Urban physical examination data deep mining and visual analysis system

Abstract

The invention belongs to the technical field of urban physical examination data analysis, and particularly discloses and provides an urban physical examination data deep mining and visual analysis system which comprises a drainage data acquisition module, a drainage overload analysis module, an intersection danger analysis module and a danger report generation module. By setting a technical system of dynamic threshold correction, multi-dimensional risk modeling and drainage intersection focusing analysis, the core problems of static property, one-sidedness and hysteresis in the prior art are effectively solved, and leap-type upgrading from extensive pipe network design to fine node prevention and control is realized; and a quantizable, traceable and extensible risk management tool is provided for an urban drainage system. And meanwhile, the drainage intersection danger index is innovatively constructed by integrating dynamic parameters such as the real-time drainage amount of the drainage branch, the overload index and the concentrated drainage time, and deep risk excavation of the key node of the focused drainage intersection is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of urban physical examination data analysis. Specifically, it relates to a system for in-depth mining and visual analysis of urban physical examination data. Background Art

[0002] With the acceleration of the urbanization process, as an important part of the infrastructure, the operation efficiency and safety of the urban drainage system are directly related to urban flood control and drainage, water environment quality, and residents' living safety, thus highlighting the importance of urban drainage physical examination.

[0003] The prior art, such as a system for optimizing the design of urban drainage networks disclosed in a Chinese invention patent application with the application number 202411759930.5, constructs a parameter dynamic correction model by integrating multi-dimensional parameters such as rainfall intensity, ground permeability, sewage concentration, and pipe cleanliness. It solves the problem of one-sided parameters caused by the traditional optimization design relying on single rainfall data, which cannot reflect the real operation state of the pipe network, and improves the accuracy of drainage efficiency and cost-benefit analysis.

[0004] Obviously, the prior art mainly has three core problems in drainage optimization: staticity, one-sidedness, and lag, making it difficult to cope with complex and changeable urban drainage scenarios. At the same time, the prior art mainly focuses on the relevant influence indicators of pipelines and does not focus on drainage confluence points, resulting in insufficient excavation depth and thus unable to further improve the pertinence of subsequent drainage optimization. Summary of the Invention

[0005] In view of this, based on the above problems, a system for in-depth mining and visual analysis of urban physical examination data is proposed.

[0006] The object of the present invention can be achieved by the following technical solutions: The present invention provides a system for in-depth mining and visual analysis of urban physical examination data, which includes: a drainage data collection module that collects the designed drainage load of the drainage confluence points in the drainage pipe network of the area to be physically examined and the positions of the drainage confluence points to which they belong, and simultaneously collects the real-time drainage volume of the drainage confluence points and each drainage branch corresponding to the drainage confluence points.

[0007] A drainage overload analysis module that generates a drainage overload index for each drainage branch based on the real-time drainage volume of each drainage branch and a preset load threshold, and determines the concentrated drainage time of each drainage branch through time series analysis.

[0008] A confluence danger analysis module that generates a drainage danger index for the drainage confluence points based on the drainage overload index, current drainage volume, and concentrated drainage time of each drainage branch, and based on the historical drainage monitoring data of the drainage confluence points, similarly calculates the drainage danger index at each historical drainage monitoring time and sets a dynamic drainage danger index threshold.

[0009] The danger report generation module, if the current drainage danger index exceeds the dynamic danger index threshold, matches the preset drainage danger mapping table to obtain the current drainage danger level, and generates a physical examination report for the drainage intersection based on the drainage intersection position and the drainage danger level.

[0010] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) By setting up a multi-dimensional evaluation system of dynamic threshold correction, multi-dimensional risk modeling, and drainage intersection focus analysis, the present invention effectively solves the core problems of staticness, one-sidedness, and lag in the prior art, realizes a leapfrog upgrade from extensive pipe network design to refined node prevention and control, provides a quantifiable, traceable, and extensible risk management tool for the urban drainage system, and can effectively reduce the economic losses caused by waterlogging and extend the service life of the pipe network.

[0011] (2) By integrating multi-dimensional parameters such as the drainage overload index, the concentrated drainage time, and the drainage danger index, the present invention comprehensively depicts the risk conduction path in complex drainage scenarios, solves the one-sidedness problem caused by single-parameter analysis, provides a more scientific decision-making basis for system scheduling, and is convenient for dealing with complex and changeable urban drainage scenarios.

[0012] (3) By integrating dynamic parameters such as the real-time drainage volume of the drainage branch, the overload index, and the concentrated drainage time, the present invention innovatively constructs the drainage intersection danger index, realizes in-depth risk excavation focusing on this key node of the drainage intersection, ensures the dynamic, comprehensive, and real-time risk assessment of the drainage system, provides technical support for precise optimization in complex urban drainage scenarios, and fills the core shortcoming that cannot adapt to the dynamic bearing capacity of the pipe network at present.

