Pumped storage power station differential grounding platform setting method and system and electronic equipment

Abstract

The invention provides a pumped storage power station differential grounding platform setting method and system and electronic equipment, and the system comprises a space-time multi-physics field feature description module which is used for collecting multi-source heterogeneous data of the whole field domain of a pumped storage power station, and a four-dimensional geoelectric structure model capable of reflecting soil resistivity space distribution and time dynamic change is constructed through the data, and a grounding short circuit fault risk distribution diagram of the whole field domain is generated according to the model and a preset short circuit current level. According to the method, the four-dimensional geoelectric structure model is constructed, so that too simplified homogenization and static assumptions in traditional design are abandoned fundamentally, the real physical environment of the complex site of the pumped storage power station can be scientifically represented with unprecedented precision and dimensionality, and a solid data and physical model foundation is laid for subsequent precise design.

Description

Technical Field

[0001] This invention belongs to the field of power system technology, and in particular relates to a method, system and electronic equipment for setting up a differentiated grounding platform for a pumped storage power station. Background Technology

[0002] Against the backdrop of a profound transformation in the global energy structure, new energy power generation forms, represented by wind and solar power, are being integrated into the power grid system on an unprecedented scale.

[0003] In traditional power engineering, the initial design phase typically involves conducting a limited number of site surveys and sampling to obtain one or a few representative average soil resistivity values. Based on this, designers refer to national or industry design specifications and guidelines, selecting a homogenized soil model as the basis for calculations. They then utilize classical electromagnetic field theory or empirical formulas to calculate the layout and dimensions of standard grounding electrodes for horizontal grounding grids and vertical grounding grids, aiming to meet the requirements of key safety indicators such as power frequency grounding resistance, contact voltage, and step voltage.

[0004] Extensive research revealed that, in existing technologies, pumped storage power stations are typically characterized by vast land areas and significant elevation differences. Their infrastructure often spans multiple areas, including upper reservoirs on mountaintops, underground powerhouses in valleys, and transmission towers along the route. Firstly, the soil composition, structure, density, and moisture content can vary drastically across different locations within the site. From hard rock to soft soil, soil resistivity can differ by several orders of magnitude. Simplifying this highly heterogeneous environment into a single, homogeneous model undoubtedly introduces substantial calculation errors, leading to significant deviations between design results and actual operating conditions. Secondly, soil resistivity is not a static parameter; it fluctuates significantly dynamically with seasonal changes, rainfall and drought, temperature variations, and even the formation and thawing of permafrost. Traditional design methods using static average values ​​cannot capture these temporal changes, potentially causing a sudden increase in grounding resistance under extreme climatic conditions, exceeding safety thresholds and creating serious safety hazards. Summary of the Invention

[0005] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide a method, system and electronic equipment for setting up a differentiated grounding platform in a pumped storage power station, so as to solve the problems of low working efficiency in the prior art.

[0006] In a first aspect, the present invention provides a differentiated grounding platform setting system for a pumped storage power station, the system comprising:

[0007] The spatiotemporal multiphysics field feature description module is used to collect multi-source heterogeneous data of the entire field of the pumped storage power station, and construct a four-dimensional geoelectric structure model that can reflect the spatial distribution and temporal dynamic changes of soil resistivity through the multi-source heterogeneous data. Based on the four-dimensional geoelectric structure model and the preset short-circuit current level, a grounding short-circuit fault risk distribution map of the entire field is generated.

[0008] The differentiated grounding platform engine module is connected to the data output end of the spatiotemporal multiphysics field feature description module. It is used to call the built-in grounding body performance database and hybrid electromagnetic field solver to perform multi-objective collaborative optimization calculations based on the four-dimensional geoelectric structure model and the risk distribution map, so as to generate a differentiated grounding platform setting scheme.

[0009] The full lifecycle intelligent management and control module is connected to the differentiated grounding platform engine module and the existing physical grounding platform. It is used to monitor the operating status of the physical grounding platform in real time through distributed sensors, predict performance degradation in combination with the four-dimensional geoelectric structure model, generate adaptive maintenance strategies, and perform closed-loop feedback calibration of the four-dimensional geoelectric structure model using measured data.

[0010] In one possible implementation of this application, the spatiotemporal multiphysics feature description module specifically includes:

[0011] Multi-source data acquisition units are set up in a distributed manner within the planned site of the pumped storage power station to acquire multi-dimensional data including soil resistivity, geological structure, topography and meteorological environment.

[0012] The four-dimensional geoelectric structure modeling unit has its data input end connected to the data output end of the multi-source data acquisition unit, and is used to fuse and process the multi-dimensional data to establish the four-dimensional geoelectric structure model.

[0013] The fault risk assessment unit is connected to the four-dimensional geoelectric structure modeling unit and the power plant main electrical system design database. It is used to calculate and generate the grounding short-circuit fault risk distribution map based on the four-dimensional geoelectric structure model.

[0014] The Central Geoelectric Database is used for the structured storage and management of raw data from the multi-source data acquisition unit, model data generated by the four-dimensional geoelectric structure modeling unit, and risk map data generated by the fault risk assessment unit.

[0015] In one possible implementation of this application, the multi-source data acquisition unit specifically includes:

[0016] The four-pole symmetric profile soil resistivity tester uses a 94 Hz current electrode power supply frequency and has a voltage measurement accuracy better than 1 microvolt, and is used to obtain soil resistivity profile data at different depths and locations.

