Water conservancy project risk early warning analysis method and system based on multi-source information

Abstract

The invention relates to the technical field of risk management, in particular to a water conservancy project risk early warning analysis method and system based on multi-source information, and the method comprises the following steps: dividing a dam body, a flood discharge gate and a spillway region according to spatial dimensions, extracting leakage monitoring records of a flood season, a dry season and an emergency weather event period, and storing the leakage monitoring records; and calculating a trigger factor frequency to generate a trigger factor feature sequence. According to the method, through hierarchical division of space and time dimensions, extraction of trigger factor frequency and analysis of support degree and confidence degree are combined, so that extraction of risk factor features is more comprehensive and accurate. In the construction of the dynamic propagation path, the spatial trajectory and the time evolution rule of the risk factor are deeply analyzed, so that the propagation path of the risk factor is clearly displayed, the accurate prediction of the risk diffusion region is realized, and a basis is provided for the division of the risk level in the subsequent region.

Description

Technical Field

[0001] The present invention relates to the technical field of risk management, and particularly to a risk early warning analysis method and system for water conservancy projects based on multi-source information. Background Art

[0002] The technical field of risk management includes multiple aspects such as risk identification, risk assessment, and risk control. The core content is to scientifically analyze and predict potential threats that may exist, so as to reduce or avoid losses caused by uncertain factors. In the technical field of risk management, information collection and analysis technologies, big data processing technologies, and multi-source information fusion technologies are widely used to dynamically monitor and early warn various risks.

[0003] Among them, the risk early warning analysis method for water conservancy projects refers to a method of analyzing and predicting potential risk factors in water conservancy projects through multi-source information collection, information fusion, and risk assessment. It covers technical matters such as external environment information collection, structural characteristic analysis, and real-time monitoring data processing of water conservancy projects. It is mainly based on the collection and fusion of multi-source information, combined with historical operation data for systematic risk modeling and dynamic update, and identifies potential threats and hidden dangers of water conservancy projects through risk assessment methods.

[0004] Existing technologies are difficult to effectively process complex spatial and temporal data in water conservancy projects in a hierarchical manner, resulting in incomplete extraction and assessment of risk factors. For example, in existing technologies, monitoring data is often simply classified according to a single dimension, without combining the characteristics of spatial scope and time period at the same time, which makes it difficult to accurately extract the characteristics of risk factors in different regions and time periods. In addition, existing technologies rely mostly on static data models for identifying risk propagation paths and are difficult to dynamically analyze the propagation laws of risk factors. For example, when the leakage monitoring data in a certain area of a dam suddenly increases, existing technologies cannot track the diffusion trend of this data in the entire area, which may lead to a lag in the judgment of risks in the downstream area. In the classification and grading of risk factors, existing technologies often rely on a single threshold for division and are difficult to handle the ambiguity and uncertainty in complex data. For example, the change in the risk level within a region may be misjudged due to a single outlier, affecting the reliability of the overall risk assessment. In terms of time series analysis, existing technologies lack accurate dynamic feature extraction for identifying sudden increase points and sudden decrease points in risk changes and are difficult to capture the key changes of risk factors. For example, during the short period of the flood season when the leakage data fluctuates violently, existing technologies may fail to timely identify the sudden increase points and cannot accurately judge the risk change trend in the critical time period. This shortcoming may cause incorrect assessment of the diffusion range and severity of flood season risks, increasing the potential safety hazards of water conservancy projects. Summary of the Invention

[0005] To solve the technical problems existing in the prior art, an embodiment of the present invention provides a risk early warning analysis method and system for water conservancy projects based on multi-source information. The technical solution is as follows:

[0006] A risk early warning analysis method for water conservancy projects based on multi-source information, comprising the following steps:

[0007] S1: Divide the dam body, flood discharge sluice and spillway areas according to the spatial dimension, extract the leakage monitoring records during the flood season, dry season and sudden weather event cycle, and calculate the trigger factor frequency to generate a trigger factor characteristic sequence;

[0008] S2: Extract the trigger factor frequency in the trigger factor characteristic sequence, compare it with the risk threshold to screen out risk factors, analyze the risk state offset relationship in the segmented interval, and determine the spatial propagation path to obtain a risk propagation path dynamic sequence;

[0009] S3: Based on the risk propagation path dynamic sequence, construct a fuzzy evaluation index, divide the leakage monitoring point data into fuzzy values and perform weighted processing to generate a regional risk fuzzy distribution characteristic;

[0010] S4: Perform clustering analysis on the regional risk fuzzy distribution characteristics, extract the differences in the characteristics of local area risk factors, identify the relevance and interaction effects, and form a multi-scale risk distribution characteristic after classification by level;

[0011] S5: Extract the time series of risk factors in the multi-scale risk distribution characteristic, predict the future change trend, analyze the sudden increase points and sudden decrease points to construct a distribution trend curve, and generate risk early warning information for water conservancy projects.

[0012] The improvement of the present invention is that the trigger factor characteristic sequence includes the support degree, confidence degree and trigger frequency of the trigger factor within a time period, the risk propagation path dynamic sequence is specifically the spatial propagation path, time propagation characteristics and risk state offset relationship of risk factors, the regional risk fuzzy distribution characteristic includes the risk level after fuzzyization, the time series corresponding to the risk level and the spatial distribution state, the multi-scale risk distribution characteristic specifically refers to the risk distribution characteristics within a local area, the relevance characteristics between regions and the classification results by level, and the risk early warning information for water conservancy projects includes the sudden increase points, sudden decrease points of risk changes and the corresponding time distribution trend curve.

[0013] The improvement of the present invention is that the specific steps of dividing the dam body, flood discharge sluice and spillway areas according to the spatial dimension, extracting the leakage monitoring records during the flood season, dry season and sudden weather event cycle, and calculating the trigger factor frequency to generate a trigger factor characteristic sequence are as follows:

[0014] S101: Based on the water conservancy project monitoring data, divide the dam body, flood discharge sluice and spillway areas according to the spatial dimension, divide the data set of each area into flood season, dry season and sudden weather event cycles according to the time dimension, extract the leakage monitoring records of each time period, and generate the regional time-segmented leakage monitoring records;

[0015] S102: Based on the regional time-segmented leakage monitoring records, compare the leakage monitoring values of each monitoring point with the preset leakage threshold, extract the triggering factors exceeding the leakage threshold and calculate the triggering frequency, and conduct statistical analysis according to the triggering frequency to generate the triggering factor frequency analysis result;

[0016] S103: Based on the triggering factor frequency analysis result, extract the timing characteristics of the triggering factors in each time period according to the time series change trend of the triggering factors, and conduct classification processing on the timing changes to generate the triggering factor characteristic sequence.