[0013] (4) By setting the dynamic drainage danger index threshold, the present invention can effectively avoid the evaluation deviation caused by parameter solidification, enable the system to respond in real time to dynamic factors such as pipe network load changes, seasonal characteristics, or equipment aging, and significantly enhance the environmental adaptability of the drainage risk assessment. Description of the Drawings

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0015] Figure 1 It is a schematic diagram of the connection of the system module structure of the present invention.

[0016] Figure 2 It is a flow chart of the overall implementation steps of the present invention.

[0017] Figure 3This is the flow chart for confirming the centralized drainage time of the present invention. Detailed implementation manners

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] Please refer to Figure 1 and Figure 2 As shown, the present invention provides an in-depth mining and visualization analysis system for urban physical examination data, which includes: a drainage data acquisition module, a drainage overload analysis module, an intersection risk analysis module, and a risk report generation module.

[0020] Among the above, the drainage overload analysis module is respectively connected to the drainage data acquisition module and the intersection risk analysis module, and the intersection risk analysis module is connected to the risk report generation module.

[0021] The drainage data acquisition module collects the designed drainage capacity of the drainage intersection points in the drainage pipe network of the area to be physically examined and the positions of the affiliated drainage intersection points, and at the same time collects the real-time drainage volumes of the drainage intersection points and each drainage branch corresponding to the drainage intersection points.

[0022] It should be added that for drainage data acquisition, a sensor array composed of electromagnetic flow meters and liquid level meters needs to be configured to collect the flow rate and water level of pipe networks with diameters of DN50 - DN2000 in real time through the RS485 / 4G communication protocol. An integrated GIS positioning unit is used to obtain the longitude and latitude coordinates of the drainage intersection points and the spatial association data of the pipe network nodes.

[0023] Exemplarily, the installation positions of the sensors can be referred to as follows: monitoring sections are set at straight pipe sections 1 - 2 times the pipe diameter length upstream from the intersection point on each branch to avoid flow state disturbance areas such as elbows and valves, and high-precision ultrasonic flow meters are uniformly installed. In addition, high-precision ultrasonic flow meters are installed at the water inlet position and the water outlet position of the drainage intersection point respectively.

[0024] The drainage overload analysis module generates the drainage overload index of each drainage branch based on the real-time drainage volume of each drainage branch and the preset load threshold, and determines the centralized drainage time of each drainage branch through time series analysis.

[0025] Specifically, the specific analysis process of the drainage overload index is as follows: A1. Calculate the difference between the real-time drainage volume and the designed drainage load to obtain the real-time drainage difference. Divide the drainage difference by the designed drainage load to obtain the relative proportion of the real-time drainage volume exceeding the designed load, denoted as the drainage full-load ratio. Calculate the average drainage difference through mean calculation, and extract the maximum drainage full-load ratio.

[0026] A2. Compose the real-time drainage volume into a drainage difference time series, and track the continuous duration of the drainage difference exceeding the preset threshold through a set time window, denoted as the drainage full-load continuous duration.

[0027] A3. Calculate the standard deviation of the drainage difference time series to obtain the volatility of the drainage difference, and calculate the average volatility through mean calculation.

[0028] A4. Based on the average drainage difference, the drainage full-load continuous duration, and the average volatility, conduct an overload compensation trigger determination. If the overload compensation is triggered, set an overload compensation evaluation factor.

[0029] A5. After normalizing the average drainage difference, the maximum drainage full-load ratio, the drainage full-load continuous duration, and the average volatility, calculate the preliminary drainage overload index through linear weighting, and compensate the preliminary drainage overload index with the overload compensation evaluation factor to obtain the final drainage overload index of each drainage branch.

[0030] It should be added that all the normalizations in the present invention can adopt the minimum-maximum normalization method, and no further explanation will be given hereinafter.

[0031] Furthermore, the overload compensation trigger determination condition in step A4 is: if any two of the average drainage difference, the drainage full-load continuous duration, and the average volatility exceed the corresponding set thresholds, it is determined that the overload compensation is triggered.

[0032] Even further, the specific setting of the overload compensation evaluation factor in step A4 is as follows: B1. Screen out the parameter items that exceed the corresponding set thresholds from the average drainage difference, the drainage full-load continuous duration, and the average volatility, denoted as deviation parameter items, and form a deviation parameter item combination.

[0033] B2. Match the deviation parameter item combination with a preset parameter deviation basic compensation mapping table to obtain a reference overload compensation factor.

[0034] B3. Normalize the deviation parameter items, and use the weighted sum value of the processing results as a variable to input into the Sigmoid function to output a target reference overload compensation factor.