[0017] The ground-penetrating radar detection device, with a center frequency set to 250 MHz, is used to detect the geological structure of underground rock-soil interfaces, karst caves, and fracture zones.

[0018] A high-precision differential global positioning system receiver with a horizontal positioning accuracy better than 1 cm and an elevation accuracy better than 2 cm is used to provide three-dimensional spatial coordinates for all acquired data.

[0019] The meteorological and environmental monitoring station is equipped with rain gauges, temperature sensors, humidity sensors, and soil temperature and humidity probes to continuously record dynamic environmental parameters that affect soil resistivity.

[0020] The low-power wide-area IoT module operates in the 470-510 MHz frequency band and uses linear frequency modulation spread spectrum technology to realize data transmission of the test instrument, detection device, receiver and monitoring station.

[0021] In one possible implementation of this application, the four-dimensional geoelectric structure modeling unit includes a data fusion and interpolation calculation module, wherein the calculation steps of the interpolation calculation module include the following:

[0022] Based on the discrete point data collected by the soil resistivity tester, and using the rock-soil interface data detected by the ground-penetrating radar as a hard constraint boundary, a high-resolution three-dimensional static soil resistivity basic model is generated by using the co-kriging interpolation algorithm.

[0023] By correlating the time series data of rainfall and temperature collected by meteorological and environmental monitoring stations over the years with the corresponding soil resistivity change data, a dynamic influence function of soil resistivity based on a time series autoregressive integral moving average model is established.

[0024] The dynamic influence function is applied to the three-dimensional static basic model to output a four-dimensional geoelectric structure model with a spatial resolution of 5 meters × 5 meters × 2 meters and a time resolution of 24 hours.

[0025] In one possible implementation of this application, the calculation steps of the fault risk assessment unit include the following:

[0026] The expected maximum single-phase ground fault current value for each area is obtained from the main electrical system design database of the power station.

[0027] At each spatial grid node of the four-dimensional geoelectric structure model, the expected grounding resistance, maximum contact voltage, and maximum step voltage are calculated under extreme dry season or deep freezing season conditions, based on the preset grounding body model.

[0028] The weighted risk index R is calculated using the formula... index =w1·f(ρ(t))+w2·g(I k The risk distribution map is generated by ) + w3·h(U), where ρ(t) is the dynamic soil resistivity, and I k U is the short-circuit current, U is the contact or step voltage, f, g, and h are normalization functions, and w1, w2, and w3 are preset weighting coefficients with values ​​of 0.5, 0.3, and 0.2, respectively.

[0029] In one possible implementation of this application, the differentiated grounding platform engine module specifically includes:

[0030] The grounding electrode performance library unit stores parameterized models of various standard and non-standard grounding electrodes. The grounding electrodes include horizontally laid flat steel grounding grids, vertically inserted angle steel grounding electrodes, deep well grounding electrodes, and flexible grounding modules made of conductive polymer and graphene composite materials. For each type of grounding electrode, the performance library stores simulation curve data of power frequency grounding resistance, impulse grounding resistance, and thermal stability performance under different soil resistivity.

[0031] The hybrid electromagnetic field solver unit adopts a hybrid calculation strategy of finite element method and boundary element method, and directly calls the data in the four-dimensional geoelectric structure model as the dielectric parameters of its calculation domain to perform accurate calculation of grounding performance;

[0032] The multi-objective optimization unit is a non-dominated sorting genetic algorithm II module, used to find the optimal solution with the optimization objectives of minimizing the total life cycle cost, minimizing the equivalent grounding resistance of the entire station, and ensuring that the contact voltage and step voltage are below the safety limit.

[0033] The design scheme generation unit receives the Pareto optimal solution set output by the multi-objective optimization unit, and automatically generates the differentiated grounding platform design scheme, including grounding electrode construction drawings, material list and construction process description, based on the selected equilibrium point.

[0034] In one possible implementation of this application, the multi-objective optimization unit optimizes a total of three objectives, wherein,

[0035] Objective 1 corresponds to minimizing the total lifecycle cost of the grounding platform, and the specific formula is as follows:

[0036]

[0037] Among them, C material For material costs, C construction For construction costs, C maintenance The annual maintenance cost is given by r, the discount rate is given by t, and the number of years is given by t.

[0038] Objective 2 corresponds to minimizing the equivalent grounding resistance of the entire station under the most unfavorable meteorological conditions determined by the four-dimensional geoelectric structure model;

[0039] Objective 3 corresponds to ensuring that the contact voltage and step voltage at all critical locations throughout the field are lower than the safety limits specified in the national standard GB / T50065-2011.

[0040] In one possible implementation of this application, the full lifecycle intelligent management and control module specifically includes:

[0041] The distributed monitoring unit consists of multiple intelligent monitoring terminals. The terminals are installed in high-risk areas or key grounding nodes identified by the fault risk assessment unit and are used to monitor grounding resistance, grounding body to ground potential, soil temperature and humidity and corrosion rate in real time.

[0042] The performance degradation prediction unit is a long short-term memory network model that takes historical data and real-time data collected by the distributed monitoring unit as input to predict the future performance degradation trend of the grounding platform and issue early warnings.

[0043] The adaptive maintenance strategy unit is activated upon receiving an early warning signal. It is used to match and generate the optimal maintenance work order from a preset maintenance measure knowledge base based on the type and location of the early warning.

