System and method for dynamically monitoring cooperative state of urban infrastructure system

Abstract

The invention relates to the technical field of smart city and complex system monitoring, and particularly discloses a dynamic monitoring system and method for the cooperative state of an urban infrastructure system. Comprising a multi-source data aggregation and governance module, an index quantification and weight calculation module, a system collaborative state dynamic monitoring engine, a collaborative monitoring evaluation and grading partition module and a visual decision support module. Firstly, multi-source heterogeneous data is processed through an adaptive space-time filtering fusion algorithm, secondly, a CRITIC-game weighting method is adopted to determine system state index weights, and finally, a dynamic interaction collaborative evaluation method based on toughness adjustment is adopted. And carrying out dynamic quantitative monitoring and evaluation on the three-dimensional collaborative level of the physical bearing capacity PCC, the real-time operation load ROL and the energy efficiency environment state EES. According to the method, a monitoring analysis framework with dynamics, robustness and interpretation is provided for cooperative operation and maintenance of an urban infrastructure system, and a scientific basis is also provided for realizing systematic scheduling and toughness improvement.

Description

Technical Field

[0001] This invention relates to the field of smart city and complex system monitoring technology, and in particular to a dynamic monitoring system and method for the collaborative status of urban infrastructure systems. Background Technology

[0002] Modern urban infrastructure systems are highly coupled and complex operating entities. Achieving their safe, efficient, and resilient coordinated operation is the core objective of smart city management, which presupposes real-time and accurate monitoring and evaluation of the overall system's operational status.

[0003] However, existing monitoring and evaluation methods have two significant limitations: First, they suffer from fragmented perspectives. Most monitoring methods target only single subsystems or performance indicators such as traffic flow, energy consumption, and water quality, lacking a holistic and coordinated perspective on the infrastructure system from three dimensions: physical carrying capacity, real-time operating load, and energy efficiency and environmental status. Second, their applicability is insufficient. Current methods involving multi-indicator collaborative analysis rely heavily on explicit physical connections or topological relationships, analyzing data through network model construction. These methods are ill-suited for the fusion analysis of the vast amount of asynchronous spatiotemporal data from multiple sources, including IoT sensors, spatial geographic information, and operational statistical reports, present in infrastructure systems. Specifically, their limitations are: first, it is difficult to directly quantify the dynamic matching and harmony of different operational states over time; second, it cannot effectively analyze the interaction between "system operational level" and "internal coordination level," thus making it difficult to predict the risk of overall efficiency decline or cascading failures caused by internal system mismatches.

[0004] Therefore, it is urgent to break through the existing technical framework and propose a monitoring method and system that can deeply integrate multi-source heterogeneous spatiotemporal data, directly quantify the dynamic coordination level between multi-dimensional states within the infrastructure system, and organically couple "operational status" and "coordination relationship" for comprehensive evaluation, so as to overcome the above limitations and provide reliable technical tools for the coordinated scheduling, preventive maintenance and resilience improvement of urban infrastructure. Summary of the Invention

[0005] The purpose of this invention is to quantitatively assess the system's coordinated operation level in terms of the three-dimensional capabilities of physical carrying capacity, real-time operating load, and energy efficiency and environmental status involved in regional urban and rural construction, thereby providing a quantitative basis for scientifically monitoring and evaluating the coordinated status of urban and rural construction and for optimizing related schemes.

