Engineering project supervision quality monitoring management system based on big data

Abstract

The invention discloses an engineering project supervision quality monitoring management system based on big data, relates to the technical field of engineering management, and compared with a traditional monitoring system, the system can process mass data from various sensors, satellite remote sensing and unmanned aerial vehicles, and solves the problem of low data processing efficiency. The distributed database and the data processing unit are utilized to realize rapid data storage and processing, and deep data analysis is performed through multiple linear regression and a decision tree model, so that the monitoring accuracy is improved; the system also effectively eliminates an information island phenomenon, data integration and interoperability are enhanced, and a quality evaluation module can accurately judge project quality and perform risk tolerance evaluation Rrld; and the decision support module helps supervisors to make accurate decisions through graphical display and decision suggestions, so that the overall efficiency of the system is improved, and the project quality and safety are guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of engineering management, in particular to an engineering project supervision quality monitoring management system based on big data. BACKGROUND

[0002] The engineering project supervision quality monitoring management system is a comprehensive tool for improving the quality management level of engineering projects, combining various technical means and management methods. It is suitable for various types of engineering projects that require full-process quality monitoring and management, especially in large projects with strict quality requirements and long construction periods, and has obvious application advantages.

[0003] The technical fields involved in this system mainly include information technology, Internet of Things technology, artificial intelligence, big data analysis and cloud computing. It realizes the monitoring and management of the whole process of engineering projects through these technical means, helps supervisors to discover and solve quality problems in time, and improves the stability and reliability of engineering quality.

[0004] However, when this system is applied to water conservancy projects, the following technical shortcomings exist:

[0005] 1. Low data processing efficiency: Water conservancy projects involve a variety of data types, such as hydrological data, meteorological data, structural health monitoring data, etc. The processing capacity of existing systems is limited, and it is difficult to quickly and efficiently analyze and process large-scale, multi-type data, especially in the face of sudden situations, the system may not be able to provide effective decision support in time.

[0006] 2. Low system integration, information island phenomenon is obvious: The monitoring of water conservancy projects often involves multiple independent subsystems, such as hydrological monitoring systems, environmental monitoring systems, structural health monitoring systems, etc. These subsystems often lack effective integration, resulting in a serious information island phenomenon, making it difficult to achieve unified management and cross-departmental collaboration of data SUMMARY

[0007] In view of the shortcomings of the prior art, the present application provides an engineering project supervision quality monitoring management system based on big data, which solves the technical shortcomings of low data processing efficiency and low system integration in the background art.

[0008] To achieve the above purpose, the present application realizes the following technical scheme: an engineering project supervision quality monitoring management system based on big data, comprising a data acquisition module, a data storage and processing module, a data analysis module, a quality evaluation module and a decision support module.

[0009] The data acquisition module is used for acquiring multi-source data in water conservancy projects, and collecting real-time data through Internet of Things sensors, satellite remote sensing and unmanned aerial vehicle equipment, and uploading the collected multi-source data to the data storage and processing module through a wireless communication network.

[0010] The data storage and processing module is used for receiving and storing multi-source data from the data acquisition module, and storing the multi-source data by using a distributed database system.

[0011] The data analysis module is used for analyzing the stored multi-source data, and performing deep analysis on the multi-source data by establishing a multiple linear regression model and a decision tree model, including extracting relevant index data, and calculating an engineering progress index Cgjs, a construction quality index Sgzls and an environmental safety index Hjaqs according to the extracted index data.

[0012] The quality evaluation module is used for calculating a comprehensive quality coefficient Zzqs according to the engineering progress index Cgjs, the construction quality index Sgzls and the environmental safety index Hjaq, and preliminarily judging the engineering quality by comparing the comprehensive quality coefficient Zzqs with a preset standard value, and then further calculating and evaluating a risk evaluation coefficient Fxps of the water conservancy project according to the judgment result.

[0013] The decision support module is used for calculating and evaluating a risk tolerance Rrld of the project according to the evaluation result of the quality evaluation module, in combination with historical data and real-time monitoring data in the multi-source data, and displaying the evaluation content of the risk tolerance Rrld, a decision suggestion report and corresponding early warning measures to a supervisor through a graphical interface.

[0014] Preferably, the data acquisition module includes a data sensing unit, a data acquisition unit and a data transmission unit.

[0015] The data sensing unit is used for being deployed at each key position of the water conservancy project, and is responsible for real-time monitoring and collecting various types of data in the engineering environment; the data types include environment-related data, structure health monitoring-related data, weather-related data and construction-related data; various types of data are comprehensively covered in the water conservancy project area and are collected in real time through remote sensing equipment and other monitoring devices.

