Assembly type steel structure transformer substation operation and maintenance management method and system, equipment and medium

Abstract

The invention discloses a fabricated steel structure transformer substation operation and maintenance management method and device, equipment and a medium, and the method comprises the steps: obtaining the operation parameters of a fabricated steel structure transformer substation, and carrying out the feature extraction of the operation parameters, and obtaining the operation state vector of the fabricated steel structure transformer substation; based on a fuzzy comprehensive evaluation method, risk identification is carried out according to the operation state vector evaluation, and the operation risk level of the fabricated steel structure transformer substation is determined; selecting a plurality of standard repair strategies from a preset repair strategy library according to the operation risk level; and performing repair simulation according to the running state vector and a standard repair strategy, determining a target repair strategy, and performing operation and maintenance management on the fabricated steel structure transformer substation based on the target repair strategy. Through state identification and risk level judgment of the fabricated steel structure transformer substation, a corresponding transformer substation repair strategy is determined, and a target repair strategy with an optimal effect is selected to provide operation and maintenance decision support, so that intelligent management of full-life-cycle operation and maintenance of the transformer substation is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of substation operation and maintenance, and particularly relates to a prefabricated steel structure substation operation and maintenance management method and system, equipment and a medium. BACKGROUND

[0002] As the core hub of modern power systems, substations bear the key functions of power voltage conversion, power flow regulation and stable supply, and their reliability and operation and maintenance efficiency directly affect the safety and economy of energy networks. With the accelerated construction of new power systems and the continuous increase of load density in the urbanization process, traditional substations face problems such as long construction period, high operation and maintenance cost, and lagging equipment state monitoring. Especially, prefabricated steel structure substations, while realizing rapid deployment and modular expansion, still have bottlenecks such as data fragmentation, decision-making relying on experience, and insufficient dynamic optimization of all factors, which makes it difficult to balance resource utilization and safety redundancy and to cope with the dynamic evolution and random risks of the whole life cycle of substations.

[0003] Current substation management field has preliminarily adopted Internet of Things and BIM technology for physical simulation of structure and equipment to simulate the dynamic evolution of the life cycle of substations, but existing technologies mainly focus on structure model visualization and power grid operation scheduling, and it is difficult to realize intelligent analysis of substation operation and maintenance status. SUMMARY

[0004] Therefore, it is necessary to propose a prefabricated steel structure substation operation and maintenance management method and system, equipment and a medium to select the best target repair strategy and provide operation and maintenance decision support, so as to realize intelligent management of the whole life cycle operation and maintenance of prefabricated steel structure substations.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a prefabricated steel structure substation operation and maintenance management method, which comprises: obtaining operation parameters of a prefabricated steel structure substation, performing feature extraction on the operation parameters to obtain an operation state vector of the prefabricated steel structure substation; performing risk identification according to the operation state vector evaluation based on a fuzzy comprehensive evaluation method to determine the operation risk level of the prefabricated steel structure substation; selecting a plurality of standard repair strategies from a preset repair strategy library according to the operation risk level, wherein the repair strategy library contains a plurality of standard repair strategies of substations corresponding to different operation risk levels; performing repair simulation according to the operation state vector and each standard repair strategy to determine a target repair strategy, and performing operation and maintenance management on the prefabricated steel structure substation based on the target repair strategy.

[0006] Further, the operation parameter is feature extracted to obtain an operation state vector of the prefabricated steel structure substation, specifically comprising: The operation parameter is processed by a sliding window according to a preset time step to obtain an operation parameter tensor of the prefabricated steel structure substation; The data in the operation parameter tensor is normalized to obtain a standard operation parameter tensor; The standard operation parameter tensor is feature extracted to obtain the operation state vector of the prefabricated steel structure substation.

[0007] Further, the operation feature parameter at least includes a structure surface feature image, a structure vibration acceleration, an environment temperature and an environment humidity of the prefabricated steel structure substation; The operation parameter is processed by a sliding window according to a preset time step to obtain an operation parameter tensor of the prefabricated steel structure substation, specifically comprising: The structure surface feature image is preprocessed to obtain a target structure surface feature image; The target structure surface feature image is input into a preset YOLO v8 algorithm for risk point identification to determine a target risk point of the prefabricated steel structure substation, wherein the risk point represents a position of an abnormal structure surface of the prefabricated steel structure substation; The target structure surface feature image, the structure vibration acceleration, the environment temperature and the environment humidity of the target risk point of the prefabricated steel structure substation are processed by a sliding window according to a preset time step to obtain the operation parameter tensor of the prefabricated steel structure substation.

[0008] Further, the operation state vector of the prefabricated steel structure substation includes surface changes, frequency trends, vibration energy, temperature changes and humidity changes.

[0009] Further, based on the fuzzy comprehensive evaluation method, the operation state vector evaluation is used for risk identification to determine the operation risk level of the prefabricated steel structure substation, specifically comprising: A substation operation and maintenance risk evaluation index system is determined according to related parameter types of the prefabricated steel structure substation, and each risk evaluation index is divided into different risk levels according to a preset rule, wherein the related parameter types include operation parameter types and other related parameter types; Based on the analytic hierarchy process and / or expert scoring method, a fuzzy relationship matrix is constructed according to the operation state vector and other related parameters of the prefabricated steel structure substation, wherein the fuzzy relationship matrix represents a risk level corresponding to each risk evaluation index; The fuzzy relationship matrix and a preset weight matrix are multiplied to obtain a fuzzy evaluation vector; determine an operation risk level of the prefabricated steel structure substation based on the fuzzy evaluation vector.