[0017] The improvement of the present invention is that the specific steps of extracting the triggering factor frequencies in the triggering factor characteristic sequence, comparing with the risk threshold to screen risk factors, analyzing the risk state offset relationship in the segmented interval, and determining the spatial propagation path to obtain the dynamic sequence of the risk propagation path are as follows:

[0018] S201: Based on the triggering factor characteristic sequence, divide the triggering factor frequencies in each time period into intervals, extract the triggering factor frequencies of each interval and compare with the preset risk frequency threshold, screen the risk factors exceeding the risk frequency threshold, and generate the interval risk factor screening result;

[0019] S202: Based on the interval risk factor screening result, analyze the change of the risk value in the segmented interval corresponding to the screened risk factors, extract the state offset relationship of the risk factors in the segmented interval, and generate the risk state offset relationship characteristic;

[0020] S203: Based on the risk state offset relationship characteristic, track the trajectory of the risk factors in the spatial dimension, and determine the propagation path by analyzing the spatial correlation and time evolution characteristics of the triggering factors to generate the dynamic sequence of the risk propagation path.

[0021] The improvement of the present invention is that based on the dynamic sequence of the risk propagation path, the specific steps of constructing a fuzzy evaluation index, dividing the leakage monitoring point data into fuzzy values and performing weighted processing to generate the regional risk fuzzy distribution characteristic are as follows:

[0022] S301: Based on the dynamic sequence of the risk propagation path, extract the risk factor propagation paths in the corresponding areas, call the multi-source monitoring data of the corresponding areas, classify and sort out the data of the leakage monitoring points and assign risk levels to generate the regional risk level data;

[0023] S302: Based on the regional risk level data, construct fuzzy evaluation indicators for the corresponding region, divide the data of each leakage monitoring point into multiple fuzzy values according to the risk level range, perform fuzzy value archiving processing on the data of all monitoring points, and generate regional fuzzy monitoring data;

[0024] S303: Based on the regional fuzzy monitoring data, call the time series monitoring data within the region, perform weighted processing on the fuzzy values of the monitoring points in each time period, obtain the fuzzy distribution state in each time period, and generate the regional risk fuzzy distribution characteristics.

[0025] The improvement of the present invention is that for constructing the fuzzy evaluation indicators for the corresponding region, the formula is adopted:

[0026]

[0027] Calculate the fuzzy value μ(x) of the monitoring point;

[0028] where x is the actual leakage amount of the leakage monitoring point, k is the parameter for adjusting the steepness of the fuzzy function curve, c is the intermediate value of the risk level, α is the fuzzy compensation coefficient, and σ is the standard deviation of the regional leakage amount.

[0029] The improvement of the present invention is that for performing weighted processing on the fuzzy values of the monitoring points in each time period, the formula is adopted:

[0030]

[0031] Calculate the fuzzy distribution state W within the target time period t , which is the fuzzy value reflecting the overall risk level of the region within this time period, and the value range is from 0 to 1;

[0032] where w i is the weight of the i-th monitoring point, β i is the time correlation factor of the i-th monitoring point, and n is the total number of monitoring points within this time period.

[0033] The improvement of the present invention is that for performing cluster analysis on the regional risk fuzzy distribution characteristics, extracting the characteristics differences of local regional risk factors, identifying the relevance and interaction effects, and forming multi-scale risk distribution characteristics after classification by levels, the specific steps are as follows:

[0034] S401: Based on the regional risk fuzzy distribution characteristics, perform clustering operations on the risk data of each local region in the distribution characteristics, extract the risk factor difference characteristics between local regions, and generate local risk factor difference characteristics;

[0035] S402: Based on the local risk factor difference characteristics, identify the interaction effects among multiple risk factors, analyze the distribution characteristics and correlation degrees of the risk factors, extract the risk factors whose correlation exceeds the preset correlation threshold, and generate risk factor correlation characteristics;

[0036] S403: Based on the risk factor correlation characteristics, classify and grade the risk factors exceeding the preset correlation threshold according to the distribution range and characteristics, and combine the distribution characteristics of the local area and the overall area to form multi-scale risk distribution characteristics.

[0037] The improvement of the present invention is as follows. The specific steps for extracting the time series of risk factors in the multi-scale risk distribution characteristics, predicting the future change trend, analyzing the sudden increase points and sudden decrease points to construct a distribution trend curve, and generating water conservancy project risk warning information are as follows:

[0038] S501: Based on the multi-scale risk distribution characteristics, extract the time series corresponding to each category of risk factors, clean and normalize the data of the time series, extract the characteristic values of the changes of the risk factors in the time series and mark the change trend, and generate risk factor time series characteristics;

[0039] S502: Based on the risk factor time series characteristics, identify the sudden increase points and sudden decrease points of the characteristic values of the risk changes in the time series, and combine the change rate and characteristic range within the time series to determine the key time periods of the risk changes, and generate risk mutation key time period characteristics;

[0040] S503: Based on the risk mutation key time period characteristics, construct the distribution trend curve of the time series, mark the sudden increase points and sudden decrease points on the time series curve, extract the visual distribution information of the risk areas and time periods, and generate water conservancy project risk warning information.

[0041] A water conservancy project risk warning analysis system based on multi-source information, the system includes:

[0042] The area division and feature extraction module, based on the water conservancy project monitoring data, divides the dam body, flood discharge sluice and spillway areas according to the spatial dimension, extracts the leakage monitoring records during the flood season, dry season and sudden weather event cycle, calculates the trigger factor frequency and analyzes its change characteristics in combination with the time dimension, and generates a trigger factor characteristic sequence;

[0043] The risk propagation path analysis module, based on the trigger factor characteristic sequence, extracts the trigger factor frequency values in each time period, compares the trigger factor frequency with the risk frequency threshold to screen out the risk factors, analyzes the state offset characteristics of the risk factors in the segmented intervals, and determines the propagation path in combination with the time and space dimensions, and generates a risk propagation path dynamic sequence;

[0044] Based on the dynamic sequence of the risk propagation path, the fuzzy distribution generation module constructs fuzzy evaluation indicators within the region, divides the leakage monitoring point data into fuzzy values, performs weighted processing on the monitoring data according to the fuzzy values, extracts the risk fuzzy distribution for each time period, and generates the regional risk fuzzy distribution characteristics;

[0045] Based on the regional risk fuzzy distribution characteristics, the risk factor grading and association module clusters the risk factor characteristics of the local regions, extracts the differential characteristics between the local regions, combines the relevance and interaction effects among multiple risk factors, grades the risk factors, and generates the multi-scale risk distribution characteristics;

[0046] Based on the multi-scale risk distribution characteristics, the risk early warning and trend prediction module extracts the time series of the risk factors, analyzes the change trend in the time series, identifies the sudden increase points and sudden decrease points in the risk change, constructs the distribution trend curve in combination with the trend characteristics, and generates the water conservancy project risk early warning information.

