involves: decomposing the inferred parameter vector into periodic seasonal components, random noise components, and long-term trend components; filtering out the periodic seasonal components and random noise components that are reversibly affected by environmental temperature and humidity, and extracting the long-term trend component as the irreversible aging trend term.

[0012] In a preferred embodiment, the step of determining the drift of the irreversible aging trend term relative to the cabin reference parameters specifically involves: assembling the extrapolated parameter vectors to construct a continuous time-varying trajectory of the extrapolated parameters; extracting a segment of the time-varying trajectory of the extrapolated parameters during the initial stage of prefabricated cabin commissioning and using its statistical mean as the cabin reference parameters; extracting the cross-sectional value of the irreversible aging trend term at the current moment as the real-time state assessment value; constructing a deviation calculation formula to calculate the relative change rate of the equivalent thermal resistance and airtightness parameters in the real-time state assessment value with the corresponding cabin reference parameters, thereby obtaining the equivalent thermal resistance drift and airtightness parameter drift.

[0013] In a preferred embodiment, the evaluation of the insulation and sealing performance of the prefabricated substation specifically involves: comparing the trend of the drift of the equivalent thermal resistance and airtightness parameters with a preset failure threshold to evaluate the insulation and sealing performance of the intelligent prefabricated substation; and generating a health status assessment report for the intelligent prefabricated substation based on the comprehensive evaluation results of its insulation and sealing performance.

[0014] The evaluation system for intelligent prefabricated substations based on digital twins includes: a digital twin construction module for constructing a digital twin of the enclosure structure of the intelligent prefabricated substation, the digital twin including the structural parameters to be identified; a parameter inversion module for iteratively optimizing the structural parameters to be identified using the measured internal temperature as a calibration target to obtain a deduced parameter vector; a trend analysis module for performing trend decomposition on the deduced parameter vector to obtain irreversible aging trend terms; and an evaluation module for evaluating the thermal insulation and sealing performance of the prefabricated substation based on the drift of the irreversible aging trend terms relative to the reference parameters of the substation.

[0015] The technical effects and advantages of the present invention, which is based on a digital twin-based intelligent prefabricated substation evaluation method and system, are as follows: This invention, by constructing a digital twin, enables the identification of the thermal insulation and airtightness performance of the enclosure structure of intelligent prefabricated substations. It performs parameter inversion and reconstruction to deduce parameter vectors, transforming the implicit physical state of the enclosure structure into explicit deduce parameter vectors. Irreversible aging characteristics are extracted from these vectors, environmental interference is eliminated, and a basis reflecting the true health status of the prefabricated modules is provided for their evaluation. Furthermore, the performance of the prefabricated modules is evaluated based on drift, thus solving the problem of limited evaluation accuracy of intelligent prefabricated substations under complex weather conditions. Attached Figure Description

[0016] Figure 1 A schematic diagram of the evaluation method for intelligent prefabricated substations based on digital twins provided in this embodiment of the invention.

[0017] Figure 2 This is a schematic diagram of the structure of an intelligent prefabricated substation evaluation system based on digital twins, provided in an embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1, Figure 1 This invention presents an evaluation method for intelligent prefabricated substations based on digital twins, comprising the following steps: S1, Construct a digital twin of the enclosure structure of the intelligent prefabricated substation, the digital twin including the structural parameters to be identified; S2, using the measured cabin temperature as the calibration target, iteratively optimizes the structural parameters to be identified to obtain the deduced parameter vector; S3, perform trend decomposition on the deduced parameter vector to obtain the irreversible aging trend term; S4. Evaluate the thermal insulation and sealing performance of the prefabricated cabin based on the drift of the irreversible aging trend term relative to the cabin reference parameters.

[0020] S1, constructing a digital twin of the enclosure structure of an intelligent prefabricated substation, the digital twin including the structural parameters to be identified.

[0021] In this embodiment, the digital twin used to construct the enclosure structure of the intelligent prefabricated substation includes: The enclosure structure of the intelligent prefabricated substation is discretized into outer wall, core layer, inner wall and indoor air nodes using the lumped parameter method, and an equivalent thermal resistance-capacitance network topology is constructed. The network topology includes the structural parameters to be identified. The structural parameters to be identified include the equivalent thermal resistance between the nodes, the equivalent heat capacity of the nodes, and the airtightness parameters. The dynamic thermal balance differential equations for each node are established based on the law of conservation of energy. By integrating the equivalent thermal resistance-capacitance network topology and the dynamic thermal balance differential equations of each node, a digital twin of the intelligent prefabricated substation enclosure structure is constructed.

