Risk grade assessment method, system and equipment for hidden danger points of transformer substation based on artificial intelligence, and medium

Abstract

The invention discloses a risk grade assessment method, system, equipment and medium for hidden danger points of a transformer substation based on artificial intelligence, and relates to the technical field of disaster early warning, and the method comprises the steps: collecting the geological data of the hidden danger points, and analyzing the geological disaster occurrence mechanism; establishing a mathematical model for different geological disaster types to obtain geological disaster occurrence rules and characteristics; selecting hidden danger point risk assessment indexes according to geological disaster types; statistical analysis is carried out on the selected risk assessment indexes, so that assessment of the risks of the hidden danger points of the transformer substation is quantified; establishing a transformer substation hidden danger point risk assessment model according to the assessment indexes and an artificial intelligence technology; and adopting a multi-attribute decision analysis algorithm, and obtaining risk levels and evaluation results of the hidden danger points through the risk evaluation model. According to the method, a mathematical statistical method and an artificial intelligence technology are combined, a complex multi-factor coupling problem is processed more effectively, and a model output result is analyzed by adopting a multi-attribute decision analysis algorithm, so that evaluation is more accurate.

Description

Technical Field

[0001] This invention relates to the field of disaster early warning technology, and in particular to a method, system, equipment and medium for risk level assessment of potential hazards in substations based on artificial intelligence. Background Technology

[0002] With the continuous growth of electricity demand, substations, as key hubs in the power system, are of paramount importance for their safe and stable operation. However, substations often face various potential risks, among which geological disasters pose a serious threat to their safety. Earthquakes, landslides, and debris flows can damage substation infrastructure, leading to equipment damage, power outages, and causing significant economic losses and social impacts. However, current technologies for analyzing the impact of geological disasters on substations lack in-depth research into the mechanisms of geological disaster occurrence, the scientific rigor and comprehensiveness of risk assessment indicators, and the adaptability of assessment models and methods.

[0003] Chinese Patent Publication No. CN103606110A discloses a graph theory-based method for substation operation risk assessment. The specific steps are as follows: data input; constructing an input data module for substation operation risk assessment; calculating the probability of substation component outages using a component outage model module; simulating the randomness of substation component outages using a Monte Carlo module to form the substation system state; identifying the connectivity of the substation system state using graph theory to determine whether load points are connected to power supply points; and assessing the substation operation risk by calculating corresponding substation operation risk indicators. This invention considers the randomness of substation events, uses the Monte Carlo method to extract the substation system state, proposes a graph theory-based connectivity identification method, transforming the substation main wiring risk assessment into a connectivity identification problem between load points and power supply points within the substation, simplifying the complexity of the analysis problem; and achieves the purpose of substation operation risk assessment.

[0004] However, the above methods only assess the risk of component outages under the operating conditions of substations, focusing on connectivity issues and load loss risks caused by component outages. They do not consider complex external factors such as geological disasters, and the assessment dimensions are not comprehensive enough. The assessment model has certain applicability for assessing the risk of substation component outages, but it has limitations when facing different scenarios. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the problem that this invention aims to solve is that existing methods do not consider complex external factors such as geological disasters, the assessment dimensions are not comprehensive enough, and the assessment models have certain applicability for substation component outage risk assessment, but have limitations when facing different scenarios.

[0007] To address the aforementioned technical problems, this invention provides the following technical solution: a risk level assessment method for substation hazard points based on artificial intelligence, comprising: collecting geological data of substation hazard points; analyzing the geological disaster occurrence mechanism of substation hazard points to obtain the internal conditions and external inducing factors of geological disaster occurrence; establishing corresponding mathematical models for different types of geological disasters to obtain the occurrence patterns and characteristics of geological disasters; selecting corresponding hazard point risk assessment indicators based on the internal conditions and external inducing factors of geological disaster occurrence, the occurrence patterns and characteristics of geological disasters, and the environmental conditions of the substation; performing statistical analysis on the selected risk assessment indicators, calculating the basic statistics of each indicator, obtaining the distribution characteristics of the indicator data, establishing a distribution model of disaster occurrence probability based on the distribution characteristics, and fusing the occurrence probability with each indicator to obtain a risk index; combining the risk index with artificial intelligence technology to establish a substation hazard point risk assessment model; and using a multi-attribute decision analysis algorithm to obtain the risk level and assessment result of the substation hazard points through the risk assessment model.