[0047] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include:

[0048] Through the hierarchical division in the spatial and temporal dimensions, combined with the extraction of the trigger factor frequency, support degree and confidence analysis, the extraction of the risk factor characteristics is made more comprehensive and accurate. In the construction of the dynamic propagation path, by deeply analyzing the spatial trajectory and temporal evolution law of the risk factors, not only the propagation path of the risk factors is clearly shown, but also the accurate prediction of the risk diffusion region is realized, providing a basis for the subsequent division of the risk levels within the region. The introduction of the fuzzy evaluation indicators and the fuzzy processing of the monitoring data overcome the uncertainty and fuzziness between different types of monitoring data, and improve the analysis ability of the risk level distribution characteristics. In the clustering operation of the regional risk factors, by identifying the risk differences between the local regions and the relevance between the regions, the classification and grading of the risks of the local and overall regions are realized, and a risk assessment system from a global perspective is established. Through the time series analysis and the identification of the sudden increase points and sudden decrease points, combined with the construction of the distribution trend curve, the risk changes in the key time periods are effectively captured, providing visual dynamic risk early warning information for the managers. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0050] Figure 1 It is the method flow chart of the present invention;

[0051] Figure 2 This is a schematic diagram of the refined process of step S1 of the present invention;

[0052] Figure 3 This is a schematic diagram of the refined process of step S2 of the present invention;

[0053] Figure 4 This is a schematic diagram of the refined process of step S3 of the present invention;

[0054] Figure 5 This is a schematic diagram of the refined process of step S4 of the present invention;

[0055] Figure 6 This is a schematic diagram of the refined process of step S5 of the present invention;

[0056] Figure 7 This is a system module diagram of the present invention. Specific embodiments

[0057] The following will describe the technical solutions in the present invention in conjunction with the accompanying drawings.

[0058] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Rather, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0059] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when their differences are not emphasized, the meanings they express are the same. "Of", "corresponding" and "corresponding" can sometimes be used interchangeably. It should be noted that when their differences are not emphasized, the meanings they express are the same.

[0060] In the embodiments of the present invention, sometimes subscripts such as W1 may be written in a non-subscript form such as W1. When their differences are not emphasized, the meanings they express are the same.

[0061] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail in conjunction with the accompanying drawings and specific embodiments.

[0062] The embodiments of the present invention provide a water conservancy project risk early warning analysis method based on multi-source information, including the following steps:

[0063] S1: Divide the dam body, flood discharge sluice and spillway areas according to the spatial dimension, extract the leakage monitoring records during the flood season, dry season and sudden weather event cycle, and calculate the trigger factor frequency to generate the trigger factor characteristic sequence;

[0064] S2: Extract the trigger factor frequencies in the trigger factor characteristic sequence, compare them with the risk thresholds to screen the risk factors, analyze the risk state offset relationship in the segmented intervals, and determine the spatial propagation path to obtain the dynamic sequence of the risk propagation path;

[0065] S3: Based on the dynamic sequence of the risk propagation path, construct fuzzy evaluation indicators, divide the leakage monitoring point data into fuzzy values and perform weighted processing to generate the regional risk fuzzy distribution characteristics;

[0066] S4: Conduct cluster analysis on the regional risk fuzzy distribution characteristics, extract the differences in the characteristics of the risk factors in the local areas, identify the relevance and interaction effects, and form the multi-scale risk distribution characteristics after classification by levels;

[0067] S5: Extract the time series of the risk factors in the multi-scale risk distribution characteristics, predict the future change trend, analyze the sudden increase points and sudden decrease points to construct the distribution trend curve, and generate the risk warning information for the water conservancy project;

[0068] The trigger factor characteristic sequence includes the support degree, confidence degree and trigger frequency of the trigger factor within the time period. The dynamic sequence of the risk propagation path is specifically the spatial propagation path of the risk factor, the time propagation characteristics and the risk state offset relationship. The regional risk fuzzy distribution characteristics include the risk levels after fuzzyization, the time series corresponding to the risk levels and the spatial distribution states. The multi-scale risk distribution characteristics specifically refer to the risk distribution characteristics within the local areas, the relevance characteristics between regions and the classification results by levels. The risk warning information for the water conservancy project includes the sudden increase points, sudden decrease points of the risk change and the corresponding time distribution trend curve.

[0069] Please refer to Figure 2 , the specific steps for dividing the dam body, flood discharge sluice and spillway areas according to the spatial dimension, extracting the leakage monitoring records during the flood season, dry season and sudden weather event cycle, and calculating the trigger factor frequency to generate the trigger factor characteristic sequence are as follows:

[0070] S101: Based on the water conservancy project monitoring data, divide the dam body, flood discharge sluice and spillway areas according to the spatial dimension, divide the data set of each area into the flood season, dry season and sudden weather event cycle according to the time dimension, extract the leakage monitoring records of each time period, and generate the regional leakage monitoring records by time period;

[0071] Extract leakage-related records based on the monitoring devices deployed in the area. Divide the data set of each area into flood season, dry season, and sudden weather event cycles according to the time dimension. Conduct statistical analysis on the monitoring data for each time period, classify and count the leakage volume data. The classification range of the leakage volume includes less than 50m 3 / h, between 50 - 200m 3 / h, and more than 200m 3 / h. Extract the monitoring data with a leakage volume of more than 200m 3 / h through data screening and record the corresponding time period. Sort the marked high-leakage volume data by area and time period, and finally generate the leakage monitoring record for each area by time period.

[0072] S102: Based on the leakage monitoring record for each area by time period, compare the leakage monitoring value of each monitoring point with the preset leakage threshold, extract the triggering factors exceeding the leakage threshold and calculate the triggering frequency, and conduct statistical analysis according to the triggering frequency to generate the analysis result of the triggering factor frequency;

[0073] Compare the leakage monitoring value of each monitoring point with the preset leakage threshold one by one. Set the leakage threshold to 150m 3 / h. Screen out the monitoring points exceeding the threshold through logical judgment, record the corresponding time period and leakage value, count the number of times each monitoring point exceeds the leakage threshold in each time period, calculate the triggering frequency of each monitoring point. The triggering frequency is divided into low frequency (less than 3 times per month), medium frequency (3 - 6 times per month), and high frequency (more than 6 times per month). Extract the upper and lower bounds of the triggering frequency and analyze the distribution range through historical data, mark the monitoring points with overlimit and high frequency, and generate the analysis result of the triggering factor frequency by combining these data.

