A method, equipment, and medium for assessing the corrosion status of substation grounding grids.

Abstract

This invention relates to a method, equipment, and medium for assessing the corrosion status of a substation grounding grid. The method includes: S11, acquiring multi-dimensional assessment index data and corroded branches of the target grounding grid; S12, obtaining the corrosion rate based on the multi-dimensional assessment index data using a corrosion rate model; S13, determining the corrosion level of the corroded branch based on the corrosion rate, the thickness loss rate of the corroded branch, and the branch resistance increment; S14, determining the remaining lifespan of the target grounding grid based on the corrosion rate and the remaining allowable corrosion thickness; and S15, generating a corrosion status assessment report of the target grounding grid based on the corrosion rate, corroded branches, the corrosion level of the corroded branches, and the remaining lifespan of the target grounding grid. This provides a grounding grid corrosion status assessment technology that integrates multi-factor coupling analysis, precise location, and lifespan prediction.

Description

Technical Field

[0001] This invention relates to the field of power equipment condition monitoring technology, and in particular to a method, equipment and medium for assessing the corrosion status of substation grounding grids. Background Technology

[0002] Substation grounding grids are core infrastructure for ensuring the safe and stable operation of power systems. Their main function is to provide a safe grounding path for power equipment, suppress fault voltage rise, and protect equipment and personnel. However, grounding grids are buried underground for extended periods and are susceptible to soil corrosive media (such as Cl). - SO4 2 The combined effects of multiple factors, such as moisture, pH value, and electrical conditions (e.g., leakage current, fault current), can easily lead to corrosion, resulting in a reduction in conductor cross-section and an increase in branch resistance. In severe cases, it can cause grounding grid failure, thereby inducing power system faults and causing significant economic losses.

[0003] Existing grounding grid corrosion assessment technologies suffer from the following main drawbacks: Traditional assessment methods often rely on single indicators (such as grounding impedance and soil resistivity), failing to consider the synergistic effects of multiple factors coupled on corrosion, resulting in low assessment accuracy; it is difficult to quantify the corrosion acceleration effect in complex environments, and data-driven models suffer from high dependence on training data and large prediction errors in small sample scenarios; thirdly, existing technologies can only achieve qualitative judgments on the degree of corrosion, failing to accurately locate corroded branches and predict remaining lifespan, making it difficult to support the precise implementation of operation and maintenance decisions; fourthly, the assessment process does not fully consider uncertainties such as parameter fluctuations and measurement errors, leading to insufficient reliability of the assessment results.

[0004] Therefore, developing a grounding grid corrosion status assessment technology that takes into account multi-factor coupling analysis, precise positioning, life prediction, and uncertainty control has become an urgent technical problem to be solved in the current power operation and maintenance field. Summary of the Invention

[0005] One of the objectives of this invention is to provide a method, equipment, and medium for assessing the corrosion status of substation grounding grids.

[0006] According to one aspect of this application, a method for assessing the corrosion status of a substation grounding grid is provided, the method comprising: S11. Obtain multi-dimensional evaluation index data and corrosion branches of the target grounding network; wherein, the target grounding network is equivalent to a resistance network including N nodes and M branches, and the corrosion branches include branches whose resistance increment is equal to or greater than the target threshold, and N and M are positive integers. S12. Based on multi-dimensional evaluation index data, the corrosion rate is obtained through a corrosion rate model. S13. Determine the corrosion level of the corrosion branch based on the corrosion rate, the thickness loss rate of the corrosion branch, and the increase in branch resistance. S14. Determine the remaining life of the target grounding grid based on the corrosion rate and the remaining allowable corrosion thickness; S15. Generate a corrosion status assessment report for the target grounding grid based on the corrosion rate, corrosion branch, corrosion level of the corrosion branch, and remaining life of the target grounding grid.

[0007] According to another aspect of this application, a computer device is provided, including a memory and a processor, wherein a computer program capable of being loaded by the processor and executing the methods described above is stored in the memory.

[0008] According to another aspect of this application, a computer-readable storage medium is provided, storing a computer program that can be loaded by a processor and executed as described above.

[0009] Compared with existing technologies, this application obtains the corrosion branches of the target grounding network by equating the target grounding network with a resistance network including N nodes and M branches, thereby accurately locating the corrosion branches of the target grounding network. Based on the multi-dimensional evaluation index data of the target grounding network, the corrosion rate is obtained through a corrosion rate model. A multi-dimensional evaluation index system is introduced to comprehensively consider the synergistic influence of multiple factors on corrosion, improving the comprehensiveness and reliability of the evaluation results. The corrosion rate calculation and corrosion branch location are completed. Furthermore, the corrosion level of the corrosion branch is determined based on the corrosion rate, the thickness loss rate of the corrosion branch, and the branch resistance increment. The remaining lifetime of the target grounding network is determined according to the corrosion rate and the remaining allowable corrosion thickness, realizing the prediction of the remaining lifetime of the target grounding network. A corrosion status assessment report including corrosion rate, each corrosion branch, the corrosion level of each corrosion branch, and the remaining lifetime of the target grounding network is generated. This provides a grounding network corrosion status assessment technology that takes into account multi-factor coupling analysis, accurate location, and lifetime prediction. Attached Figure Description

[0010] Figure 1 A flowchart of a method for assessing the corrosion status of a substation grounding grid according to an embodiment of this application is shown; Figure 2 A schematic diagram of a substation grounding grid corrosion status assessment device according to an embodiment of this application is shown. Figure 3 Exemplary systems that can be used to implement the various embodiments described in this application are shown. Detailed Implementation

[0011] The present application will now be described in further detail with reference to the accompanying drawings.

[0012] In a typical configuration of this application, the terminal, the device of the service network, and the trusted party all include one or more processors (e.g., a central processing unit (CPU)), input / output interfaces, network interfaces, and memory.