[0044] The model closed-loop calibration unit is used to periodically compare the actual measured values ​​collected by the distributed monitoring unit with the theoretical calculated values, and trigger the inversion calculation program when the cumulative error exceeds a preset threshold, so as to reverse correct the local soil resistivity parameters in the four-dimensional geoelectric structure model.

[0045] Secondly, the present invention provides a method for setting up a differentiated grounding platform in a pumped storage power station, applicable to the differentiated grounding platform setting system for a pumped storage power station described in any of the above claims, wherein the method includes the following steps:

[0046] The process involves performing a spatiotemporal multiphysics field characteristic description across the entire field. This includes acquiring soil resistivity, geological structure, topography, and meteorological data through multi-source data acquisition units deployed within the pumped storage power station area. Subsequently, a four-dimensional geoelectric structure modeling unit is used to fuse and process the acquired data, establishing a four-dimensional geoelectric structure model that reflects the non-uniform distribution of soil resistivity in three-dimensional space and its dynamic changes over time. Finally, using a fault risk assessment unit, combined with the expected short-circuit current level of the power station, a ground fault risk level distribution map for the entire field is calculated and generated based on this four-dimensional model.

[0047] The optimization of differentiated grounding platform schemes is carried out. Specifically, the differentiated grounding platform engine module is started, and the four-dimensional geoelectric structure model and risk distribution map generated in step one are loaded through the hybrid electromagnetic field solver unit. Then, the multi-objective optimization unit aims to minimize the system's total life cycle cost, optimize grounding performance, and maximize safety margin. Using the grounding body model, size, and layout stored in the grounding body performance library unit as decision variables, the hybrid electromagnetic field solver unit is called to run a non-dominated sorting genetic algorithm to obtain a set of Pareto optimal design schemes. Finally, the design scheme generation unit determines and outputs a set of specific and differentiated grounding platform construction schemes for different risk areas from the optimal solution set.

[0048] The system implements intelligent management and closed-loop control throughout the entire lifecycle of the grounding platform. After the grounding platform is constructed, distributed monitoring units deployed on-site conduct long-term continuous online monitoring of the key performance parameters and local environmental parameters of the grounding platform. The performance degradation prediction unit uses the monitoring data to predict the future state of the grounding platform and issue early warnings. The adaptive maintenance strategy unit automatically generates preventive maintenance tasks based on the early warning information. At the same time, the model closed-loop calibration unit continuously compares the measured data with the calculation results of the system model, and initiates an inversion program when significant deviations are found to correct and update the four-dimensional geoelectric structure model.

[0049] Thirdly, the present invention provides an electronic device, the electronic device comprising: a processor and a memory;

[0050] The memory is used to store computer programs;

[0051] The processor is used to execute the computer program stored in the memory, so that the electronic device performs the above-described method for setting up a differentiated grounding platform for a pumped storage power station.

[0052] As described above, the method, system, and electronic equipment for setting up a differentiated grounding platform for a pumped storage power station according to the present invention have the following beneficial effects:

[0053] 1. When the pumped storage power station differentiated grounding platform of the present invention is used, it constructs a four-dimensional geoelectric structure model, which fundamentally abandons the overly simplified homogenization and static assumptions in traditional design. It can scientifically characterize the real physical environment of the complex site of the pumped storage power station with unprecedented accuracy and dimension, laying a solid data and physical model foundation for subsequent accurate design.

[0054] 2. When the pumped storage power station differentiated grounding platform of the present invention is used, by introducing a design engine based on a multi-objective optimization algorithm, the present invention incorporates multiple mutually restrictive engineering objectives such as safety, economy and reliability into a unified optimization framework, which can generate a highly targeted and resource-allocated differentiated design scheme, avoiding investment waste caused by excessive global conservatism or safety hazards caused by insufficient local design, and achieving global optimization.

[0055] 3. When the differentiated grounding platform of the pumped storage power station of the present invention is in use, by constructing an intelligent management and closed-loop feedback system throughout the entire life cycle, the present invention transforms the management of the grounding platform from post-event, passive fault repair to pre-event, proactive performance prediction and preventive maintenance, and realizes the continuous evolution of the system through the model self-calibration mechanism, which greatly improves the long-term operational reliability and management efficiency of the pumped storage power station grounding platform. Attached Figure Description

[0056] Figure 1 The diagram shows a schematic representation of the pumped storage power station differentiated grounding platform setting system of the present invention in one embodiment.

[0057] Figure 2 The diagram shows the composition of the spatiotemporal multiphysics field feature description module in one embodiment of the pumped storage power station differentiated grounding platform setting system of the present invention.

[0058] Figure 3 The diagram shows a schematic representation of the differential grounding platform engine module in one embodiment of the pumped storage power station differential grounding platform setting system of the present invention.

[0059] Figure 4 The diagram shows the composition of the intelligent management and control module for the entire life cycle of a pumped storage power station differentiated grounding platform setting system according to one embodiment of the present invention.

[0060] Figure 5 The diagram shows a step-by-step illustration of the method for setting up a differentiated grounding platform for a pumped storage power station according to an embodiment of the present invention.

[0061] Figure 6 The diagram shown is a structural schematic of an electronic device according to an embodiment of the present invention.