[0022] It should be noted that, based on the law of conservation of energy, a dynamic thermal balance differential equation is established for each node.

[0023] The dynamic thermal equilibrium differential equation for the outer wall node is as follows: , In the formula, For the heat capacity of the outer wall nodes, This represents the total solar radiation intensity. The solar radiation absorption coefficient of the outer wall surface. The effective light-receiving area of ​​the outer wall. For the outer wall node temperature, The ambient temperature, For core node temperature, For external convection heat transfer thermal resistance, For the outer layer's thermal resistance, For time derivative.

[0024] The dynamic thermal equilibrium differential equation for the core node is as follows: , In the formula, For the core node heat capacity, The temperature of the inner wall nodes. This is the thermal resistance of the inner layer.

[0025] The dynamic thermal equilibrium differential equation for the inner wall nodes is as follows: , In the formula, For the heat capacity of the inner wall nodes, This is the internal convection heat transfer thermal resistance.

[0026] The differential equation for the dynamic thermal balance of the indoor air nodes is as follows: , In the formula, For indoor air node heat capacity, The heat output of the electrical equipment inside the cabin. For the fresh air supply to the air conditioning system, For permeation sensible heat power, This refers to the indoor air node temperature.

[0027] It should be noted that the outer wall node temperature represents the thermal state of the outer metal plate and its outer surface, the core layer node temperature represents the thermal state of the intermediate insulation material, the inner wall node temperature represents the thermal state of the inner metal plate and its inner surface, and the indoor air node temperature represents the average thermal state of the air inside the cabin.

[0028] It should be noted that the external convective heat transfer resistance connects the external environment and the outer wall node, the outer thermal conductivity resistance connects the outer wall node and the core node, the inner thermal conductivity resistance connects the core node and the inner wall node, and the internal convective heat transfer resistance connects the inner wall node and the indoor air node.

[0029] In this embodiment, the construction of the equivalent thermal resistivity-capacitance network topology specifically involves: By utilizing the equivalent thermal resistance, the outer wall, core layer, inner wall and indoor air nodes are connected in series to form the main heat conduction loop; Geothermal capacity is connected in parallel to the outer wall and core layer nodes to construct energy storage branches; The solar radiation intensity is converted into an equivalent heat flow source and applied to the outer wall nodes, while the heat generated by the equipment inside the cabin is superimposed as a power source onto the indoor air nodes. Couple the main heat conduction circuit and the energy storage branch to construct an equivalent thermal resistance-capacitance network topology.

[0030] In this embodiment, the process of establishing the dynamic thermal balance differential equations for each node includes calculating the infiltration sensible heat power of the indoor air nodes, specifically: Calculate the static pressure difference between the inside and outside of the prefabricated cabin based on the ambient wind speed and the fresh air supply of the air conditioning system. Based on the pre-set orifice outflow model, and based on the air tightness parameters and air static pressure difference, the instantaneous infiltration air mass flow rate through the gaps in the prefabricated cabin enclosure structure is calculated. By combining the specific heat capacity of air with the real-time temperature difference between the inside and outside of the chamber, the instantaneous infiltration air mass flow rate is converted into infiltration sensible heat power.

[0031] The formula for calculating the instantaneous infiltration air mass flow rate through the gaps in the prefabricated cabin enclosure structure is as follows: , In the formula, For instantaneous infiltration air mass flow rate, The static pressure difference between the inside and outside of the cabin. air density, This refers to the airtightness parameter.

[0032] Furthermore, the instantaneous infiltration air mass flow rate is converted into infiltration sensible heat power.

[0033] The calculation formula for the permeation sensible heat power is as follows: , In the formula, For permeation sensible heat power, This is the specific heat capacity of air.

[0034] It should be noted that the preset orifice outflow model is a physical model based on Bernoulli's equation describing the fluid passing through the orifice, which is existing technology.

[0035] It should be noted that this embodiment calculates the infiltration sensible heat power, mapping the invisible climate disturbances and temperature disturbances of the external environment into the internal calculable heat load, completing the conversion from environmental physical parameters to optimal model parameters. Furthermore, by considering the infiltration heat flow in the digital twin process, the thermal conductivity and insulation performance and airtightness performance of the building envelope can be identified more accurately, thereby eliminating the equivalent thermal resistance inversion deviation caused by ignoring the minute external interactions at the physical mechanism level.

[0036] S2 uses the measured cabin temperature as the calibration target to iteratively optimize the structural parameters to be identified, thereby obtaining the deduced parameter vector.

