Municipal engineering quality monitoring intelligent analysis system

Abstract

The invention relates to the technical field of quality monitoring, in particular to a municipal engineering quality monitoring intelligent analysis system, which comprises a data receiving module based on structural integrity monitoring points and environmental factor monitoring points, the data receiving module receives and records real-time loads and flows of bridges and roads, analyzes temperature and humidity in the environment of a plurality of monitoring points, and sends the data to a cloud server; partition processing is carried out on the collected load and flow data. According to the invention, through comprehensive processing of real-time monitoring data, accuracy and response speed of municipal engineering monitoring are improved, data partition processing and a dynamic parameter adjustment strategy allow adjustment of a monitoring strategy according to specific requirements of different areas, load response is optimized, and ability of problem prevention and timely correction is enhanced. The phase-space reconstruction further deepens the data analysis capability and enhances the accuracy of predicting and identifying potential risks, so that the monitoring system can make decisions on the basis of wider data, and comprehensive risk assessment and quality assurance are provided for engineering management.

Description

Technical Field

[0001] The present invention relates to the technical field of quality monitoring, and in particular to an intelligent analysis system for monitoring the quality of municipal engineering projects. Background Art

[0002] The field of quality monitoring technology covers a range of methods and tools used to ensure that products and services meet predetermined quality standards. This area typically includes aspects such as quality assessment, process control, defect management and continuous improvement. Through real-time monitoring, data analysis and feedback mechanisms, quality monitoring systems can promptly identify problems in the production or execution process and take corrective measures. In addition, these systems can also analyze quality data to discover potential quality trends and root causes of problems, thereby helping companies optimize workflows and improve product quality.

[0003] Among them, the municipal engineering quality monitoring intelligent analysis system refers to the use of advanced data processing technology and machine learning algorithms to monitor and analyze the construction quality of municipal engineering. The purpose of this type of system is mainly to ensure that municipal engineering construction projects can meet safety standards and quality requirements, and prevent and reduce engineering defects and accidents. Through continuous monitoring and data analysis of engineering projects, the system can provide real-time feedback and suggestions to help the engineering management team adjust construction strategies and improve construction quality in a timely manner.

[0004] Existing technologies have obvious deficiencies in real-time data processing and dynamic response. In particular, when faced with rapid changes in environmental factors and structural loads, monitoring strategies are often unable to be adjusted in real time, affecting the accuracy and reliability of monitoring. This static data processing method is particularly insufficient in municipal engineering monitoring, because these projects often involve wide areas and complex environments, and any monitoring lag may cause safety risks and economic losses. The limitations of traditional methods in data analysis depth and dimensions often lead to insufficient identification and early warning capabilities for potential risks, and are unable to effectively respond to changing engineering needs. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose an intelligent analysis system for monitoring the quality of municipal engineering projects.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: A municipal engineering quality monitoring intelligent analysis system comprises:

[0007] The data receiving module receives and records the real-time load and flow of bridges and roads based on the structural integrity monitoring points and environmental factor monitoring points, analyzes the temperature and humidity in the environment of multiple monitoring points, and generates a real-time monitoring data set by partitioning the collected load and flow data and identifying the differences between multiple monitoring points by region;

[0008] The phase space reconstruction module is based on the real-time monitoring data set, identifies the fluctuation characteristics in the load response, analyzes the change trend under time delay, reconstructs the load response phase space, and generates a reconstructed phase space data set through comparison and correlation processing between dynamic data;

[0009] The dynamic parameter adjustment module is based on the reconstructed phase space data set, and by analyzing the current monitoring data of the structural integrity and environmental factors, determines the impact of the current environment on the load, adjusts the load response parameters of the differentiated areas as needed, introduces the differences of the monitoring points in multiple areas, and constructs a prediction model for parameter optimization;

[0010] The network stability analysis module extracts key area nodes based on the parameter optimized prediction model, performs stability analysis on key nodes in the network, combines the load response changes of multiple nodes, determines the load response changes of vulnerable connections, identifies potential failure nodes, and generates network stability analysis results.