[0010] Further, the method further comprises: based on a preset reinforcement learning algorithm, performing repair simulation according to the operation state vector and each of the standard repair strategies to obtain a repair response index corresponding to each of the standard repair strategies, wherein the reinforcement learning algorithm is used to simulate the influence of different repair decisions on the operation performance of the prefabricated steel structure substation according to the operation state vector; performing weighted calculation according to the repair response index and a preset index weight to obtain a repair effect comprehensive score of each of the standard repair strategies; taking the standard repair strategy corresponding to the maximum repair effect comprehensive score as a target repair strategy to perform operation and maintenance management of the prefabricated steel structure substation based on the target repair strategy.

[0011] Further, the method further comprises: performing digital modeling on the prefabricated steel structure substation to build a digital twin model of the prefabricated steel structure substation; performing analysis according to the target repair strategy and the digital twin model, and image displaying operation and maintenance analysis results of the prefabricated steel structure substation.

[0012] To achieve the above-mentioned purposes, the second aspect of the present application provides a prefabricated steel structure substation operation and maintenance management system, the system comprising: a parameter acquisition module configured to acquire operation parameters of a prefabricated steel structure substation, perform feature extraction on the operation parameters, and obtain an operation state vector of the prefabricated steel structure substation; a risk assessment module configured to perform risk identification based on fuzzy comprehensive evaluation method according to the operation state vector evaluation, and determine an operation risk level of the prefabricated steel structure substation; a strategy selection module configured to select a plurality of standard repair strategies according to the operation risk level in a preset repair strategy library, wherein the repair strategy library contains a plurality of standard repair strategies of substations corresponding to different operation risk levels; performing repair simulation according to the operation state vector and each of the standard repair strategies to determine a target repair strategy, and performing operation and maintenance management of the prefabricated steel structure substation based on the target repair strategy.

[0013] To achieve the above object, the third aspect of the present application provides a computer readable storage medium, which stores a computer program, and the computer program, when executed by a processor, causes the processor to perform the steps of the method according to the first aspect.

[0014] To achieve the above object, the fourth aspect of the present application provides a computer device, which comprises a memory and a processor, and the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to perform the steps of the method according to the first aspect.

[0015] The embodiment of the present application has the following beneficial effects: The embodiment of the present application provides an assembled steel structure substation operation and maintenance management method, which comprises the following steps: obtaining operation parameters of an assembled steel structure substation, performing feature extraction on the operation parameters to obtain an operation state vector of the assembled steel structure substation; performing risk identification according to the operation state vector evaluation based on a fuzzy comprehensive evaluation method to determine the operation risk level of the assembled steel structure substation; selecting a plurality of standard repair strategies in a preset repair strategy library according to the operation risk level, wherein the repair strategy library comprises a plurality of standard repair strategies of substations corresponding to different operation risk levels; performing repair simulation according to the operation state vector and each standard repair strategy to determine a target repair strategy, and performing operation and maintenance management on the assembled steel structure substation based on the target repair strategy. Through the state identification and risk level judgment of the assembled steel structure substation, the corresponding substation repair strategy is determined, and the target repair strategy with the best effect is selected to provide operation and maintenance decision support, so that the intelligent management of the whole life cycle operation and maintenance of the assembled steel structure substation is realized. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0017] Among them: Figure 1 It is a flowchart of the assembled steel structure substation operation and maintenance management method in the embodiment of the present application; Figure 2 It is a structure block diagram of the assembled steel structure substation operation and maintenance management system in the embodiment of the present application; Figure 3 It is an internal structure diagram of the computer device in the embodiment of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0019] In order to improve the design quality and safety of the prefabricated steel structure substation, the present application proposes a prefabricated steel structure substation operation and maintenance management method based on artificial intelligence and digital twinning. Through digital twinning modeling, state recognition and risk point positioning, operation and maintenance decision support of the prefabricated steel structure substation, the performance perception, risk judgment and intelligent decision-making ability of the prefabricated steel structure substation are improved, so as to realize intelligent management of the prefabricated steel structure substation from design selection, prefabricated construction to whole life cycle operation and maintenance, thereby significantly improving the whole life cycle value creation ability of the substation facility.

[0020] In an embodiment of the present application, a prefabricated steel structure substation operation and maintenance management method is proposed, which can be referred to Figure 1 , Figure 1 The flowchart of the prefabricated steel structure substation operation and maintenance management method in the embodiment of the present application is shown in the figure, and the method comprises: Step 100, obtaining the operation parameters of the prefabricated steel structure substation, performing feature extraction on the operation parameters, and obtaining the operation state vector of the prefabricated steel structure substation.

[0021] In the present embodiment, a plurality of types of sensors are deployed in the prefabricated steel structure substation to collect different types of operation data. For example, the sensors can include unmanned aerial vehicles, vibration sensors, temperature sensors and humidity sensors, etc., wherein the unmanned aerial vehicles can collect image data of the prefabricated steel structure substation, the vibration sensors can collect structural vibration acceleration of the substation, the temperature sensors can collect surface temperature data and / or ambient temperature data of the prefabricated steel structure substation, and the humidity sensors can collect environmental humidity of the prefabricated steel structure substation. The different types of operation parameters collected are subjected to parameter feature extraction to obtain the operation state vector of the prefabricated steel structure substation.

[0022] Step 200, based on the fuzzy comprehensive evaluation method, the operation state vector is evaluated to identify the risk, and the operation risk level of the prefabricated steel structure substation is determined.