[0037] In this embodiment, the iterative optimization of the structural parameters to be identified to obtain the derivation parameter vector specifically involves: Physical constraints are set for the structural parameters to be identified, and a multi-dimensional optimization space is constructed based on these physical constraints. Solve the dynamic thermal balance differential equations for each node to obtain the theoretical response sequence of the cabin temperature of the digital twin; Based on the root mean square error criterion, the fitting residual between the theoretical response sequence and the measured cabin temperature is calculated, and the objective function for optimization is constructed based on the degree of approximation of the residual value. Based on the objective function, the structural parameters to be identified are iterated in the multidimensional optimization space until the fitting residual converges to the preset approximation threshold, and the inferred parameters at the current time are obtained. Arrange the time series derivation parameters into a derivation parameter vector.

[0038] It should be noted that the structure parameter vector to be identified is: , In the formula, The parameter vector to be identified.

[0039] It should be noted that the iterative optimization process of the structural parameters to be identified aims to find a set of optimal inference parameters with the goal of minimizing the error between the cabin temperature of the digital twin and the measured cabin temperature. Therefore, an optimization objective function based on root mean square error is constructed.

[0040] The objective function for optimization is specifically formulated as follows: , In the formula, Here, N is the objective function value, N is the number of data points within the observation window, and k is the time step index. To measure the temperature inside the cabin, The cabin temperature of the digital twin.

[0041] Furthermore, during the inversion process, it is necessary to calculate the theoretical temperature curve corresponding to the current candidate inference parameters. In this embodiment, the fourth-order Runge-Kutta method is used to numerically solve the dynamic thermal balance differential equation of each node. The calculation is performed cyclically within the intercepted observation window to obtain the theoretical response sequence of the temperature inside the digital twin cabin.

[0042] The formula for numerically solving the dynamic thermal equilibrium differential equations at each node using the fourth-order Runge-Kutta method is as follows: , In the formula: For digital twins in The theoretical temperature value at that moment, Here, h represents the current time point and h represents the time step. The slope of the starting point of the observation window interval. The first predicted slope at the midpoint of the observation window interval. The second predicted slope is the midpoint of the observation window interval. The slope is the estimated slope at the end of the observation window interval, and n is the step index.

[0043] It should be noted that the iterative process of the structural parameters to be identified within a multidimensional optimization space based on the objective function specifically involves using a particle swarm optimization algorithm to find the minimum objective function value within the multidimensional optimization space. The system converges to a preset minimum value and outputs the current parameter combination as the inference parameters for that time window.

[0044] S3, perform trend decomposition on the inferred parameter vector to obtain the irreversible aging trend term.

[0045] In this embodiment, the process of performing trend decomposition on the inferred parameter vector to obtain the irreversible aging trend term specifically involves: The trend decomposition of the inferred parameter vector is decoupled into periodic seasonal components, random noise components, and long-term trend components; The periodic seasonal components and random noise components that are reversibly affected by ambient temperature and humidity are filtered out, and the long-term trend component is extracted as the irreversible aging trend term.

[0046] It should be noted that, in this embodiment, the step of decomposing the trend of the deduced parameter vector adopts a seasonal trend decomposition algorithm. Specifically, by setting seasonal windows and trend windows, and through inner and outer loop iterations, the Loess smoothing technique is used to gradually separate the periodic term and the trend term.

[0047] The inner loop is used for iterative updates of parameter components. In each inner loop, the algorithm alternately uses Loess smoothing technology to smooth the detrended sequence to update the periodic component, and smooths the de-periodic sequence to update the trend component. Through multiple alternating smoothing, the periodic component and the trend component gradually converge and are decoupled.

[0048] The outer loop is used for robust weighting of outliers. After each round of the inner loop ends, the outer loop is started to calculate the residual weights. For outlier data points that deviate significantly from the fitted curve, the algorithm assigns them very small robust weights. In the Loess smoothing process of the next round of the inner loop, the influence of these outliers will be suppressed.

[0049] It should be noted that filtering out the periodic seasonal component that is reversibly affected by ambient temperature and humidity refers to the fact that, for example, the thermal conductivity of insulation materials (such as rock wool) in smart prefabricated substations fluctuates with moisture content. When the environment dries, the moisture content decreases and the thermal resistance can be restored. However, the structural collapse caused by material aging and pulverization is a change in physical form and cannot be restored with the environment. Therefore, it exhibits a monotonic trend and is regarded as an irreversible aging trend.

[0050] S4. Evaluate the thermal insulation and sealing performance of the prefabricated cabin based on the drift of the irreversible aging trend term relative to the cabin reference parameters.