[0006] To achieve the above objectives, the present invention provides a dynamic monitoring system for the collaborative status of urban infrastructure systems, comprising: a multi-source data aggregation and governance module, an indicator quantification and weight calculation module, a dynamic monitoring engine for the collaborative status of systems, a collaborative monitoring, evaluation and hierarchical zoning module, and a visualization decision support module; The multi-source data aggregation and governance module is used to acquire raw observation data of the target area within a preset time period, including the physical carrying capacity (PCC) dimension of urban and rural construction, the real-time operating load (ROL) dimension, and the energy efficiency and environmental status (EES) dimension. The module also performs preprocessing such as cleaning and interpolation on the raw observation data to form a basic index dataset. The indicator quantification and weight calculation module, as a post-module of the multi-source data aggregation and governance module, uses an adaptive spatiotemporal filtering fusion calculation method to process the basic indicator dataset and construct a standardized indicator matrix. Based on matrix Using the CRITIC-game weighting method, the indicator weight vectors within PCC, ROL, and EES are calculated respectively, and the output is... , , ;in For time samples, Corresponding to PCC, ROL, and EES. For indexes of metrics within a dimension, , , These are the indicator weight vectors for PCC, ROL, and EES, respectively. The system's collaborative state dynamic monitoring engine includes a multi-dimensional development index synthesis unit and a collaborative state analysis unit. As a post-module of the index quantification and weight calculation module, it is used to receive... , , This engine uses a multi-dimensional development index synthesis unit to linearly weight and aggregate standardized indicators of each dimension according to the received weights, generating time-series indices representing the levels of PCC, ROL, and EES. , , This refers to the three-dimensional development index; then, the collaborative state analysis unit calls the built-in dynamic interactive collaborative evaluation method based on resilience adjustment to... , , As input, calculate the dynamic coupling strength. Resilience perception and overall development level and system coordination ; The collaborative monitoring, evaluation, and hierarchical zoning module includes a collaborative level monitoring and evaluation unit, a system imbalance mode classification unit, and a key limiting factor identification unit. As a back-end module of the system collaborative state dynamic monitoring engine, it is used to receive... , , and system coordination This module first uses a collaborative level monitoring and evaluation unit to assess the collaborative development level based on a pre-defined collaborative development level spectrum. The values ​​are mapped to output the qualitative coordination level of the target region; subsequently, the system imbalance mode partitioning unit is based on... , , The relative size relationship among the three and The system classifies regions into specific types of system imbalance mode areas according to preset rules. Finally, the key constraint factor identification unit identifies and outputs a set of key constraint factors that restrict the coordinated operation of the system by calculating the obstacle degree of each indicator for regions identified as imbalance modes, thus forming multi-level monitoring and evaluation results. The visualization decision support module, with its built-in visualization template, serves as a post-module to the collaborative monitoring and evaluation and hierarchical zoning module. It integrates and graphically visualizes the received multi-level monitoring and evaluation results. Based on the received collaborative development level, system imbalance mode zone type, key limiting factor set, and three-dimensional development index data, this module calls the built-in visualization template to automatically generate a comprehensive report including a PCC-ROL-EES system status radar comparison chart, a development index time series evolution chart, and a structured monitoring and evaluation conclusion panel.

[0007] Preferably, in the multi-source data aggregation and governance module, the original observation data includes statistical data from statistical yearbooks, spatial data from geographic information systems, remote sensing image data, and IoT sensor data; The spatiotemporal resolution of the original observation data is as follows: the time granularity is based on annual, quarterly, or monthly data, and the spatial granularity is based on administrative division units or regular grid units. The observation data for the Physical Carrying Capacity (PCC) dimension include road network density and connectivity, key section traffic capacity, pipeline system design capacity, power supply network maximum load, and communication base station coverage density. The observation data for the Real-Time Operating Load (ROL) dimension includes real-time traffic flow, regional instantaneous energy consumption, peak hourly water supply, data center computing load, and public transportation passenger flow. The observation data of the Energy Efficiency and Environmental Status (EES) dimension include the comprehensive pipeline leakage rate, energy consumption per unit output value, noise compliance coverage rate, air quality index of key areas, and green coverage rate.

[0008] Preferably, in the multi-source data aggregation and governance module, the data cleaning includes removing duplicate records and correcting obviously erroneous data; The data imputation uses mean imputation, regression imputation, or spatial imputation methods to complete the missing data.

[0009] Preferably, the implementation steps of the indicator quantification and weight calculation module are as follows: S1. The basic index dataset is preprocessed using an adaptive spatiotemporal filtering fusion calculation method. Specifically, an exponential weighted sliding filter and dynamic standardization fusion algorithm are used, as shown in the following formula: ; in, , This represents the dynamic standard deviation within the current time window. The dynamic mean is calculated using an exponentially weighted moving average. The preset time period length, For time samples The interval from the reference time point, The preset time decay coefficient, The time interval is the sample interval; S2, the CRITIC-game-theoretic weighting method calculates the indicator weight vector within a dimension, specifically including: S21, CRITIC weighting formula: ; ; in, For dimension Next The initial weights of each indicator, Representing dimensions Next The amount of information in each indicator For dynamic standard deviation, Representing dimensions Next The first indicator and the first The correlation coefficient between the indicators To sum the variables, iterate through all metrics in that dimension; S22, Game Theory Equilibrium: ; in, For dimension Next The final weights of each indicator; the constraint condition for this equilibrium is... .

[0010] Preferably, the implementation steps of the system collaborative status dynamic monitoring engine are as follows: S3, The multidimensional development index synthesis unit generates a time series index representing the three-dimensional levels. , , : For dimensions In time samples The index above for: ; in, For dimension The total number of indicators below Standardized index values In time The corresponding value below; S4. The cooperative state analysis unit uses a dynamic interactive cooperative evaluation method based on resilience adjustment to calculate the system's cooperative degree. Specifically, it includes: S41. Calculate the dynamic coupling strength : ; in, The adjustment parameter is used to control the steepness of the Logistic function curve. Dimensions calculated within a time window With dimension The time-varying correlation coefficient; S42. Calculate the overall resilience perception status level. : ; in, For dimension The corresponding toughness adjustment factor, For dimension Composite Index Time series variance; S43, Computational System Coordination : ; in, To adjust the parameters, map the results to Interval.