[0023] In the present embodiment, based on the fuzzy comprehensive evaluation method, the operation state vector of the prefabricated steel structure substation is evaluated to identify the risk of the connection structure, waterproof performance, fireproof performance, pipeline arrangement, etc., identify and locate the possible high-risk points of the structure, and determine the operation risk level of the prefabricated steel structure substation.

[0024] Step 300, selecting a plurality of standard repair strategies from a preset repair strategy library according to the operation risk level, wherein the repair strategy library contains a plurality of standard repair strategies of the substation corresponding to different operation risk levels.

[0025] In the embodiment, the repair strategy library contains the standard repair strategies that can be adopted by each operation risk level. Therefore, after determining the operation risk level of the prefabricated steel substation, the repair strategy that can be implemented by the prefabricated steel substation under the current condition can be determined.

[0026] Step 400, repairing simulation according to the operation state vector and each standard repair strategy to determine the target repair strategy, so as to realize operation and maintenance management of the prefabricated steel substation based on the target repair strategy.

[0027] In the embodiment, the influence of different standard repair strategies on the operation performance of the substation is evaluated through the operation state vector of the prefabricated steel substation, and then the optimal repair strategy is selected as the target repair strategy, so as to realize effective operation and maintenance management of the prefabricated steel substation based on the target repair strategy.

[0028] In the embodiment, the operation data is collected by deploying a plurality of sensors in the substation, and the feature extraction is performed to form the operation state vector, so that the real-time operation state of the substation can be accurately perceived, and multi-dimensional information such as structural vibration, temperature and humidity is covered. The risk is evaluated according to the operation state vector by using the fuzzy comprehensive evaluation method, so that the risks of the prefabricated steel substation in connection structure, waterproof, fireproof and pipeline arrangement and other aspects can be accurately identified, the high-risk points of the structure are located, the operation risk level is determined, and reliable basis is provided for subsequent targeted treatment, so that accidents caused by insufficient risk identification are avoided. The corresponding standard repair strategy is selected from the preset repair strategy library based on the operation risk level, and the repair simulation is performed in combination with the operation state vector to determine the optimal target repair strategy, so that the scientific decision of operation and maintenance management is realized, the decision accuracy and rationality are improved, and the stable operation of the substation is ensured. From the design selection, prefabricated construction to the whole life cycle operation and maintenance in each stage, the data fragmentation bottleneck is broken, the whole element dynamic optimization is realized, the resource utilization rate and safety redundancy are balanced, the dynamic evolution and random risk of the substation are effectively coped with, the whole life cycle value creation ability of the substation is improved, and strong support is provided for the operation and maintenance of the substation in the new power system construction and urbanization process, so as to ensure the safety and economy of the energy network.

[0029] In an embodiment of the present application, the prefabricated steel substation operation and maintenance management method further comprises: Step 500, digitally modeling the prefabricated steel substation to build a digital twin model of the prefabricated steel substation.

[0030] In this embodiment, based on BIM technology, digital modeling is performed on the prefabricated steel structure substation building, structure, equipment and pipeline.

[0031] Specifically, modeling the prefabricated steel structure substation specifically includes digital modeling of the substation enclosure structure, roof structure and door and window structure to optimize the waterproof and fireproof performance of the substation building and ensure the operation efficiency and safety of the steel structure substation.

[0032] Structure modeling specifically includes simulating the stress of the main steel structure, optimizing the column, beam and support system, and improving the stability of the structure; detailed simulation of the welding, bolt connection and nested assembly method of the steel components, optimization of the construction process and reduction of assembly errors. Equipment and pipeline modeling specifically includes digital modeling of each device in the substation according to its physical and electrical characteristics, including modeling of the geometry, size, material properties and electrical parameters of the device; simulating the pipeline layout, performing collision detection, optimizing the pipeline layout, and improving safety and maintainability.

[0033] Step 600, according to the target repair strategy and the digital twin model, analyze and image the operation and maintenance analysis results of the prefabricated steel structure substation.

[0034] In this embodiment, the prefabricated steel structure substation digital twin model and analysis results are displayed in a graphical manner, and different professional teams can collaborate on the same platform through cloud computing collaborative design, intelligent analysis and decision-making and other technical means. A human-computer interaction interface is provided to facilitate user operation and management of the model.

[0035] The operation and maintenance analysis results of the prefabricated steel structure substation are displayed in an image, so that the operation and maintenance personnel can intuitively and clearly understand the operation status, risk points and effect of the repair strategy after execution of the substation, and can timely discover potential problems and hidden dangers, quickly respond, and improve the efficiency and accuracy of operation and maintenance management. The provided operation and maintenance management human-computer interaction interface facilitates user operation and management of the model, and users can view relevant information of the substation at any time according to their own needs, monitor and manage the operation and maintenance work in real time, improve the participation and control of users in the operation and maintenance process, and improve the overall operation and maintenance management experience.

[0036] In an embodiment of the present application, step 100, feature extraction is performed on the operation parameters to obtain the operation state vector of the prefabricated steel structure substation, specifically including: Step 110, the operation parameters are processed by sliding window according to the preset time step to obtain the operation parameter tensor of the prefabricated steel structure substation.

[0037] In the embodiment, the sensors collect data at preset frequencies, for example, the image collection frequency of the unmanned aerial vehicle is once a week, the vibration sensor data collection frequency is 50 Hz, the temperature and humidity data collection frequency is once an hour, and the like.

[0038] Based on this, the time domain of the collected operation parameters is divided into multiple time steps according to a preset time step, and the operation parameter tensor of the assembled steel structure substation is formed according to the operation parameter data corresponding to each time step.