[0074] S103: Based on the analysis result of the triggering factor frequency, extract the temporal characteristics of the triggering factor in each time period according to the time series change trend of the triggering factor, and conduct classification processing on the temporal change to generate the characteristic sequence of the triggering factor;

[0075] By statistically analyzing the fluctuation amplitude of the trigger frequency within each time period, where the fluctuation amplitude is obtained by calculating the difference between the maximum and minimum frequencies, the fluctuation amplitudes are classified into the following ranges: high fluctuation (fluctuation amplitude greater than 50%), medium fluctuation (fluctuation amplitude between 20% - 50%), and low fluctuation (fluctuation amplitude less than 20%). The trigger factors in the high - fluctuation category are marked as the category with drastic changes, the trigger factors in the medium - fluctuation category are marked as the category with moderate changes, and the trigger factors in the low - fluctuation category are marked as the category with stable changes. Further analyze the distribution characteristics of the trigger factors in different fluctuation categories in the time series, sort and classify the distribution trends of the trigger factors in each time period for each category, extract the distribution characteristics and change trends of the trigger factors, and finally generate the trigger - factor characteristic sequence.

[0076] Please refer to Figure 3 , extract the trigger - factor frequencies in the trigger - factor characteristic sequence, compare them with the risk threshold to screen for risk factors, analyze the risk - state offset relationship in the segmented interval, and the specific steps to determine the spatial propagation path to obtain the dynamic sequence of the risk - propagation path are as follows:

[0077] S201: Based on the trigger - factor characteristic sequence, divide the trigger - factor frequencies within each time period into intervals, extract the trigger - factor frequencies in each interval, compare them with the preset risk - frequency threshold, screen for risk factors that exceed the risk - frequency threshold, and generate the screening results of interval risk factors;

[0078] The process of dividing the trigger - factor frequency data within each time period into intervals is as follows: Set the interval ranges as low frequency (less than 3 times), medium frequency (3 - 6 times), and high frequency (greater than 6 times). Extract the trigger - factor frequencies within each interval, compare them with the preset risk - frequency threshold (the threshold is set to 5 times), screen for risk factors with frequencies higher than the threshold through comparison, mark the screened high - frequency risk factors and organize them by interval, and finally generate the screening results of interval risk factors.

[0079] S202: Based on the screening results of interval risk factors, analyze the changes in the risk values in the segmented intervals corresponding to the screened risk factors, extract the state - offset relationship of the risk factors in the segmented intervals, and generate the risk - state offset - relationship characteristics;

[0080] The process of analyzing the changes in the risk values of the screened risk factors in the segmented intervals is as follows: Extract the risk - factor values within each interval, classify the states through the fluctuation of the risk values within the interval. Set the state - offset ranges as significant increase (the risk value within the interval increases by more than 30% compared to the previous time period), slight increase (the risk value within the interval increases between 10% - 30%), and decrease (the risk value within the interval decreases by more than 10%). Record the state - offset relationship of the risk factors within each interval and classify and organize them according to the offset states, and finally generate the risk - state offset - relationship characteristics.

[0081] S203: Track the spatial dimension of risk factors based on the characteristics of risk state offset relationships. By analyzing the spatial correlation and temporal evolution characteristics of trigger factors, and determining the propagation path, generate a dynamic sequence of risk propagation paths.

[0082] First, extract the spatial monitoring point data related to the trigger factor. Set the spatial correlation judgment condition as the physical distance between monitoring points is less than 1 km, and the risk value change trends are similar within the same time period (the difference in the increase or decrease of the risk value does not exceed 10%). The monitoring points that meet the above conditions are marked as a combination of related monitoring points. Calculate the average risk value level of the monitoring points in each combination to represent the risk factor level in this area. For the temporal evolution characteristics, extract the risk factor data of each monitoring point at different time periods. Set the temporal evolution judgment range as the increase in the risk value per hour is greater than 20%. For the monitoring points that meet the conditions, mark the key points of their changes (including the starting point and the highest point of the change) in the time series. Further judge the change direction of these monitoring points. The change directions include the continuous increase, decrease, or stabilization of the risk factor value. Mark the monitoring points with similar change directions as part of the same propagation path. Finally, record the propagation trajectory of the risk factor in the spatial dimension, and mark the high-risk areas and time periods on the trajectory, and organize and generate a dynamic sequence of risk propagation paths.

[0083] Please refer to Figure 4 , based on the dynamic sequence of risk propagation paths, construct fuzzy evaluation indicators, divide the leakage monitoring point data into fuzzy values and perform weighted processing. The specific steps to generate the fuzzy distribution characteristics of regional risks are as follows:

[0084] S301: Based on the dynamic sequence of risk propagation paths, extract the risk factor propagation paths in the corresponding area, call the multi-source monitoring data in the corresponding area, classify and organize the data of leakage monitoring points and assign risk levels to generate regional risk level data.

[0085] Call the multi-source monitoring data in the area, including leakage volume, soil moisture, and surface water level, etc. Classify and organize the data of each monitoring point one by one, and allocate them to different regional ranges according to the actual location of the monitoring points. Set the range for dividing risk levels as low risk (leakage volume is less than 50m 3 / h, soil moisture is lower than 30%), medium risk (leakage volume is between 50 - 200m 3 / h, soil moisture is between 30% - 70%) and high risk (leakage volume is greater than 200m 3 / h, when the soil humidity is higher than 70%), extract the leakage amounts at the monitoring points respectively and compare them with the corresponding preset risk ranges, mark the monitoring points with leakage amounts in the medium-risk and high-risk ranges, analyze their risk levels in the current area in combination with the historical risk change records of the monitoring points, integrate the data of all the monitoring points within the area range, and finally generate the area risk level data.

[0086] S302: Based on the area risk level data, construct the fuzzy evaluation index for the corresponding area, divide the data of each leakage monitoring point into multiple fuzzy values according to the risk level range, perform fuzzy value archiving processing on the data of all the monitoring points, and generate the area fuzzy monitoring data;

[0087] For constructing the fuzzy evaluation index for the corresponding area, use the formula:

[0088]

[0089] Calculate the fuzzy value μ(x) of the monitoring point;

[0090] Among them, x is the actual leakage amount of the leakage monitoring point, which is obtained by collecting through real-time monitoring equipment. For example, a flowmeter can directly record the leakage amount data in each time period. k is a parameter that adjusts the steepness of the fuzzy function curve and determines the transition characteristics of the fuzzy function. The value of k is determined by sensitivity analysis of the leakage amount data distribution range within the monitoring area. For example, the final value is determined by comparing the accuracy of curve fitting under different k values.