[0013] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory. Memory is an example of computer-readable media.

[0014] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PCM), programmable random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0015] The devices referred to in this application include, but are not limited to, terminals, network devices, or devices formed by integrating terminals and network devices through a network. The terminals include, but are not limited to, any mobile electronic product capable of human-computer interaction (e.g., via a touchpad), such as smartphones and tablets. These mobile electronic products can use any operating system, such as Android or iOS. The network devices include electronic devices capable of automatically performing numerical calculations and information processing according to pre-set or stored instructions. Their hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), and embedded devices. The network devices include, but are not limited to, computers, network hosts, single network servers, multiple network server clusters, or clouds composed of multiple servers. Here, a cloud consists of a large number of computers or network servers based on cloud computing, where cloud computing is a type of distributed computing, consisting of a virtual supercomputer composed of a group of loosely coupled computer clusters. The network includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, VPN network, wireless ad hoc network, etc. Preferably, the device can also be a program running on the terminal, network device, or a device formed by integrating the terminal and network device, network device, touch terminal, or network device and touch terminal through a network.

[0016] Of course, those skilled in the art should understand that the above-described devices are merely examples, and other existing or future devices that are applicable to this application should also be included within the scope of protection of this application, and are hereby incorporated by reference.

[0017] In the description of this application, "multiple" means two or more, unless otherwise expressly and specifically defined.

[0018] refer to Figure 1This invention provides a method for assessing the corrosion status of a substation grounding grid, comprising steps S11, S12, S13, S14, and S15. In step S11, multi-dimensional assessment index data and corrosion branches of the target grounding grid are acquired; wherein the target grounding grid is equivalent to a resistance network including N nodes and M branches, and the corrosion branches include branches whose resistance increment is equal to or greater than a target threshold, where N and M are positive integers; in step S12, the corrosion rate is obtained based on the multi-dimensional assessment index data using a corrosion rate model; in step S13, the corrosion level of the corrosion branch is determined according to the corrosion rate, the thickness loss rate of the corrosion branch, and the branch resistance increment; in step S14, the remaining lifetime of the target grounding grid is determined according to the corrosion rate and the remaining allowable corrosion thickness; in step S15, a corrosion status assessment report of the target grounding grid is generated based on the corrosion rate, corrosion branches, the corrosion level of the corrosion branches, and the remaining lifetime of the target grounding grid.

[0019] Specifically, in step S11, multi-dimensional evaluation index data and corrosion branches of the target grounding network are acquired. The target grounding network is equivalent to a resistance network comprising N nodes and M branches. Corrosion branches include branches whose resistance increment is equal to or greater than the target threshold, where N and M are positive integers. In some embodiments, the multi-dimensional evaluation index data includes, but is not limited to, soil environmental parameters, electrical condition parameters, conductor characteristic parameters, and maintenance record parameters. In some embodiments, nodes include welding points between grounding network conductors, conductor ends, and downlead connection points extending above the ground. Branches include metal conductor segments between two adjacent nodes. In some embodiments, the initial reference resistance of a branch can be calculated based on the conductor's material, cross-sectional area, length, etc. For example, the target grounding network is equivalent to a resistance network with 32 nodes and 48 branches. In some embodiments, the branch resistance increment includes, but is not limited to, the ratio between the difference between the actual resistance of the branch and the initial reference resistance and the initial reference resistance. For example, by calculating the difference ΔR = (R1 - R0) between the actual resistance R1 and the initial reference resistance R0 of branch a, the branch resistance increment of branch a = ΔR / R0. If ΔR / R0 equals the target threshold, then branch a is determined to be a corrosion branch. For the specific process of determining corrosion branches, please refer to the corresponding embodiments below, which will not be elaborated here.

[0020] In step S12, the corrosion rate is obtained through a corrosion rate model based on multi-dimensional evaluation index data. In some embodiments, the corrosion rate includes, but is not limited to, the rate of corrosion, typically expressed in mm / year. For example, v = 0.02 mm / year, v = 0.20 mm / year. In some embodiments, the corrosion rate of the target grounding network can be obtained through a corrosion rate model based on multi-dimensional evaluation index data of the target grounding network. In other embodiments, the corrosion rate of the corrosion branch can also be obtained through a corrosion rate model based on multi-dimensional evaluation index data of the corrosion branch. In some embodiments, the corrosion rate model includes, but is not limited to, a backpropagation neural network model or a combination of an electrochemical corrosion rate model and a grey prediction model. In this embodiment, to improve the prediction accuracy of the corrosion rate, two model prediction algorithms are provided; the combination model of the electrochemical corrosion rate model and the grey prediction model is for small sample or newly built substation scenarios; the backpropagation neural network model is for large sample scenarios. Different algorithm structures are provided based on different corrosion rate models to improve the accuracy of the corrosion rate. For a detailed explanation of obtaining the corrosion rate through the corrosion rate model, please refer to the corresponding embodiments below, which will not be repeated here.