[0039] Step 120, normalizing the data in the operation parameter tensor to obtain a standard operation parameter tensor.

[0040] In the embodiment, the data in the operation parameter tensor is normalized, and the specific formula is:

[0041] In the formula, x min is the minimum value of the data of the target parameter type, x max is the maximum value of the data of the target parameter type, wherein the target parameter type is any one of all parameter types, x norm is the normalized standard data.

[0042] The data in the operation parameter tensor is normalized to unify the operation parameter data of different types and different dimensions to a standard scale, eliminate the data processing deviation caused by the value range difference between parameters, improve the comparability and consistency of the data, and provide more accurate and reliable data support for subsequent feature extraction and analysis. The normalized data can make the subsequent long short-term memory network algorithm and other models converge faster, improve the training efficiency and accuracy of the model, enhance the ability to capture long-term dependencies in the operation parameter time series, and thus more accurately extract the operation state features.

[0043] Step 130, according to the standard operation parameter tensor, feature extraction is performed to obtain an operation state vector of the assembled steel structure substation, which is used for subsequent structure state recognition or risk assessment.

[0044] In the embodiment, the normalized standard operation parameter tensor is input into a preset long short-term memory network algorithm network, the long-term dependencies in the time series of the standard operation parameter tensor are processed through a gating mechanism, and an operation state vector of the assembled steel structure substation is obtained.

[0045] The long short-term memory network algorithm is used to process the normalized standard operation parameter tensor, long-term dependence and key features in the operation parameter time sequence can be fully mined, and core feature vectors reflecting the operation state of the prefabricated steel structure substation are effectively extracted, thereby providing more representative and judgmental basis for subsequent risk assessment and operation and maintenance decision-making.

[0046] In an embodiment of the present application, the operation characteristic parameters at least include a structure surface feature image of the prefabricated steel structure substation, structure vibration acceleration, ambient temperature and ambient humidity. Then, Step 110, the operation parameters are processed by a sliding window according to a preset time step to obtain an operation parameter tensor of the prefabricated steel structure substation, specifically including: Step 111, the structure surface feature image is preprocessed to obtain a target structure surface feature image.

[0047] In the present embodiment, the structure surface feature image of the prefabricated steel structure substation photographed by the unmanned aerial vehicle is preprocessed by image cropping, grayscale, contrast enhancement and the like to remove noise in the image, facilitating subsequent feature extraction.

[0048] Step 112, the target structure surface feature image is input into a preset YOLO v8 algorithm for risk point identification to determine a target risk point of the prefabricated steel structure substation, wherein the risk point represents a position of an abnormality on the structure surface of the prefabricated steel structure substation.

[0049] In the present embodiment, the structure surface feature image of the substation is labeled with damage such as fire retardant paint falling off, node connection loosening, structure member cracking and structure surface rusting, and YOLO v8 is used for training to output a detection model, which is deployed to a visualization platform device to identify the damage position of the input target structure surface feature image based on the detection model, and determine the risk point, damage position, damage type and confidence of the prefabricated steel structure substation.

[0050] The YOLO v8 algorithm based on deep learning is used to identify the risk point of the preprocessed target structure surface feature image, which can quickly and accurately detect various damages on the structure surface of the prefabricated steel structure substation and determine detailed information such as damage position, type and confidence. The algorithm realizes the intelligentization and automation of risk point identification, without the need for manual checking and analysis of a large number of images, greatly saving manpower and time cost, improving the work efficiency of operation and maintenance management, and avoiding recognition errors caused by human factors, thereby enhancing the objectivity and accuracy of risk assessment.

[0051] Step 113, the target structure surface feature image of the target risk point of the assembled steel structure substation, the structure vibration acceleration, the environment temperature and the environment humidity are processed according to the preset time step in a sliding window, and the operation parameter tensor of the assembled steel structure substation is obtained.

[0052] In the embodiment, the time domain of the collected target structure surface feature image of the target risk point, the structure vibration acceleration, the environment temperature and the environment humidity is divided into multiple time steps according to the preset time step, and the operation parameter tensor of the assembled steel structure substation is formed according to the data corresponding to each time step.

[0053] By dividing the data according to the time step, the time sequence characteristics of the operation parameters are fully considered, and the change trend and mutual relationship of different operation parameters in the time dimension can be captured. This is of great significance for accurately evaluating the operation state of the substation and predicting potential risks, because many faults and abnormal conditions develop gradually over time. By analyzing the time series data, the dynamic operation behavior of the substation can be better understood, abnormal signs can be found in time, and measures can be taken in advance to prevent and repair.

[0054] In an embodiment of the present application, the operation state vector of the assembled steel structure substation includes surface change, frequency trend, vibration energy, temperature change and humidity change.

[0055] Specifically, the structure surface feature image is collected by the unmanned aerial vehicle, and the surface change can be determined by the performance of the target structure surface feature image at different time steps.

[0056] The vibration acceleration is monitored by a vibration sensor, and the vibration sensor uses a piezoelectric acceleration sensor. After obtaining the vibration acceleration data, the acceleration signal in the 0.1Hz-100Hz frequency band is extracted by band-pass Chebyshev filtering, and then the frequency spectrum curve is obtained by E =∑ a 2 ( t )Δ t The vibration energy is calculated; then the acceleration data is subjected to fast Fourier transform to obtain a frequency spectrum, and the frequency band energy can be obtained by integrating the frequency spectrum curve over the frequency band. According to the energy ratio between different frequency bands (such as the energy ratio of low frequency to high frequency), it can be judged whether the structure has stiffness degradation, and then the fatigue degree is evaluated by an empirical formula.