[0091] c is the intermediate value of the risk level, representing the average value of the risk level range, and its value is the mean of the upper and lower boundary values of this risk level. For example, the upper and lower boundaries of the medium risk are 50 and 200m 3 / h, then c is 125m 3 / h, α is the fuzzy compensation coefficient, which reflects the influence of environmental sensitivity or external disturbance within the area and is determined through sensitivity experiments of the leakage amount to the risk. For example, compare the leakage change amplitudes under different environmental disturbances (such as rainfall or earthquake conditions) in multiple monitors, analyze the fluctuation degree of the leakage within the area, and then set α. The higher the fluctuation degree, the larger the value of α. σ is the standard deviation of the area leakage amount, which reflects the fluctuation degree of the leakage amount data within the area. The standard deviation is obtained through the calculation formula obtained, x i is the leakage value of the i-th monitoring point, is the average leakage value of the monitoring point, and n′ is the number of monitoring points.

[0092] Taking a certain monitoring point with a leakage amount x = 120m3 / h as an example, the risk level range is medium risk (50 - 200m 3 / h), set c = 125, sensitivity analysis yields k = 0.5, experimental analysis gives the fuzzy compensation coefficient α = 0.2, and the standard deviation σ = 15 is calculated within the region. Substitute into the formula:

[0093] The value range of the fuzzy value μ(x) is from 0 to 1, which is used to represent the membership degree of the leakage risk at a certain monitoring point in a specific risk level. According to the specific risk level, it can be divided according to the following ranges: Low risk: μ(x) < 0.4 indicates that the risk of this leakage volume is relatively low, and the leakage volume of the corresponding monitoring point is close to or lower than the lower limit of the risk level, with high safety. Medium risk: 0.4 ≤ μ(x) ≤ 0.7 indicates that the risk of this leakage volume is medium, and the leakage volume of the corresponding monitoring point is in the middle area of the risk level range, which is within the normal monitoring range and needs to be paid attention to. High risk: μ(x) > 0.7 indicates that the risk of this leakage volume is relatively high, and the leakage volume of the corresponding monitoring point is close to or exceeds the upper limit of the risk level, which may pose a certain threat to the project stability and needs to be processed preferentially. It is calculated that μ(x) ≈ 0.62, indicating that the leakage risk of this monitoring point belongs to the medium risk range. The specific analysis is as follows: According to the range division of the fuzzy value, μ(x) ≈ 0.62 falls within the medium risk range, indicating that the leakage volume of this monitoring point is close to the middle value and belongs to the normal level of the risk level range.

[0094] S303: Based on the regionally fuzzified monitoring data, call the time series monitoring data within the region, perform weighted processing on the fuzzy values of the monitoring points under each time period, obtain the fuzzy distribution state within each time period, and generate the regional risk fuzzy distribution characteristics;

[0095] Perform weighted processing on the fuzzy values of the monitoring points under each time period, using the formula:

[0096]

[0097] Calculate the fuzzy distribution state W within the target time period t , the fuzzy value reflecting the overall risk level of the region within this time period, with a value range of 0 to 1;

[0098] Among them, w i is the weight of the i-th monitoring point, and the weight is dynamically adjusted according to the risk level distribution of the area where the monitoring point is located. For example, the monitoring points in high-risk areas are given higher weights, and the weight value is determined through the analysis of the proportion of risk levels within the region. β i is the time correlation factor of the i-th monitoring point, which is used to reflect the influence intensity of the risk change of the monitoring point within the current time period relative to the overall change. The time correlation factor is calculated through the change amplitude of the fuzzy value of the monitoring point within the time period, and the formula is Δμ iIt represents the change amount of the fuzzy value of the \(i\)-th monitoring point. \(n\) is the total number of monitoring points within this time period, which can be directly obtained from the number of monitoring devices. It represents the sum of the change amounts of the fuzzy values of all monitoring points, which is used to normalize the change amount of the current monitoring point to calculate the relative influence intensity. \(j\) represents the index variable involved in the summation operation, which is used to represent the numbers of all monitoring points, from the 1st monitoring point to the \(n\)-th monitoring point.

[0099] Taking the 5 monitoring points in the target area as an example, the weight \(w\) i is 1.2, 1.0, 0.8, 1.1, and 1.3 respectively. The fuzzy value \(\mu\) i (\(x\)) of the monitoring points is 0.8, 0.5, 0.2, 0.7, and 0.9 respectively. The time correlation factor \(\beta\) i is 1.1, 1.0, 0.9, 1.2, and 1.3 respectively. The calculation formula is:

[0100]

[0101] To quantify the risk level of the fuzzy distribution state within the time period, the value of \(W\) t is divided according to the following ranges: Low risk: \(W\) t ≤0.3, indicating that the risk level within the time period is relatively low, the risk fuzzy values of the monitoring points in the area are generally small, and the overall state is stable; Medium risk: 0.3 < \(W\) t ≤0.6, indicating that there is a certain degree of risk within the time period, the risk fuzzy values of some monitoring points are relatively high, but it has not reached the significant risk state; Medium-high risk: 0.6 < \(W\) t ≤0.8, indicating that the risk level of the area within the time period is relatively high, the risk fuzzy values of most monitoring points are relatively high, and the possible development trend needs to be concerned; High risk: \(W\) t > 0.8, indicating that the area as a whole is in a high-risk state within the time period, the fuzzy values of the monitoring points are highly concentrated in the high-risk range, and emergency management measures need to be taken. According to the division, the calculation result \(W\) t ≈0.685 falls into the medium-high risk range. \(W\) t = 0.685 indicates that within the current time period, the overall risk level formed by the superposition of the fuzzy value weights of multiple monitoring points in the area is relatively high, but it has not reached the highest-level risk state. This means that although the leakage risk of some monitoring points is relatively significant, it is still within the controllable range.