[0011] As a further solution of the present invention, the step of acquiring the real-time load and flow is specifically as follows:

[0012] Receive data from structural integrity monitoring points and environmental factor monitoring points on bridges and roads to generate preliminary load and flow data sets;

[0013] Performing time synchronization on the preliminary load and flow data sets, unifying the data format, and generating synchronized load and flow data;

[0014] Based on the synchronous load and flow data, the weighted average value of the data at each monitoring point is calculated to evaluate the real-time load and flow, using the formula:

[0015]

[0016] Get real-time load and flow data;

[0017] Among them, d i represents the load or flow data of the i-th monitoring point, F avg Represents the real-time load and traffic after weighted average.

[0018] As a further solution of the present invention, the step of acquiring the real-time monitoring data set is specifically:

[0019] Based on the synchronous load flow data, analyzing the temperature and humidity in the environments of multiple monitoring points, calculating the statistical characteristics of the environmental data, and obtaining environmental characteristic data;

[0020] Based on the environmental characteristic data, the environmental difference analysis between regions is carried out using the formula:

[0021]

[0022] Calculate and obtain real-time monitoring data set;

[0023] Among them, x i represents the environmental data of the ith monitoring point, represents the global average environmental data, represents the variance of environmental data, and D represents the results of the analysis of environmental differences among regions.

[0024] As a further solution of the present invention, the step of obtaining the reconstructed phase space data set is specifically:

[0025] Extract load response data from the real-time monitoring data set, determine the frequency and amplitude of multiple load fluctuations by a spectrum analysis method, and obtain fluctuation characteristic data;

[0026] Based on the fluctuation characteristic data, a dynamic time warping algorithm is used to analyze and compare the fluctuation data at different time points to obtain time delay trend data;

[0027] Using the time delay trend data, the formula is used:

[0028]

[0029] Reconstruct the load response phase space to generate a reconstructed phase space data set;

[0030] Among them, γ represents the adjustment weight of time change on reconstruction, μ represents the adjustment weight of response amplitude, and δp i , δq i They represent the load response difference and response time difference at consecutive time points respectively, and δt represents the time interval.

[0031] As a further solution of the present invention, the step of obtaining the prediction model of parameter optimization is specifically as follows:

[0032] Extracting load response data from the reconstructed phase space data set, analyzing it based on current structural integrity monitoring data, calculating the real-time impact of environmental factors on the load, and obtaining an environmental impact assessment result;

[0033] Analyze the environmental impact assessment results by statistical methods, determine the adjustment requirements of load response parameters of multi-region monitoring points, and generate regional response adjustment data;

[0034] According to the regional response adjustment data, parameter optimization is performed using the formula:

[0035]

[0036] Build and generate prediction models with optimized parameters;

[0037] Among them, κi Represents the adjustment factor for load parameters, λ i represents the adjustment coefficient for environmental parameters, v i and u i They represent real-time load and environment data from differentiated monitoring points respectively.

[0038] As a further solution of the present invention, the steps of obtaining the network stability analysis result are specifically as follows:

[0039] Based on the parameter optimized prediction model, the data of key area nodes are analyzed, key nodes are extracted using data mining technology, and a key node list is obtained;

[0040] Performing stability analysis on the key node list, calculating the stability index of each node using dynamic system theory, and generating node stability analysis data;

[0041] Combining the node stability analysis data and the load response change information of multiple nodes in the network, the formula is adopted:

[0042]

[0043] Analyze and identify potential failed nodes and vulnerable connections in the network, and generate network stability analysis results;

[0044] Among them, R f represents the network stability analysis result, L i represents the load response of node i, D i represents the vulnerability index of node i, P i Represents the weight parameter of node i.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are:

[0046] In the present invention, the accuracy and response speed of municipal engineering monitoring are improved through comprehensive processing of real-time monitoring data. Data partition processing and dynamic parameter adjustment strategies allow monitoring strategies to be adjusted according to specific needs of different regions, optimize load response, and strengthen the ability to prevent and correct problems in a timely manner. Phase space reconstruction further deepens the ability to analyze data and enhances the accuracy of predicting and identifying potential risks. It enables the monitoring system to implement decisions based on a wider range of data, providing comprehensive risk assessment and quality assurance for engineering management. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a system flow chart of the present invention;

[0048] Figure 2 A flow chart of the steps for obtaining real-time load and flow in the present invention;

[0049] Figure 3 A flowchart of the steps for obtaining a real-time monitoring data set of the present invention;

[0050] Figure 4 A flow chart of the steps for obtaining a phase space data set for reconstruction of the present invention;

[0051] Figure 5 A flow chart of the steps for obtaining the prediction model for parameter optimization of the present invention;