[0016] The data acquisition unit is responsible for monitoring large areas and inaccessible areas by using unmanned aerial vehicle inspection, satellite remote sensing and installed Internet of Things sensors; the unmanned aerial vehicle is equipped with a high-precision camera and a sensor, and is used for acquiring images and environmental data of the engineering site from the air; the satellite remote sensing is used for acquiring macro geographic and environmental change information.

[0017] The data transmission unit is configured to transmit the data collected by the data sensing unit and the data acquisition unit through a wireless communication network; during the data transmission, the data transmission unit is further configured to encrypt the transmitted data and perform integrity check on the transmitted data.

[0018] Preferably, the data storage and processing module comprises a data receiving unit and a data management unit.

[0019] The data receiving unit is configured to receive the multi-source data from the data acquisition module, process multiple data formats, support access of high-concurrent data flow, and perform preliminary check on the received multi-source data, and then pass the checked multi-source data to the data management unit for further processing.

[0020] The data management unit is configured to store and manage the multi-source data passed by the data receiving unit in a distributed manner, store the multi-source data on multiple nodes according to a certain strategy by using a distributed database system, and support quick retrieval and query of the multi-source data.

[0021] Preferably, the data analysis module comprises a data processing unit and an index calculation unit.

[0022] The data processing unit comprises a multiple linear regression subunit and a decision tree analysis subunit.

[0023] The multiple linear regression subunit is configured to perform regression analysis on the multi-source data of the water conservancy project; by constructing a multiple linear regression model, taking the input variables of each stage of the project as independent variables, and taking the actual progress or quality result as a dependent variable, the influence degree of each independent variable on the dependent variable is analyzed; wherein the input variables of each stage of the project include material strength, engineering quantity and weather condition; the specific model expression is as follows:

[0024] Y = β0+ β1X1+ β2X2+ … + βnXn+ ∈;

[0025] In the formula, Y represents the predicted value of the model, including the progress of the project; X1, X2, …, Xn are independent variables, representing the multi-source data including material strength, engineering quantity and weather condition; β0 is the intercept term, β1, β2, …, βn are the regression coefficients of each variable, and ∈ is the error term.

[0026] Preferably, the decision tree analysis subunit is used for classification and decision analysis of multi-source data, wherein the multi-source data includes planned engineering quantity Jhl, actual engineering quantity Sjl, quality standard value Zbz, material strength Cqd, construction precision Sjd, safety score Aqz of current environmental condition, and environmental condition preset safety threshold Yaqz; by constructing a decision tree model, taking the characteristics of the multi-source data as nodes, and by recursive division, the multi-source data is divided into different categories or states; wherein the division of each node is based on the principle of information gain to establish the optimal decision path.

[0027] Preferably, the index calculation unit includes a progress index calculation subunit, a quality index calculation subunit, and a safety index calculation subunit.

[0028] The progress index calculation subunit calculates the engineering progress index Cgjs by extracting the planned engineering quantity Jhl and the actual engineering quantity Sjl in the decision tree analysis subunit, and the specific formula is as follows:

[0029]

[0030] The quality index calculation subunit extracts the quality standard value Zbz, the material strength Cqd, and the construction precision Sjd from the multi-source data and performs dimensionless processing, and then calculates the construction quality index Sgzls by the following formula:

[0031]

[0032] The safety index calculation subunit extracts the safety score Aqz of the current environmental condition and the environmental condition preset safety threshold Yaqz based on the analysis of the relevant data of the environment in the multi-source data by the decision tree model, and calculates the environmental safety index Hjaqs, and the specific formula is as follows:

[0033]

[0034] Finally, the engineering progress index Cgjs, the construction quality index Sgzls, and the environmental safety index Hjaqs are transmitted to the quality evaluation module.

[0035] Preferably, the quality evaluation module includes a comprehensive quality calculation unit, a quality comparison unit, and a risk assessment unit.

[0036] The comprehensive quality calculation unit calculates the comprehensive quality coefficient Zzqs by the following formula:

[0037]

[0038] The quality comparison unit compares and evaluates the comprehensive quality coefficient Zzqs using a preset first comprehensive quality threshold Q1 and a second comprehensive quality threshold Q2, wherein the first comprehensive quality threshold Q1 > the second comprehensive quality threshold Q2. The specific evaluation content is as follows:

[0039] If the comprehensive quality coefficient Zzqs ≥ the first comprehensive quality threshold Q1, it means that the project quality is qualified and meets or exceeds the standard threshold. At this time, the current standard and quality control measures will continue to be maintained and the first judgment result will be generated.