[0062] Illustrations: 1. Spatiotemporal multiphysics field feature description module; 2. Differentiated grounding platform engine module; 3. Full lifecycle intelligent management and control module; 101. Multi-source data acquisition unit; 102. Four-dimensional geoelectric structure modeling unit; 103. Fault risk assessment unit; 104. Central geoelectric database; 201. Grounding body performance library unit; 202. Hybrid electromagnetic field solver unit; 203. Multi-objective optimization unit; 204. Design scheme generation unit; 301. Distributed monitoring unit; 302. Performance degradation prediction unit; 303. Adaptive maintenance strategy unit; 304. Model closed-loop calibration unit. Detailed Implementation

[0063] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0064] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0065] Furthermore, the use of terms such as "first" and "second" in this application is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. If the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed in this application.

[0066] Specifically, such as Figure 1 As shown, in one embodiment of the invention, the pumped storage power station differentiated grounding platform setting system of the present invention includes:

[0067] The spatiotemporal multiphysics field feature description module 1 is used to collect multi-source heterogeneous data of the entire field of the pumped storage power station, and construct a four-dimensional geoelectric structure model that can reflect the spatial distribution and temporal dynamic changes of soil resistivity through the multi-source heterogeneous data. Based on the four-dimensional geoelectric structure model and the preset short-circuit current level, a grounding short-circuit fault risk distribution map of the entire field is generated.

[0068] The differentiated grounding platform engine module 2 is connected to the data output end of the spatiotemporal multiphysics field feature description module. It is used to call the built-in grounding body performance database and hybrid electromagnetic field solver to perform multi-objective collaborative optimization calculations based on the four-dimensional geoelectric structure model and the risk distribution map, so as to generate a differentiated grounding platform setting scheme.

[0069] The full lifecycle intelligent management and control module 3 is connected to the differentiated grounding platform engine module and the existing physical grounding platform. It is used to monitor the operating status of the physical grounding platform in real time through distributed sensors, predict performance degradation in combination with the four-dimensional geoelectric structure model, generate adaptive maintenance strategies, and perform closed-loop feedback calibration of the four-dimensional geoelectric structure model using measured data.

[0070] It should be noted that, in this embodiment, the spatiotemporal multiphysics feature description module 1 is used to collect multi-source heterogeneous data of the entire pumped storage power station, and to construct a four-dimensional geoelectric structure model that reflects the spatial distribution and temporal dynamic changes of soil resistivity. Then, based on the model and a preset short-circuit current level, a ground fault risk distribution map of the entire field is generated. Specifically, as shown... Figure 2 As shown, the spatiotemporal multiphysics feature description module 1 specifically includes:

[0071] A multi-source data acquisition unit 101 is deployed in a distributed manner within the planned site of the pumped storage power station to acquire multi-dimensional data, including soil resistivity, geological structure, topography, and meteorological environment. Specifically, the multi-source data acquisition unit 101 includes a four-pole symmetric profile soil resistivity meter, a ground-penetrating radar detection device, a meteorological environment monitoring station, and a low-power wide-area IoT module. The four-pole symmetric profile soil resistivity meter uses a 94 Hz current electrode power supply frequency and has a voltage measurement accuracy better than 1 microvolt, used to acquire soil resistivity profile data at different depths and locations. The ground-penetrating radar detection device has a center frequency set to 250 MHz, used to detect underground rock-soil interfaces, karst caves, and fracture zones, among other geological structures. High-precision differential... The GPS receiver has a horizontal positioning accuracy better than 1 cm and an elevation accuracy better than 2 cm, providing three-dimensional spatial coordinates for all collected data. The meteorological and environmental monitoring station is equipped with rain gauges, temperature sensors, humidity sensors, and soil temperature and humidity probes to continuously record dynamic environmental parameters affecting soil resistivity. During measurement, based on the site's topography and geological unit divisions, a combination of Winner and Schramberg electrode arrangements is used for data acquisition, with the electrode spacing gradually increasing from 2 meters to 200 meters to achieve resistivity profile scanning from shallow surface to deep underground depths. In critical engineering areas such as power plants, switchyards, and dams, the grid of measurement points is densified to 20 meters × 20 meters, while in general areas, a 100-meter × 100-meter grid is used.

[0072] The four-dimensional geoelectric structure modeling unit 102 has its data input end connected to the data output end of the multi-source data acquisition unit 101. It is used to fuse and process multi-dimensional data to establish a four-dimensional geoelectric structure model. Specifically, the four-dimensional geoelectric structure modeling unit 102 includes a data fusion and interpolation calculation module. The calculation steps of the interpolation calculation module are as follows:

[0073] First, based on the discrete point data collected by the soil resistivity tester and the rock-soil interface data detected by the ground-penetrating radar as the hard constraint boundary, a high-resolution three-dimensional static soil resistivity basic model is generated using the co-kriging interpolation algorithm.

[0074] Then, the time series data of rainfall, temperature and other data collected by meteorological and environmental monitoring stations over the years are correlated with the soil resistivity change data of the corresponding period to establish a dynamic influence function of soil resistivity based on the time series autoregressive integral moving average model.

[0075] Finally, the dynamic influence function is applied to the three-dimensional static basic model to output a four-dimensional geoelectric structure model with a spatial resolution of 5 meters × 5 meters × 2 meters and a time resolution of 24 hours.

[0076] Furthermore, in this embodiment, based on this, the module enters the stage of constructing the dynamic influence function. It retrieves historical data from meteorological and environmental monitoring stations over the past few years (e.g., at least three consecutive years) and performs correlation analysis with soil resistivity change data measured synchronously during a specific period. Through complex statistical calculations, it establishes a dynamic influence function for soil resistivity based on a time-series autoregressive integral moving average model.