[0052] Figure 6 The figure is a flow chart of the steps for obtaining the network stability analysis results of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0055] Embodiment 1

[0056] See also Figure 1 , a municipal engineering quality monitoring intelligent analysis system includes:

[0057] The data receiving module receives and records the real-time load and flow of bridges and roads based on the structural integrity monitoring points and environmental factor monitoring points, analyzes the temperature and humidity in the environment of multiple monitoring points, and generates a real-time monitoring data set by partitioning the collected load and flow data and identifying the differences between multiple monitoring points by region;

[0058] The phase space reconstruction module is based on the real-time monitoring data set. It identifies the fluctuation characteristics in the load response, analyzes the change trend under time delay, reconstructs the load response phase space, and generates a reconstructed phase space data set through comparison and correlation processing between dynamic data.

[0059] The dynamic parameter adjustment module is based on the reconstructed phase space data set. By analyzing the current monitoring data of structural integrity and environmental factors, it determines the impact of the current environment on the load, adjusts the load response parameters of the differentiated areas as needed, introduces the differences of monitoring points in multiple areas, and builds a prediction model for parameter optimization.

[0060] The network stability analysis module extracts key area nodes based on a parameter-optimized prediction model, performs stability analysis on key nodes in the network, combines the load response changes of multiple nodes, determines the load response changes of vulnerable connections, identifies potential failure nodes, and generates network stability analysis results.

[0061] The real-time monitoring data set specifically includes monitoring point differences, regional load data, and environmental temperature and humidity information. The reconstructed phase space data set specifically includes fluctuation characteristic data, time delay trends, and phase space structures. The parameter optimization prediction model specifically includes load response parameter adjustment results, differentiated regional data, and environmental impact assessment. The network stability analysis results include key node analysis, vulnerable connection identification, and potential failure nodes.

[0062] See also Figure 2 ,The steps for obtaining real-time load and flow are as follows:

[0063] Receive data from structural integrity monitoring points and environmental factor monitoring points on bridges and roads to generate preliminary load and flow data sets;

[0064] Among them, the data of the structural integrity monitoring points and environmental factor monitoring points of bridges and roads are received, and the formula is used Calculate and obtain the original load and flow data sets;

[0065] Where D init represents a preliminary load and flow data set, r i represents the data received by the i-th monitoring point, and N represents the total number of monitoring points.

[0066] Detailed explanation of the formula and the process of formula calculation and derivation:

[0067] The formula is used to accumulate the data of all monitoring points to form a preliminary data set. For example, there are three monitoring points, and the data of each point is 100, 150 and 200 respectively. The calculation process of the formula is:

[0068] D init =100+150+200=450

[0069] The result 450 represents the sum of data of all monitoring points at the time point.

[0070] Perform time synchronization on the preliminary load and flow data sets, unify the data format, and generate synchronized load and flow data;

[0071] Among them, execution time synchronization and data format unification are performed according to the formula Calculate and generate synchronous load flow data;

[0072] Where D sync Represents the synchronized load and flow data, D init,i represents the data of the i-th monitoring point, and N represents the total number of monitoring points.

[0073] Detailed explanation of the formula and the process of formula calculation and derivation:

[0074] The formula is used to calculate the average value of all monitoring point data. Set the initial data set to D init The value is 450, and there are three monitoring points. The calculation process is as follows:

[0075]

[0076] The result 150 represents the average data value after synchronization.

[0077] Based on the synchronous load and flow data, the weighted average of the data at each monitoring point is calculated to evaluate the real-time load and flow using the formula:

[0078]

[0079] Get real-time load and flow data;

[0080] Among them, d i represents the load or flow data of the i-th monitoring point, F avg Represents the real-time load and traffic after weighted average.

[0081] formula:

[0082]

[0083] Detailed explanation of the formula and the process of formula calculation and derivation:

[0084] The formula is used to calculate the weighted average load and flow, where d i represents the data of the ith monitoring point, and n represents the total number of monitoring points. In the formula, the contribution of the data of each monitoring point to the average value is weighted according to its proportion relative to the total amount of data.

[0085] There are three monitoring points. After synchronization, the data are d1=120, d2=150 and d3=180 respectively. The total data volume The calculation process is as follows:

[0086]

[0087] Results avg=148.67 represents the calculated weighted average load and flow.