[0035] B4. Multiply the reference overload compensation factor and the reference overload compensation factor as the final overload compensation evaluation factor.

[0036] Exemplarily, the corresponding set threshold for the drainage difference is an interval value of ±5% to ±20% of the set drainage load, and the specific value can be comprehensively set in combination with the health assessment report of the pipeline.

[0037] It can be understood that during the operation of the drainage system, the overload risk is affected by the coupling of multiple parameters such as drainage difference, duration, and volatility. A single parameter or simple weighting cannot accurately reflect the risk differences in complex deviation scenarios such as short-term high-fluctuation overload and long-term mild overload. Through the three-layer architecture of "screening deviation - mapping benchmark - dynamic correction", the combination of qualitative and quantitative analysis and multi-dimensional risk quantification can be achieved, and the robustness of the system can be well improved.

[0038] It should be explained that the main purpose of setting the overload compensation evaluation factor is to accurately identify complex overload risk scenarios during the operation of the drainage system through the systematic integration and dynamic quantification of multi-dimensional parameters, effectively solve the problem of one-sidedness in single-parameter evaluation, provide an accurate quantitative basis for optimizing drainage scheduling strategies and formulating equipment operation and maintenance plans, and significantly improve the adaptive ability of the system to complex load fluctuations.

[0039] Exemplarily, different basic compensation coefficients are assigned according to the quantity and type of deviation parameters, such as the deviation combination of two parameters vs the deviation of the full-parameter combination, to reflect the complexity and impact degree of the deviation. For example, when the number of deviation parameter items is three, the value of the benchmark overload compensation factor is set to 1. When the number of deviation parameter items is two and they are the average drainage difference and the duration of full drainage load exceeding the corresponding set threshold, the value of the benchmark overload compensation factor is set to 0.8. When the number of deviation parameter items is two and they are the average drainage difference and the average volatility exceeding the corresponding set threshold, the value of the benchmark overload compensation factor is set to 0.6. When the number of deviation parameter items is two and they are the duration of full drainage load and the average volatility exceeding the corresponding set threshold, the value of the benchmark compensation factor is set to 0.5.

[0040] It can be understood that the differences in the values of the benchmark overload compensation factors for different combinations of deviation parameters are mainly based on the contribution degree of each parameter to the overload risk and the complexity of the combined risk. For example, the average drainage difference, as a direct overload criterion, is the core parameter determining the level of the compensation factor. Combinations involving it, such as "drainage difference and duration" and "drainage difference and volatility", have a significantly higher compensation factor than combinations without the drainage difference, such as "duration and volatility", because they are directly related to the intensity of immediate overload. The deviation of all three full parameters has a multi-dimensional superposition of risks due to the simultaneous coverage of overload intensity, persistence, and volatility, so the highest compensation factor is given. The combination of "drainage difference and duration" reflects the cumulative risk of persistent overload, so the compensation factor is higher than the combination of "drainage difference and volatility" that only reflects intermittent impacts. Combinations without the drainage difference have mainly potential risks because they do not exceed the immediate drainage capacity, so the compensation factor is the lowest. This setting realizes differential responses to complex overload scenarios by highlighting core risk indicators and quantifying the risk superposition effect.

[0041] It should be added that the benchmark compensation factor, based on a preset parameter deviation-based compensation mapping table, converts industry specifications, historical failure cases, and engineering practice experience into quantifiable basic coefficients to ensure standardized responses to known typical deviation scenarios such as single-parameter mild overlimit and multi-parameter combination risks, and avoid evaluation chaos caused by over-reliance on real-time data, such as the highest compensation triggered by three-item full deviation. The target compensation factor captures the subtle fluctuation characteristics of current operating data in real time through the normalization processing of deviation parameters and the mapping of the Sigmoid function, making up for dynamic change scenarios that cannot be covered by preset rules. Combining the two can achieve efficient responses to simple scenarios and fine discrimination of complex scenarios.

[0042] Specifically, please refer to Figure 3 As shown, the specific confirmation time of the centralized drainage time includes: D1. Import the historical daily average drainage volume of each drainage branch, and after dividing the real-time drainage volume according to a preset time period, construct a drainage volume time series data set including the average flow rate, peak flow rate, and flow rate change rate of each time period.

[0043] D2. Detect the drainage volume time series data set of each drainage branch through a local maximum search algorithm, and count the candidate peak time periods that meet the peak flow rate threshold and have a continuous duration exceeding the minimum duration threshold.

[0044] D3. Cluster the candidate peak time periods through the OPTICS density clustering algorithm, and merge adjacent time periods with overlapping time or an interval less than the first preset duration to generate a centralized drainage time period cluster.

[0045] Among them, the OPTICS density clustering algorithm is an existing algorithm, and the specific clustering process will not be elaborated here.