[0021] In step S13, the corrosion level of the corroded branch is determined based on the corrosion rate, the thickness loss rate of the corroded branch, and the branch resistance increment. In some embodiments, the thickness loss rate includes the ratio between the branch's loss degree and its initial thickness. In some embodiments, the branch's loss degree can be obtained based on the loss rate. For example, the loss degree is equal to the product of the loss rate and time. In some embodiments, the corrosion rate can be the corrosion rate of the target grounding grid or the corrosion rate of the corroded branch. In some embodiments, the system presets corrosion rate ranges, thickness loss rate ranges, and branch resistance increment ranges corresponding to different corrosion levels, so as to determine the corrosion level of the corroded branch based on the corrosion rate of the target grounding grid, the thickness loss rate, and the branch resistance increment. For example, corrosion levels are divided into 5 grades: Grade 0 (slight corrosion): corrosion rate range includes v < 0.02 mm / year, thickness loss rate range includes thickness loss rate < 5%, and branch resistance increment range includes branch resistance increment ΔR / R0 < 2%; Grade 1 (mild corrosion): corrosion rate range includes 0.02 ≤ v < 0.05 mm / year, thickness loss rate range includes thickness loss rate 5–10%, and branch resistance increment range includes branch resistance increment 2% ≤ ΔR / R0 < 5%; Grade 2 (moderate corrosion): corrosion rate range includes 0.05 ≤ v < 0.10 mm / year, thickness loss rate < 0.02 mm / year, thickness loss rate < 0.05 ...5 mm / year, thickness loss rate < 0.05 mm / year, thickness loss rate < 0.05 mm / year, thickness loss rate < 0.05 mm / year, thickness loss rate < 0.05 mm / year, thickness loss rate < 0.05 mm / year, thickness loss rate < 0.05 mm / year, thickness loss rate < 0.05 mm / year, thickness loss rate < 0. The corrosion rate range includes: thickness loss rate 10–20%; branch resistance increment range includes: branch resistance increment 5% ≤ ΔR / R0 < 10%; Level 3 (severe corrosion): corrosion rate range includes: 0.10 ≤ v < 0.20 mm / year; thickness loss rate range includes: thickness loss rate 20–30%; branch resistance increment range includes: branch resistance increment 10% ≤ ΔR / R0 < 20%; Level 4 (fracture risk): corrosion rate range includes: v ≥ 0.20 mm / year; thickness loss rate range includes: thickness loss rate ≥ 30%; branch resistance increment range includes: branch resistance increment ΔR / R0 ≥ 20%. Of course, those skilled in the art will understand that the specific correspondence between the corrosion rate range, thickness loss rate range, branch resistance increment range, and corrosion level described above is merely specific. Other existing or future possible correspondences between corrosion rate ranges, thickness loss rate ranges, branch resistance increment ranges, and specific corrosion levels, if applicable to this application, are also within the scope of protection of this application and are incorporated herein by reference.

[0022] In step S14, the remaining lifetime of the target grounding grid is determined based on the corrosion rate and the remaining allowable corrosion thickness. In some embodiments, t = Δt_rem / v, where t includes the remaining lifetime, v includes the corrosion rate, and Δt_rem includes the remaining allowable corrosion thickness (mm). In some embodiments, the remaining allowable corrosion thickness = maximum allowable corrosion thickness - current corroded thickness. In some embodiments, the maximum allowable corrosion thickness t_limit = t0 × 30% (or calculated based on the thermal stability of the substation grounding grid), where t0 includes the initial thickness. In some embodiments, the current corroded thickness can be determined based on the branch resistance increment. For example, the current cross-sectional area is calculated based on R = ρ × (L / S), and then the current thickness is calculated. Here, R includes the actual resistance of the corroded branch, ρ includes the resistivity, S includes the current cross-sectional area, and L includes the length of the corroded branch. The current corroded thickness is equal to the initial thickness minus the current thickness. In some embodiments, the corrosion rate can be the corrosion rate of the target grounding grid or the corrosion rate specific to the corroded branch. The remaining allowable corrosion thickness can be the remaining allowable corrosion thickness of the target grounding grid or the remaining allowable corrosion thickness specific to the corroded branch. For example, if the corrosion rate is the corrosion rate of the target grounding grid, and the remaining allowable corrosion thickness is the remaining allowable corrosion thickness of the target grounding grid, then the remaining lifetime of the target grounding grid can be directly obtained based on the above formula for calculating the remaining lifetime. As another example, if the corrosion rate is the corrosion rate of the target grounding grid, and the remaining allowable corrosion thickness is the remaining allowable corrosion thickness specific to a corrosion branch, then the remaining lifetime of the target grounding grid can be determined based on the minimum remaining allowable corrosion thickness and the corrosion rate of the target grounding grid. Yet another example, if the corrosion rate is the corrosion rate specific to a corrosion branch, and the remaining allowable corrosion thickness is the remaining allowable corrosion thickness of the target grounding grid, then the remaining lifetime of the target grounding grid can be determined based on the maximum corrosion rate and the remaining allowable corrosion thickness. Finally, if the corrosion rate is the corrosion rate specific to a corrosion branch, and the remaining allowable corrosion thickness is also specific to a corrosion branch, then the remaining lifetime of each corrosion branch is determined based on its corrosion rate and remaining allowable corrosion thickness, and the minimum remaining lifetime is determined as the remaining lifetime of the target grounding grid.

[0023] In step S15, a corrosion status assessment report for the target grounding grid is generated based on the corrosion rate, corroded branches, corrosion levels of the corroded branches, and the remaining lifespan of the target grounding grid. For example, the corrosion rate, the corrosion levels of each corroded branch of the target grounding grid, and the remaining lifespan of the target grounding grid are statistically included in the corrosion status assessment report so that the user can clearly understand the corrosion status of the target grounding grid. The output assessment report states: The substation grounding grid is classified as Level 1, with mild corrosion. Three corroded branches have been located, and the remaining lifespan is 56–64 years. Enhanced monitoring (testing every 6 years) is recommended, and anti-corrosion coatings should be applied to the corroded branches.