[0102] Please refer to Figure 5 , and the specific steps for clustering analysis of the fuzzy distribution characteristics of the regional risk, extracting the characteristic differences of the local regional risk factors, identifying the relevance and interactive influence, and forming the multi-scale risk distribution characteristics after classification are as follows:

[0103] S401: Based on the fuzzy distribution characteristics of regional risks, perform clustering operations on the risk data of each local area in the distribution characteristics, extract the characteristics of the differences in risk factors between local areas, and generate local risk factor difference characteristics;

[0104] The process of performing clustering operations on the risk data of each local area in the distribution characteristics is as follows. For example, in the dam area of a certain water conservancy project, a total of 50 monitoring points are set, and the fuzzy value range of each monitoring point is between 0.1 and 0.9. The fuzzy values of some high-risk monitoring points exceed 0.8, and the fuzzy values of the monitoring points in other areas are concentrated between 0.3 and 0.6. After converting the fuzzy values into a unified range value through normalization processing, a clustering method based on Euclidean distance is used to analyze the risk characteristics between the monitoring points. Suppose that through calculation, the average Euclidean distance between each group of monitoring points is 0.1. After setting the clustering threshold to 0.15, three clustering categories are obtained. Among them, the fuzzy values of the first group of risk points are all above 0.8, mainly distributed in the flood discharge area of the dam; the fuzzy values of the second group of risk points are concentrated between 0.5 and 0.6, distributed in the central area of the dam; the fuzzy values of the third group of risk points are relatively low, distributed in the edge area of the dam. According to the above clustering results, extract the average risk fuzzy value, the distribution density of risk points, and the proportion of high-risk points in different areas, compare the characteristic differences of the three types of clustering results, and generate local risk factor difference characteristics.

[0105] S402: Based on the local risk factor difference characteristics, identify the interactive effects between multiple risk factors, analyze the distribution characteristics and correlation degrees of risk factors, extract the risk factors whose correlation exceeds the preset correlation threshold, and generate risk factor correlation characteristics;

[0106] The process of identifying the interactive effects between multiple risk factors is as follows. For example, perform time series analysis on the leakage fuzzy value and water level fuzzy value in the dam area and the spillway area. Extract the change sequences of the leakage fuzzy value and water level fuzzy value through a sliding time window (set to 1 hour, for example), and calculate their correlation coefficients. If within a certain time period, the leakage fuzzy value in the dam area increases from 0.6 to 0.8, and at the same time the water level fuzzy value in the spillway area rises from 0.5 to 0.7, and the calculated correlation coefficient is 0.85 (greater than the preset threshold of 0.8), it indicates that there is a strong interactive correlation between the two. Further analyze the directionality of the interactive effect and find that when the change rate of the dam leakage value exceeds 10%, the change rate of the spillway water level value reaches 15% in the same time period, indicating that there is a causal relationship between the two. By recording these interactive relationships and analyzing their change amplitudes, screen out the interactive relationship between the dam leakage value and the spillway water level value as a key risk factor pair, and generate risk factor correlation characteristics.

[0107] S403: Based on the risk factor correlation features, classify and grade the risk factors exceeding the preset correlation threshold according to the distribution range and characteristics, and combine the distribution characteristics of the local area and the overall area to form multi-scale risk distribution features;

[0108] The process of classifying and grading the risk factors exceeding the preset correlation threshold according to the distribution range and characteristics is as follows. For example, among the risk factor correlation features extracted in the above dam body area and spillway area, the leakage fuzzy value and the water level fuzzy value are the main factors, and they are classified and graded by calculating the cross-region coverage ratio and the fluctuation amplitude. Suppose the leakage fuzzy value in the dam body area covers 80% of the total number of monitoring points, and its fluctuation amplitude is 0.3, while the water level fuzzy value in the spillway area covers 60% of the total number of monitoring points, and the fluctuation amplitude is 0.25. Set the coverage ratio threshold to 70% and the fluctuation amplitude threshold to 0.2. Classify the leakage fuzzy value in the dam body area into the high-risk factor group, and classify the water level fuzzy value in the spillway area into the medium-risk factor group. In addition, for risk factors with a fluctuation amplitude lower than 0.1 but a coverage range exceeding 90%, such as the meteorological impact fuzzy value in the spill area, classify them into the low-risk factor group. Combining these classification results, generate cross-region risk factor classification, and combine the distribution characteristics of each region to form multi-scale risk distribution features.

[0109] Please refer to Figure 6 , the specific steps to extract the time series of risk factors in the multi-scale risk distribution features, predict the future change trend, analyze the sudden increase points and sudden decrease points to construct the distribution trend curve, and generate the risk warning information of the water conservancy project are as follows:

[0110] S501: Based on the multi-scale risk distribution features, extract the time series corresponding to each category of risk factors, clean and normalize the time series data, extract the characteristic values of the changes of the risk factors in the time series and mark the change trend to generate the risk factor time series characteristics;

[0111] The process of extracting the time series corresponding to each category of risk factors is as follows. For example, in a certain water conservancy project, extract the time series of the high-risk factors in the dam body area as the daily leakage monitoring value series, and extract the time series of the medium-risk factors as the hourly water level change value series. After screening and removing obvious incorrect data points (such as negative leakage values or values exceeding the equipment monitoring range) and duplicate data, normalize the time series to a unified time step of the hourly level to ensure the comparability of the time series of each risk factor. In the cleaned data, extract the characteristic values of the risk factor time series by calculating the mean value, standard deviation of the daily leakage value and the maximum value of the water level change, and mark the risk change characteristics through the change trend of the characteristic values. For example, the leakage value gradually increases (the daily mean value increases from 200m 3 / h to 300m 3 / h), and the water level shows a fluctuating trend (the maximum value fluctuates between 60 cm and 80 cm), finally generating the time series characteristics of risk factors.

[0112] S502: Based on the time series characteristics of risk factors, identify the sudden increase points and sudden decrease points of the characteristic values of risk changes in the time series. Combine the change rate and characteristic range within the time series to determine the critical time period of risk changes, and generate the characteristics of the critical time period of risk mutation;

[0113] The process of identifying the sudden increase points and sudden decrease points of the characteristic values of risk changes in the time series is, for example, in the time series of leakage monitoring values. When the leakage value suddenly rises from 300 m 3 / h to 450 m 3 / h within one hour, it is marked as a sudden increase point; in the time series of water level change values, when the water level drops from 80 cm to 50 cm and the drop amplitude is greater than the set threshold of 30 cm, it is marked as a sudden decrease point. By combining the change rate of the leakage value time series (such as the leakage value rising at a rate of 10% per hour within 24 hours) and the characteristic range of water level changes (such as the fluctuation range of the maximum water level between 60 cm and 80 cm), determine the critical time period of risk changes. For example, the 3 hours before and after the sudden increase point of the leakage value and the time period with a larger water level drop are identified as critical time periods, and finally generate the characteristics of the critical time period of risk mutation.