[0040] If the first comprehensive quality threshold Q1 > the comprehensive quality coefficient Zzqs ≥ the second comprehensive quality threshold Q2, it means that the project quality is qualified, but only meets the minimum qualified standard threshold. At this time, further quality improvement and inspection are carried out, including calculating and evaluating the risk assessment coefficient Fxps, identifying potential problems and formulating improvement plans, and generating a second judgment result.

[0041] If the second comprehensive quality threshold Q2 > the comprehensive quality coefficient Zzqs, it indicates that the project quality is unqualified. At this time, emergency measures should be taken to solve the quality problem, and a detailed investigation and analysis should be carried out, including re-evaluating and improving the project design, construction and quality management processes, and generating a third judgment result.

[0042] Preferably, the risk assessment unit is used to further calculate the risk assessment coefficient Fxps based on the second judgment result; after extracting the rainfall Gjy, real-time water level Ssw, soil moisture Trs, equipment maintenance frequency Swx, and accident frequency Ssc from multi-source data within a fixed period and performing dimensionless processing, the risk assessment coefficient Fxps is calculated using the following formula:

[0043]

[0044] In the formula, w1, w2, w3, w4 and w5 represent the weight coefficients of rainfall Gjy, real-time water level Ssw, soil moisture Trs, number of equipment maintenance Swx and number of accidents Scs within a fixed period, respectively, and 0 < w1 ≤ 1, 0 < w2 ≤ 1, 0 < w3 ≤ 1, 0 < w4 ≤ 1, 0 < w5 ≤ 1, w1 + w2 + w3 + w4 + w5 = 1, and wi represents the weight coefficient of the i-th parameter;

[0045] The risk assessment coefficient Fxps is evaluated by setting a first risk threshold E1 and a second risk threshold E2, where the first risk threshold E1 > the second risk threshold E2. The specific evaluation content is as follows:

[0046] If the risk assessment coefficient Fxps is greater than the first risk threshold E1, a first risk result is generated, indicating that the water conservancy project has serious potential problems and hidden dangers, and countermeasures are taken, including adjusting the monitoring frequency, implementing a comprehensive maintenance plan, conducting a site evaluation, and starting an emergency response program;

[0047] If the first risk threshold E1 is greater than or equal to the risk assessment coefficient Fxps and less than the second risk threshold E2, a second risk result is generated, further monitoring and checking the water conservancy project

[0048] If the second risk threshold E2 is greater than or equal to the risk assessment coefficient Fxps, a third risk result is generated, and regular monitoring and maintenance work continues, and the current project operation state is maintained.

[0049] Preferably, the decision support module includes a risk tolerance calculation unit and a graphical display unit;

[0050] The risk tolerance calculation unit is used to correlate the environmental safety index Hjaqs, the comprehensive quality coefficient Zzqs, and the risk assessment coefficient Fxps, and after dimensionless processing, the risk tolerance Rrld is obtained, specifically in the following manner:

[0051]

[0052] In the formula, Hjaqs represents the environmental safety index, V represents the second correction constant, F1 and F2 are weight coefficients, where 0 < F1 ≤ 1, 0 < F2 ≤ 1, and F1 + F2 = 1.

[0053] Preferably, the graphical display unit includes a data visualization subunit and a decision suggestion generation subunit;

[0054] The data visualization subunit is used to display the calculated risk tolerance Rrld to the supervisor through a graphical interface;

[0055] The decision suggestion generation subunit compares the risk tolerance Rrld with the first risk tolerance threshold R1 and the second risk tolerance threshold R2 to generate decision suggestions and warning measures, specifically as follows:

[0056] If the risk tolerance Rrld is greater than the first risk tolerance threshold R1, the problem causing serious risk is prioritized and the monitoring frequency of risk factors is adjusted, and a red warning is issued;

[0057] If the first risk tolerance threshold R1 is greater than or equal to the risk tolerance Rrld and less than the second risk tolerance threshold R2, the checking frequency is adjusted, the risk points are monitored, and preventive measures are taken, and a yellow warning is issued;

[0058] If the second risk tolerance threshold R2 is greater than or equal to the risk tolerance Rrld, the normal operation process is continued, and no additional measures are taken immediately, and no pre-warning is performed.

[0059] The application provides an engineering project supervision quality monitoring management system based on big data.

[0060] (1) The engineering project supervision quality monitoring management system based on big data significantly improves the data processing capability and system integration by closely integrating the data acquisition module, the data storage and processing module, the data analysis module, the quality evaluation module and the decision support module; compared with the traditional monitoring system, the system can process massive data from various sensors and devices, including Internet of Things sensors, satellite remote sensing and unmanned aerial vehicles, solving the problem of insufficient data processing capability in the past; through the distributed database system and the efficient data management unit, the system can realize fast storage and processing of multi-source data, providing a solid data foundation for subsequent analysis and decision-making; in addition, the integrated multiple linear regression model and decision tree model in the system can deeply analyze the real-time monitoring data of the project, extract key indicators, and perform comprehensive quality evaluation, significantly improving the accuracy and comprehensiveness of monitoring.