[0011] Preferably, in the collaborative monitoring, evaluation, and hierarchical zoning module, the preset collaborative development level spectrum in the collaborative level monitoring and evaluation unit is specifically as follows: Collaborative Development Level Spectrum (CDGS) based on system synergy The value range is divided into five levels: when Time: System detuning stage; when Time: Warning and Attention Level; when Time: Basic Coordination Level; when At this time: Normal operating level; when Time: High-efficiency collaborative level.

[0012] Preferably, in the collaborative monitoring, assessment, and hierarchical zoning module, the preset rule for the system imbalance mode classification unit to categorize a region into a specific type of system imbalance mode zone is as follows: Preset a collaboration threshold and compare and judge and Size: when hour: like and If so, it is determined to be: a physical carrying capacity lagging imbalance zone; like and If so, it is determined to be: a real-time operating load lag type imbalance zone; like and If so, it is determined to be: an energy efficiency and environmental status lagging imbalance zone; when If so, it is determined to be: a normal collaborative operation zone; The value depends on the actual application scenario. Select from within.

[0013] Preferably, in the collaborative monitoring, evaluation, and hierarchical zoning module, the step of the key constraint factor identification unit identifying and outputting the key constraint factor set specifically includes: Calculate the obstacle degree of the indicator: For regions identified as having an imbalance pattern, their respective dimensions... Each indicator below Calculate its obstacle degree : ; in, For this area Standardized mean of the indicator For dimension Next The final weight of each indicator; Screening key factors: By obstacle Sort the indicators from largest to smallest and select the top N indicators to form a set of key constraint factors, where N is a preset positive integer.

[0014] Preferably, in the visual decision support module, the structured monitoring and evaluation conclusion panel integrates the collaborative development level, the type of system imbalance mode area, and the list of key limiting factors.

[0015] This invention also provides a method for dynamic monitoring of the collaborative status of urban infrastructure systems, comprising the following steps: S1. Data Acquisition and Standardization: Acquire multi-source raw observation data of the target area under the dimensions of Physical Carrying Capacity (PCC), Real-time Operating Load (ROL), and Energy Efficiency and Environmental Status (EES), and perform preprocessing including cleaning and interpolation. Then, use an adaptive spatiotemporal filtering fusion calculation method to generate a standardized index matrix. S2. Weight Calculation and Index Synthesis: Based on the standardized indicator matrix, the CRITIC-game weighting method is used to determine the internal indicator weight vectors for the three dimensions of PCC, ROL, and EES, respectively. Weighted calculations are then performed to generate time-series indices representing the development levels of each dimension. , , ; S3. Dynamic evaluation of system synergy: This involves evaluating the three time-series indices... , , Input a dynamic interactive collaborative evaluation model based on resilience adjustment, and calculate its dynamic coupling strength sequentially. Overall resilience perception level and the final system synergy ; S4. Collaborative Monitoring, Evaluation, and Pattern Determination: Based on the system's degree of collaboration. The level of collaboration is determined by comparing the value with the collaborative development level spectrum, and at the same time based on... , , The relative magnitudes of the three factors are used to determine specific system imbalance mode areas based on preset thresholds; for areas identified as imbalance modes, the set of key limiting factors is selected by calculating the obstacle degree of each indicator. S5. Result Generation and Visualization: Based on the aforementioned collaborative development level, system imbalance mode type, key limiting factor set, and three-dimensional development index, generate a visual report containing multi-dimensional comparative analysis and monitoring and evaluation conclusions.

[0016] The present invention employs the above-mentioned dynamic monitoring system and method for the collaborative status of urban infrastructure systems, and its beneficial effects are as follows: (1) By introducing an adaptive spatiotemporal filtering fusion algorithm, the system can dynamically fuse and denoise multi-source, heterogeneous, and asynchronous IoT sensor, spatial geographic and operational report data, effectively overcoming the limitations of traditional static standardization methods in processing asynchronous spatiotemporal data, filling missing values ​​in sequences and suppressing measurement noise, so that the preprocessed data can better reflect the recent operational trends of the infrastructure system. (2) By adopting the CRITIC-game weighting method, the system not only objectively reflects the contrast strength of the data itself and the conflict between indicators when determining the weight of the indicators, but also optimizes the weight allocation through game theory, overcoming the one-sidedness of single objective weighting methods such as entropy weighting, and making the generated state indices of each dimension more robust and explanatory. (3) By constructing a dynamic interactive collaborative evaluation model based on resilience adjustment, this invention systematically quantifies the dynamic correlation between the three-dimensional states of PCC, ROL, and EES, as well as the overall volatility of the system. This model can sensitively capture the evolution of the system's collaborative state, and its output of multi-level monitoring and evaluation conclusions of "collaboration level - imbalance mode - key factors" provides an operable technical solution optimization basis for accurately locating operational shortcomings. Attached Figure Description