[0046] D4. Extract the start time, end time, and peak drainage volume ratio of each time period cluster, where the peak drainage volume ratio is the ratio of the total drainage volume within the cluster to the historical daily average drainage volume.

[0047] D5. Assign priority weights to each time period cluster based on the peak drainage volume ratio, screen the concerned time period clusters with weights greater than the preset weight threshold, and calculate the arithmetic mean of their start time and end time as the time anchor point.

[0048] Exemplarily, if a cluster contains 3 candidate time periods with start times of 7:15, 7:30, and 7:45 respectively, the average start time is 7:30, and the average end time is obtained in the same way, which reflects the typical start and end rules of centralized drainage.

[0049] D6. Calculate the standard deviation of the start time and end time corresponding to each candidate peak time period within each cluster of the concerned time periods. If the standard deviations of the start time and end time within the cluster of concerned time periods are both less than the second preset threshold, generate a core time period with the time point as the center and the standard deviation as the boundary. If the standard deviation exceeds the third preset threshold, take the minimum value of the start time within the cluster and the maximum value of the end time as the boundaries of the core time period.

[0050] D7. Perform secondary merging on the core time periods with an interval less than the second preset duration and the total proportion of peak drainage volume after merging greater than the third reference threshold to obtain the final centralized drainage time.

[0051] In a specific embodiment, the first preset duration can specifically take a value of 30 minutes, and the second preset threshold and the third preset threshold corresponding to the standard deviation can take values of 30% and 60% respectively.

[0052] Exemplarily, if the core time period of cluster 1 is from 8:00 to 9:00 and the core time period of cluster 2 is from 9:15 to 10:00, with an interval of 15 minutes between them, which satisfies that the time interval is less than the preset threshold of 30 minutes, they can be merged into 8:00 - 10:00. Ensure that the main drainage load is covered within the minimum time range to provide an accurate time reference for pipe network scheduling.

[0053] It should be explained that the operation management of the drainage system is similar to the traffic flow regulation of the traffic system. It is necessary to accurately grasp the time and intensity of the "flow peak" to avoid the system "overloading" and causing paralysis. In traffic management, if the traffic flow density and duration of the morning and evening rush hours are not considered, it is very easy to cause road congestion and even traffic accidents. Similarly, if the drainage system ignores the time period characteristics of centralized drainage of each branch, it may cause risks such as sewage overflow and waterlogging due to the instantaneous flow exceeding the carrying capacity of the pipe network. Affected by the functions of the service areas, drainage types, and weather conditions of different drainage branches, there are significant differences in the time and intensity of the drainage peaks.

[0054] It can be understood that by accurately identifying the centralized drainage time periods of each drainage branch, the operation efficiency and safety of the drainage system can be significantly improved. In addition, it can also assist in the pipe network planning and expansion decision-making. By analyzing the long-term centralized drainage data, the weak links of the pipe network can be located to provide data support for new construction or renovation projects, realizing the transformation of the drainage system from passive response to active control.

[0055] Furthermore, the determination process of the candidate peak time periods in step D2 is as follows: Set a double threshold for peak determination, and the double threshold is that the flow value exceeds the average daily flow times and the continuous duration exceeds the preset second duration.

[0056] The real-time drainage volume is composed into a drainage volume sequence, and the drainage volume sequence is scanned point by point. When it is detected that the flow rate at a certain moment first exceeds the double threshold and is in a non-peak state, it is marked as the peak starting point.

[0057] Starting from the peak starting point, continuously verify whether the subsequent flow rate continuously meets the double threshold condition. If it is satisfied, mark the time point from the peak starting point to the time point when the flow rate first does not meet the threshold condition as the candidate peak period.

[0058] It should be added that the preset second duration can be set to 30 minutes. Specifically, it can be set to 1.5.

[0059] The intersection risk analysis module generates a drainage risk index for the drainage intersection based on the drainage overload index, the current drainage volume, and the centralized drainage time of each drainage branch, and based on the historical drainage monitoring data of the drainage intersection, similarly calculates the drainage risk index during each historical drainage monitoring, and sets a dynamic drainage risk index threshold.

[0060] Specifically, the specific generation process of the drainage risk index of the drainage intersection includes: E1. Based on the centralized drainage time periods of each drainage branch, calculate the drainage concentration degree of the drainage intersection. If the drainage concentration degree is less than the set threshold, record the ratio of the sum of the current drainage volumes of each drainage branch to the designed drainage load of the drainage intersection as the current drainage load ratio, and use it as the drainage risk index.

[0061] E2. Otherwise, extract the measured water volumes of the water inlet and the water outlet from the real-time drainage volume of the drainage intersection and calculate the drainage anomaly coefficient.