[0008] As a preferred embodiment of the risk level assessment method for substation hidden danger points based on artificial intelligence described in this invention, the analysis of the geological disaster occurrence mechanism of substation hidden danger points includes analyzing the geological structure morphology, physical and mechanical parameters of soil and rock, groundwater level and flow state of the area where the substation is located based on geological structure analysis algorithm, rock and soil mechanical property analysis algorithm and hydrogeological condition analysis algorithm, respectively, to obtain the internal conditions and external inducing factors of geological disaster occurrence.

[0009] As a preferred embodiment of the risk level assessment method for substation hidden danger points based on artificial intelligence as described in this invention, the method of obtaining the occurrence law and characteristics of geological disasters includes constructing mathematical models describing displacement, velocity, and occurrence environment characteristics for different types of geological disasters, and obtaining the occurrence law and characteristics of geological disasters based on the analysis of the characteristics.

[0010] As a preferred embodiment of the risk level assessment method for substation hidden danger points based on artificial intelligence as described in this invention, the substation environmental conditions include the geographical environment, geological conditions, climate characteristics, and the types and configurations of its internal facilities.

[0011] As a preferred embodiment of the risk level assessment method for substation hidden danger points based on artificial intelligence as described in this invention, the following steps are taken: before performing statistical analysis on the selected risk assessment indicators, the acquired historical geological disaster data is preprocessed; the calculation of the basic statistics of each indicator includes calculating the mean, variance and standard deviation of each indicator to obtain the distribution characteristics of the indicator data.

[0012] As a preferred embodiment of the risk level assessment method for substation hidden danger points based on artificial intelligence as described in this invention, the establishment of the substation hidden danger point risk assessment model includes: reducing the dimensionality of the risk index, building an artificial intelligence assessment model framework based on a neural network model, and inputting the dimensionality-reduced risk index into the neural network model for training and optimization, thereby establishing the substation hidden danger point risk assessment model.

[0013] As a preferred embodiment of the risk level assessment method for substation hidden danger points based on artificial intelligence as described in this invention, the method for obtaining the risk level and assessment result of substation hidden danger points through the risk assessment model includes: based on the output of the risk assessment model, using a multi-attribute decision analysis algorithm to analyze the output result to obtain the risk level and assessment result of substation hidden danger points.

[0014] To address the aforementioned technical problems, this invention provides the following technical solution: a system for assessing the risk level of substation hazard points based on artificial intelligence, comprising: a data acquisition module, a pattern calculation module, an indicator quantification module, an assessment model construction module, and an assessment module; the data acquisition module collects geological data of substation hazard points, analyzes the geological disaster occurrence mechanism of substation hazard points, and obtains the internal conditions and external inducing factors of geological disaster occurrence; the pattern calculation module establishes corresponding mathematical models for different types of geological disasters to obtain the occurrence patterns and characteristics of geological disasters; the indicator quantification module selects corresponding hazard point risk assessment indicators based on the internal conditions and external inducing factors of geological disaster occurrence, the occurrence patterns and characteristics of geological disasters, and the environmental conditions of the substation, performs statistical analysis on the selected risk assessment indicators, calculates the basic statistics of each indicator, initially obtains the distribution characteristics of the indicator data, establishes a distribution model of disaster occurrence probability based on the distribution characteristics, and integrates the occurrence probability with each indicator to obtain a risk index; the assessment model construction module combines the risk index with artificial intelligence technology to establish a substation hazard point risk assessment model; the assessment module uses a multi-attribute decision analysis algorithm to obtain the risk level and assessment result of the substation hazard points through the risk assessment model.

[0015] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the risk level assessment method for substation hidden danger points based on artificial intelligence as described above.

[0016] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the risk level assessment method for substation hazard points based on artificial intelligence as described above.

[0017] The beneficial effects of this invention are as follows: By integrating knowledge from multiple disciplines, this invention deeply analyzes the mechanisms of geological disasters and comprehensively considers factors such as geological structure, rock and soil mechanics, and hydrogeology. Simultaneously, based on risk management theory, it selects assessment indicators covering multiple dimensions such as disaster probability, hazard level, and disaster loss. This overcomes the shortcomings of traditional methods, which often use single or inappropriately selected indicators. It can more accurately and comprehensively reflect the true risk status of potential hazards in substations, providing a reliable basis for subsequently developing targeted risk prevention and control measures.