[0017] Figure 1 This is a system block diagram of a dynamic monitoring system for the collaborative status of urban infrastructure systems according to the present invention; Figure 2 This is a flowchart of a method for dynamic monitoring of the collaborative status of urban infrastructure systems according to the present invention; Figure 3 This is a time-series chart showing the trend of the three-dimensional comprehensive index and system synergy of the present invention; Figure 4 This is a comparative analysis chart of the three-dimensional comprehensive index of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments and the accompanying drawings. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of the invention. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0019] Example 1, such as Figure 1 As shown, the present invention provides a dynamic monitoring system for the collaborative status of urban infrastructure systems, comprising: a multi-source data aggregation and governance module, an indicator quantification and weight calculation module, a dynamic monitoring engine for the collaborative status of systems, a collaborative monitoring, evaluation and hierarchical zoning module, and a visualization decision support module.

[0020] 1. Multi-source data aggregation and governance module: Acquires raw observation data (including statistical data from statistical yearbooks, spatial data from geographic information systems, remote sensing image data, and IoT sensor data) of the target area within a preset time period, including the physical carrying capacity dimension of urban and rural construction (PCC, including road network density and connectivity, key section capacity, pipeline system design capacity, power supply network maximum load, communication base station coverage density, etc.), the real-time operating load dimension (including real-time traffic flow, regional instantaneous energy consumption, peak hour water supply, data center computing load, public transportation passenger flow, etc.), and the energy efficiency and environmental status dimension (EES, including comprehensive pipeline leakage rate, energy consumption per unit output value, noise compliance zone coverage rate, air quality index of key areas, green coverage rate, etc.). The raw observation data is preprocessed by cleaning and interpolation to form a basic indicator dataset. The spatiotemporal resolution for acquiring raw observation data is as follows: time granularity is based on annual, quarterly, or monthly periods, and spatial granularity is based on administrative division units or regular grid units. In this embodiment, the time granularity is selected as annual.

[0021] Data cleaning includes techniques such as removing duplicate records and correcting obvious errors; data imputation uses mean imputation, regression imputation or spatial imputation methods to complete missing data.

[0022] 2. Indicator Quantification and Weight Calculation Module: As a downstream module of the multi-source data aggregation and governance module, this module extracts the time-series observations of each individual indicator across the three dimensions of PCC, ROL, and EES from the basic indicator dataset, constructs a standardized indicator matrix, and calculates the indicator weight vectors within the three dimensions. The specific steps are as follows: (1) The time series observations are preprocessed using an adaptive spatiotemporal filtering fusion calculation method to construct a standardized index matrix. Specifically, an exponentially weighted sliding filter and dynamic standardization fusion algorithm are used, as shown in the following formula: ; in, , This represents the dynamic standard deviation within the current time window. The dynamic mean is calculated using an exponentially weighted moving average. The preset time period length, For time samples The interval from the reference time point, The preset time decay coefficient, For time sample intervals, For time samples, Corresponding to PCC, ROL, and EES. This is an index of metrics within a dimension.

[0023] (2) Based on matrix The weight vectors of indicators within PCC, ROL, and EES are calculated using the CRITIC-game weighting method. ①CRITIC weighting formula: ; ; in, For dimension Next The initial weights of each indicator; Representing dimensions Next The information content of each indicator combines the comparative strength (variance) and conflict (correlation with other indicators). For dynamic standard deviation; Representing dimensions Next The first indicator and the first Correlation coefficients between the indicators; To sum the variables, iterate through all metrics in that dimension; ②Game theory equilibrium: ; in, For dimension Next The final weights of each indicator; this equilibrium is achieved through iterative optimization of weight allocation, with the following constraints: .

[0024] The final output is , , These correspond to the optimal weight allocation for the Basic Bearing Capacity (PCC), Development-Driven ROL, and Energy Efficiency and Environmental Status (EES) dimensions, respectively, and the weights within each dimension satisfy the following conditions: .

[0025] 3. System Collaborative Status Dynamic Monitoring Engine: Includes a multi-dimensional development index synthesis unit and a collaborative status analysis unit. As a post-module of the index quantification and weight calculation module, it receives... , , Through the multidimensional development index synthesis unit, the standardized indicators of each dimension are linearly weighted and aggregated according to the received weights to generate time series indices representing the levels of PCC, ROL, and EES. , , This refers to the three-dimensional development index; then, the collaborative state analysis unit calls the built-in dynamic interactive collaborative evaluation method based on resilience adjustment to... , , As input, calculate the dynamic coupling strength. Resilience perception and overall development level and system coordination Specifically: (1) Multidimensional development index synthesis unit generates time series index , , : For dimensions ( (corresponding to PCC, ROL, and EES dimensions respectively) in time samples The index above for: ; in, For dimension The total number of indicators below Standardized index values In time The corresponding value below.