[0114] S503: Based on the characteristics of the critical time period of risk mutation, construct the distribution trend curve of the time series. By marking the sudden increase points and sudden decrease points on the time series curve, extract the visual distribution information of the risk area and time period, and generate the risk warning information for water conservancy projects;

[0115] The process of constructing the distribution trend curve of the time series is, for example, plotting the time series characteristics of the above-mentioned leakage value and water level change as broken line trend curves respectively, and marking the sudden increase points and sudden decrease points on the curves with red dots and green dots respectively. On the leakage value curve, clearly identify the critical time point when the leakage value suddenly increases from 300 m 3 / h to 450 m 3 / h, and at the same time mark the growth rate within this time period. On the water level change curve, reflect the rapid decline characteristics of the water level in some time periods by continuously marking the positions of sudden decrease points, and mark the range and law of water level changes through the overall fluctuation trend of the curve. Combining the above trend curves, further extract the distribution information of each risk factor in the time dimension, and integrate the high-risk area corresponding to the sudden increase point of the leakage value and the medium-risk area corresponding to the sudden decrease point of the water level into one, generating the risk warning information for water conservancy projects with visual characteristics for managers to refer to and make decisions.

[0116] Please refer to Figure 7, a water conservancy project risk early warning analysis system based on multi-source information, the system includes:

[0117] The regional division and feature extraction module, based on the water conservancy project monitoring data, divides the dam body, flood discharge sluice and spillway areas according to the spatial dimension, extracts the leakage monitoring records in the flood season, dry season and sudden weather event cycle, calculates the trigger factor frequency and analyzes its change characteristics in combination with the time dimension, and generates a trigger factor feature sequence;

[0118] The risk propagation path analysis module, based on the trigger factor feature sequence, extracts the trigger factor frequency values in each time period, compares the trigger factor frequency with the risk frequency threshold to screen out risk factors, analyzes the state offset characteristics of risk factors in the segmented interval, and determines the propagation path in combination with the time and space dimensions, and generates a risk propagation path dynamic sequence;

[0119] The fuzzy distribution generation module, based on the risk propagation path dynamic sequence, constructs fuzzy evaluation indexes in the area, divides the leakage monitoring point data into fuzzy values, performs weighted processing on the monitoring data according to the fuzzy values, extracts the risk fuzzy distribution in each time period, and generates the regional risk fuzzy distribution characteristics;

[0120] The risk factor grading and association module, based on the regional risk fuzzy distribution characteristics, clusters the risk factor characteristics of the local area, extracts the difference characteristics between the local areas, and combines the relevance and interaction effects between multiple risk factors to grade the risk factors and generate multi-scale risk distribution characteristics;

[0121] The risk early warning and trend prediction module, based on the multi-scale risk distribution characteristics, extracts the time series of risk factors, analyzes the change trend in the time series, identifies the sudden increase points and sudden decrease points in the risk change, constructs a distribution trend curve in combination with the trend characteristics, and generates water conservancy project risk early warning information.

[0122] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. These three situations, where A and B can be singular or plural. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context.

[0123] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural item(s). For example, at least one of a, b, or c may represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c may be single or plural.

[0124] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above - mentioned processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0125] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0126] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0127] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the couplings, direct couplings, or communication connections shown or discussed with each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0129] In addition, in each embodiment of the present invention, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0130] If the above-mentioned function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that makes a contribution to the prior art, or a part of this 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 for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0131] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A water conservancy project risk early warning analysis method based on multi-source information, characterized in that: The following steps are involved: S1: Divide the dam, flood gate and spillway areas according to the spatial dimension, extract the leakage monitoring records of the flood season, dry season and sudden weather event period, calculate the trigger factor frequency and generate the trigger factor feature sequence; S2: extracting the trigger factor frequency in the trigger factor feature sequence, comparing it with the risk threshold to screen the risk factor, analyzing the risk state offset relationship of the segmented interval, determining the spatial propagation path to obtain a dynamic sequence of the risk propagation path; S3: Based on the dynamic sequence of the risk propagation path, a fuzzy evaluation index is constructed, the leakage monitoring point data is divided into fuzzy values ​​and weighted, and the regional risk fuzzy distribution characteristics are generated; S4: cluster analysis is performed on the fuzzy distribution characteristics of regional risks to extract the differences in risk factor characteristics in local areas, identify correlations and interactive effects, and form multi-scale risk distribution characteristics after grading and classification; S5: Extract the time series of risk factors in the multi-scale risk distribution characteristics, predict future change trends, analyze sudden increase points and sudden decrease points to construct a distribution trend curve, and generate water conservancy project risk warning information.

2. The water conservancy project risk early warning analysis method based on multi-source information according to claim 1 is characterized by: The trigger factor feature sequence includes the support, confidence and trigger frequency of the trigger factor within the time period; the risk propagation path dynamic sequence specifically includes the spatial propagation path, time propagation characteristics and risk state offset relationship of the risk factor; the regional risk fuzzy distribution characteristics include the fuzzified risk level, the time series corresponding to the risk level and the spatial distribution state; the multi-scale risk distribution characteristics specifically refer to the risk distribution characteristics in the local area, the correlation characteristics between regions and the grading and classification results; the water conservancy project risk warning information includes the sudden increase points, sudden decrease points of risk changes and the corresponding time distribution trend curve.

3. The water conservancy project risk early warning analysis method based on multi-source information according to claim 1 is characterized by: The specific steps of dividing the dam, flood gate and spillway areas according to the spatial dimension, extracting the leakage monitoring records of the flood season, dry season and sudden weather event period, and calculating the trigger factor frequency to generate the trigger factor feature sequence are as follows: S101: Based on the water conservancy project monitoring data, the dam body, flood discharge gate and spillway areas are divided according to the spatial dimension, and the data set of each area is divided into flood season, dry season and sudden weather event period according to the time dimension, and the leakage monitoring records of each time period are extracted to generate regional leakage monitoring records by time period; S102: Based on the regional leakage monitoring records in different time periods, the leakage monitoring value of each monitoring point is compared with a preset leakage threshold, the trigger factor exceeding the leakage threshold is extracted and the trigger frequency is calculated, and statistical analysis is performed according to the trigger frequency to generate a trigger factor frequency analysis result; S103: Based on the trigger factor frequency analysis result, according to the time series change trend of the trigger factor, extract the time series characteristics of the trigger factor in each time period, and classify the time series changes to generate a trigger factor feature sequence.