[0018] This invention combines mathematical statistics with artificial intelligence, utilizing principal component analysis to reduce the dimensionality of risk assessment indicators, effectively reducing data redundancy and improving computational efficiency. Leveraging the powerful data processing and pattern recognition capabilities of neural network models, it uncovers the complex nonlinear relationship between geological hazards and substation risks, constructing a more accurate and adaptive risk assessment model. Compared to traditional assessment models, this model can more effectively handle complex multi-factor coupling problems. Furthermore, a multi-attribute decision analysis algorithm is used to analyze the model's output, obtaining the risk level and assessment results for substation hazard points, thus making the assessment more accurate. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a scenario diagram of a risk level assessment method for substation hidden danger points based on artificial intelligence, as shown in Example 1. Detailed Implementation

[0021] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0022] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0023] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides a risk level assessment method for substation hidden danger points based on artificial intelligence, including, for example... Figure 1 As shown:

[0024] Step 1: Collect geological data of potential hazards at substations and analyze the geological disaster occurrence mechanism at these hazards.

[0025] Specifically, taking a substation in a mountainous area as an example, the area is located near a plate boundary, with frequent geological activity and a large annual precipitation.

[0026] Geological structure analysis algorithms are used to obtain parameters such as fault distribution and fold morphology in the area; rock and soil mechanical property analysis algorithms are used to determine physical and mechanical parameters such as compressive strength and internal friction angle of the rock and soil; and a hydrogeological condition analysis system is used to monitor groundwater level and average flow velocity, such as a groundwater level of 5 meters and an annual average flow velocity of 0.5 meters / day.

[0027] These parameters indicate that the area has a complex geological structure, poor rock and soil stability, and frequent groundwater activity, making it prone to geological disasters such as landslides and debris flows.

[0028] In another alternative embodiment, taking a coastal substation as an example, the substation is located in a soft soil foundation area and is frequently affected by typhoons.

[0029] The geological structure analysis algorithm determines the thickness of the soft soil layer in the area, such as 10 meters; the rock and soil mechanics property analysis algorithm is used to determine the compression coefficient, shear strength and other parameters of the soft soil; the hydrogeological condition analysis system is used to monitor the groundwater level affected by tides, such as fluctuations of 2-4 meters.

[0030] Analysis: Soft soil foundations may experience geological disasters such as ground subsidence and foundation instability under the influence of heavy rainfall and storm surges caused by typhoons.

[0031] Step 2: Establish corresponding mathematical models for different types of geological disasters to obtain the occurrence patterns and characteristics of geological disasters.

[0032] For different types of geological hazards, mathematical models describing displacement, velocity, and environmental characteristics are constructed respectively. Based on the analysis of these characteristics, the occurrence patterns and characteristics of geological hazards are obtained.

[0033] Specifically, for the identified landslide and debris flow disaster types, differential equation modeling is used. For landslides, parameters such as landslide mass and sliding surface friction coefficient are set. Probabilistic statistical methods are used to collect data on the timing and scale of historical landslides and debris flows in the area. Numerical simulation modeling sets parameters such as the simulation area range and grid accuracy.

[0034] A differential equation model of landslide displacement over time is constructed, and a numerical simulation model is used to visually demonstrate the disaster occurrence process and accurately explore the laws and characteristics of geological disasters.

[0035] In another optional embodiment, for disaster types such as ground subsidence and foundation instability, differential equation modeling is used to set soft soil deformation parameters, loading rates, etc.; probabilistic statistical methods are used to collect historical typhoon impact data and ground subsidence monitoring data in the area; numerical simulation modeling sets parameters such as simulation time step and spatial range.

[0036] A differential equation model of the relationship between ground settlement and time and load is constructed, and the development trend of disaster is predicted through numerical simulation model.

[0037] Step 3: Select the corresponding risk assessment indicators for potential hazard points based on the type of geological disaster.

[0038] Specifically, based on the internal conditions and external triggering factors of geological disasters obtained in step 1, risk assessment indicators can be selected. For example, if soft soil foundations may experience geological disasters such as ground subsidence and foundation instability due to heavy rainfall and storm surges caused by typhoons, the selected indicators can be indicators such as rainfall intensity and soil water absorption capacity.

[0039] Based on the geological disaster occurrence patterns and characteristics obtained in step 2, specific risk assessment indicators can be selected, such as constructing a differential equation model of the relationship between ground subsidence and time and load for disaster types such as ground subsidence and foundation instability, and predicting the development trend of ground subsidence and foundation instability through numerical simulation models. The selected indicators can be subsidence depth, subsidence time, etc.