[0026] (2) Calculate the system synergy degree using a dynamic interactive synergy evaluation method based on resilience adjustment. : ① Calculate the dynamic coupling strength : ; in, The adjustment parameter is used to control the steepness of the Logistic function curve. Dimensions calculated within a time window With dimension The time-varying correlation coefficient; ② Calculate the overall resilience perception level : ; in, For dimension The corresponding toughness adjustment factor, For dimension Composite Index The time series variance characterizes the volatility (instability) of development in this dimension. ③ Computational system coordination : ; in, To adjust the parameters, map the results to Interval.

[0027] 4. Collaborative Monitoring, Evaluation, and Hierarchical Zoning Module: This module includes a collaborative level monitoring and evaluation unit, a system imbalance mode classification unit, and a key limiting factor identification unit. As a back-end module of the system collaborative state dynamic monitoring engine, it receives data... , , and system coordination The system outputs a qualitative level of coordination for the target region, classifies the region into a specific type of system imbalance mode region, and identifies and outputs a set of key limiting factors that restrict the coordinated operation of the system; specifically: (1) First, through the collaborative level monitoring and evaluation unit, based on the collaborative development level spectrum, the collaborative development level is assessed. The values ​​are mapped to output the qualitative level of collaboration in the target region; Collaborative Development Scale (CDGS) based on system synergy The value range is divided into at least five levels: when Time: System detuning stage; when Time: Warning and Attention Level; when Time: Basic Coordination Level; when At this time: Normal operating level; when Time: High-efficiency collaborative level.

[0028] (2) Subsequently, the system imbalance mode partitioning unit is based on , , The relative size relationship among the three and The value is used to classify the region into a specific type of system imbalance mode region according to the following preset rules; Preset a collaboration threshold and compare and Size: when hour: like and If so, it is determined to be: a physical carrying capacity lagging imbalance zone; like and If so, it is determined to be: a real-time operating load lag type imbalance zone; like and If so, it is determined to be: an energy efficiency and environmental status lagging imbalance zone; when If so, it is determined to be: a normal collaborative operation zone; The value depends on the actual application scenario. Select from within.

[0029] (3) Finally, the key constraint factor identification unit identifies and outputs a set of key constraint factors that restrict the coordinated operation of the system for areas identified as being in an imbalance mode by calculating the obstacle degree of each indicator, thus forming a multi-level monitoring and evaluation result; the specific steps are as follows: ① Calculate the obstacle degree of the indicator: For regions identified as having an imbalance pattern, their respective dimensions... Each indicator below Calculate its obstacle degree : ; in, For this area Standardized mean of the indicator For dimension Next The final weight of each indicator; ② Screening key factors: By obstacle Sort the indicators from largest to smallest and select the top N indicators to form a set of key constraint factors, where N is a preset positive integer.

[0030] 5. Visualization Decision Support Module: Built-in visualization templates serve as a downstream module of the collaborative monitoring and evaluation and hierarchical zoning module, used to integrate and graphically display the multi-level monitoring and evaluation results received. Based on the received data on collaborative development level, system imbalance mode type, key limiting factor set, and three-dimensional development index, the system automatically generates a comparison chart of PCC-ROL-EES system status radar (reflecting the overall system status). , , (Relative size), development index time series evolution diagram (shown) , , and A comprehensive report combining the trend analysis and structured monitoring and assessment conclusions panel (integrating the levels of synergistic development, types of system imbalance patterns, and a list of key limiting factors). The time-series charts of the three-dimensional comprehensive index and system synergy are shown below. Figure 3 As shown in the figure, the three-dimensional comprehensive index comparison analysis chart is as follows: Figure 4 As shown.

[0031] Example 2, as follows Figure 2 As shown, a method for dynamic monitoring of the collaborative status of urban infrastructure systems using the above-mentioned system includes the following steps: S1. Data Acquisition and Standardization: Acquire multi-source raw observation data (including IoT sensor data, spatial geographic information, infrastructure operation reports, and remote monitoring data) of the target area under the dimensions of Physical Capacity (PCC), Real-time Operating Load (ROL), and Energy Efficiency and Environmental Status (EES), and perform preprocessing including cleaning and interpolation. An adaptive spatiotemporal filtering fusion calculation method is used to process the preprocessed raw observation data: first, an exponentially weighted moving average is applied to the time-series data to estimate the dynamic mean and variance; then, a fusion function is used to eliminate dimensions and generate a spatiotemporally consistent standardized index matrix. This enables dynamic alignment and denoising of asynchronous data from multiple sources.