[0061] (2) The engineering project supervision quality monitoring management system based on big data effectively solves the information island phenomenon in the traditional engineering project monitoring system, enhances the integration and data interoperability of the system; by seamlessly connecting the data acquisition, storage, processing, analysis and decision support modules, the system realizes comprehensive sharing and collaborative processing of data; the quality evaluation module compares the comprehensive quality coefficient Zzqs with the preset comprehensive quality threshold to accurately judge the engineering quality and calculate the risk assessment coefficient Fxps for further risk tolerance Rrld evaluation; the decision support module uses graphical display and decision suggestion generation subunit to intuitively present the evaluation results to the supervisors, helping them make accurate decisions; such integrated design not only reduces information islands, but also improves the overall efficiency of the system, enabling supervisors to quickly respond to potential risks and ensure the quality and safety of the engineering project. BRIEF DESCRIPTION OF DRAWINGS

[0062] Figure 1 The figure is a schematic diagram of the framework structure of the engineering project supervision quality monitoring management system based on big data. DETAILED DESCRIPTION

[0063] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of the present application.

[0064] Embodiment 1

[0065] Please refer to Figure 1 A big data-based engineering project supervision quality monitoring management system, comprising a data acquisition module, a data storage and processing module, a data analysis module, a quality evaluation module and a decision support module.

[0066] The data acquisition module is configured to acquire multi-source data in a water conservancy project, and acquire real-time data through Internet of Things sensors, satellite remote sensing and unmanned aerial vehicle equipment, and upload the acquired multi-source data to the data storage and processing module through a wireless communication network.

[0067] The data storage and processing module is configured to receive and store the multi-source data from the data acquisition module, and store the multi-source data using a distributed database system.

[0068] The data analysis module is configured to analyze the stored multi-source data, and perform in-depth analysis on the multi-source data by establishing a multiple linear regression model and a decision tree model, including extracting relevant index data, and calculating an engineering progress index Cgjs, a construction quality index Sgzls and an environmental safety index Hjaqs according to the extracted index data.

[0069] The quality evaluation module is configured to calculate a comprehensive quality coefficient Zzqs according to the engineering progress index Cgjs, the construction quality index Sgzls and the environmental safety index Hjaq, and preliminarily judge the engineering quality by comparing the comprehensive quality coefficient Zzqs with a preset standard value, and then further calculate and evaluate a risk evaluation coefficient Fxps of the water conservancy project according to the judgment result.

[0070] The decision support module is configured to calculate and evaluate a risk tolerance Rrld of the project according to the evaluation result of the quality evaluation module, in combination with historical data and real-time monitoring data in the multi-source data, and display the evaluation content of the risk tolerance Rrld, a decision suggestion report and corresponding early warning measures to a supervisor through a graphical interface.

[0071] In this embodiment, through the comprehensive integration of data collection, storage, processing, analysis, evaluation and decision support modules, efficient management and application of multi-source data are realized; the system can collect data from Internet of Things sensors, satellite remote sensing and unmanned aerial vehicles in real time, and store them efficiently through a distributed database system; the data analysis module uses multiple linear regression and decision tree models to deeply mine real-time monitoring data, accurately calculates engineering progress, construction quality and environmental safety index, thereby generating comprehensive quality coefficient Zzqs and risk assessment coefficient Fxps; the quality evaluation module compares the comprehensive quality coefficient Zzqs with the standard value to judge the engineering quality, and further evaluates the risk tolerance Rrld; the decision support module displays the risk tolerance Rrld and decision suggestions to the supervisors through a graphical interface, improving the accuracy and response speed of the decision, thereby effectively protecting the engineering quality and safety, reducing the information island phenomenon, and enhancing the overall monitoring and management capability of the system.

[0072] Embodiment 2

[0073] Please refer to Figure 1 The data collection module includes a data sensing unit, a data acquisition unit and a data transmission unit;

[0074] The data sensing unit is arranged at each key position of the water conservancy project, responsible for real-time monitoring and collecting various types of data in the engineering environment; the data types include environment-related data, structure health monitoring-related data, weather-related data and construction-related data; through remote sensing equipment and other monitoring devices, the water conservancy project area is comprehensively covered and various types of data are collected in real time;

[0075] The data acquisition unit is responsible for monitoring large areas and inaccessible areas through unmanned aerial vehicle inspection, satellite remote sensing and installation of Internet of Things sensors; the unmanned aerial vehicle is equipped with high-precision cameras and sensors to obtain images and environmental data of the engineering site from the air, and satellite remote sensing is used to obtain macro geographic and environmental change information;

[0076] The data transmission unit is used to transmit the data collected by the data sensing unit and the data acquisition unit through a wireless communication network; during data transmission, the data transmission unit is also responsible for encrypting and checking the integrity of the transmitted data.