[0062] E3. Mark the drainage branches with a drainage overload index greater than the set warning overload index as the concerned branches, and calculate the ratio of the number of concerned branches to the total number of drainage branches, and record it as the warning coverage ratio.

[0063] E4. Analyze the drainage anomaly coefficient and the warning coverage ratio to obtain a drainage risk compensation factor, and correct the current drainage load ratio through the drainage risk compensation factor to obtain the final drainage risk index.

[0064] The embodiments of the present invention innovatively construct a drainage intersection risk index by integrating dynamic parameters such as the real-time drainage volume, overload index, and centralized drainage time of the drainage branch, realizing in-depth risk mining focusing on the key node of the drainage intersection, ensuring the dynamic, comprehensive, and real-time risk assessment of the drainage system, providing technical support for precise optimization in complex urban drainage scenarios, and filling the core shortcoming that cannot adapt to the dynamic bearing capacity of the pipe network currently.

[0065] Understandably, when the drainage concentration is low, the drainage of each branch is dispersed, and the load at the confluence point is mainly determined by the total flow. Therefore, the current drainage load ratio is directly used as the risk index to ensure simple and efficient evaluation. When the drainage concentration is high, the concentrated drainage of multiple branches is likely to cause coupling risks such as flow superposition and pressure imbalance. Therefore, the drainage anomaly coefficient and the warning coverage ratio are introduced, and the load ratio is corrected by the risk compensation factor to comprehensively capture systematic risks. Its significance lies in realizing the accurate identification of the dangerous state of the drainage confluence point by differentiating evaluations in different scenarios, taking into account the calculation efficiency of simple scenarios and the risk comprehensiveness of complex scenarios. Among them, the drainage anomaly coefficient reflects the dynamic balance of inflow and outflow, and the warning coverage ratio reflects the universality of overloaded branches.

[0066] It should be added that by combining the multi-level calculations of the drainage anomaly coefficient, the warning coverage ratio, and the concentration, a complete chain of "real-time data collection - multi-dimensional risk assessment - dynamic threshold correction - precise warning response" can be formed, which can effectively respond to the real-time changes in complex drainage scenarios.

[0067] Furthermore, the statistical process of the drainage concentration includes: mapping the concentrated drainage periods of all drainage branches to a unified time axis to generate a binary matrix .

[0068] Based on the number of drainage branches connected to the drainage confluence point, the current cumulative drainage time period is divided into monitoring time windows.

[0069] For each monitoring time window, count the number of drainage branches within the monitoring time window, denoted as the number of concentrated branches , and the number of concentrated branches is the sum of the elements in each row of the matrix . represents the monitoring time window number, .

[0070] Based on the concentrated drainage time periods of each drainage branch, calculate the total drainage duration of all drainage branches, denoted as .

[0071] Calculate the drainage concentration , , is the total number of drainage branches.

[0072] Exemplarily, the confluence point is connected to 3 branches, the current cumulative drainage time period is from 8:00 to 11:00, and the time windows are divided into 8:00 - 9:00, 9:00 - 10:00, and 10:00 - 11:00.

[0073] Count the number of branches in the centralized drainage state simultaneously. For example, if the centralized period of branch A is 08:00 - 09:00 and that of branch B is 08:30 - 09:30, then the overlap count within the 08:30 - 09:00 window is 2.

[0074] Understandably, represents the maximum proportion of branches in centralized drainage within a single window, reflecting the intensity of centralized drainage. It is the ratio of the total duration of centralized drainage of all branches to the total number of minutes in a day. For example, if the total duration of centralized drainage of all branches is 800 minutes, then , indicating that the total duration of centralized drainage accounts for 56% of the day, reflecting the persistence of centralized drainage.

[0075] Multiply the two items to obtain the drainage concentration , which combines the intensity and persistence of centralized drainage. When the intensity is high and the persistence is strong, the value will be high; otherwise, it will be low. This standardized calculation enables the drainage concentration to comprehensively and objectively reflect the centralized characteristics of the drainage system in the time dimension, providing a quantitative basis for subsequent judgment of drainage risks.

[0076] It is also understandable that by calculating the drainage concentration through the two dimensions of the proportion of overlapping branches in the time window + the proportion of the total centralized duration, the spatio - temporal coupling effect of multi - branch centralized drainage can be accurately captured, significantly improving the accuracy of overload analysis.

[0077] Furthermore, the specific statistical process of the statistical drainage anomaly coefficient includes: taking the difference between the measured water volumes at the water inlet and the water outlet to obtain the difference in water inflow and outflow.

[0078] Calculate the volatility of the difference in water inflow and outflow by calculating the standard deviation of the real - time difference in water inflow and outflow , and simultaneously calculate the change rate of the difference in water inflow and outflow .