[0032] S2. Weight Calculation and Index Synthesis: Based on Standardized Index Matrix The CRITIC-game weighting method is used to calculate the internal indicator weight vectors for the three dimensions of PCC, ROL, and EES. First, the contrast strength and conflict of each indicator are calculated to obtain the initial weights. Then, by introducing a contrast strength factor for a secondary weighting optimization step, the optimal comprehensive weight vector is solved. , , Based on this weight, the indicators of each dimension are weighted and aggregated to generate a comprehensive index that represents the operational status level of each dimension. , , .

[0033] S3. Dynamic Evaluation of System Coordination: Combining three comprehensive indices , , Input the dynamic interaction and collaborative evaluation model based on resilience adjustment, and calculate in sequence: (1) Dynamic coupling strength (2) The overall state level of resilience perception is obtained by summing the time-varying correlation coefficients between dimensions through the Logistic function transformation; The current level is weighted and summed based on the variance of each dimension index (representing state volatility); (3) System synergy ,Will and The sum is mapped to a final evaluation value between 0 and 1 through another Logistic function, thereby dynamically quantifying the overall collaborative state of the system.

[0034] S4. Collaborative Monitoring, Evaluation, and Pattern Determination: Based on the system's degree of collaboration. The value is compared with the collaborative development level spectrum to determine the collaborative level of the target system, and at the same time, based on , , The relative magnitudes of the three factors, combined with a preset collaborative threshold, are used to further determine the specific imbalance mode region to which the system belongs; for regions identified as imbalance modes, the key limiting factor set is selected by calculating the obstacle degree of each indicator. S5. Result Generation and Visualization: Based on the collaborative development level, system imbalance mode type, key limiting factors, and three-dimensional development index output from the above steps, a diagnostic report is automatically generated by calling a visualization template. The report includes a radar chart showing the comparison of the PCC-ROL-EES system state structure, a curve graph reflecting the time-series evolution of the index and collaborative degree, and a structured panel integrating all diagnostic conclusions, providing an intuitive basis for collaborative operation and maintenance and scheduling decisions of the infrastructure system.

[0035] Therefore, this invention adopts the above-mentioned dynamic monitoring system and method for the collaborative status of urban infrastructure systems. 1) By introducing an adaptive spatiotemporal filtering fusion algorithm, the system can dynamically fuse and denoise multi-source, heterogeneous, and asynchronous IoT sensor, spatial geographic, and operational report data, effectively overcoming the limitations of traditional static standardization methods in processing asynchronous spatiotemporal data, filling missing values ​​in sequences, and suppressing measurement noise, making the preprocessed data better reflect the recent operational trends of the infrastructure system; 2) By adopting the CRITIC-game weighting method, when determining the weights of indicators, the system not only objectively reflects the comparative strength of the data itself and the conflict between indicators, but also optimizes the weight allocation through game theory, overcoming the one-sidedness of single objective weighting methods such as entropy weighting, making the generated state indices of each dimension more robust and explanatory; 3) By constructing a dynamic interactive collaborative evaluation model based on resilience adjustment, the system realizes the comprehensive quantification of the dynamic correlation between the three-dimensional states of PCC, ROL, and EES, as well as the overall volatility of the system. This model can sensitively capture the evolution of the system's collaborative state. Its output of multi-level monitoring and evaluation conclusions, including "collaboration level - imbalance mode - key factors," provides an operational basis for optimizing technical solutions to accurately pinpoint operational shortcomings.

[0036] It is worth noting that all contents not described in detail in this invention are existing technologies and are well known to those skilled in the art.