[0077] In this embodiment, through the close cooperation of the data sensing unit, data acquisition unit, and data transmission unit, comprehensive and real-time monitoring of the water conservancy project environment is achieved. The data sensing unit is deployed in key locations and can collect environmental, structural health, meteorological, and construction data in real time, thereby ensuring the comprehensiveness and timeliness of the data. The data acquisition unit conducts detailed monitoring of large and inaccessible areas through drone inspections, satellite remote sensing, and IoT sensors, ensuring extensive coverage and diversity of monitoring data. The data transmission unit transmits the collected data to the central system via a wireless network and performs encryption and integrity checks, enhancing the security and reliability of data transmission. Overall, the design of the data acquisition module not only improves the comprehensiveness and accuracy of data acquisition but also ensures the security and integrity of data transmission, ensuring the data quality and stability of the engineering monitoring system.

[0078] Example 3

[0079] Please see Figure 1 Preferably, the data storage and processing module includes a data receiving unit and a data management unit;

[0080] The data receiving unit is responsible for receiving multi-source data from the data acquisition module, processing multiple data formats, and supporting the access of high-concurrency data streams; it also performs preliminary verification on the received multi-source data, and then transmits the verified multi-source data to the data management unit for further processing.

[0081] The data management unit is responsible for the distributed storage and management of multi-source data transmitted by the data receiving unit. By utilizing a distributed database system, the multi-source data is distributed and stored on multiple nodes according to a certain strategy, and the rapid retrieval and query of multi-source data is supported.

[0082] In this embodiment, the data storage and processing module, through the effective cooperation of the data receiving unit and the data management unit, achieves efficient management and processing of multi-source data. The data receiving unit not only supports the processing of various data formats but also can handle the access of high-concurrency data streams, ensuring the flexibility and efficiency of data reception. After preliminary verification, the data is transmitted to the data management unit, laying an accurate foundation for subsequent processing. The data management unit utilizes a distributed database system for distributed storage and management of data. This design optimizes the data storage strategy and improves the data access speed and retrieval efficiency. Overall, this module significantly enhances the system's ability to process massive amounts of data, ensuring efficient data storage and timely retrieval, and meeting the high requirements of engineering project monitoring for data processing.

[0083] Example 4

[0084] Please see Figure 1The data analysis module includes a data processing unit and an indicator calculation unit;

[0085] The data processing unit includes a multiple linear regression subunit and a decision tree analysis subunit;

[0086] The multiple linear regression subunit is used to perform regression analysis on multi-source data of water conservancy projects. By constructing a multiple linear regression model, the input variables at each stage of the project are used as independent variables, and the actual progress or quality results are used as dependent variables to analyze the influence of each independent variable on the dependent variable. The input variables at each stage of the project include material strength, project quantity, and weather conditions. The specific model expression is as follows:

[0087] Y=β0+β1X1+β2X2+…+βnXn+∈;

[0088] In the formula, Y represents the predicted value of the model, including the project progress; X1, X2, ..., Xn are independent variables, representing multi-source data including material strength, project quantity and weather conditions; β0 is the intercept term, β1, β2, ..., βn are the regression coefficients of the independent variables, and ∈ is the error term.

[0089] Preferably, the decision tree analysis subunit is used to classify and analyze multi-source data, wherein the multi-source data includes planned engineering quantity Jhl, actual engineering quantity Sjl, quality standard value Zbz, material strength Cqd, construction accuracy Sjd, safety score of current environmental conditions Aqz, and preset safety threshold Yaqz of environmental conditions; by constructing a decision tree model, using the features of the multi-source data as nodes, the multi-source data is divided into different categories or states through recursive partitioning; wherein the partitioning of each node is based on the principle of information gain to establish the optimal decision path.

[0090] Preferably, the index calculation unit includes a schedule index calculation subunit, a quality index calculation subunit, and a safety index calculation subunit:

[0091] The progress index calculation subunit calculates the progress index Cgjs by extracting the planned quantity of work Jhl and the actual quantity of work Sjl from the decision tree analysis subunit. The specific formula is as follows:

[0092]

[0093] The quality index calculation subunit extracts the quality standard value Zbz, material strength Cqd, and construction accuracy Sjd from multi-source data, performs dimensionless processing, and then calculates the construction quality index Sgzls using the following formula:

[0094]

[0095] The safety index calculation subunit extracts the safety score Aqz of the current environmental condition and the preset safety threshold Yaqz of the environmental condition based on the analysis of the relevant data of the environment in the multi-source data by the decision tree model, and calculates and obtains the environmental safety index Hjaqs, and the specific formula is:

[0096]

[0097] Finally, the engineering progress index Cgjs, the construction quality index Sgzls and the environmental safety index Hjaqs are transmitted to the quality evaluation module.