[0057] The environment temperature and the structure temperature are monitored by a temperature sensor, and then the temperature change is determined. Combined with the thermal expansion coefficient of the material, the thermal deformation amount of the structure is calculated, and then it can be evaluated whether the temperature effect of the structure component and the material exceeds the design allowable range.

[0058] The humidity around or on the surface of the measuring structure is monitored by the humidity sensor, and then the humidity change is determined to judge the corrosion activity of the environment to the steel structure, so as to evaluate the corrosion rate, corrosion mechanism and remaining life according to the empirical formula.

[0059] In an embodiment of the present application, step 200, based on the fuzzy comprehensive evaluation method, risk identification is performed according to the operating state vector evaluation, and the operating risk level of the prefabricated steel structure substation is determined, which specifically includes: Step 210, determining the substation operation and maintenance risk assessment index system according to the related parameter types of the prefabricated steel structure substation, and dividing each risk assessment index into different risk levels according to the preset rules, wherein the related parameter types include operating parameter types and other related parameter types.

[0060] In this embodiment, the operating parameter types can include surface topography, vibration frequency, vibration energy, environmental temperature, environmental humidity, surface damage location and surface damage degree, etc. Other related parameter types also include: structure parameter types, such as structure size, structure material, construction time, construction quality, waterproof design, fireproof design; environmental parameter types, such as foundation settlement, earthquake, strong / typhoon, region, season and groundwater corrosion, etc.; management factor types, such as management system, patrol system, emergency plan, accident frequency and data management, etc.; human factor types, such as professional skill, safety awareness, intentional damage, personnel allocation and violation operation, etc.

[0061] According to the above-mentioned related parameter types, the risk assessment indexes can also be divided into four categories: structure factors, environmental factors, management factors and human factors, each of which contains several risk assessment indexes.

[0062] In an embodiment, the specific indexes of the substation connection structure risk assessment include: load transfer, deformation adaptability, durability, construction convenience, maintenance and inspection convenience when the keel system is connected with the main body steel structure; structural strength, installation convenience, corrosion resistance, matching with external wall material, and waterproof design at the contact with the external wall plate of the enclosure structure embedded part.

[0063] In an embodiment, the specific indexes of the substation waterproof performance risk assessment include: external wall waterproof performance, roof waterproof performance, and bathroom waterproof performance. The waterproof design specifically includes three methods of material waterproofing, construction waterproofing, and structure waterproofing. In the waterproof performance identification, a digital twin model of the steel structure substation waterproof node is established to integrate information such as waterproof materials, structures, and construction nodes. Physical property parameters are added to the model to simulate the actual situation, analyze the flow of rainwater at key parts such as roof, joints, and walls, and judge the waterproof performance level of the substation.

[0064] In an embodiment, the specific indexes of the risk assessment of the fireproof performance of the substation include fireproof performance, corrosion resistance, construction convenience, environmental friendliness, durability and long-term effectiveness, multifunctionality, and economic benefits. In the identification of the fireproof performance, a digital twin model of the fireproof surface of the steel structure substation is established, information of fireproof coatings, structures, components, and the like is integrated, the fireproof performance and the physicochemical properties are analyzed, and the fireproof performance grade of the substation is determined.

[0065] In an embodiment, the specific indexes of the risk assessment of the pipeline arrangement of the power station include safety, functionality, economy, maintainability, and aesthetics. When the pipelines are arranged, the air pipes are preferentially arranged on the highest floor; the bridge is arranged above the water pipes to avoid the water pipes being arranged above the electrical bridge; the bus bridge is independently arranged on a floor, and the turning of the bus bridge is avoided; and the fire-fighting water pipes are arranged on the lower floor to facilitate the daily maintenance and repair of the fire-fighting facilities.

[0066] In the calculation of the risk indexes, each risk assessment index is divided into five grades of low risk, lower risk, medium risk, higher risk, and high risk according to relevant criteria. The relevant criteria can be one or a combination of a questionnaire survey method, an expert scoring method, and relevant specifications and standards, without limitation.

[0067] Referring to Table 1, Table 1 is a characteristic representation corresponding to each risk grade of different risk indexes. It can be understood that the risk indexes in the table are not all, but only some examples.

[0068] Table 1: Division criteria of risk indexes

[0069] The embodiment comprehensively considers the operating parameters and other related parameters, including multiple factors such as structure, environment, management, and human factors, to form a comprehensive risk assessment index system. This makes the risk assessment of the prefabricated steel structure substation more comprehensive and systematic, can identify potential risks from multiple dimensions, avoids the omission of risks due to inadequate consideration of factors, and provides a solid foundation for subsequent accurate risk grade determination. Each risk assessment index is divided into five grades of low risk, lower risk, medium risk, higher risk, and high risk according to the preset rules, and the characteristic representations of each grade are clearly defined, such as specific quantitative standards such as surface morphology damage area, construction time, and foundation settlement. This provides a more accurate basis for subsequent fuzzy evaluation, making the risk assessment results more valuable and operable.

[0070] Step 220, based on the analytic hierarchy process and / or expert scoring method, a fuzzy relationship matrix is constructed according to the operating state vector and other related parameters of the prefabricated steel structure substation. The fuzzy relationship matrix represents the risk grade corresponding to each risk assessment index.

[0071] In this embodiment, a fuzzy relationship matrix is ​​constructed to represent the membership of the risk assessment indicators to each risk level, that is, the possibility of each risk assessment indicator at each risk level. The fuzzy relationship matrix is ​​as follows:

[0072] Where, r i1 ~ r i5 Respectively represent the membership of risk assessment indicators in the five risk levels, the value range is [0,1], and the sum of the membership of each row is 1. R ] is the fuzzy relationship matrix.