[0040] In addition, the selection of risk assessment indicators should be customized based on the specific circumstances of the potential hazards in the substation and the assessment objectives. For example, is it assessing the failure risk of internal facilities in the substation, or assessing the impact of the external environment (such as geological disasters, climate change, etc.) on the substation?

[0041] For example, if the objective is the impact of the external environment on the substation, then the indicators should focus on the probability of geological disasters, the scope of impact, and the intensity of the disasters.

[0042] Indicators should be selected based on risk management theory. Risk management theory suggests that risk assessment should be considered from multiple dimensions, including the probability of disaster occurrence, the severity (danger level) of the disaster, and the potential losses caused by the disaster. To ensure comprehensiveness, indicators from multiple levels should be selected, such as collecting data from historical disaster data, geological environment, facility status, meteorological conditions, and other aspects.

[0043] The selection of risk assessment indicators will be directly affected by the actual situation of the substation and its external environment, including its geographical environment, geological conditions, climate characteristics, and the types and configurations of its internal facilities.

[0044] For example, for substations located in mountainous areas, the probability and impact of landslides and debris flows are key indicators; while for substations located in coastal areas, the stability of typhoons, storm surges, and soft soil foundations is more important.

[0045] Step 4: Perform statistical analysis on the selected risk assessment indicators, calculate the basic statistics of each indicator, obtain the distribution characteristics of the indicator data, establish a distribution model of the probability of disaster occurrence based on the distribution characteristics, and integrate the probability of occurrence with each indicator to obtain the risk index, so as to quantify the risk assessment of substation hidden danger points.

[0046] Specifically, collect historical data, meteorological data, geological data, and substation facility operation data related to geological disasters. Data sources can include historical disaster records, geological survey reports, meteorological station data, and substation equipment monitoring data.

[0047] Data cleaning techniques are used to remove outliers and missing data. For potential outliers, a threshold can be set to remove them. The processed data will be used for further analysis.

[0048] Mean and variance analysis: First, calculate the mean, variance, standard deviation, and other basic statistics for each indicator to gain a preliminary understanding of the data's distribution characteristics. For example, the annual average probability and standard deviation of different types of geological disasters can be calculated to help understand the volatility of potential risks.

[0049] Regression analysis: For indicators that can be described by numerical relationships, regression analysis can be used to establish the relationship between disaster frequency and geological factors (such as precipitation, earthquake intensity, soil type, etc.). For example, linear regression or multiple regression models can be used to quantify the impact of different factors on disaster probability.

[0050] Probability distribution modeling: By establishing a distribution model of the probability of disaster occurrence (such as normal distribution, log-normal distribution, etc.), the probability of a disaster occurring within a certain period of time can be calculated. For example, a Poisson distribution model of disaster occurrence can be established using historical data to estimate the probability of a landslide occurring in the next year.

[0051] Taking common indicators as examples, these include the probability of geological disasters, the degree of danger, and the losses caused by the disasters. By comprehensively considering factors such as the probability of disasters, the degree of danger, and the losses, a comprehensive risk index R can be constructed, expressed by the formula:

[0052] R = P × D × L

[0053] Where P represents the probability of a disaster occurring, D represents the intensity of the disaster, and L represents the loss caused by the disaster.

[0054] Step 5: Combine the risk index with artificial intelligence technology to establish a risk assessment model for potential hazards in substations.

[0055] Specifically, the neural network model building module selects the backpropagation neural network, sets the number of network layers to 3, the number of input layer nodes to be determined according to the number of risk assessment indicators, the number of hidden layer nodes to be 10, and the number of output layer nodes to be 1.

[0056] The risk index processed in step 4 is dimensionality reduced, and the dimensionality-reduced data is input into the backpropagation neural network model for training and optimization to establish a risk assessment model for substation hidden danger points.

[0057] Step 6: Using a multi-attribute decision analysis algorithm, the risk level and assessment results of potential hazards in the substation are obtained through a risk assessment model.

[0058] Specifically, the multi-attribute decision analysis algorithm can employ the fuzzy comprehensive evaluation algorithm. Based on the neural network model, the risk level is assessed using the fuzzy comprehensive evaluation algorithm. The specific steps are as follows:

[0059] First, based on the output of the neural network model, determine the fuzzy membership functions for risk assessment indicators (such as disaster probability, disaster intensity, and losses). The membership function represents the degree of membership of each indicator value within a certain fuzzy level (e.g., low, medium, and high risk levels). Typically, the membership function can be set using expert judgment or historical data.