[0037] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A dynamic monitoring system for the collaborative status of urban infrastructure systems, characterized in that, include: Multi-source data aggregation and governance module, indicator quantification and weight calculation module, system collaborative status dynamic monitoring engine, collaborative monitoring and evaluation and hierarchical partitioning module, and visualization decision support module; The multi-source data aggregation and governance module is used to acquire raw observation data of the target area within a preset time period, including the physical carrying capacity (PCC) dimension of urban and rural construction, the real-time operating load (ROL) dimension, and the energy efficiency and environmental status (EES) dimension. The module also performs preprocessing such as cleaning and interpolation on the raw observation data to form a basic index dataset. The indicator quantification and weight calculation module, as a post-module of the multi-source data aggregation and governance module, uses an adaptive spatiotemporal filtering fusion calculation method to process the basic indicator dataset and construct a standardized indicator matrix. Based on matrix Using the CRITIC-game weighting method, the indicator weight vectors within PCC, ROL, and EES are calculated respectively, and the output is... , , ;in For time samples, Corresponding to PCC, ROL, and EES. For indexes of metrics within a dimension, , , These are the indicator weight vectors for PCC, ROL, and EES, respectively. The system's collaborative state dynamic monitoring engine includes a multi-dimensional development index synthesis unit and a collaborative state analysis unit. As a post-module of the index quantification and weight calculation module, it is used to receive... , , This engine uses a multi-dimensional development index synthesis unit to linearly weight and aggregate standardized indicators of each dimension according to the received weights, generating time-series indices representing the levels of PCC, ROL, and EES. , , This refers to the three-dimensional development index; then, the collaborative state analysis unit calls the built-in dynamic interactive collaborative evaluation method based on resilience adjustment to... , , As input, calculate the dynamic coupling strength. Resilience perception and overall development level and system coordination ; The collaborative monitoring, evaluation, and hierarchical zoning module includes a collaborative level monitoring and evaluation unit, a system imbalance mode classification unit, and a key limiting factor identification unit. As a back-end module of the system collaborative state dynamic monitoring engine, it is used to receive... , , and system coordination This module first uses a collaborative level monitoring and evaluation unit to assess the collaborative development level based on a pre-defined collaborative development level spectrum. The values ​​are mapped to output the qualitative level of collaboration in the target region; Subsequently, the system imbalance mode partitioning unit is based on , , The relative size relationship among the three and The system classifies regions into specific types of system imbalance mode areas according to preset rules. Finally, the key constraint factor identification unit identifies and outputs a set of key constraint factors that restrict the coordinated operation of the system by calculating the obstacle degree of each indicator for regions identified as imbalance modes, thus forming multi-level monitoring and evaluation results. The visualization decision support module, with its built-in visualization template, serves as a post-module to the collaborative monitoring and evaluation and hierarchical zoning module. It integrates and graphically visualizes the received multi-level monitoring and evaluation results. Based on the received collaborative development level, system imbalance mode zone type, key limiting factor set, and three-dimensional development index data, this module calls the built-in visualization template to automatically generate a comprehensive report including a PCC-ROL-EES system status radar comparison chart, a development index time series evolution chart, and a structured monitoring and evaluation conclusion panel.

2. The urban infrastructure system collaborative status dynamic monitoring system according to claim 1, characterized in that, In the multi-source data aggregation and governance module, the raw observation data includes statistical data from statistical yearbooks, spatial data from geographic information systems, remote sensing image data, and IoT sensor data; The spatiotemporal resolution of the original observation data is as follows: the time granularity is based on annual, quarterly, or monthly data, and the spatial granularity is based on administrative division units or regular grid units. The observation data for the Physical Carrying Capacity (PCC) dimension include road network density and connectivity, key section capacity, pipeline system design capacity, power supply network maximum load, and communication base station coverage density. The observation data for the Real-Time Operating Load (ROL) dimension includes real-time traffic flow, regional instantaneous energy consumption, peak hourly water supply, data center computing load, and public transportation passenger flow. The observation data of the Energy Efficiency and Environmental Status (EES) dimension include the comprehensive pipeline leakage rate, energy consumption per unit output value, noise compliance coverage rate, air quality index of key areas, and green coverage rate.

3. The urban infrastructure system collaborative status dynamic monitoring system according to claim 1, characterized in that, In the multi-source data aggregation and governance module, the data cleaning includes removing duplicate records and correcting obviously erroneous data; The data imputation uses mean imputation, regression imputation, or spatial imputation methods to complete the missing data.

4. The urban infrastructure system collaborative status dynamic monitoring system according to claim 1, characterized in that, The specific implementation steps of the indicator quantification and weight calculation module are as follows: S1. The basic index dataset is preprocessed using an adaptive spatiotemporal filtering fusion calculation method. Specifically, an exponential weighted sliding filter and dynamic standardization fusion algorithm are used, as shown in the following formula: ； in, , This represents the dynamic standard deviation within the current time window. The dynamic mean is calculated using an exponentially weighted moving average. The preset time period length, For time samples The interval from the reference time point, The preset time decay coefficient, The time interval is the sample interval; S2, the CRITIC-game-theoretic weighting method calculates the indicator weight vector within a dimension, specifically including: S21, CRITIC weighting formula: ； ； in, For dimension Next The initial weights of each indicator, Representing dimensions Next The amount of information in each indicator For dynamic standard deviation, Representing dimensions Next The first indicator and the first The correlation coefficient between the indicators To sum the variables, iterate through all metrics in that dimension; S22, Game Theory Equilibrium: ； in, For dimension Next The final weights of each indicator; the constraint condition for this equilibrium is... .