[0073] By constructing a fuzzy relationship matrix and utilizing the analytic hierarchy process (AHP) and expert scoring methods, the degree of membership of risk assessment indicators to each risk level is numerically quantified, reflecting the likelihood of risk assessment indicators at different risk levels in a more scientific and objective manner. Incorporating the operating state vector and other relevant parameters of the prefabricated steel structure substation into the construction of the fuzzy relationship matrix fully integrates multiple aspects of information, enabling the risk assessment results to comprehensively reflect the actual operation of the substation, avoiding assessment bias caused by considering only a single factor. This provides more comprehensive and accurate data support for subsequent comprehensive evaluation of substation operation risk levels.

[0074] Step 230: Multiply the fuzzy relationship matrix and the preset weight matrix to obtain a fuzzy evaluation vector.

[0075] In this embodiment, the analytic hierarchy process (AHP) and expert scoring method are used to determine the risk assessment indicators and weights. The weights corresponding to the risk assessment indicators form a weight matrix. The fuzzy relationship matrix and the weight matrix are multiplied together to obtain a fuzzy evaluation result. Based on the fuzzy evaluation result, the operational risk level of the prefabricated steel structure substation is determined.

[0076] Specifically, the weights of each risk indicator are multiplied by the fuzzy relationship matrix to obtain the fuzzy evaluation vector { B}={ b 1, b 2, …, b 5}.

[0077] in .

[0078] Where, b j The probability of the target risk level, j Any one from 1 to 5, i 1~ n Any one of i risk assessment indicators,U i The first prefabricated steel structure substation i Risk assessment indicator parameters, r ij For the i The risk assessment indicator is j The degree of membership of a risk level.

[0079] Step 240: Determine the operation risk level of the prefabricated steel structure substation based on the fuzzy evaluation vector.

[0080] In this embodiment, the fuzzy evaluation vector { B The risk level corresponding to the maximum value in} is the operating risk level of the prefabricated steel structure substation.

[0081] This embodiment of the present invention achieves a comprehensive evaluation of substation operational risk by multiplying a fuzzy relationship matrix with a weight matrix to generate a fuzzy evaluation vector. This comprehensive evaluation method fully considers the impact of each risk assessment indicator and its weight, integrating information from multiple indicators into a comprehensive risk assessment result. This provides a comprehensive, objective, and quantitative basis for ultimately determining the substation's operational risk level, helping to more accurately grasp the substation's overall operational risk status.

[0082] In one embodiment of the present invention, the risk level includes low risk, lower risk, medium risk, higher risk and high risk. The repair strategy includes one or more repair actions, and the action vector a t ∈{A1, A2, A3, A4, A5, A6, A7, A8}, where A1 represents component replacement, A2 represents overall reinforcement, A3 represents local reinforcement, A4 represents node optimization, A5 represents structural repair welding, A6 represents surface treatment, A7 represents enhanced monitoring, and A8 represents no treatment. When the prefabricated steel structure transformer is at low risk, A7 or A8 can be adopted; when the prefabricated steel structure transformer is at relatively low risk, one or more combinations of A7, A6, and A5 can be adopted; when the prefabricated steel structure transformer is at medium risk, one or more combinations of A3, A4, and A5 can be adopted; when the prefabricated steel structure transformer is at high risk, one or more combinations of A1, A3, and A4 can be adopted; when the prefabricated steel structure transformer is at high risk, one or more combinations of A1 and A2 can be adopted.

[0083] In one embodiment of the present invention, step 400, performing a repair simulation based on the operating state vector and various standard repair strategies, determining a target repair strategy, and performing operation and maintenance management of the prefabricated steel structure substation based on the target repair strategy, specifically includes: Step 410, based on the preset reinforcement learning algorithm, simulate repair according to the operating state vector and each standard repair strategy to obtain the repair response index corresponding to each standard repair strategy, wherein the reinforcement learning algorithm is used to simulate the influence of different repair decisions on the operating performance of the prefabricated steel structure substation according to the operating state vector.

[0084] In this embodiment, the operating state vector of the prefabricated steel structure substation is s t =[ d t , f t , T t , M t ], wherein d t is the structure surface feature, f t is the structure frequency change, T t is the temperature change, M t is the humidity change. The operating state vector s t is input to the reinforcement learning model. The reinforcement learning model selects a repair strategy and performs a corresponding repair action s t according to the operating state vector a t to obtain the repair response index corresponding to each standard repair strategy.

[0085] In an embodiment, the repair response index includes repair time, repair cost, technical effect, and long-term operation and maintenance benefit, etc. (1) The repair time is the repair working hours of a single worker to complete this work, which can be evaluated according to historical data or expert scoring method. (2) The repair cost is the total cost of human cost, material cost, equipment cost, and management cost required in the repair process. (3) The technical effect is the performance of the steel structure of the substation after repair, including structure strength, surface appearance, structure durability, etc. The structure strength is evaluated by stress test, vibration frequency monitoring, etc. The structure durability is evaluated by calculating the corrosion resistance and fatigue life. The surface appearance is evaluated by expert scoring method. (4) The long-term operation and maintenance benefit is the weighted sum of the future maintenance cost reduction, service life extension, and failure rate reduction of the steel structure of the substation after repair.

[0086] Step 420, according to the repair response index and the preset index weight, weighted calculation is performed to obtain the repair effect comprehensive score of each standard repair strategy.