[0079] Statistical drainage anomaly coefficient , , where \(e\) is the natural constant, and are respectively the permitted values of the volatility of the difference in water inflow and outflow and the change rate under normal circumstances set in advance, and are respectively the weights set for the volatility of the difference in water inflow and outflow and the change rate of the difference in water inflow and outflow.

[0080] Understandably, the use of the exponential function form in the formula can more accurately reflect the non-linear relationship between the degree of drainage anomaly and fluctuations and the rate of change. In an actual drainage system, a slight deviation from the normal range has a relatively small impact on the anomaly coefficient. However, as the degree of deviation increases, the rate of increase in the anomaly level accelerates. The characteristics of the exponential function make the formula change smoothly when the deviation is small and respond sensitively when the deviation is large, conforming to this non-linear rule. This avoids the inability of the simple linear weighted summation function to reflect this non-linear characteristic of "the larger the deviation, the more significant the anomaly".

[0081] In the formula, The operation ensures that only when or the corresponding factors will make a positive contribution. This highlights the abnormal situation of "exceeding the normal reference value" and avoids the interference of minor fluctuations such as those within the reference value on the anomaly coefficient. Simple linear summation would include all fluctuations and even minor changes within the normal range in the calculation, reducing the accuracy of anomaly assessment.

[0082] Understandably, the pre-set allowable values for the volatility and rate of change of the difference in water inflow and outflow under normal conditions mainly come from the statistical analysis of the long-term historical operation data of the drainage system, from which the typical parameter ranges under normal operating conditions are extracted. Refer to the definitions of system operation parameters in relevant standards and specifications of the drainage industry.

[0083] Specifically, the specific setting process of the dynamic drainage risk index threshold includes: counting the maximum value of the consecutive monitoring times when the drainage risk index exceeds the pre-set baseline threshold in historical monitoring, and dividing it by the total number of drainage monitoring times to obtain the ratio of continuous drainage monitoring times.

[0084] Arrange the drainage risk index in ascending order of monitoring time, use the median order as the segmentation point, and calculate the proportion of the number of over-limit monitoring times and the average drainage risk index after the segmentation point.

[0085] Comprehensively statistically obtain the correction factor based on the ratio of continuous drainage monitoring times, the proportion of over-limit monitoring times, and the average drainage risk index.

[0086] After correcting the pre-set baseline drainage risk index threshold through the correction factor, the corrected drainage risk index threshold is obtained.

[0087] In the embodiment of the present invention, by setting the dynamic drainage risk index threshold, the evaluation deviation caused by parameter solidification can be effectively avoided, enabling the system to respond in real time to dynamic factors such as changes in pipe network load, seasonal characteristics, or equipment aging, and significantly enhancing the environmental adaptability of drainage risk assessment.

[0088] Understandably, the proportion of over-limit monitoring times after the segmentation point is the ratio of the sum of drainage monitoring times with a drainage risk index greater than the corresponding set threshold after the segmentation order to the sum of drainage monitoring times after the segmentation order.

[0089] It should be added that the main purpose of setting the segmentation point is to divide historical data into a previous baseline segment and a recent concerned segment. By focusing on the data after the segmentation point, the latest evolution trend of the pipe network state can be effectively captured. Selecting the median order instead of a fixed time window as the segmentation point can not only avoid the subjectivity of artificial division, but also dynamically adapt to the change of data volume, ensuring the balance of data volume in the baseline segment and the concerned segment. Furthermore, it can reduce the interference of repaired problems or outdated working conditions in early historical data, and strengthen the response sensitivity to recent risk signals, such as sudden overloads, making the threshold dynamic adjustment more in line with the actual carrying capacity of the current system.

[0090] It also needs to be added that the ratio of continuous drainage monitoring times quantifies the cumulative effect of long-term overloads, revealing the deterioration trend of the pipe network under continuous high load. The proportion of over-limit monitoring times focuses on the recent risk evolution frequency, capturing the accelerated risks of environmental mutations or pipe network aging. The average drainage risk index after the segmentation point measures the harm intensity of recent over-limit events, avoiding misjudgments of high-frequency low-risk or low-frequency high-risk events. Thus, full-scenario coverage and precise grading of risk perception are achieved.

[0091] Embodiments of the present invention integrate multi-dimensional parameters such as drainage overload index, concentrated drainage time, and drainage risk index, comprehensively depict the risk conduction path in complex drainage scenarios, solve the one-sidedness problem caused by single-parameter analysis, provide a more scientific decision-making basis for system scheduling, and facilitate coping with complex and changeable urban drainage scenarios.

[0092] The risk report generation module, if the current drainage risk index exceeds the dynamic risk index threshold, matches the preset drainage risk mapping table to obtain the current drainage risk level, and generates a physical examination report for the drainage junction based on the drainage junction position and the drainage risk level.