[0088] See also Figure 3 ,The specific steps for obtaining the real-time monitoring data set are:

[0089] Based on the synchronous load flow data, analyze the temperature and humidity in the environment of multiple monitoring points, calculate the statistical characteristics of the environmental data, and obtain the environmental characteristic data;

[0090] Among them, the temperature and humidity in the environment of multiple monitoring points are analyzed according to the formula Calculate the variance of the environmental data.

[0091] In the formula, E represents the variance of environmental data, x i represents the environmental data of the ith monitoring point, and μ represents the average value of the environmental data.

[0092] Detailed explanation of the formula and the process of formula calculation and derivation:

[0093] The formula is used to calculate the variance of environmental data (including temperature and humidity). Variance is a statistic that measures the degree of dispersion of data distribution. For example, if there are three monitoring points with environmental data values ​​of 15℃, 20℃ and 25℃, the average value of the environmental data is 20℃. The calculation of variance E will be

[0094]

[0095] The results show that the variance of the environmental data is about 16.67, which indicates the degree of fluctuation of the temperature data at the monitoring points relative to the average value, which helps to evaluate the stability of environmental conditions.

[0096] Based on the environmental characteristic data, the environmental difference analysis between regions is carried out using the formula:

[0097]

[0098] Calculate and obtain real-time monitoring data set;

[0099] Among them, x i represents the environmental data of the ith monitoring point, represents the global average environmental data, represents the variance of environmental data, and D represents the results of the analysis of environmental differences among regions.

[0100] formula:

[0101]

[0102] Detailed explanation of the formula and the process of formula calculation and derivation:

[0103] The formula is used to analyze the environmental differences between regions and calculate the standard deviation of multi-regional environmental data. i represents the environmental data of the ith region, is the global average environmental data, is the variance of the environmental data, which is used to normalize the deviation of the multi-regional data from the mean.

[0104] For example, there are three areas with environmental data values ​​of 15, 20, and 25 respectively, and the global average is 20, the variance of the environmental data If is 5, then the calculation of D will be:

[0105]

[0106] The results show that the standard deviation of the environmental difference analysis between regions is 10, indicating that the deviation of multi-regional environmental data from the average value is large.

[0107] See also Figure 4 , the specific steps for obtaining the reconstructed phase space data set are:

[0108] Extract load response data from real-time monitoring data sets, determine the frequency and amplitude of multiple load fluctuations through spectrum analysis methods, and obtain fluctuation characteristic data;

[0109] Among them, the load response data is extracted from the real-time monitoring data set according to the formula Calculate the average spectral characteristics of the load response.

[0110] In the formula, R i represents the response intensity of the ith data point, A i represents the corresponding amplitude, and n represents the total number of data points.

[0111] Detailed explanation of the formula and the process of formula calculation and derivation:

[0112] The formula is used to calculate the average spectral characteristics of load response data collected from multiple data points. The overall average spectral characteristics are obtained by summing the product of the response strength and its amplitude of each data point and dividing by the total number of data points.

[0113] For example, if there are three data points with response intensities of 5, 10 and 15, and corresponding amplitudes of 2, 4 and 6, the above formula is applied:

[0114]

[0115] The results show that the average spectral characteristic of each data point is 46.67, referring to the response intensity and amplitude of all data points. This value is used to evaluate the overall load response performance.

[0116] Based on the fluctuation characteristic data, the dynamic time warping algorithm is used to analyze and compare the fluctuation data at different time points to obtain the time delay trend data;

[0117] Among them, the frequency and amplitude of multi-load fluctuations are determined by spectrum analysis method, according to the formula Calculate the spectrum intensity.

[0118] In the formula, f i represents the frequency of the ith data point, A i represents the corresponding amplitude, and n represents the total number of data points.

[0119] Detailed explanation of the formula and the process of formula calculation and derivation:

[0120] The formula is used to calculate the spectral intensity from the spectrum analysis, by taking the square root of the sum of the products of the square of the frequency and the amplitude of all data points, to obtain an indicator that characterizes the overall spectral intensity.

[0121] For example, if there are three data points with frequencies of 100 Hz, 200 Hz and 300 Hz, and corresponding amplitudes of 2, 3 and 4, the above formula is applied:

[0122]

[0123] The results show that the spectrum intensity obtained by combining the frequency and amplitude of all data points is 707.11, which is used to measure the overall spectrum energy distribution.