[0087] In the embodiment, the index parameters of repair time, repair cost, technical effect and long-term operation benefit corresponding to the repair strategy are weighted calculated according to the corresponding weights, and the repair effect comprehensive score of each standard repair strategy is obtained, and the reward function is as follows: r t ω 1 c 1- ω 2 c 2+ ω 3 c 3+ ω 4 c 4 In the formula, c 1 is the repair time score, c 2 is the repair cost score, c 3 is the technical effect score, c 4 is the long-term operation benefit score, ω 1~ ω 4 are the weight coefficients of each index respectively. The repair effect comprehensive score r t The greater the value is, the better the repair strategy effect is.

[0088] By calculating the repair effect comprehensive score of each standard repair strategy, the multi-dimensional repair response index can be integrated into a comprehensive score result scientifically and reasonably, the relative importance of different indexes in repair decision is fully considered, the deviation caused by simple average or subjective judgment is avoided, and the evaluation of repair strategy is more scientific and accurate.

[0089] Step 430, the standard repair strategy corresponding to the maximum repair effect comprehensive score is taken as the target repair strategy, and the assembly type steel structure substation is managed and maintained based on the target repair strategy.

[0090] In the embodiment, the repair strategy with the best repair effect is selected to manage and maintain the assembly type steel structure substation, so as to realize intelligent operation and maintenance of the assembly type steel structure substation.

[0091] Finally, the running state vector, repair action, reward function and state vector after repair s t +1 are stored in the experience pool of the reinforcement learning model, the experience replay mechanism and the target network are used to train the reinforcement learning model, the network is updated, so that the reinforcement learning can adaptively learn the optimal repair strategy, and the long-term optimization of the substation operation and maintenance is realized.

[0092] ​​The embodiment of the application takes the standard repair strategy corresponding to the maximum repair effect comprehensive score as the target repair strategy, realizes operation and maintenance decision based on data driving and intelligent algorithm, can automatically select the optimal repair strategy according to the actual operation state and repair demand of the substation, and improves the intelligent level of substation operation and maintenance management and the scientificity of decision-making. The operation state vector, repair action, reward function and state vector after repair are stored in the experience pool of the reinforcement learning model, and the experience replay mechanism and the target network are used to train the reinforcement learning model, so that the self-optimization and learning ability of the model are continuously improved. With the continuous accumulation of experience data, the reinforcement learning model can adaptively learn and adjust the optimal repair strategy, so that it can better adapt to the change of the operation state of the substation and the dynamic adjustment of the operation and maintenance demand, realize the long-term optimization and continuous improvement of the operation and maintenance of the substation, and further improve the operation performance, safety and economic benefit of the substation.

[0093] In an embodiment of the application, an assembly type steel structure substation operation and maintenance management system is provided, which can be referred to Figure 2 , Figure 2 The structural diagram of the assembly type steel structure substation operation and maintenance management system in the embodiment of the application is shown in FIG. 1, and the system comprises: The parameter acquisition module 201 is configured to acquire the operation parameters of the assembly type steel structure substation, perform feature extraction on the operation parameters, and obtain the operation state vector of the assembly type steel structure substation.

[0094] The risk assessment module 202 is configured to perform risk identification based on the fuzzy comprehensive evaluation method according to the operation state vector evaluation, and determine the operation risk level of the assembly type steel structure substation.

[0095] The strategy selection module 203 is configured to select a plurality of standard repair strategies from the preset repair strategy library according to the operation risk level, wherein the repair strategy library comprises a plurality of standard repair strategies of substations corresponding to different operation risk levels; perform repair simulation according to the operation state vector and each standard repair strategy, determine the target repair strategy, and perform operation and maintenance management on the assembly type steel structure substation based on the target repair strategy.

[0096] The assembled steel structure substation operation and maintenance management system of the embodiment of the present application can accurately perceive the real-time operation state of the substation by deploying various sensors in the substation to collect operation data and performing feature extraction to form an operation state vector; the fuzzy comprehensive evaluation method is used to evaluate the risk according to the operation state vector, which can accurately identify the risks of the assembled steel structure substation in multiple aspects, locate the high-risk points of the structure and determine the operation risk level, provide a reliable basis for subsequent targeted treatment, and avoid accidents caused by insufficient risk identification; based on the operation risk level, the corresponding standard repair strategy is selected from the preset repair strategy library, and the repair simulation is performed in combination with the operation state vector to determine the optimal target repair strategy, so that the scientific decision of operation and maintenance is realized, the decision accuracy and rationality are improved, and the stable operation of the substation is ensured. From the design selection, assembled construction to the whole life cycle operation of each stage, it plays a role, breaks the data fragmentation bottleneck, realizes the dynamic optimization of all factors, balances the resource utilization rate and safety redundancy, effectively copes with the dynamic evolution and random risk of the substation, improves the whole life cycle value creation ability of the substation, provides strong support for the operation and maintenance of the substation in the process of new power system construction and urbanization, and guarantees the safety and economy of the energy network.

[0097] Figure 3 The internal structure diagram of the computer device in one embodiment of the present application is shown. The computer device can be a terminal or a system. As shown in the figure, Figure 3 The computer device includes a processor, a memory and a network interface connected by a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and can also store a computer program. When the computer program is executed by the processor, the processor can implement each step in the above method embodiment. The internal memory can also store a computer program. When the computer program is executed by the processor, the processor can execute each step in the above method embodiment. Those skilled in the art can understand, Figure 3 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0098] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the computer program being executed by the processor to make the processor execute each step in the above method embodiment.