[0077] The fault risk assessment unit 103 has its data input terminal connected to the four-dimensional geoelectric structure modeling unit 102 and the power plant main electrical system design database. It is used to calculate and generate a ground fault short-circuit risk distribution map based on the four-dimensional geoelectric structure model, and to conduct a forward-looking safety risk assessment. Specifically, the fault risk assessment unit 103 performs the following steps:

[0078] First, obtain the expected maximum single-phase ground fault current value for each area from the power plant's main electrical system design database;

[0079] Then, at each spatial grid node of the four-dimensional geoelectric structure model, based on the preset grounding body model, the expected grounding resistance, maximum contact voltage, and maximum step voltage under extreme dry season or deep freezing season conditions are calculated.

[0080] Finally, the weighted risk index R is calculated using the formula... index =w1·f(ρ(t))+w2·g(I k The risk distribution map is generated by )+w3·h(U), where ρ(t) is the dynamic soil resistivity, and I k U is the short-circuit current, U is the contact or step voltage, f, g, and h are normalization functions, and w1, w2, and w3 are preset weighting coefficients with values ​​of 0.5, 0.3, and 0.2, respectively.

[0081] The Central Geoelectric Database 104 is used for structured storage and management of raw data from the multi-source data acquisition unit 101, model data generated by the four-dimensional geoelectric structure modeling unit 102, and risk map data generated by the fault risk assessment unit 103. For example, PostgreSQL is selected as the basic database platform, combined with its PostGIS extension for processing complex two-dimensional / three-dimensional geospatial data, and the TimescaleDB extension for efficient storage and querying of massive amounts of time-series data. The database's internal table structure stores the raw measurement data from the multi-source data acquisition unit 101, the model data cubes generated by the four-dimensional geoelectric structure modeling unit 102, and the risk layer data generated by the fault risk assessment unit 103, respectively. To achieve rapid retrieval and access to massive amounts of data, the database establishes composite indexes, particularly a spatiotemporal index mechanism combining R-tree-based spatial indexes and timestamp-based B-tree indexes, ensuring high response speed for upper-layer applications performing complex queries.

[0082] Furthermore, in this embodiment, as Figure 3 As shown, the differentiated grounding platform engine module 2 specifically includes a grounding body performance library unit 201, a hybrid electromagnetic field solver unit 202, a multi-objective optimization unit 203, and a design scheme generation unit 204. Specifically, the grounding body performance library unit 201 internally stores parametric models of various standard and non-standard grounding bodies. Grounding bodies include horizontally laid flat steel grounding grids, vertically inserted angle steel grounding electrodes, deep well grounding electrodes, and flexible grounding modules made of conductive polymer and graphene composite materials. For each type of grounding body, the performance library stores power frequency grounding resistance and impulse grounding resistance under different soil resistivities. Simulation curves of ground resistance and thermal stability performance are used. The hybrid electromagnetic field solver unit 202 employs a hybrid calculation strategy combining the finite element method and the boundary element method, directly calling data from the four-dimensional geoelectric structure model as the dielectric parameters of its computational domain to perform accurate calculations of grounding performance. The multi-objective optimization unit 203 is a non-dominated sorting genetic algorithm II module used to solve for the optimal solution with the optimization objectives of minimizing the total life cycle cost, minimizing the equivalent grounding resistance of the entire station, and ensuring that the contact voltage and step voltage are below the safety limit. Specifically, the multi-objective optimization unit 203 optimizes a total of three objectives:

[0083] Objective 1: Minimize the total lifecycle cost of the grounding platform, which is determined by the formula... Define, where C material For material costs, C construction For construction costs, C maintenance The annual maintenance cost is given by r, the discount rate is given by t, and the number of years is given by t.

[0084] Objective 2: Minimize the total equivalent grounding resistance of the entire station under the most unfavorable meteorological conditions determined by the four-dimensional geoelectric structure model;

[0085] Objective 3: Ensure that the contact voltage and step voltage at all critical locations throughout the field are below the safety limits specified in the national standard GB / T50065-2011.

[0086] Furthermore, in this embodiment, the design scheme generation unit 204 receives the Pareto optimal solution set output by the multi-objective optimization unit 203, and automatically generates a differentiated grounding platform design scheme including grounding electrode construction drawings, material list and construction process description according to the selected equilibrium point.

[0087] Specifically, in this embodiment, as Figure 4 As shown, the full lifecycle intelligent management and control module 3 specifically includes a distributed monitoring unit 301, a performance degradation prediction unit 302, an adaptive maintenance strategy unit 303, and a model closed-loop calibration unit 304. Specifically, the distributed monitoring unit 301 consists of multiple intelligent monitoring terminals, which are installed at high-risk areas or key grounding nodes identified by the fault risk assessment unit 103. These terminals are used to monitor grounding resistance, grounding electrode potential to ground, soil temperature and humidity, and corrosion rate in real time. The performance degradation prediction unit 302 uses a long short-term memory network model with historical data and the data from the distributed monitoring unit 301. The real-time data collected is used as input to predict the future performance degradation trend of the grounding platform and issue early warnings. The adaptive maintenance strategy unit 303 is activated after receiving the warning signal. It is used to match and generate the optimal maintenance work order from the preset maintenance measures knowledge base according to the type and location of the warning. The model closed-loop calibration unit 304 is used to periodically compare the actual measured values ​​collected by the distributed monitoring unit 301 with the theoretical calculated values. When the cumulative error exceeds the preset threshold, it triggers the inversion calculation program to reverse correct the local soil resistivity parameters in the four-dimensional geoelectric structure model.