[0124] Using the time-delayed trend data, the formula is:

[0125]

[0126] Reconstruct the load response phase space to generate a reconstructed phase space data set;

[0127] Among them, γ represents the adjustment weight of time change on reconstruction, μ represents the adjustment weight of response amplitude, and δp i , δq i They represent the load response difference and response time difference at consecutive time points respectively, and δt represents the time interval.

[0128] formula:

[0129]

[0130] Detailed explanation of the formula and the process of formula calculation and derivation:

[0131] The formula is used to reconstruct the load response phase space by weighted summing the load response change rate at each time point. i and δq iThey represent the load response difference and response time difference at time t respectively, δt is the time interval, and γ and μ are the adjustment coefficients.

[0132] For example, set the load response data at three time points, and the change rate is as follows:

[0133] δp1=0.5, δq1=1.0, δt=1

[0134] δp2=0.7, δq2=1.5, δt=1

[0135] δp3=0.6, δq3=1.2, δt=1

[0136] Setting γ = 2 and μ = 3, the application of the formula is:

[0137]

[0138] S recon =(1+3)+(1.4+4.5)+(1.2+3.6)=4+5.9+4.8=14.7

[0139] Calculation result S recon =14.7 indicates that the strength index of the reconstructed load response phase space data set is 14.7 by comprehensively referring to the load response change rate and time change rate at all time points, which helps to better analyze the dynamic changes of the load response.

[0140] See also Figure 5 , the steps for obtaining the prediction model with parameter optimization are as follows:

[0141] Extract load response data from the reconstructed phase space data set, analyze it based on the current structural integrity monitoring data, calculate the real-time impact of environmental factors on the load, and obtain the environmental impact assessment results;

[0142] Among them, the load response data is extracted from the reconstructed phase space data set and analyzed based on the current structural integrity monitoring data. According to the formula Calculate the impact of environmental factors on load.

[0143] In the formula, a i represents the importance coefficient of the i-th monitoring point, d i Represents the data influence strength of the i-th monitoring point.

[0144] Detailed explanation of the formula and the process of formula calculation and derivation:

[0145] In this step, in order to calculate the impact of environmental factors on the load, a weighted summation method is used. The data d of each monitoring point i Obtained through actual measurement, and the importance coefficient a iBased on data analysis, it is used to adjust the contribution of each monitoring point data to the result. For example, a monitoring point is located in a critical part of the structure. i The value will be higher than other monitoring points in non-critical locations.

[0146] Actual example: There are three monitoring points, whose data influence intensities d are 15, 20 and 25 respectively, and the corresponding importance coefficients a are 0.5, 1.0 and 1.5 respectively. The calculation process is as follows:

[0147] F=(0.5×15)+(1.0×20)+(1.5×25)=7.5+20+37.5=65

[0148] The results show that after integrating the data and importance of all monitoring points, the overall impact assessment value of the environment on the load is 65.

[0149] Analyze the environmental impact assessment results through statistical methods, determine the adjustment requirements of load response parameters of multi-region monitoring points, and generate regional response adjustment data;

[0150] Among them, the environmental impact assessment results are analyzed by statistical methods to determine the adjustment requirements of the load response parameters of multi-region monitoring points. Compute regional response adjustment data.

[0151] Where b i represents the adjustment factor of the ith region, e i Represents the environmental impact assessment results of the ith region.

[0152] Detailed explanation of the formula and the process of formula calculation and derivation:

[0153] To adjust the load response parameters of multiple regions, refer to the target environmental impact assessment results of each region. Formula R calculates the adjustment factor b for all regions i The corresponding environmental impact assessment results i The adjustment factor b is i Reflects the sensitivity of the region to environmental changes or the need for adjustment. i Values ​​higher indicate areas that require greater adjustment.

[0154] Actual example: There are three areas, whose environmental impact assessment results e are 30, 45 and 60 respectively, and the corresponding adjustment factors b are 1.2, 0.8 and 1.0 respectively. The calculation process is as follows:

[0155]

[0156] The results show that, on average, the regional response adjustment data is 44 after referring to the environmental impacts and adjustment needs of multiple regions.