[0098] In this embodiment, the data analysis module realizes deep analysis and accurate evaluation of the water conservancy engineering data through the cooperative work of the data processing unit and the index calculation unit; the multiple linear regression subunit and the decision tree analysis subunit in the data processing unit are respectively responsible for regression analysis and classification decision, thereby revealing the influence of different variables on the engineering progress and quality, as well as the category and state of the engineering data; this analysis method not only can identify the key role of each factor, but also can optimize the decision-making process; the progress index calculation subunit, the quality index calculation subunit and the safety index calculation subunit calculate the engineering progress index Cgjs, the construction quality index Sgzls and the environmental safety index Hjaq respectively, and provide multi-dimensional evaluation; this comprehensive index calculation not only accurately reflects the actual situation of the project, but also provides detailed data support for subsequent quality evaluation; the comprehensiveness and accuracy of parameter collection make the analysis results more valuable, and enhance the monitoring ability of the system to various aspects of the project, thereby ensuring the efficient management and safe operation of the project.

[0099] Embodiment 5

[0100] Please refer to Figure 1 , the quality evaluation module includes a comprehensive quality calculation unit, a quality comparison unit and a risk assessment unit:

[0101] The comprehensive quality calculation unit calculates and obtains the comprehensive quality coefficient Zzqs by the following formula:

[0102]

[0103] The quality comparison unit compares and evaluates the comprehensive quality coefficient Zzqs by presetting the first comprehensive quality threshold Q1 and the second comprehensive quality threshold Q2, wherein the first comprehensive quality threshold Q1 > the second comprehensive quality threshold Q2, and the specific evaluation content is as follows:

[0104] If the comprehensive quality coefficient Zzqs is greater than or equal to the first comprehensive quality threshold Q1, it means that the engineering quality is qualified, meets or exceeds the standard threshold, at this time the current standard and quality control measures are maintained and the first judgment result is generated;

[0105] If the first comprehensive quality threshold Q1 > the comprehensive quality coefficient Zzqs ≥ the second comprehensive quality threshold Q2, it indicates that the engineering quality is qualified, but only meets the minimum qualified standard threshold, at this time further quality improvement and inspection are carried out, including calculating the evaluation risk assessment coefficient Fxps, identifying potential problems and making improvement plans, and generating a second judgment result;

[0106] If the second comprehensive quality threshold Q2 > the comprehensive quality coefficient Zzqs, it indicates that the engineering quality is unqualified, at this time emergency measures are taken to solve the quality problem, and detailed investigation and analysis are carried out, including re-evaluation and improvement of engineering design, construction and quality management process, and a third judgment result is generated.

[0107] Preferably, the risk assessment unit is used to further calculate the evaluation risk assessment coefficient Fxps according to the second judgment result; by extracting the rainfall Gjy, real-time water level Ssw, soil moisture Trs, equipment maintenance frequency Swx and accident frequency Scs in a fixed period from multi-source data and carrying out dimensionless processing, the risk assessment coefficient Fxps is calculated by the following formula:

[0108]

[0109] In the formula, w1, w2, w3, w4 and w5 respectively represent the weight coefficients of the rainfall Gjy, real-time water level Ssw, soil moisture Trs, equipment maintenance frequency Swx and accident frequency Scs in a fixed period, and 0 < w1 ≤ 1, 0 < w2 ≤ 1, 0 < w3 ≤ 1, 0 < w4 ≤ 1, 0 < w5 ≤ 1, w1 + w2 + w3 + w4 + w5 = 1, wi represents the weight coefficient of the i-th parameter;

[0110] The risk assessment coefficient Fxps is evaluated by presetting the first risk threshold E1 and the second risk threshold E2, and the first risk threshold E1 > the second risk threshold E2, and the specific evaluation content is:

[0111] If the risk assessment coefficient Fxps > the first risk threshold E1, a first risk result is generated at this time, indicating that there are serious potential problems and hidden dangers in the water conservancy project, at this time countermeasures are taken, including adjusting the monitoring frequency, implementing a comprehensive maintenance plan, conducting on-site evaluation, and starting an emergency response scheme;

[0112] If the first risk threshold E1 ≥ the risk assessment coefficient Fxps > the second risk threshold E2, a second risk result is generated at this time, further monitoring and checking the water conservancy project

[0113] If the second risk threshold E2 ≥ the risk assessment coefficient Fxps, a third risk result is generated at this time, and the current engineering operation state is maintained, and the routine monitoring and maintenance work is continued.