[0051] In this embodiment, the step of basing the irreversible aging trend term on the drift relative to the cabin reference parameter specifically means: By combining the aforementioned inference parameter vectors, a continuous time-varying trajectory of the inference parameters is constructed; Extract time-varying trajectory segments of the inferred parameters during the initial stage of prefabricated module commissioning, and use their statistical average as the module's baseline parameters; Extract the cross-sectional value of the irreversible aging trend term at the current moment as the real-time status assessment value; A deviation calculation formula is constructed to calculate the relative change rate of the equivalent thermal resistance and airtightness parameters in the real-time state assessment value with the corresponding cabin reference parameters, thereby obtaining the equivalent thermal resistance drift and airtightness parameter drift.

[0052] It should be noted that the initial stage of operation of the prefabricated module refers to a specific operating cycle of the prefabricated module, generally the first three months, during which the equipment parameters are relatively stable.

[0053] The constructed deviation calculation formula is as follows: , In the formula, This represents the rate of change of the real-time condition assessment value relative to the cabin baseline parameters. This is a real-time status assessment value. These are the baseline parameters for the cabin.

[0054] Using the deviation calculation formula, based on the equivalent thermal resistance and airtightness parameters in the cabin reference parameters, the equivalent thermal resistance drift and airtightness parameter drift are calculated respectively.

[0055] In this embodiment, the evaluation of the thermal insulation and sealing performance of the prefabricated cabin specifically includes: Based on the drift of equivalent thermal resistance and airtightness parameters, the change trend of the drift is compared with the preset failure threshold to evaluate the insulation and sealing performance of the intelligent prefabricated substation. Based on the evaluation results of the insulation and sealing performance of the intelligent prefabricated substation, a health status assessment report for the intelligent prefabricated substation is generated.

[0056] It should be noted that the preset failure threshold is set based on the design specifications of integrated intelligent prefabricated substations and historical operation and maintenance experience, with the equivalent thermal resistance drift degree set accordingly. and airtightness parameter drift Table 1 presents the judgment logic for evaluating the insulation and sealing performance of intelligent prefabricated substations, with the failure threshold set in Table 1.

[0057] Table 1

[0058] It should be noted that the deterioration of the thermal insulation performance of the intelligent prefabricated substation can be physically manifested as a decrease in the thermal resistance value, while the deterioration of the sealing performance can be manifested as an increase in the equivalent gap area, that is, an increase in the value of the airtightness parameter.

[0059] Example 2, Figure 2 This invention presents an intelligent prefabricated substation evaluation system based on digital twins, comprising: The digital twin construction module is used to construct a digital twin of the enclosure structure of an intelligent prefabricated substation. The digital twin includes the structural parameters to be identified. The parameter inversion module is used to iteratively optimize the parameters of the structure to be identified by using the measured cabin temperature as the calibration target, and obtain the deduced parameter vector. The trend analysis module is used to perform trend decomposition on the inferred parameter vector to obtain irreversible aging trend terms; The evaluation module is used to assess the thermal insulation and sealing performance of the prefabricated cabin based on the drift of the irreversible aging trend term relative to the cabin reference parameters.

[0060] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0061] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0062] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0063] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0064] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0065] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An evaluation method for intelligent prefabricated substations based on digital twins, characterized in that, Includes the following steps: Construct a digital twin of the enclosure structure of an intelligent prefabricated substation, the digital twin including the structural parameters to be identified; Using the measured cabin temperature as the calibration target, the structural parameters to be identified are iteratively optimized to obtain the deduced parameter vector. Trend decomposition of the inferred parameter vector yields the irreversible aging trend term; The thermal insulation and sealing performance of the prefabricated cabin is evaluated based on the drift of the irreversible aging trend term relative to the cabin reference parameters.

2. The evaluation method for intelligent prefabricated substations based on digital twins according to claim 1, characterized in that, The digital twin used to construct the enclosure structure of the intelligent prefabricated substation includes: The enclosure structure of the intelligent prefabricated substation is discretized into outer wall, core layer, inner wall and indoor air nodes using the lumped parameter method, and an equivalent thermal resistance-capacitance network topology is constructed. The network topology includes the structural parameters to be identified. The structural parameters to be identified include the equivalent thermal resistance between the nodes, the equivalent heat capacity of the nodes, and the airtightness parameters. The dynamic thermal balance differential equations for each node are established based on the law of conservation of energy. By integrating the equivalent thermal resistance-capacitance network topology and the dynamic thermal balance differential equations of each node, a digital twin of the intelligent prefabricated substation enclosure structure is constructed.