[0024] In some embodiments, obtaining a corroded branch includes: acquiring the measured voltage value of each node using a potentiometer; wherein the measured voltage value is generated by injecting a current with known electrical parameters into the resistor network; based on the measured voltage value of each node, solving for the actual resistance of each branch using the Newton-Raphson algorithm; for each branch, determining the branch resistance increment by comparing the actual resistance of the branch with an initial reference resistance; if the branch resistance increment is equal to or greater than a target threshold, the branch is determined to be a corroded branch. In some embodiments, the known electrical parameters include, but are not limited to, frequency, current magnitude, etc. Typically, a low-frequency sinusoidal current is injected into the resistor network. For example, a 5Hz low-frequency sinusoidal current with an amplitude of 1A is injected into the resistor network. A high-precision potentiometer (accuracy ±1μV) is used to measure the measured voltage value of each node. Further, based on the measured voltage value of each node, the actual resistance of each branch is solved using the Newton-Raphson algorithm (for a detailed explanation of this part, please refer to the corresponding embodiments below, which will not be repeated here). For each branch, the actual resistance of the branch is subtracted from its initial reference resistance, and then divided by the initial reference resistance to obtain the branch resistance increment. The system presets a target threshold; if the branch resistance increment is equal to or greater than the target threshold, the branch is identified as a corrosion branch. For example, branches numbered 12#, 25#, and 37# are identified as corrosion branches if their resistance increment exceeds 10%. In this embodiment, the Newton-Raphson algorithm is used to accurately locate corrosion branches in the target grounding grid.

[0025] In some embodiments, the actual resistance of each branch is solved using the Newton-Raphson algorithm based on the measured voltage values ​​of each node. This includes: calculating the simulated voltage value of each node based on the current simulated resistance and establishing the current node voltage-branch current equation; wherein the current node voltage-branch current equation includes the current sensitivity of the voltage of each node to the resistance of each branch; determining the voltage difference of each node based on the simulated voltage value and the measured voltage value of each node; if there is a node whose voltage difference is equal to or greater than the target difference, determining the resistance adjustment value of each branch based on the current node voltage-branch current equation and the voltage difference, so as to adjust the current simulated resistance of each branch based on the resistance adjustment value; repeating the above steps of determining the current node voltage-branch current equation and the current simulated resistance based on the adjusted current simulated resistance of each branch until the voltage difference of each node is less than the target difference. In some embodiments, the initial value of the current simulated resistance can be randomly determined by the system, or an initial reference resistance can be used as the initial value. Based on the initial value, the algorithm of this embodiment is repeatedly iterated to the actual resistance. For example, a resistor network includes nodes 1, 2, 3, branch A between nodes 1 and 2, branch B between nodes 1 and 3, and branch C between nodes 2 and 3. Branch A corresponds to resistor R1, branch B to resistor R2, and branch C to resistor R3. The current simulated resistance of R1, R2, and R3 is 2Ω, and the calculated simulated voltages of nodes 1, 2, and 3 should be V1, V2, and V3, respectively. The measured voltage values ​​of nodes 1, 2, and 3 are v1, v2, and v3, respectively, and the voltage differences between nodes 1, 2, and 3 are ΔV1(v1-V1), ΔV2(v2-V2), and ΔV3(v3-V3), respectively. There are nodes (e.g., nodes 1 and 2) with voltage differences greater than the target difference (0.00001V). In some embodiments, the node voltage-branch current equation includes the current sensitivity of the voltage of each node to the resistance of each branch. For example, the node voltage-branch current equation specifically involves a sensitivity matrix, which establishes a linear relationship between the change in node voltage and the adjustment of branch resistance. For instance, the first row of the sensitivity matrix includes elements such as ∂V1 / ∂R1, ∂V1 / ∂R2, and ∂V1 / ∂R3; the second row includes elements such as ∂V2 / ∂R1, ∂V2 / ∂R2, and ∂V2 / ∂R3; and the third row includes elements such as ∂V3 / ∂R1, ∂V3 / ∂R2, and ∂V3 / ∂R3. Taking ∂V1 / ∂R1 as an example, it represents the sensitivity (or partial derivative) of the voltage at node 1 to the change in resistance of branch A; that is, the corresponding change in voltage at node 1 when the resistance of branch A changes slightly. In some embodiments, the product of the current sensitivity matrix and the resistance adjustment value of each branch is equal to the voltage difference of each node; the resistance adjustment value of each branch is obtained by solving the matrix equation.For example, specifically, a resistance adjustment vector containing the resistance adjustment values ​​of each branch and a voltage difference vector containing the voltage differences of each node are constructed. Based on the linear relationship that the product of the current sensitivity matrix and the resistance adjustment vector equals the voltage difference vector, the matrix equation is solved to obtain the resistance adjustment value of each branch. Further, based on the resistance adjustment value of each branch and the current simulated resistance of each branch, the adjusted current simulated resistance of each branch is obtained. For example, the adjusted current simulated resistance = the original current simulated resistance + the corresponding resistance adjustment value. The above steps are repeated based on the adjusted current simulated resistance until all voltage differences are less than the target difference, and the current simulated resistance of each branch is taken as the actual resistance of each branch.