[0114] In this embodiment, the quality evaluation module realizes comprehensive evaluation of engineering quality and risk management through the cooperation of the comprehensive quality calculation unit, the quality comparison unit and the risk assessment unit; the comprehensive quality calculation unit accurately calculates the comprehensive quality coefficient Zzqs, and through comparison with the preset quality thresholds Q1 and Q2, the qualified state of engineering quality and the corresponding measures can be clearly judged; if the quality is not up to standard, the system will generate the corresponding judgment result and propose improvement suggestions; the risk assessment unit calculates the risk assessment coefficient Fxps through analysis of multi-source data such as rainfall, water level, soil humidity, equipment maintenance frequency and accident frequency, and carries out risk level assessment according to the set risk thresholds E1 and E2; this method not only can accurately identify potential risks, but also can take corresponding measures in time to effectively reduce the occurrence of engineering accidents and hidden dangers; the comprehensiveness of parameter collection ensures the accuracy of risk assessment, so that the system can accurately monitor the engineering quality and safety, thereby improving the scientificity and effectiveness of engineering management.

[0115] Embodiment 6

[0116] Please refer to Figure 1 , the decision support module includes a risk tolerance calculation unit and a graphical display unit;

[0117] The risk tolerance calculation unit is used to obtain the risk tolerance Rrld by associating the environmental safety index Hjaqs, the comprehensive quality coefficient Zzqs and the risk assessment coefficient Fxps, and after dimensionless processing, and specifically in the following way:

[0118]

[0119] In the formula, Hjaqs represents the environmental safety index, V represents the second correction constant, F1 and F2 are weight coefficients, wherein 0

[0120] Preferably, the graphical display unit includes a data visualization subunit and a decision suggestion generation subunit;

[0121] The data visualization subunit is used to display the calculated risk tolerance Rrld to the supervisor through a graphical interface;

[0122] The decision suggestion generation subunit compares the first risk tolerance threshold R1 and the second risk tolerance threshold R2 with the risk tolerance Rrld to generate decision suggestions and warning measures, specifically:

[0123] If the risk tolerance Rrld is greater than the first risk tolerance threshold R1, the problem causing serious risk is preferentially processed, the monitoring frequency of the risk factors is adjusted, and a red early warning is issued.

[0124] If the first risk tolerance threshold R1 is greater than or equal to the risk tolerance Rrld and less than the second risk tolerance threshold R2, the monitoring frequency is adjusted, the risk points are monitored, and preventive measures are taken, and a yellow early warning is issued.

[0125] If the second risk tolerance threshold R2 is greater than or equal to the risk tolerance Rrld, the normal operation process is continued, no additional measures are taken immediately, and no early warning is performed.

[0126] In the embodiment, the decision support module provides efficient and intuitive risk management and decision support for the engineering project through the risk tolerance calculation unit and the graphical display unit. The risk tolerance calculation unit accurately calculates the risk tolerance Rrld by combining the environmental safety index Hjaqs, the comprehensive quality coefficient Zzqs and the risk assessment coefficient Fxps and through dimensionless processing, so as to scientifically support the risk management decision with data basis. The graphical display unit presents the result to the supervisors through a visual interface, so that the complex data and risk assessment results are clear at a glance. By comparing the risk tolerance Rrld with the preset thresholds R1 and R2, the system can generate corresponding decision suggestions and early warning measures, so as to flexibly cope with different risk levels, timely adjust the monitoring frequency and take appropriate early warning measures, and ensure the safety and quality of the engineering. The modular design improves the scientificity and timeliness of the decision, so that the engineering project can quickly take effective measures when facing potential risks, thereby significantly improving the overall efficiency of the engineering management.