[0088] like Figure 5 As shown, in one embodiment of the invention, the method for setting up a differentiated grounding platform for a pumped storage power station according to the present invention is applied to the differentiated grounding platform setting system for a pumped storage power station described in any of the above claims, wherein the method includes the following steps:

[0089] Step S502: Perform full-field spatiotemporal multiphysics field feature description;

[0090] Step S504: Optimize the differentiated grounding platform scheme;

[0091] Step S506: Perform intelligent management and closed-loop control of the grounding platform throughout its entire lifecycle.

[0092] It should be noted that, in this embodiment, a full-field spatiotemporal multiphysics characteristic description is performed. Specifically, this is achieved by systematically deploying and operating multi-source data acquisition units 101 within the planned area of ​​the pumped storage power station to comprehensively acquire multi-source, heterogeneous, and multi-dimensional data, including multi-depth soil resistivity, underground rock and soil structure, high-precision three-dimensional topography, and key meteorological environmental factors. Subsequently, a four-dimensional geoelectric structure modeling unit 102 is activated to perform deep fusion, collaborative interpolation, and temporal modeling processing on the massive amount of acquired data, ultimately establishing a four-dimensional geoelectric structure model that can reflect the non-uniform distribution of soil resistivity in three-dimensional space and its dynamic changes over time with high resolution. Based on this model, a fault risk assessment unit 103 is further used, combined with the expected short-circuit current levels of each area obtained from the main electrical system design, to calculate and generate a visualized distribution map of grounding fault risk levels across the entire field and time domain under the worst-case operating conditions that the four-dimensional model can simulate.

[0093] Furthermore, in this embodiment, the optimization of the differentiated grounding platform scheme is performed. After completing the full-field spatiotemporal multiphysics characteristic description described above, the differentiated grounding platform engine module 2 is immediately started. First, the hybrid electromagnetic field solver unit 202 is activated and fully loads the four-dimensional geoelectric structure model and risk distribution map generated in step one as the background physical environment for its calculation. Then, the multi-objective optimization unit 203 starts running. The multi-objective optimization unit 203 takes minimizing the system's total life cycle cost, optimizing grounding performance under the worst conditions, and maximizing the safety margin of the entire field as its three parallel optimization objectives. It uses the model, size, quantity, burial depth, and spatial layout of various grounding bodies stored in the grounding body performance library unit 201 as adjustable decision variables, repeatedly calls the hybrid electromagnetic field solver unit 202 to accurately evaluate the performance of each generated candidate scheme, and performs efficient global optimization through the built-in non-dominated sorting genetic algorithm II. After hundreds of generations of evolutionary iterations, a set of Pareto optimal solutions representing different design compromise schemes is obtained. Finally, through the interactive interface provided by the design scheme generation unit 204, the chief engineer carefully determines a final scheme from the optimal solution set based on specific engineering constraints and preferences, and the system automatically outputs a complete set of specific and differentiated grounding platform construction scheme documents for different risk areas.

[0094] Furthermore, in this embodiment, intelligent management and closed-loop control of the grounding platform throughout its entire lifecycle are implemented. After the grounding platform is constructed and put into operation according to the optimized scheme output from the above steps, distributed monitoring units 301 deployed at key and high-risk locations on-site perform long-term, continuous, and high-frequency online monitoring of the grounding platform's key performance parameters and its local microenvironment parameters. The obtained real-time data stream is input into the performance degradation prediction unit 302. The performance degradation prediction unit 302 utilizes its internal, fully trained long short-term memory network model to scientifically predict the future health status and performance degradation trend of the grounding platform, and can issue early warnings before potential failure risks occur. Once an early warning is triggered, the adaptive maintenance strategy unit 303 automatically matches and generates preventative maintenance task work orders with clear guidance significance from its expert knowledge base based on the detailed information of the early warning, guiding maintenance personnel to perform precise and efficient maintenance operations. Meanwhile, the model closed-loop calibration unit 304 continuously compares and verifies the massive amount of measured data monitored in the background with the theoretical calculation results of the system model. Once it finds that the systematic deviation between the two exceeds the preset calibration threshold, it immediately starts the inversion calculation program. Based on the measured data, it performs local and refined corrections and updates to the four-dimensional geoelectric structure model, thereby ensuring that the entire design and management system can adaptively evolve with the evolution of the physical system and maintain long-term accuracy and effectiveness.

[0095] In the embodiments provided by this invention, it should be understood that the disclosed apparatus or method can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of the apparatus or module or unit may be electrical, mechanical, or other forms.

[0096] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of the present invention, depending on actual needs. For example, the functional modules / units in the various embodiments of the present invention may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0097] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. 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 implementations should not be considered beyond the scope of this invention.

[0098] This invention also provides an electronic device, such as... Figure 6 As shown, the electronic device includes a processor and a memory.

[0099] The memory is used to store computer programs.

[0100] The processor is configured to execute a computer program stored in the memory to cause the electronic device to perform any of the methods described above.

[0101] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0102] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0103] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. 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.