[0093] Embodiments of the present invention effectively solve the core problems of staticness, one-sidedness, and lag in the prior art by setting a technical system of dynamic threshold correction + multi-dimensional risk modeling + drainage junction focused analysis, realizing a leapfrog upgrade from extensive pipe network design to refined node prevention and control, providing a quantifiable, traceable, and extensible risk management tool for urban drainage systems, and being able to effectively reduce the economic losses caused by waterlogging and extend the service life of the pipe network.

[0094] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of this technology can make various modifications or supplements to the described specific embodiments or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. An in-depth mining and visualization analysis system for urban physical examination data, characterized in that, The system includes: A drainage data collection module, which collects the designed drainage capacity of the drainage intersection points in the drainage pipe network of the area to be physically examined and the locations of the drainage intersection points to which they belong, and simultaneously collects the real-time drainage volumes of the drainage intersection points and each drainage branch corresponding to the drainage intersection points; A drainage overload analysis module, which generates a drainage overload index for each drainage branch based on the real-time drainage volume of each drainage branch and a preset load threshold, and determines the concentrated drainage time of each drainage branch through time series analysis; An intersection risk analysis module, which generates a drainage risk index for the drainage intersection point based on the drainage overload index, the current drainage volume, and the concentrated drainage time of each drainage branch, and based on the historical drainage monitoring data of the drainage intersection point, similarly calculates the drainage risk index during each historical drainage monitoring, and sets a dynamic drainage risk index threshold; A risk report generation module, if the current drainage risk index exceeds the dynamic risk index threshold, matches a preset drainage risk mapping table to obtain the current drainage risk level, and generates a physical examination report for the drainage intersection point based on the location of the drainage intersection point and the drainage risk level.

2. The in-depth mining and visual analysis system for urban physical examination data according to claim 1, wherein: The specific analysis process of the drainage overload index is as follows: Calculate the difference between the real-time drainage volume and the designed drainage capacity to obtain the real-time drainage difference, divide the drainage difference by the designed drainage capacity to obtain the relative proportion of the real-time drainage volume exceeding the designed capacity, denoted as the drainage full load ratio, calculate the average drainage difference through mean calculation, and extract the maximum drainage full load ratio; Form a drainage difference time series with the real-time drainage volume, and track the continuous duration of the drainage difference exceeding a preset threshold through a set time window, denoted as the drainage full load duration; Calculate the standard deviation of the drainage difference time series to obtain the volatility of the drainage difference, and calculate the average volatility through mean calculation; Perform an overload compensation trigger determination based on the average drainage difference, the drainage full load duration, and the average volatility. If overload compensation is triggered, set an overload compensation evaluation factor; Normalize the average drainage difference, the maximum drainage full load ratio, the drainage full load duration, and the average volatility, and then calculate the preliminary drainage overload index through linear weighting. Compensate the preliminary drainage overload index with the overload compensation evaluation factor to obtain the final drainage overload index for each drainage branch.

3. The in-depth mining and visualization analysis system for urban physical examination data according to claim 2, characterized in that: The overload compensation trigger determination condition is: if any two of the average drainage difference, the drainage full load duration, and the average volatility exceed the corresponding set thresholds, it is determined that overload compensation is triggered.

4. The in-depth mining and visualization analysis system for urban physical examination data according to claim 2, characterized in that: The specific setting of the overload compensation evaluation factor is as follows: Select the parameter items that exceed the corresponding set thresholds from the average drainage difference, the drainage full load duration, and the average volatility, denoted as deviation parameter items, and form a deviation parameter item combination; Match the deviation parameter item combination with a preset parameter deviation basic compensation mapping table to obtain a reference overload compensation factor; Normalize the deviation parameter items, and use the weighted sum value of the processing results as a variable to input into the Sigmoid function to output the target reference overload compensation factor; Multiply the reference overload compensation factor by the reference overload compensation factor to obtain the final overload compensation evaluation factor.

5. A system for in-depth mining and visualization analysis of urban physical examination data according to claim 1, characterized in that: The specific confirmation time of the concentrated drainage time includes: Import the historical average daily drainage volume of each drainage branch, divide the real-time drainage volume according to a preset time period, and construct a drainage volume time series dataset including the average flow rate, peak flow rate, and flow rate change rate of each time period; Detect the drainage volume time series dataset of each drainage branch through the local maximum search algorithm, and count the candidate peak time periods that meet the peak flow rate threshold and have a continuous duration exceeding the minimum duration threshold; Cluster the candidate peak time periods through the OPTICS density clustering algorithm, merge adjacent time periods with overlapping or spaced time less than the first preset duration, and generate a concentrated drainage time period cluster; Extract the start time, end time, and peak drainage volume ratio of each time period cluster, where the peak drainage volume ratio is the ratio of the total drainage volume within the cluster to the historical average daily drainage volume; Assign a priority weight to each time period cluster based on the peak drainage volume ratio, screen the concerned time period clusters with weights greater than the preset weight threshold, and calculate the arithmetic mean of their start time and end time as the time point; Calculate the standard deviation of the start time and end time corresponding to each candidate peak time period within each concerned time period cluster. If the standard deviations of the start time and end time within the concerned time period cluster are both less than the second preset threshold, expand and generate a core time period centered on the time point with the standard deviation as the boundary. If the standard deviation exceeds the third preset threshold, take the minimum start time and the maximum end time within the cluster as the core time period boundary; Perform secondary merging on the core time periods with an interval less than the second preset duration and a total peak drainage volume ratio greater than the third reference threshold after merging to obtain the final concentrated drainage time.