[0026] In some embodiments, establishing the current node voltage-branch current equation based on the current simulated resistance includes: calculating the original branch current distribution of the resistor network based on the current simulated resistance of each branch; establishing an adjoint network with the same topology as the resistor network and the same branch resistance value as the current simulated resistance value; applying a unit current excitation to the node positions corresponding to each node to be measured in the adjoint network, and calculating the adjoint branch current distribution in the adjoint network; wherein, the nodes to be measured include nodes whose voltage sensitivity to each branch resistance is to be determined; calculating the current sensitivity of each node's voltage to each branch resistance based on the product of the original branch current distribution and the adjoint branch current distribution, thereby establishing the current node voltage-branch current equation. In this embodiment, specifically, the current node voltage-branch current equation is established based on Tellegen's theorem. For example, based on the topology of the resistor network and the current simulated resistance of each original branch, the original branch current is calculated based on Kirchhoff's laws, thereby obtaining the original branch current distribution of the resistor network. In some embodiments, the topology of the adjoint network is the same as that of the resistive network, and the resistance values ​​of each branch in the adjoint network are the same as the current simulated resistance of the corresponding original branch in the resistive network. For example, for the three-node resistive network described above, a low-frequency current of 3A is injected into node 1, and the currents of each original branch in the resistive network (e.g., IA, IB, IC) are calculated using Kirchhoff's laws based on the current simulated resistance. In the adjoint network, to obtain the current sensitivity of the voltage of node 3 to the resistance of each branch, a unit current of 1A is applied to node 3 of the adjoint network (while removing the excitation source from the resistive network in the adjoint network). Based on the current simulated resistance, the currents of each branch in the adjoint network (e.g., Ia, Ib, Ic) are calculated using Kirchhoff's laws. Then, based on Tellegen's theorem, the current sensitivities of node 3 to each of the three branches are -IA×Ia, -IB×Ib, and -IC×Ic, respectively. Similarly, by applying a unit current excitation to nodes 1 and 2 of the adjoint network, the above steps are repeated to calculate the current sensitivity (i.e., the other row elements of the current sensitivity matrix) for nodes 1 and 2 respectively.

[0027] In some embodiments, the corrosion rate model includes a backpropagation neural network model. Step S12 includes: inputting a standardized dataset into the backpropagation neural network model to output the corrosion rate; wherein the standardized dataset is obtained based on multi-dimensional evaluation index data; the neural network model is obtained by: randomly generating multiple sets of initial model parameters based on the topology of the backpropagation neural network model; inputting the training standardized dataset into the backpropagation neural network model corresponding to each set of initial model parameters for prediction, obtaining multiple prediction results; wherein the training standardized dataset corresponds to corrosion rate label data; using the error between each prediction result and the corrosion rate label data as an evaluation index, performing selection, crossover, and mutation operations on multiple sets of initial model parameters, so as to obtain the optimal initial model parameters with the smallest error after iterative evolution of a preset number of generations; assigning the optimal initial model parameters to the backpropagation neural network model, and training the backpropagation neural network model using the training standardized dataset and the corrosion rate label data until the error between the prediction result output by the backpropagation neural network model and the corrosion rate label data satisfies the preset convergence condition, thereby obtaining the corrosion rate model. For example, in cases with large samples and large amounts of data, the erosion rate can be directly output by inputting the standardized dataset into the backpropagation neural network model (error backpropagation neural network model). In some embodiments, the standardized dataset is obtained by preprocessing multi-dimensional evaluation index data. For details on this part, please refer to the corresponding embodiments below, which will not be repeated here. In some embodiments, the topology of the backpropagation neural network model includes, but is not limited to, an input layer, a hidden layer, and an output layer. For example, the topology of the backpropagation neural network includes: 10 neurons in the input layer (e.g., corresponding to 10 preprocessed standardized data); two hidden layers, with 16 neurons in the first layer and ReLU activation function, and 8 neurons in the second layer and ReLU activation function; and 1 neuron in the output layer (corresponding to the erosion rate); with Linear activation function. In this embodiment, a genetic algorithm is used to improve the speed of determining model parameters, thereby quickly obtaining a trained backpropagation neural network model. For example, multiple sets of initial model parameters are randomly generated, and the optimal initial model parameters are obtained based on these multiple sets of initial model parameters using a genetic algorithm. In some embodiments, to distinguish between the standardized dataset used when applying the model and the standardized dataset used when building the model, the standardized dataset used when building the model is referred to here as the training standardized dataset, which corresponds to erosion rate label data. The training standardized dataset is input into the backpropagation neural network model corresponding to each initial model parameter to obtain multiple prediction results. For each prediction result, the prediction result is subtracted from the corresponding erosion rate label data to obtain the erosion rate error.The multiple sets of initial model parameters are selected, crossovered, and mutated to obtain the optimal initial model parameters. For example, initial model parameters with small corrosion rate errors (e.g., less than the target corrosion rate error, or the last n corrosion rate errors in descending order of corrosion rate) are retained to perform a selection operation on multiple sets of initial model parameters. For the selected initial model parameters, crossover and mutation operations are performed. For example, the initial model parameters to be retained include: [x1, x2, x3, x4, x5, x6, x7, x8, x9, x10], [y1, y2, y3, y4, y5, y6, y7, y8, y9, y10], [z1, z2, z3, z4, z5, z6, z7, z8, z9, z10]. x2 and y2 are randomly swapped, x7 and y7 are randomly swapped, and z6 and z8 are randomly mutated, etc., to perform crossover and mutation operations on the initial model parameters. After a preset number of iterations (e.g., 100 generations), the optimal initial model parameters with the highest fitness are obtained. In some embodiments, the error between each prediction result and the corrosion rate label data is used as an evaluation metric to construct a fitness function. For example, the smaller the error, the higher the fitness. The optimal initial model parameters are assigned to the model parameters of the backpropagation neural network model. Using multiple training normalized datasets and the corresponding corrosion rate label data for each training normalized dataset, the model is trained through the backpropagation correction mechanism of the backpropagation neural network model itself until the error between the prediction result output by the backpropagation neural network model and the corrosion rate label data satisfies a preset convergence condition, thus obtaining the corrosion rate model.