[0060] Based on the evaluation indicators and membership functions, a fuzzy relation matrix is ​​constructed. This matrix represents the fuzzy relationship between each indicator and different risk levels. For example, indicator 1 (disaster probability) may have some fuzzy relationship with low risk (0.2), medium risk (0.5), and high risk (0.3).

[0061] By synthesizing the fuzzy relation matrix and the weight vector, a fuzzy synthesis matrix is ​​obtained. Through fuzzy synthesis operations (usually weighted averaging), the influence of various indicators can be integrated to obtain the fuzzy assessment result of the comprehensive risk level.

[0062] Defuzzification methods such as the Max Membership Principle or the centroid method are used to transform the fuzzy assessment results into specific risk levels (e.g., low, medium, and high risk).

[0063] Finally, the overall risk level of the potential hazards in the substation is output. For example, if the overall assessment result is high risk, it indicates that the hazard requires close attention and corresponding preventive measures.

[0064] In another alternative embodiment, the multi-attribute decision analysis algorithm can also employ the analytic hierarchy process (AHP), with the following steps:

[0065] The risk assessment of potential hazards in substations is broken down into multiple levels, typically including the target level (risk level assessment), the criteria level (such as the probability of disaster occurrence, disaster intensity, loss, etc.), and the indicator level (specific assessment indicators).

[0066] For example, the target layer is "risk level", and the criteria layer includes disaster occurrence probability, disaster intensity, disaster loss, etc.

[0067] Based on historical data, a judgment matrix is ​​constructed by scoring the relative importance of each pair of evaluation indicators. For example, if the probability of a disaster occurring is considered more important than the intensity of the disaster, a higher weight score can be given.

[0068] Consistency checks (such as calculating the consistency ratio CR) are used to ensure the consistency of the judgment matrix. If the CR value exceeds the set threshold, it indicates that the consistency of the judgment matrix is ​​poor and needs to be adjusted.

[0069] The weights of each evaluation indicator are calculated using the eigenvector method or the weighted average method. For example, the weight of the probability of disaster occurrence is 0.4, the disaster intensity is 0.3, and the loss is 0.3.

[0070] The output of the neural network model (such as probability, intensity, loss, etc.) is combined with the weights of each indicator to calculate the comprehensive score of each potential hazard point. The comprehensive score is calculated as follows: Comprehensive score = Disaster occurrence probability score × weight + Disaster intensity score × weight + Disaster loss score × weight.

[0071] Risk levels are determined based on the overall score (e.g., a score range of 0-3 indicates low risk, 3-6 indicates medium risk, and 6-9 indicates high risk).

[0072] Example 2, the second embodiment of the present invention, differs from the first embodiment in that it provides an artificial intelligence-based risk level assessment system for substation hazard points, comprising a data acquisition module, a pattern calculation module, an indicator quantification module, an assessment model construction module, and an assessment module. The data acquisition module collects geological data of substation hazard points, analyzes the geological disaster occurrence mechanism of the hazard points, and obtains the internal conditions and external triggering factors of geological disasters. The pattern calculation module establishes corresponding mathematical models for different types of geological disasters to obtain the occurrence patterns and characteristics of geological disasters. The indicator quantification module selects corresponding hazard point risk assessment indicators based on the internal conditions and external triggering factors of geological disasters, the occurrence patterns and characteristics of geological disasters, and the environmental conditions of the substation. It performs statistical analysis on the selected risk assessment indicators, calculates the basic statistics of each indicator, initially obtains the distribution characteristics of the indicator data, establishes a distribution model of the probability of disaster occurrence based on the distribution characteristics, and integrates the probability of occurrence with each indicator to obtain a risk index. The assessment model construction module combines the risk index with artificial intelligence technology to establish a risk assessment model for substation hazard points. The assessment module uses a multi-attribute decision analysis algorithm to obtain the risk level and assessment result of the substation hazard points through the risk assessment model.