[0157] Adjust the data according to the regional response and optimize the parameters using the formula:

[0158]

[0159] Build and generate prediction models with optimized parameters;

[0160] Among them, κ i Represents the adjustment factor for load parameters, λ i represents the adjustment coefficient for environmental parameters, v i and u i They represent real-time load and environment data from differentiated monitoring points respectively.

[0161] formula:

[0162]

[0163] Detailed explanation of the formula and the process of formula calculation and derivation:

[0164] This step builds a prediction model with optimized parameters. Formula P new Used to calculate the optimal load response parameters of multi-region monitoring points. Parameter κ i and λ i It is the adjustment coefficient obtained based on data analysis, corresponding to the influence weight of load parameters and environmental parameters respectively. i and u i They represent the real-time load and environmental parameters from differentiated monitoring points respectively.

[0165] The number of monitoring points is set to 3, the load parameter v of each monitoring point is 100, 150 and 200, and the environmental parameter u is 80, 120 and 160. The adjustment coefficient κ is 0.5, 0.3 and 0.4, and the environmental adjustment coefficient λ is 0.2, 0.3 and 0.25. The calculation process is as follows:

[0166] P new =(0.5×100+0.2×80)+(0.3×150+0.3×120)+(0.4×200+0.25×160)=50+16+45+36+80+40=267

[0167] Results new The value is 267, which indicates the optimized total load response parameters calculated by the prediction model based on the adjustment coefficient under given load and environmental parameters.

[0168] See also Figure 6 , the specific steps for obtaining the network stability analysis results are:

[0169] Based on the prediction model with parameter optimization, the data of key area nodes are analyzed, and the key nodes are extracted using data mining technology to obtain a list of key nodes;

[0170] Among them, based on the prediction model of parameter optimization, the data of key regional nodes are analyzed, and the key nodes are extracted using data mining technology. Calculate the key node influence score.

[0171] Where N k Represents the criticality score of the node, P i represents the number of connections of the ith node, L i Represents the load factor of the i-th node.

[0172] Detailed explanation of the formula and the process of formula calculation and derivation:

[0173] The formula evaluates the importance of multiple nodes in the network. The influence score N of each node k is its number of connections P i and load factor L i The number of connections is directly obtained from the network topology data, while the load factor is obtained through network traffic analysis. For example, a node has 10 connections, and the load factor of each connection is set to 0.5. The criticality score of the node is N k The calculation is 10×0.5=5.

[0174] Conduct stability analysis on the key node list, use dynamic system theory to calculate the stability index of each node, and generate node stability analysis data;

[0175] Among them, by analyzing the stability of key nodes in the network, according to the formula Calculate network stability.

[0176] In the formula, S represents network stability, L i represents the load response of node i, P i Represents the number of connections of node i.

[0177] Detailed explanation of the formula and the process of formula calculation and derivation:

[0178] The formula is used to evaluate the overall stability of the network. By averaging the ratio of the load response of each node to the number of connections, a quantitative indicator of network stability is obtained. For example, there are 3 nodes in the network, with load responses of 30, 40, and 50 respectively, and the number of connections is 3, 4, and 5 respectively. The network stability S is calculated as

[0179]

[0180] Combining the node stability analysis data and the load response change information of multiple nodes in the network, the formula is used:

[0181]

[0182] Analyze and identify potential failed nodes and vulnerable connections in the network, and generate network stability analysis results;

[0183] Among them, R f represents the network stability analysis result, L i represents the load response of node i, D i represents the vulnerability index of node i, P i Represents the weight parameter of node i.

[0184] formula:

[0185]

[0186] Detailed explanation of the formula and the process of formula calculation and derivation:

[0187] For example, suppose a network has 3 nodes, the node load responses are 30, 40, 50, the vulnerability index is 1.0, 1.5, 2.0, and the node weights are 3, 4, 5. The calculation process is:

[0188]

[0189] The results illustrate the overall response of the network to load changes, with higher values ​​indicating that the network is more sensitive to load changes at weak connections.