4. The water conservancy project risk early warning analysis method based on multi-source information according to claim 1 is characterized by: The specific steps of extracting the trigger factor frequency in the trigger factor feature sequence, comparing with the risk threshold to screen the risk factor, analyzing the risk state offset relationship of the segmented interval, and determining the spatial propagation path to obtain the risk propagation path dynamic sequence are as follows: S201: Based on the trigger factor feature sequence, the trigger factor frequency in each time period is divided into intervals, the trigger factor frequency in each interval is extracted and compared with a preset risk frequency threshold, risk factors exceeding the risk frequency threshold are screened, and interval risk factor screening results are generated; S202: Based on the interval risk factor screening result, analyzing the change of the risk value in the segmented interval corresponding to the screened risk factor, extracting the state deviation relationship of the risk factor in the segmented interval, and generating risk state deviation relationship characteristics; S203: Based on the risk state deviation relationship characteristics, the spatial dimension of the risk factor is tracked, and the spatial correlation and time evolution characteristics of the triggering factor are analyzed, and the propagation path is determined to generate a dynamic sequence of the risk propagation path.

5. The water conservancy project risk early warning analysis method based on multi-source information according to claim 1 is characterized by: Based on the dynamic sequence of risk propagation paths, fuzzy evaluation indicators are constructed, leakage monitoring point data are divided into fuzzy values ​​and weighted, and the specific steps of generating regional risk fuzzy distribution characteristics are as follows: S301: Based on the dynamic sequence of risk propagation paths, extract the risk factor propagation paths in the corresponding area, call the multi-source monitoring data of the corresponding area, classify and sort the data of the leakage monitoring points and assign risk levels to generate regional risk level data; S302: Based on the regional risk level data, construct a fuzzy evaluation index for the corresponding region, divide the data of each leakage monitoring point into multiple fuzzy values ​​according to the risk level range, perform fuzzy value archiving processing on the data of all monitoring points, and generate regional fuzzy monitoring data; S303: Based on the regional fuzzy monitoring data, the time series monitoring data in the region is called, the fuzzy values ​​of the monitoring points in each time period are weighted, the fuzzy distribution state in each time period is obtained, and the regional risk fuzzy distribution characteristics are generated.

6. The water conservancy project risk early warning analysis method based on multi-source information according to claim 5 is characterized by: To construct the fuzzy evaluation index of the corresponding area, the formula is used: Calculate the fuzzy value μ(x) of the monitoring point; Among them, x is the actual leakage amount at the leakage monitoring point, k is the parameter for adjusting the steepness of the fuzzy function curve, c is the middle value of the risk level, α is the fuzzy compensation coefficient, and σ is the standard deviation of the regional leakage amount.

7. The water conservancy project risk early warning analysis method based on multi-source information according to claim 5 is characterized by: The fuzzy values ​​of the monitoring points in each time period are weighted using the formula: Calculate the fuzzy distribution state W within the target time period t , a fuzzy value reflecting the overall risk level of the region during the time period, ranging from 0 to 1; Among them, w i is the weight of the i-th monitoring point, β i is the time correlation factor of the ith monitoring point, and n is the total number of monitoring points in the time period.

8. The water conservancy project risk early warning analysis method based on multi-source information according to claim 1 is characterized by: The specific steps of clustering the fuzzy distribution characteristics of regional risks, extracting the differences in the characteristics of local regional risk factors, identifying the correlation and interaction, and forming multi-scale risk distribution characteristics after classification are as follows: S401: Based on the regional risk fuzzy distribution characteristics, cluster the risk data of each local area in the distribution characteristics, extract the risk factor difference characteristics between the local areas, and generate local risk factor difference characteristics; S402: Based on the local risk factor difference characteristics, identify the interaction between multiple risk factors, analyze the distribution characteristics and correlation degree of the risk factors, extract the risk factors whose correlation exceeds a preset correlation threshold, and generate risk factor correlation characteristics; S403: Based on the risk factor association characteristics, the risk factors exceeding the preset association threshold are graded and classified according to the distribution range and characteristics, and the distribution characteristics of the local area and the overall area are combined to form a multi-scale risk distribution feature.

9. The water conservancy project risk early warning analysis method based on multi-source information according to claim 1 is characterized by: The specific steps of extracting the time series of risk factors in the multi-scale risk distribution characteristics, predicting future change trends, analyzing sudden increase points and sudden decrease points to construct a distribution trend curve, and generating water conservancy project risk warning information are as follows: S501: Based on the multi-scale risk distribution characteristics, extract the time series corresponding to each category of risk factors, clean and organize the time series data, extract the characteristic values ​​of the risk factor changes in the time series and mark the change trends, and generate risk factor time series characteristics; S502: Based on the risk factor time series characteristics, identify the sudden increase points and sudden decrease points of the characteristic values ​​of the risk change in the time series, determine the key time period of the risk change in combination with the change rate and characteristic range in the time series, and generate the risk mutation key time period characteristics; S503: Based on the characteristics of the key time period of risk mutation, a distribution trend curve of the time series is constructed, and by marking the sudden increase points and sudden decrease points on the time series curve, the visual distribution information of the risk area and time period is extracted to generate water conservancy project risk warning information.

10. The water conservancy project risk early warning analysis system based on multi-source information is characterized by: According to any one of claims 1 to 9, the water conservancy project risk early warning analysis method based on multi-source information is implemented, and the system comprises: The regional division and feature extraction module divides the dam, flood gate and spillway areas according to the spatial dimension based on the water conservancy project monitoring data, extracts the leakage monitoring records of the flood season, dry season and sudden weather event period, calculates the trigger factor frequency and analyzes its change characteristics in combination with the time dimension, and generates the trigger factor feature sequence; The risk propagation path analysis module extracts the trigger factor frequency value in each time period based on the trigger factor feature sequence, compares the trigger factor frequency with the risk frequency threshold to screen out the risk factor, analyzes the state deviation characteristics of the risk factor in the segmented interval, determines the propagation path by combining the time and space dimensions, and generates a dynamic sequence of the risk propagation path; The fuzzy distribution generation module constructs the fuzzy evaluation index in the region based on the dynamic sequence of the risk propagation path, divides the leakage monitoring point data into fuzzy values, performs weighted processing on the monitoring data according to the fuzzy values, extracts the risk fuzzy distribution of each time period, and generates the regional risk fuzzy distribution characteristics; The risk factor classification and association module clusters the risk factor characteristics of the local area based on the regional risk fuzzy distribution characteristics, extracts the difference characteristics between the local areas, and classifies the risk factors based on the correlation and interaction between multiple risk factors to generate multi-scale risk distribution characteristics; The risk warning and trend prediction module is based on the multi-scale risk distribution characteristics, extracts the time series of risk factors, analyzes the changing trends in the time series, identifies the sudden increase and decrease points in risk changes, constructs a distribution trend curve based on the trend characteristics, and generates water conservancy project risk warning information.

Images