[0104] This application embodiment may also provide a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application embodiment are generated. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0105] When the computer program product is executed by a computer, the computer performs the method described in the foregoing method embodiments. The computer program product can be a software installation package; when the foregoing method is required, the computer program product can be downloaded and executed on the computer.

[0106] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0107] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A differentiated grounding platform setting system for a pumped storage power station, characterized in that, include: The spatiotemporal multiphysics field feature description module is used to collect multi-source heterogeneous data of the entire field of the pumped storage power station, and construct a four-dimensional geoelectric structure model that can reflect the spatial distribution and temporal dynamic changes of soil resistivity through the multi-source heterogeneous data. Based on the four-dimensional geoelectric structure model and the preset short-circuit current level, a grounding short-circuit fault risk distribution map of the entire field is generated. The differentiated grounding platform engine module is connected to the data output end of the spatiotemporal multiphysics field feature description module. It is used to call the built-in grounding body performance database and hybrid electromagnetic field solver to perform multi-objective collaborative optimization calculations based on the four-dimensional geoelectric structure model and the risk distribution map, so as to generate a differentiated grounding platform setting scheme. The full lifecycle intelligent management and control module is connected to the differentiated grounding platform engine module and the existing physical grounding platform. It is used to monitor the operating status of the physical grounding platform in real time through distributed sensors, predict performance degradation in combination with the four-dimensional geoelectric structure model, generate adaptive maintenance strategies, and perform closed-loop feedback calibration of the four-dimensional geoelectric structure model using measured data.

2. The differentiated grounding platform setting system for pumped storage power stations according to claim 1, characterized in that, The spatiotemporal multiphysics feature description module specifically includes: Multi-source data acquisition units are set up in a distributed manner within the planned site of the pumped storage power station to acquire multi-dimensional data including soil resistivity, geological structure, topography and meteorological environment. The four-dimensional geoelectric structure modeling unit has its data input end connected to the data output end of the multi-source data acquisition unit, and is used to fuse and process the multi-dimensional data to establish the four-dimensional geoelectric structure model. The fault risk assessment unit is connected to the four-dimensional geoelectric structure modeling unit and the power plant main electrical system design database. It is used to calculate and generate the grounding short-circuit fault risk distribution map based on the four-dimensional geoelectric structure model. The Central Geoelectric Database is used for the structured storage and management of raw data from the multi-source data acquisition unit, model data generated by the four-dimensional geoelectric structure modeling unit, and risk map data generated by the fault risk assessment unit.

3. The differentiated grounding platform setting system for pumped storage power stations according to claim 2, characterized in that, The multi-source data acquisition unit specifically includes: The four-pole symmetric profile soil resistivity tester uses a 94 Hz current electrode power supply frequency and has a voltage measurement accuracy better than 1 microvolt, and is used to obtain soil resistivity profile data at different depths and locations. The ground-penetrating radar detection device, with a center frequency set to 250 MHz, is used to detect the geological structure of underground rock-soil interfaces, karst caves, and fracture zones. A high-precision differential global positioning system receiver with a horizontal positioning accuracy better than 1 cm and an elevation accuracy better than 2 cm is used to provide three-dimensional spatial coordinates for all acquired data. The meteorological and environmental monitoring station is equipped with rain gauges, temperature sensors, humidity sensors, and soil temperature and humidity probes to continuously record dynamic environmental parameters that affect soil resistivity. The low-power wide-area IoT module operates in the 470-510 MHz frequency band and uses linear frequency modulation spread spectrum technology to realize data transmission of the test instrument, detection device, receiver and monitoring station.

4. The differentiated grounding platform setting system for pumped storage power stations according to claim 2, characterized in that, The four-dimensional geoelectric structure modeling unit includes a data fusion and interpolation calculation module, wherein the calculation steps of the interpolation calculation module include the following: Based on the discrete point data collected by the soil resistivity tester, and using the rock-soil interface data detected by the ground-penetrating radar as a hard constraint boundary, a high-resolution three-dimensional static soil resistivity basic model is generated by using the co-kriging interpolation algorithm. By correlating the time series data of rainfall and temperature collected by meteorological and environmental monitoring stations over the years with the corresponding soil resistivity change data, a dynamic influence function of soil resistivity based on a time series autoregressive integral moving average model is established. The dynamic influence function is applied to the three-dimensional static basic model to output a four-dimensional geoelectric structure model with a spatial resolution of 5 meters × 5 meters × 2 meters and a time resolution of 24 hours.

5. The differentiated grounding platform setting system for pumped storage power stations according to claim 2, characterized in that, The calculation steps of the fault risk assessment unit include the following: The expected maximum single-phase ground fault current value for each area is obtained from the main electrical system design database of the power station. At each spatial grid node of the four-dimensional geoelectric structure model, the expected grounding resistance, maximum contact voltage, and maximum step voltage are calculated under extreme dry season or deep freezing season conditions, based on the preset grounding body model. The weighted risk index R is calculated using the formula... index =w1·f(ρ(t))+w2·g(I k The risk distribution map is generated by ) + w3·h(U), where ρ(t) is the dynamic soil resistivity, and I k U is the short-circuit current, U is the contact or step voltage, f, g, and h are normalization functions, and w1, w2, and w3 are preset weighting coefficients with values ​​of 0.5, 0.3, and 0.2, respectively.