[0190] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A municipal engineering quality monitoring intelligent analysis system, characterized in that: The system comprises: The data receiving module receives and records the real-time load and flow of bridges and roads based on the structural integrity monitoring points and environmental factor monitoring points, analyzes the temperature and humidity in the environment of multiple monitoring points, and generates a real-time monitoring data set by partitioning the collected load and flow data and identifying the differences between multiple monitoring points by region; The phase space reconstruction module is based on the real-time monitoring data set, identifies the fluctuation characteristics in the load response, analyzes the change trend under time delay, reconstructs the load response phase space, and generates a reconstructed phase space data set through comparison and correlation processing between dynamic data; The dynamic parameter adjustment module is based on the reconstructed phase space data set, and by analyzing the current monitoring data of the structural integrity and environmental factors, determines the impact of the current environment on the load, adjusts the load response parameters of the differentiated areas as needed, introduces the differences of the monitoring points in multiple areas, and constructs a prediction model for parameter optimization; The network stability analysis module extracts key area nodes based on the parameter optimized prediction model, performs stability analysis on key nodes in the network, combines the load response changes of multiple nodes, determines the load response changes of vulnerable connections, identifies potential failure nodes, and generates network stability analysis results.

2. The municipal engineering quality monitoring intelligent analysis system according to claim 1 is characterized in that: The steps for obtaining the real-time load and flow are specifically as follows: Receive data from structural integrity monitoring points and environmental factor monitoring points on bridges and roads to generate preliminary load and flow data sets; Performing time synchronization on the preliminary load and flow data sets, unifying the data format, and generating synchronized load and flow data; Based on the synchronous load and flow data, the weighted average value of the data at each monitoring point is calculated to evaluate the real-time load and flow, using the formula: Get real-time load and flow data; Among them, d i represents the load or flow data of the i-th monitoring point, F avg Represents the real-time load and traffic after weighted average.

3. The municipal engineering quality monitoring intelligent analysis system according to claim 2 is characterized in that: The steps for obtaining the real-time monitoring data set are specifically as follows: Based on the synchronous load flow data, analyzing the temperature and humidity in the environments of multiple monitoring points, calculating the statistical characteristics of the environmental data, and obtaining environmental characteristic data; Based on the environmental characteristic data, the environmental difference analysis between regions is carried out using the formula: Calculate and obtain real-time monitoring data set; Among them, x i represents the environmental data of the ith monitoring point, represents the global average environmental data, represents the variance of environmental data, and D represents the results of the analysis of environmental differences among regions.

4. The municipal engineering quality monitoring intelligent analysis system according to claim 3 is characterized in that: The steps for obtaining the reconstructed phase space data set are specifically as follows: Extract load response data from the real-time monitoring data set, determine the frequency and amplitude of multiple load fluctuations by a spectrum analysis method, and obtain fluctuation characteristic data; Based on the fluctuation characteristic data, a dynamic time warping algorithm is used to analyze and compare the fluctuation data at different time points to obtain time delay trend data; Using the time delay trend data, the formula is used: Reconstruct the load response phase space to generate a reconstructed phase space data set; Among them, γ represents the adjustment weight of time change on reconstruction, μ represents the adjustment weight of response amplitude, and δp i , δq i They represent the load response difference and response time difference at consecutive time points respectively, and δt represents the time interval.

5. The municipal engineering quality monitoring intelligent analysis system according to claim 4 is characterized in that: The steps for obtaining the parameter-optimized prediction model are specifically as follows: Extracting load response data from the reconstructed phase space data set, analyzing it based on current structural integrity monitoring data, calculating the real-time impact of environmental factors on the load, and obtaining an environmental impact assessment result; Analyze the environmental impact assessment results by statistical methods, determine the adjustment requirements of load response parameters of multi-region monitoring points, and generate regional response adjustment data; According to the regional response adjustment data, parameter optimization is performed using the formula: Build and generate parameter-optimized prediction models; Among them, κ i Represents the adjustment factor for load parameters, λ i represents the adjustment coefficient for environmental parameters, v i and u i They represent real-time load and environment data from differentiated monitoring points respectively.

6. The municipal engineering quality monitoring intelligent analysis system according to claim 5 is characterized in that: The steps for obtaining the network stability analysis result are specifically as follows: Based on the parameter optimized prediction model, the data of key area nodes are analyzed, key nodes are extracted using data mining technology, and a key node list is obtained; Performing stability analysis on the key node list, calculating the stability index of each node using dynamic system theory, and generating node stability analysis data; Combining the node stability analysis data and the load response change information of multiple nodes in the network, the formula is adopted: Analyze and identify potential failed nodes and vulnerable connections in the network, and generate network stability analysis results; Among them, R f represents the network stability analysis result, L i represents the load response of node i, D i represents the vulnerability index of node i, P i Represents the weight parameter of node i.

Images