6. The in-depth mining and visualization analysis system for urban physical examination data according to claim 5, characterized in that: The determination process of the candidate peak time period is as follows: Set a dual threshold for peak determination, where the dual threshold is that the flow value exceeds times the daily average flow and the duration exceeds a preset second duration; Form a drainage volume sequence with the real-time drainage volume, scan the drainage volume sequence point by point. When it is detected that the flow rate at a certain moment first exceeds the double threshold and is in a non-peak state, mark it as the peak start point; Starting from the peak start point, continuously verify whether the subsequent flow rate continuously meets the double threshold condition. If it is satisfied, mark the time point from the peak start point to the time point when the flow rate first does not meet the threshold condition as the candidate peak time period.

7. The in-depth mining and visualization analysis system for urban physical examination data according to claim 1, wherein: The specific generation process of the drainage risk index of the drainage confluence point includes: Based on the concentrated drainage time periods of each drainage branch, calculate the drainage concentration of the drainage confluence point. If the drainage concentration is less than the set threshold, record the ratio of the sum of the current drainage volumes of each drainage branch to the designed drainage load of the drainage confluence point as the current drainage load ratio and use it as the drainage risk index; Otherwise, extract the measured water volumes of the inlet and outlet from the real-time drainage volume of the drainage confluence point and count the drainage anomaly coefficient; Record the drainage branches with a drainage overload index greater than the set warning overload index as the concerned branches, and count the ratio of the number of concerned branches to the total number of drainage branches, which is recorded as the warning coverage ratio; Comprehensively analyze the drainage anomaly coefficient and the warning coverage ratio to obtain a drainage risk compensation factor, and correct the current drainage load ratio through the drainage risk compensation factor to obtain the final drainage risk index.

8. The in-depth mining and visualization analysis system for urban physical examination data according to claim 7, characterized in that: The statistical process of the drainage concentration includes: Map the centralized drainage periods of all drainage branches to a unified timeline to generate a binary matrix ; Based on the number of drainage branches connected to the drainage confluence point, divide the current cumulative drainage time period into monitoring time windows; Count the number of drainage branches within each monitoring time window, and record it as the number of concentrated branches , where the number of concentrated branches is the sum of the elements in each row of the matrix . represents the monitoring time window number, ; Based on the centralized drainage time periods of each drainage branch, calculate the sum of the drainage durations of all drainage branches, denoted as ; Calculating the drainage concentration , , is the total number of drainage branches.

9. The in-depth mining and visualization analysis system for urban physical examination data according to claim 7, characterized in that: The specific statistical process of counting the drainage anomaly coefficient includes: The difference between the measured water volumes at the water inlet and the water outlet is obtained to get the difference between the inflow and outflow water volumes; The real-time difference in water inflow and outflow is used to calculate the volatility of the difference in water inflow and outflow through standard deviation , and at the same time, the change rate of the difference in water inflow and outflow is calculated ; Statistical drainage anomaly coefficient , , is the natural constant, and are respectively the permitted values of the difference volatility and the change rate of the water inflow and outflow under normal conditions preset in advance, and are respectively the weights of the set difference volatility of the water inflow and outflow and the change rate of the difference of the water inflow and outflow.

10. The in-depth mining and visualization analysis system for urban physical examination data according to claim 1, characterized in that: The specific setting process of the dynamic drainage danger index threshold includes: Count the maximum value of the consecutive monitoring times when the drainage danger index exceeds the preset baseline threshold in historical monitoring, and divide it by the total number of drainage monitoring times to obtain the ratio of continuous drainage monitoring times; Arrange the drainage danger index in ascending order of monitoring time, take the median order as the dividing point, and calculate the proportion of the number of over-limit monitoring times and the average drainage danger index after the dividing point; A correction factor is statistically obtained by integrating the ratio of continuous drainage monitoring times, the proportion of over-limit monitoring times, and the average drainage danger index; The preset baseline drainage danger index threshold is corrected by the correction factor to obtain the corrected drainage danger index threshold.

Images