[0028] In some embodiments, a standardized dataset is obtained by preprocessing the dataset, including: acquiring multi-dimensional evaluation index data; wherein the multi-dimensional evaluation index data includes soil environmental parameters, electrical operating condition parameters, conductor characteristic parameters, and operation and maintenance record parameters; and preprocessing the multi-dimensional evaluation index data to obtain the standardized dataset. In some embodiments, soil environmental parameters include, but are not limited to, pH value, soil resistivity, and Cl. - Content, SO4 2- Content, moisture content, etc. In some embodiments, electrical operating condition parameters include, but are not limited to, annual growth rate of grounding resistance, leakage current density, etc. In some embodiments, conductor characteristic parameters include, but are not limited to, material, initial thickness, cross-sectional area, galvanizing thickness, etc. In some embodiments, maintenance record parameters include, but are not limited to, whether the facility is cathodic protection, overhaul records, whether there is chemical pollution in the surrounding area, etc. For example, soil environmental parameters are collected by soil parameter sensors: pH=7.2, soil resistivity ρ_s=150Ω·m, Cl - Content C_Cl=300mg / kg, SO4 2-The soil composition is: C_SO4 = 500 mg / kg, moisture content W = 15%; electrical parameters are collected through the electrical parameter monitoring unit: annual growth rate of grounding resistance is 1.2% / year, leakage current density J_leak = 0.1 A / m²; conductor characteristic parameters are obtained through design drawings and ultrasonic testing: material is galvanized steel, initial thickness t0 = 8 mm, cross-sectional area S = 480 mm², galvanizing thickness is 0.8 mm; maintenance records are entered: no cathodic protection has been implemented, no major repair records in the past 5 years, and no chemical pollution in the surrounding area. In some embodiments, soil parameter sensors include, but are not limited to, pH sensors, soil resistivity sensors, ion sensors, and moisture content sensors; the electrical parameter monitoring unit includes, but is not limited to, branch resistance testers and leakage current monitors; the conductor testing equipment includes, but is not limited to, ultrasonic detectors and eddy current detectors. In some embodiments, preprocessing includes, but is not limited to, removing abnormal data and normalization processing. For example, outlier data is removed using the 3σ criterion; all parameters are normalized to the [0,1] interval, such as pH=7.2 after normalization as (7.2-3.5) / (10.0-3.5)=0.57; there is no missing data, so the standardized dataset is output directly.

[0029] In some embodiments, the multi-dimensional evaluation index data includes electrical operating condition parameters and conductor characteristic parameters, and the corrosion rate model includes an electrochemical corrosion rate model and a grey prediction model. Step S12 includes: obtaining multiple historical corrosion rates arranged in chronological order by substituting multiple sets of electrical operating condition parameters and conductor characteristic parameters into the electrochemical corrosion rate model; wherein, the multiple sets of electrical operating condition parameters are arranged in chronological order; and inputting the multiple historical corrosion rates arranged in chronological order into the grey prediction model to obtain the corrosion rate of the target grounding grid. For example, in the case of small samples or newly built substations, the corrosion rate can be predicted by combining the electrochemical corrosion rate model and the grey prediction model. In some embodiments, the calculation formula of the electrochemical corrosion rate model includes: v=k×i_corr×M / (n×F×ρ); where k is the corrosion rate coefficient (taken as 8.76×10). 4 In this model, i_corr represents the corrosion current density (μA / cm²), M represents the molar mass of the metal (55.85 g / mol for galvanized steel), n represents the electron transfer number (n=2 for iron), F represents the Faraday constant (96500 C / mol), and ρ represents the metal density (7.85 g / cm³ for steel). Multiple sets of electrical operating condition parameters and conductor characteristic parameters arranged in chronological order are substituted into the electrochemical corrosion rate model to obtain multiple historical corrosion rates arranged in chronological order. These historical corrosion rates are then input into a grey prediction model to obtain the corrosion rate. In some embodiments, the grey prediction model is a GM(1,1) model with a background value weight of 0.5 and a prediction step size of 1-5 years. By mining trends in small sample data, corrosion trend prediction is completed.

[0030] In some embodiments, the method further includes step S16 (not shown): based on multi-dimensional evaluation index data, setting uncertain parameters and fluctuation ranges to obtain multiple sets of random multi-dimensional evaluation index data; based on the multiple sets of random multi-dimensional evaluation index data, obtaining multiple corrosion rates through a corrosion rate model to statistically obtain a corrosion rate confidence interval that meets the target confidence level; determining the remaining lifetime confidence interval of the target grounding grid under the target confidence level based on the corrosion rate confidence interval and the remaining allowable corrosion thickness. In some embodiments, to improve accuracy, the Monte Carlo method is used to quantify the impact of parameter fluctuations and measurement errors on the evaluation results, and output the evaluation results with confidence intervals. For example, setting uncertain parameters and fluctuation ranges: soil resistivity ±10%, leakage current density ±15%, corrosion current density ±8%; each simulation randomly selects parameter values ​​and substitutes them into the corrosion rate model to calculate the corrosion rate, and finally statistically obtains a 95% confidence interval for the corrosion rate as [0.038, 0.042] mm / year. The remaining 95% confidence interval is calculated based on a 95% confidence interval of [0.038, 0.042] mm / year and the remaining allowable corrosion thickness (e.g., the remaining 95% confidence interval is [56, 64] years).

[0031] Figure 2 A schematic diagram of a substation grounding grid corrosion status assessment device according to an embodiment of this application is shown. The device includes modules one, two, three, four, and five. Module one is used to acquire multi-dimensional assessment index data and corrosion branches of the target grounding grid; wherein, the target grounding grid is equivalent to a resistance network including N nodes and M branches, and the corrosion branches include branches whose branch resistance increment is equal to or greater than the target threshold, where N and M are positive integers; module one is used to obtain the corrosion rate based on the multi-dimensional assessment index data through a corrosion rate model; module one is used to determine the corrosion level of the corrosion branch according to the corrosion rate, the thickness loss rate of the corrosion branch, and the branch resistance increment; module one is used to determine the remaining lifetime of the target grounding grid according to the corrosion rate and the remaining allowable corrosion thickness; module one is used to generate a corrosion status assessment report of the target grounding grid according to the corrosion rate, corrosion branches, corrosion level of the corrosion branches, and remaining lifetime of the target grounding grid.