[0073] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0074] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0075] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0076] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented in combination with any of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0077] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A risk level assessment method for substation hidden danger points based on artificial intelligence, characterized in that: include, Collect geological data of potential hazards at substations, analyze the geological disaster occurrence mechanism of potential hazards at substations, and obtain the internal conditions and external triggering factors for geological disasters; Establish corresponding mathematical models for different types of geological hazards to obtain the occurrence patterns and characteristics of geological hazards; Based on the internal conditions and external triggering factors of geological disasters, the occurrence patterns and characteristics of geological disasters, and the environmental conditions of substations, corresponding risk assessment indicators for potential hazards are selected. Statistical analysis is performed on the selected risk assessment indicators, the basic statistics of each indicator are calculated, the distribution characteristics of the indicator data are obtained, a distribution model of the probability of disaster occurrence is established based on the distribution characteristics, and the probability of occurrence is integrated with each indicator to obtain the risk index. By combining risk indices with artificial intelligence technology, a risk assessment model for potential hazards in substations will be established. A multi-attribute decision analysis algorithm is used to derive the risk level and assessment results of potential hazards in substations through the aforementioned risk assessment model.

2. The risk level assessment method for substation hidden danger points based on artificial intelligence as described in claim 1, characterized in that: The analysis of the geological disaster occurrence mechanism at the substation potential hazard point includes, based on geological structure analysis algorithm, rock and soil mechanical property analysis algorithm, and hydrogeological condition analysis algorithm, analyzing the geological structure morphology, rock and soil physical and mechanical parameters, groundwater level and flow state of the substation area, respectively, to obtain the internal conditions and external inducing factors of geological disaster occurrence.

3. The risk level assessment method for substation hidden danger points based on artificial intelligence as described in claim 2, characterized in that: The method for obtaining the occurrence patterns and characteristics of geological disasters includes constructing mathematical models describing displacement, velocity, and environmental characteristics for different types of geological disasters, and obtaining the occurrence patterns and characteristics of geological disasters based on the analysis of these characteristics.

4. The risk level assessment method for substation hidden danger points based on artificial intelligence as described in claim 3, characterized in that: The environmental conditions of the substation include the geographical environment, geological conditions, climate characteristics, and the types and configurations of its internal facilities.

5. The risk level assessment method for substation hidden danger points based on artificial intelligence as described in claim 4, characterized in that: Before performing statistical analysis on the selected risk assessment indicators, the acquired historical geological disaster data is preprocessed. The calculation of the basic statistics for each indicator includes calculating the mean, variance, and standard deviation of each indicator to obtain the distribution characteristics of the indicator data.

6. The risk level assessment method for substation hidden danger points based on artificial intelligence as described in claim 5, characterized in that: The establishment of the substation hidden danger risk assessment model includes: reducing the dimensionality of the risk index, building an artificial intelligence assessment model framework based on a neural network model, and inputting the dimensionality-reduced risk index into the neural network model for training and optimization, thereby establishing the substation hidden danger risk assessment model.

7. The risk level assessment method for substation hidden danger points based on artificial intelligence as described in claim 6, characterized in that: The risk level and assessment results of substation hidden danger points obtained through the risk assessment model include: based on the output of the risk assessment model, a multi-attribute decision analysis algorithm is used to analyze the output results to obtain the risk level and assessment results of substation hidden danger points.

8. A risk level assessment system for substation hidden danger points based on artificial intelligence, employing the risk level assessment method for substation hidden danger points based on artificial intelligence as described in any one of claims 1 to 7, characterized in that: It includes a data acquisition module, a pattern calculation module, an indicator quantification module, an evaluation model construction module, and an evaluation module; The data acquisition module collects geological data of potential hazards in the substation, analyzes the geological disaster occurrence mechanism of the potential hazards in the substation, and obtains the internal conditions and external triggering factors for the occurrence of geological disasters. The pattern calculation module establishes corresponding mathematical models for different types of geological disasters to obtain the occurrence patterns and characteristics of geological disasters. The index quantification module selects corresponding risk assessment indicators for hidden danger points based on the internal conditions and external triggering factors of geological disasters, the occurrence patterns and characteristics of geological disasters, and the environmental conditions of substations. It performs statistical analysis on the selected risk assessment indicators, calculates the basic statistics of each indicator, obtains the distribution characteristics of the indicator data, establishes a distribution model of the probability of disaster occurrence based on the distribution characteristics, and integrates the probability of occurrence with each indicator to obtain the risk index. The assessment model construction module combines risk index with artificial intelligence technology to establish a risk assessment model for potential hazards in substations. The assessment module employs a multi-attribute decision analysis algorithm to derive the risk level and assessment results of potential hazards in substations through the risk assessment model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the risk level assessment method for substation hidden danger points based on any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the risk level assessment method for substation hidden danger points based on any one of claims 1 to 7.

Images