[0099] In one embodiment, a computer readable storage medium is provided, storing a computer program, the computer program being executed by the processor to make the processor execute each step in the above method embodiment.

[0100] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer readable storage medium, and when the program is executed, the processes of the above-mentioned embodiment methods can be included. Any reference to memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0101] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0102] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for operation and maintenance management of an assembled steel structure substation, characterized in that: The method comprises: Acquiring operating parameters of the prefabricated steel structure substation, performing feature extraction on the operating parameters, and obtaining an operating state vector of the prefabricated steel structure substation; Based on the fuzzy comprehensive evaluation method, risk identification is performed according to the operation state vector assessment to determine the operation risk level of the prefabricated steel structure substation; Selecting a plurality of standard repair strategies from a preset repair strategy library according to the operation risk level, wherein the repair strategy library contains a plurality of standard repair strategies for substations corresponding to different operation risk levels; A repair simulation is performed according to the operating state vector and each of the standard repair strategies to determine a target repair strategy, so as to perform operation and maintenance management of the prefabricated steel structure substation based on the target repair strategy.

2. The method according to claim 1, wherein The feature extraction of the operating parameters to obtain the operating state vector of the prefabricated steel structure substation specifically includes: Performing sliding window processing on the operating parameters according to a preset time step to obtain an operating parameter tensor of the prefabricated steel structure substation; Normalizing the data in the operating parameter tensor to obtain a standard operating parameter tensor; Feature extraction is performed based on the standard operating parameter tensor to obtain an operating state vector of the prefabricated steel structure substation.

3. The method according to claim 2, wherein The operating characteristic parameters at least include the structural surface characteristic image, structural vibration acceleration, ambient temperature and ambient humidity of the prefabricated steel structure substation; Then, the operating parameters are subjected to sliding window processing according to a preset time step to obtain the operating parameter tensor of the prefabricated steel structure substation, which specifically includes: Preprocessing the structural surface feature image to obtain a target structural surface feature image; Inputting the target structure surface feature image into a preset YOLO v8 algorithm to perform risk point identification, and determining the target risk points of the prefabricated steel structure substation, wherein the risk points represent locations where abnormalities occur on the surface of the prefabricated steel structure substation; The target structural surface feature image, structural vibration acceleration, ambient temperature and ambient humidity of the target risk point of the prefabricated steel structure substation are subjected to sliding window processing according to a preset time step to obtain the operating parameter tensor of the prefabricated steel structure substation.

4. The method according to claim 3, wherein The operating state vector of the prefabricated steel structure substation includes surface changes, frequency trends, vibration energy, temperature changes and humidity changes.

5. The method according to claim 1, wherein The fuzzy comprehensive evaluation method is used to perform risk identification based on the operation state vector assessment to determine the operation risk level of the prefabricated steel structure substation, specifically including: Determine a substation operation and maintenance risk assessment index system based on relevant parameter types of the prefabricated steel structure substation, and divide each risk assessment index into different risk levels according to preset rules, wherein the relevant parameter types include operation parameter types and other relevant parameter types; Based on the analytic hierarchy process and / or the expert scoring method, a fuzzy relationship matrix is ​​constructed according to the operating state vector and other relevant parameters of the prefabricated steel structure substation, wherein the fuzzy relationship matrix represents the risk level corresponding to each risk assessment indicator; Multiplying the fuzzy relationship matrix and a preset weight matrix to obtain a fuzzy evaluation vector; An operation risk level of the prefabricated steel structure substation is determined based on the fuzzy evaluation vector.

6. The method according to claim 1, wherein The repair simulation is performed according to the operating state vector and each of the standard repair strategies to determine a target repair strategy, so as to perform operation and maintenance management of the prefabricated steel structure substation based on the target repair strategy, specifically including: Based on a preset reinforcement learning algorithm, a repair simulation is performed according to the operating state vector and each of the standard repair strategies to obtain a repair response indicator corresponding to each of the standard repair strategies, wherein the reinforcement learning algorithm is used to simulate the impact of different repair decisions on the operating performance of the prefabricated steel structure substation according to the operating state vector; Perform weighted calculation based on the repair response index and the preset index weight to obtain a comprehensive score of the repair effect of each standard repair strategy; The standard repair strategy corresponding to the maximum comprehensive repair effect score is used as the target repair strategy, so as to perform operation and maintenance management of the prefabricated steel structure substation based on the target repair strategy.

7. The method according to claim 1, wherein The method further comprises: Digitally modeling the prefabricated steel structure substation to build a digital twin model of the prefabricated steel structure substation; An analysis is performed based on the target repair strategy and the digital twin model, and the operation and maintenance analysis results of the prefabricated steel structure substation are displayed graphically.

8. An operation and maintenance management system for an assembled steel structure substation, characterized in that: The system comprises: A parameter acquisition module is used to acquire the operating parameters of the prefabricated steel structure substation, perform feature extraction on the operating parameters, and obtain an operating state vector of the prefabricated steel structure substation; a risk assessment module, configured to identify risks based on the fuzzy comprehensive evaluation method and the operation state vector assessment to determine the operation risk level of the prefabricated steel structure substation; a strategy selection module, configured to select a plurality of standard repair strategies from a preset repair strategy library according to the operation risk level, wherein the repair strategy library contains a plurality of standard repair strategies for substations corresponding to different operation risk levels; A repair simulation is performed according to the operating state vector and each of the standard repair strategies to determine a target repair strategy, so as to perform operation and maintenance management of the prefabricated steel structure substation based on the target repair strategy.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

Images