[0032] Here, the specific implementation methods corresponding to Module 1, Module 2, Module 3, Module 4, and Module 5 are the same as or similar to the specific embodiments of steps S11, S12, S13, S14, and S15 above, and therefore will not be repeated here, but are included by reference.

[0033] In addition to the methods and devices described in the above embodiments, this application also provides a computer-readable storage medium storing computer code that, when executed, performs the method described in any of the preceding embodiments.

[0034] This application also provides a computer program product that, when executed by a computer device, performs the method described in any of the preceding claims.

[0035] This application also provides a computer device, the computer device comprising: One or more processors; Memory, used to store one or more computer programs; When the one or more computer programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the method as described in any of the preceding methods.

[0036] Figure 3 Exemplary systems that can be used to implement the various embodiments described in this application are shown; like Figure 3 As shown in some embodiments, system 300 can function as any of the devices described in each of the embodiments. In some embodiments, system 300 may include one or more computer-readable media having instructions (e.g., system memory or NVM / storage device 320) and one or more processors (e.g., one or more processors 305) coupled to the one or more computer-readable media and configured to execute the instructions to implement the module and thus perform the actions described in this application.

[0037] In one embodiment, the system control module 310 may include any suitable interface controller to provide any suitable interface to at least one of the processors 305 and / or any suitable device or component communicating with the system control module 310.

[0038] The system control module 310 may include a memory controller module 330 to provide an interface to the system memory 315. The memory controller module 330 may be a hardware module, a software module, and / or a firmware module.

[0039] System memory 315 can be used, for example, to load and store data and / or instructions for system 300. In one embodiment, system memory 315 may include any suitable volatile memory, such as suitable DRAM. In some embodiments, system memory 315 may include double data rate type quad synchronous dynamic random access memory (DDR4 SDRAM).

[0040] In one embodiment, the system control module 310 may include one or more input / output (I / O) controllers to provide interfaces to the NVM / storage device 320 and (one or more) communication interfaces 325.

[0041] For example, NVM / storage device 320 may be used to store data and / or instructions. NVM / storage device 320 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (one or more) non-volatile storage devices (e.g., one or more hard disk drives (HDDs), one or more optical disc drives (CDs), and / or one or more digital universal optical disc (DVD) drives).

[0042] NVM / storage device 320 may include storage resources that are physically part of a device on which system 300 is mounted, or that can be accessed by the device without necessarily being part of it. For example, NVM / storage device 320 may be accessed via a network through one or more communication interfaces 325.

[0043] One or more communication interfaces 325 may provide the system 300 with an interface to communicate over one or more networks and / or with any other suitable device. The system 300 may wirelessly communicate with one or more components of a wireless network in accordance with any of one or more wireless network standards and / or protocols.

[0044] In one embodiment, at least one of the processors 305 may be logically packaged with one or more controllers of the system control module 310 (e.g., memory controller module 330). In one embodiment, at least one of the processors 305 may be logically packaged with one or more controllers of the system control module 310 to form a system-in-package (SiP). In one embodiment, at least one of the processors 305 may be integrated with the logic of one or more controllers of the system control module 310 on the same die. In one embodiment, at least one of the processors 305 may be integrated with the logic of one or more controllers of the system control module 310 on the same die to form a system-on-a-chip (SoC).

[0045] In various embodiments, system 300 may be, but is not limited to, a server, workstation, desktop computing device, or mobile computing device (e.g., laptop computing device, handheld computing device, tablet computer, netbook, etc.). In various embodiments, system 300 may have more or fewer components and / or different architectures. For example, in some embodiments, system 300 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touchscreen display), a non-volatile memory port, multiple antennas, a graphics chip, an application-specific integrated circuit (ASIC), and a speaker.

[0046] It should be noted that this application can be implemented in software and / or a combination of software and hardware, for example, using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In one embodiment, the software program of this application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium, such as RAM memory, a magnetic or optical drive, a floppy disk, or similar devices. Furthermore, some steps or functions of this application can be implemented in hardware, for example, as circuitry that cooperates with a processor to perform the various steps or functions.

[0047] Furthermore, a portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0048] Communication media include media through which communication signals containing, for example, computer-readable instructions, data structures, program modules, or other data are transmitted from one system to another. Communication media can include guided transmission media (such as cables and wires (e.g., optical fibers, coaxial cables, etc.)) and wireless (unguided transmission) media capable of propagating energy waves, such as sound, electromagnetic, RF, microwave, and infrared. Computer-readable instructions, data structures, program modules, or other data can be embodied as modulated data signals in, for example, wireless media (such as carrier waves or similar mechanisms embodied as part of spread spectrum technology). The term "modulated data signal" refers to a signal whose one or more characteristics are altered or set in a manner that encodes information in the signal. Modulation can be analog, digital, or a hybrid modulation technique.

[0049] By way of example and not limitation, computer-readable storage media may include volatile and non-volatile, removable and non-removable media implemented by any method or technique for storing information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include, but are not limited to, volatile memories such as random access memory (RAM, DRAM, SRAM); and non-volatile memories such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic / ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disks, magnetic tapes, CDs, DVDs); or other media now known or hereafter developed capable of storing computer-readable information / data for use by a computer system.

[0050] Herein, one embodiment of this application includes an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the apparatus is triggered to run a method and / or technical solution based on the foregoing embodiments of this application.