3. The evaluation method for intelligent prefabricated substations based on digital twins according to claim 2, characterized in that, The construction of the equivalent thermal resistivity-capacitance network topology specifically involves: By utilizing the equivalent thermal resistance, the outer wall, core layer, inner wall and indoor air nodes are connected in series to form the main heat conduction loop; Geothermal capacity is connected in parallel to the outer wall and core layer nodes to construct energy storage branches; The solar radiation intensity is converted into an equivalent heat flow source and applied to the outer wall nodes, while the heat generated by the equipment inside the cabin is superimposed as a power source onto the indoor air nodes. Couple the main heat conduction circuit and the energy storage branch to construct an equivalent thermal resistance-capacitance network topology.

4. The evaluation method for intelligent prefabricated substations based on digital twins according to claim 2, characterized in that, The process of establishing the dynamic thermal balance differential equations for each node includes calculating the infiltration sensible heat power of the indoor air nodes, specifically: Calculate the static pressure difference between the inside and outside of the prefabricated cabin based on the ambient wind speed and the fresh air supply of the air conditioning system. Based on the pre-set orifice outflow model, and based on the air tightness parameters and air static pressure difference, the instantaneous infiltration air mass flow rate through the gaps in the prefabricated cabin enclosure structure is calculated. By combining the specific heat capacity of air with the real-time temperature difference between the inside and outside of the chamber, the instantaneous infiltration air mass flow rate is converted into infiltration sensible heat power.

5. The evaluation method for intelligent prefabricated substations based on digital twins according to claim 4, characterized in that, The iterative optimization of the structural parameters to be identified to obtain the derivation parameter vector is specifically as follows: Physical constraints are set for the structural parameters to be identified, and a multi-dimensional optimization space is constructed based on these physical constraints. Solve the dynamic thermal balance differential equations for each node to obtain the theoretical response sequence of the cabin temperature of the digital twin; Based on the root mean square error criterion, the fitting residual between the theoretical response sequence and the measured cabin temperature is calculated, and the objective function for optimization is constructed based on the degree of approximation of the residual value. Based on the objective function, the structural parameters to be identified are iterated in the multidimensional optimization space until the fitting residual converges to the preset approximation threshold, and the inferred parameters at the current time are obtained. Arrange the time series derivation parameters into a derivation parameter vector.

6. The evaluation method for intelligent prefabricated substations based on digital twins according to claim 5, characterized in that, The process of performing trend decomposition on the inferred parameter vector to obtain the irreversible aging trend term specifically involves: The trend decomposition of the inferred parameter vector is decoupled into periodic seasonal components, random noise components, and long-term trend components; The periodic seasonal components and random noise components that are reversibly affected by ambient temperature and humidity are filtered out, and the long-term trend component is extracted as the irreversible aging trend term.

7. The evaluation method for intelligent prefabricated substations based on digital twins according to claim 6, characterized in that, The drift of the irreversible aging trend term relative to the cabin reference parameter is specifically as follows: By combining the aforementioned inference parameter vectors, a continuous time-varying trajectory of the inference parameters is constructed; Extract time-varying trajectory segments of the inferred parameters during the initial stage of prefabricated module commissioning, and use their statistical average as the module's baseline parameters; Extract the cross-sectional value of the irreversible aging trend term at the current moment as the real-time status assessment value; A deviation calculation formula is constructed to calculate the relative change rate of the equivalent thermal resistance and airtightness parameters in the real-time state assessment value with the corresponding cabin reference parameters, thereby obtaining the equivalent thermal resistance drift and airtightness parameter drift.

8. The evaluation method for intelligent prefabricated substations based on digital twins according to claim 7, characterized in that, The evaluation of the thermal insulation and sealing performance of the prefabricated cabin specifically includes: Based on the drift of equivalent thermal resistance and airtightness parameters, the change trend of the drift is compared with the preset failure threshold to evaluate the insulation and sealing performance of the intelligent prefabricated substation. Based on the evaluation results of the insulation and sealing performance of the intelligent prefabricated substation, a health status assessment report for the intelligent prefabricated substation is generated.

9. A system using the digital twin-based intelligent prefabricated substation evaluation method as described in any one of claims 1-8, comprising: The digital twin construction module is used to construct a digital twin of the enclosure structure of an intelligent prefabricated substation. The digital twin includes the structural parameters to be identified. The parameter inversion module is used to iteratively optimize the parameters of the structure to be identified by using the measured cabin temperature as the calibration target, and obtain the deduced parameter vector. The trend analysis module is used to perform trend decomposition on the inferred parameter vector to obtain irreversible aging trend terms; The evaluation module is used to assess the thermal insulation and sealing performance of the prefabricated cabin based on the drift of the irreversible aging trend term relative to the cabin reference parameters.

Images