6. The differentiated grounding platform setting system for pumped storage power stations according to claim 1, characterized in that, The differentiated grounding platform engine module specifically includes: The grounding electrode performance library unit stores parameterized models of various standard and non-standard grounding electrodes. The grounding electrodes include horizontally laid flat steel grounding grids, vertically inserted angle steel grounding electrodes, deep well grounding electrodes, and flexible grounding modules made of conductive polymer and graphene composite materials. For each type of grounding electrode, the performance library stores simulation curve data of power frequency grounding resistance, impulse grounding resistance, and thermal stability performance under different soil resistivity. The hybrid electromagnetic field solver unit adopts a hybrid calculation strategy of finite element method and boundary element method, and directly calls the data in the four-dimensional geoelectric structure model as the dielectric parameters of its calculation domain to perform accurate calculation of grounding performance. The multi-objective optimization unit is a non-dominated sorting genetic algorithm II module, used to find the optimal solution with the optimization objectives of minimizing the total life cycle cost, minimizing the equivalent grounding resistance of the entire station, and ensuring that the contact voltage and step voltage are below the safety limit. The design scheme generation unit receives the Pareto optimal solution set output by the multi-objective optimization unit, and automatically generates the differentiated grounding platform design scheme, including grounding electrode construction drawings, material list and construction process description, based on the selected equilibrium point.

7. The differentiated grounding platform setting system for pumped storage power stations according to claim 6, characterized in that, The multi-objective optimization unit optimizes a total of three objectives, among which... Objective 1 corresponds to minimizing the total lifecycle cost of the grounding platform, and the specific formula is as follows: Among them, C material For material costs, C construction For construction costs, C maintenance The annual maintenance cost is given by r, the discount rate is given by t, and the number of years is given by t. Objective 2 corresponds to minimizing the equivalent grounding resistance of the entire station under the most unfavorable meteorological conditions determined by the four-dimensional geoelectric structure model; Objective 3 corresponds to ensuring that the contact voltage and step voltage at all critical locations throughout the field are lower than the safety limits specified in the national standard GB / T50065-2011.

8. The differentiated grounding platform setting system for pumped storage power stations according to claim 1, characterized in that, The intelligent management and control module for the entire lifecycle specifically includes: The distributed monitoring unit consists of multiple intelligent monitoring terminals. The terminals are installed in high-risk areas or key grounding nodes identified by the fault risk assessment unit and are used to monitor grounding resistance, grounding body to ground potential, soil temperature and humidity and corrosion rate in real time. The performance degradation prediction unit is a long short-term memory network model that takes historical data and real-time data collected by the distributed monitoring unit as input to predict the future performance degradation trend of the grounding platform and issue early warnings. The adaptive maintenance strategy unit is activated upon receiving an early warning signal. It is used to match and generate the optimal maintenance work order from a preset maintenance measure knowledge base based on the type and location of the early warning. The model closed-loop calibration unit is used to periodically compare the actual measured values ​​collected by the distributed monitoring unit with the theoretical calculated values, and trigger the inversion calculation program when the cumulative error exceeds a preset threshold, so as to reverse correct the local soil resistivity parameters in the four-dimensional geoelectric structure model.

9. A method for setting up a differentiated grounding platform in a pumped storage power station, characterized in that, The method is applied to the differential grounding platform setting system for pumped storage power stations according to any one of claims 1-8, wherein the method includes the following steps: The process involves performing a spatiotemporal multiphysics field characteristic description across the entire field. This includes acquiring soil resistivity, geological structure, topography, and meteorological data through multi-source data acquisition units deployed within the pumped storage power station area. Subsequently, a four-dimensional geoelectric structure modeling unit is used to fuse and process the acquired data, establishing a four-dimensional geoelectric structure model that reflects the non-uniform distribution of soil resistivity in three-dimensional space and its dynamic changes over time. Finally, using a fault risk assessment unit, combined with the expected short-circuit current level of the power station, a ground fault risk level distribution map for the entire field is calculated and generated based on this four-dimensional model. The optimization of differentiated grounding platform schemes is carried out. Specifically, the differentiated grounding platform engine module is started, and the four-dimensional geoelectric structure model and risk distribution map generated in step one are loaded through the hybrid electromagnetic field solver unit. Then, the multi-objective optimization unit aims to minimize the system's total life cycle cost, optimize grounding performance, and maximize safety margin. Using the grounding body model, size, and layout stored in the grounding body performance library unit as decision variables, the hybrid electromagnetic field solver unit is called to run a non-dominated sorting genetic algorithm to obtain a set of Pareto optimal design schemes. Finally, the design scheme generation unit determines and outputs a set of specific and differentiated grounding platform construction schemes for different risk areas from the optimal solution set. The system implements intelligent management and closed-loop control throughout the entire lifecycle of the grounding platform. After the grounding platform is constructed, distributed monitoring units deployed on-site conduct long-term continuous online monitoring of the key performance parameters and local environmental parameters of the grounding platform. The performance degradation prediction unit uses the monitoring data to predict the future state of the grounding platform and issue early warnings. The adaptive maintenance strategy unit automatically generates preventive maintenance tasks based on the early warning information. At the same time, the model closed-loop calibration unit continuously compares the measured data with the calculation results of the system model, and initiates an inversion program when significant deviations are found to correct and update the four-dimensional geoelectric structure model.

10. An electronic device, characterized in that, The electronic device includes a processor and a memory; wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to enable the electronic device to perform the method for setting up a differentiated grounding platform for a pumped storage power station as described in claim 9.

Images