[0051] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in the apparatus claims may also be implemented by a single unit or device in software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

Claims

1. A method for assessing the corrosion status of a substation grounding grid, characterized in that, The methods include: S11. Obtain multi-dimensional evaluation index data and corrosion branches of the target grounding network; wherein, the target grounding network is equivalent to a resistance network including N nodes and M branches, and the corrosion branches include branches whose branch resistance increment is equal to or greater than the target threshold, and N and M are positive integers. S12. Based on the multi-dimensional evaluation index data, the corrosion rate is obtained through the corrosion rate model; S13. Determine the corrosion level of the corrosion branch based on the corrosion rate, the thickness loss rate of the corrosion branch, and the branch resistance increment. S14. Determine the remaining lifespan of the target grounding grid based on the corrosion rate and the remaining allowable corrosion thickness; S15. Generate a corrosion status assessment report on the target grounding grid based on the corrosion rate, the corrosion branch, the corrosion level of the corrosion branch, and the remaining life of the target grounding grid.

2. The method according to claim 1, characterized in that, Obtaining the eroded branch includes: The measured voltage values ​​of each node are obtained by a potential measuring instrument; wherein, the measured voltage values ​​are generated by injecting current with known electrical parameter information into the resistor network; Based on the measured voltage values ​​of each node, the actual resistance of each branch is solved using the Newton-Raphson algorithm. For each branch, the branch resistance increment is determined by comparing the actual resistance of the branch with the initial reference resistance; if the branch resistance increment is equal to or greater than the target threshold, the branch is determined to be a corrosion branch.

3. The method according to claim 2, characterized in that, The calculation of the actual resistance of each branch based on the measured voltage values ​​of each node using the Newton-Raphson algorithm includes: The simulated voltage value of each node is calculated based on the current simulated resistance, and the current node voltage-branch current equation is established; wherein, the current node voltage-branch current equation includes the current sensitivity of the voltage of each node to the resistance of each branch. The voltage difference between each node is determined based on the simulated voltage value of each node and the measured voltage value of each node. If there is a node with a voltage difference equal to or greater than the target difference, the resistance adjustment value of each branch is determined based on the current node voltage-branch current equation and the voltage difference, so as to adjust the current analog resistance of each branch based on the resistance adjustment value; Based on the adjusted current analog resistance of each branch, repeat the above steps of determining the current node voltage-branch current equation and the current analog resistance until the voltage difference of each node is less than the target difference.

4. The method according to claim 3, characterized in that, The voltage-branch current equation for the current node is established based on the current simulated resistance, including: Based on the current simulated resistance of each branch, calculate the original branch current distribution of the resistor network; Establish a companion network with the same topology as the resistor network, and with each branch resistance value being the same as the current simulated resistance value; A unit current excitation is applied to the node position corresponding to each node to be measured in the accompanying network, and the distribution of the accompanying branch current in the accompanying network is calculated; wherein, the node to be measured includes the node whose sensitivity of the voltage to each branch resistance is to be determined. Based on the product of the original branch current distribution and the accompanying branch current distribution, the current sensitivity of the voltage of each node to the resistance of each branch is calculated, thereby establishing the current node voltage-branch current equation.

5. The method according to claim 1, characterized in that, The corrosion rate model includes a backpropagation neural network model. Step S12 includes: inputting a standardized dataset into the backpropagation neural network model to output the corrosion rate; wherein, the standardized dataset is obtained based on the multi-dimensional evaluation index data; the neural network model is obtained through the following method: Multiple sets of initial model parameters are randomly generated based on the topology of the backpropagation neural network model. The training standardized dataset is input into the backpropagation neural network model corresponding to the initial model parameters of each group for prediction, and multiple prediction results are obtained; wherein, the training standardized dataset corresponds to erosion rate label data; Using the error between each prediction result and the corrosion rate label data as an evaluation index, the multiple sets of initial model parameters are selected, crossed, and mutated to obtain the optimal initial model parameters with the smallest error after a preset number of iterations. The optimal initial model parameters are assigned to the backpropagation neural network model, and the backpropagation neural network model is trained using the training standardized dataset and the corrosion rate label data until the error between the prediction result output by the backpropagation neural network model and the corrosion rate label data meets the preset convergence condition, thus obtaining the corrosion rate model.

6. The method according to claim 5, characterized in that, The standardized dataset obtained based on the multi-dimensional evaluation index data includes: Obtain the multi-dimensional evaluation index data; wherein, the multi-dimensional evaluation index data includes soil environmental parameters, electrical operating condition parameters, conductor characteristic parameters, and operation and maintenance record parameters; The multi-dimensional evaluation index data is preprocessed to obtain the standardized dataset.

7. The method according to claim 1, characterized in that, The multi-dimensional evaluation index data includes electrical operating condition parameters and conductor characteristic parameters; the corrosion rate model includes an electrochemical corrosion rate model and a grey prediction model; step S12 includes: By substituting multiple sets of electrical operating condition parameters and conductor characteristic parameters into the electrochemical corrosion rate model, multiple historical corrosion rates arranged in chronological order are obtained; wherein, the multiple sets of electrical operating condition parameters are arranged in chronological order. The corrosion rates are obtained by inputting the multiple historical corrosion rates arranged in chronological order into the gray prediction model.

8. The method according to claim 1, characterized in that, Also includes: Based on the multi-dimensional evaluation index data, uncertain parameters and fluctuation ranges are set to obtain multiple sets of random multi-dimensional evaluation index data. Based on the multiple sets of random multidimensional evaluation index data, multiple corrosion rates are obtained through the corrosion rate model, and the corrosion rate confidence interval that meets the target confidence level is statistically obtained. The remaining lifetime confidence interval of the target grounding grid at the target confidence level is determined based on the corrosion rate confidence interval and the remaining allowable corrosion thickness.

9. A computer device, characterized in that, It includes a memory and a processor, wherein the memory stores a method for assessing the corrosion status of a substation grounding grid as described in any one of claims 1 to 8, which can be loaded and executed by the processor.

10. A computer-readable storage medium, characterized in that, The system stores a method for assessing the corrosion status of a substation grounding grid, as described in any one of claims 1 to 8, which can be loaded by a processor and executed.

Images