5. The urban infrastructure system collaborative status dynamic monitoring system according to claim 4, characterized in that, The specific implementation steps of the system collaborative status dynamic monitoring engine are as follows: S3, The multidimensional development index synthesis unit generates a time series index representing the three-dimensional levels. , , : For dimensions In time samples The index above for: ； in, For dimension The total number of indicators below Standardized index values In time The corresponding value below; S4. The cooperative state analysis unit uses a dynamic interactive cooperative evaluation method based on resilience adjustment to calculate the system's cooperative degree. Specifically, it includes: S41. Calculate the dynamic coupling strength : ； in, The adjustment parameter is used to control the steepness of the Logistic function curve. Dimensions calculated within a time window With dimension The time-varying correlation coefficient; S42. Calculate the overall resilience perception status level. : ； in, For dimension The corresponding toughness adjustment factor, For dimension Composite Index Time series variance; S43, Computational System Coordination : ； in, To adjust the parameters, map the results to Interval.

6. The urban infrastructure system collaborative status dynamic monitoring system according to claim 1, characterized in that, In the collaborative monitoring, evaluation, and hierarchical zoning module, the pre-set collaborative development level spectrum in the collaborative level monitoring and evaluation unit is specifically as follows: Collaborative Development Level Spectrum (CDGS) based on system synergy The value range is divided into five levels: when Time: System detuning stage; when Time: Warning and Attention Level; when Time: Basic Coordination Level; when At this time: Normal operating level; when Time: High-efficiency collaborative level.

7. The urban infrastructure system collaborative status dynamic monitoring system according to claim 1, characterized in that, In the collaborative monitoring, assessment, and hierarchical zoning module, the preset rule for the system imbalance mode classification unit to categorize a region into a specific type of system imbalance mode zone is as follows: Preset a collaboration threshold and compare and judge and Size: when hour: like and If so, it is determined to be: a physical carrying capacity lagging imbalance zone; like and If so, it is determined to be: a real-time operating load lag type imbalance zone; like and If so, it is determined to be: an energy efficiency and environmental status lagging imbalance zone; when If so, it is determined to be: a normal collaborative operation zone; The value depends on the actual application scenario. Select from within.

8. The urban infrastructure system collaborative status dynamic monitoring system according to claim 1, characterized in that, In the collaborative monitoring, evaluation, and hierarchical zoning module, the specific steps for the key constraint factor identification unit to identify and output the key constraint factor set are as follows: Calculate the obstacle degree of the indicator: For regions identified as having an imbalance pattern, their respective dimensions... Each indicator below Calculate its obstacle degree : ； in, For this area Standardized mean of the indicator For dimension Next The final weight of each indicator; Screening key factors: By obstacle Sort the indicators from largest to smallest and select the top N indicators to form a set of key constraint factors, where N is a preset positive integer.

9. The urban infrastructure system collaborative status dynamic monitoring system according to claim 1, characterized in that, In the visualization decision support module, the structured monitoring and evaluation conclusion panel integrates the collaborative development level, the type of system imbalance mode area, and the list of key limiting factors.

10. A method for dynamic monitoring of the collaborative status of an urban infrastructure system using the urban infrastructure system collaborative status dynamic monitoring system according to any one of claims 1-9, characterized in that, Includes the following steps: S1. Data Acquisition and Standardization: Acquire multi-source raw observation data of the target area under the dimensions of Physical Carrying Capacity (PCC), Real-time Operating Load (ROL), and Energy Efficiency and Environmental Status (EES), and perform preprocessing including cleaning and interpolation. Then, use an adaptive spatiotemporal filtering fusion calculation method to generate a standardized index matrix. S2. Weight Calculation and Index Synthesis: Based on the standardized indicator matrix, the CRITIC-game weighting method is used to determine the internal indicator weight vectors for the three dimensions of PCC, ROL, and EES, respectively. Weighted calculations are then performed to generate time-series indices representing the development levels of each dimension. , , ; S3. Dynamic evaluation of system synergy: This involves evaluating the three time-series indices... , , Input a dynamic interactive collaborative evaluation model based on resilience adjustment, and calculate its dynamic coupling strength sequentially. Overall resilience perception level and the final system synergy ; S4. Collaborative Monitoring, Evaluation, and Pattern Determination: Based on the system's degree of collaboration. The level of collaboration is determined by comparing the value with the collaborative development level spectrum, and at the same time based on... , , The relative magnitudes of the three factors are used to determine specific system imbalance mode areas based on preset thresholds; for areas identified as imbalance modes, the set of key limiting factors is selected by calculating the obstacle degree of each indicator. S5. Result Generation and Visualization: Based on the aforementioned collaborative development level, system imbalance mode type, key limiting factor set, and three-dimensional development index, generate a visual report containing multi-dimensional comparative analysis and monitoring and evaluation conclusions.

Images