[0127] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A big data-based engineering project supervision quality monitoring management system, characterized in that: The system comprises a data acquisition module, a data storage and processing module, a data analysis module, a quality evaluation module and a decision support module. The data acquisition module is used for collecting multi-source data in water conservancy projects, and collecting real-time data through Internet of Things sensors, satellite remote sensing and unmanned aerial vehicle equipment, and uploading the collected multi-source data to the data storage and processing module through a wireless communication network. The data storage and processing module is used for receiving and storing multi-source data from the data acquisition module, and storing the multi-source data by using a distributed database system. The data analysis module is used for analyzing the stored multi-source data, and performing deep analysis on the multi-source data by establishing a multiple linear regression model and a decision tree model, including extracting relevant index data, and calculating an engineering progress index Cgjs, a construction quality index Sgzls and an environmental safety index Hjaqs according to the extracted index data. The quality evaluation module is used for calculating a comprehensive quality coefficient Zzqs according to the engineering progress index Cgjs, the construction quality index Sgzls and the environmental safety index Hjaqs, and preliminarily judging the engineering quality by comparing the comprehensive quality coefficient Zzqs with a preset standard value, and then further calculating a risk evaluation coefficient Fxps of the water conservancy project according to the judgment result and evaluating the risk evaluation coefficient Fxps. The decision support module is used for calculating a risk tolerance Rrld of the project according to the evaluation result of the quality evaluation module and combining historical data and real-time monitoring data in the multi-source data, and evaluating the risk tolerance Rrld. The evaluation content of the risk tolerance Rrld and a decision suggestion report and corresponding early warning measures are displayed to a supervisor through a graphical interface.

2. The big data-based engineering project supervision quality monitoring and management system according to claim 1, characterized in that: The data acquisition module comprises a data sensing unit, a data acquisition unit and a data transmission unit. The data sensing unit is arranged at each key position of the water conservancy project, and is responsible for real-time monitoring and collecting various types of data in the engineering environment; the data types include environment-related data, structure health monitoring-related data, weather-related data and construction-related data. Various types of data are comprehensively covered in the water conservancy project area and are collected in real time through remote sensing equipment and other monitoring devices. The data acquisition unit is responsible for monitoring large areas and inaccessible areas through unmanned aerial vehicle inspection, satellite remote sensing and installation of Internet of Things sensors; the unmanned aerial vehicle is equipped with a high-precision camera and a sensor, and is used for obtaining images and environmental data of the engineering site from the air; satellite remote sensing is used for obtaining macro geographic and environmental change information. The data transmission unit is used for transmitting the data collected by the data sensing unit and the data acquisition unit through a wireless communication network. During data transmission, the data transmission unit is also responsible for encrypting and checking the integrity of the transmitted data.

3. The big data based engineering project supervision quality monitoring management system according to claim 1, characterized in that: The data storage and processing module comprises a data receiving unit and a data management unit. The data receiving unit is responsible for receiving multi-source data from the data acquisition module, processing various data formats and supporting access of high-concurrency data streams; and performing preliminary verification on the received multi-source data, and then passing the verified multi-source data to the data management unit for further processing. The data management unit is responsible for distributed storage and management of multi-source data transmitted by the data receiving unit, and the multi-source data is stored on multiple nodes according to a certain strategy by using a distributed database system, and fast retrieval and query of the multi-source data are supported.

4. The big data-based engineering project supervision quality monitoring and management system according to claim 1, characterized in that: The data analysis module comprises a data processing unit and an index calculation unit; The data processing unit comprises a multiple linear regression subunit and a decision tree analysis subunit; The multiple linear regression subunit is used for regression analysis of the multi-source data of the water conservancy project; a multiple linear regression model is constructed, the input variables of each stage of the project are used as independent variables, and the actual progress or quality result is used as a dependent variable, so as to analyze the influence degree of each variable on the dependent variable; wherein the input variables of each stage of the project include material strength, engineering quantity and weather condition; and the specific model expression is as follows: Y = β0 + β1X1 + β2X2 + … + βnXn + ∈; In the formula, Y represents the predicted value of the model, including the engineering progress; X1, X2, …, Xn are independent variables, representing multi-source data including material strength, engineering quantity and weather condition; β0 is an intercept term, β1, β2, …, βn are regression coefficients of each variable, and ∈ is an error term.

5. The big data-based engineering project supervision quality monitoring and management system according to claim 4, characterized in that: The decision tree analysis subunit is used for classification and decision analysis of the multi-source data, wherein the multi-source data includes planned engineering quantity Jhl, actual engineering quantity Sjl, quality standard value Zbz, material strength Cqd, construction accuracy Sjd, safety score Aqz of the current environmental condition and environmental condition preset safety threshold Yaqz; a decision tree model is constructed, the characteristics of the multi-source data are used as nodes, and the multi-source data is divided into different categories or states by recursive division; wherein the division of each node is based on the principle of information gain, and the optimal decision path is established.

6. The big data-based engineering project supervision quality monitoring and management system according to claim 5, characterized in that: The index calculation unit comprises a progress index calculation subunit, a quality index calculation subunit and a safety index calculation subunit: The progress index calculation subunit calculates the engineering progress index Cgjs by extracting the planned engineering quantity Jhl and the actual engineering quantity Sjl in the decision tree analysis subunit, and the specific formula is as follows: The quality index calculation subunit extracts the quality standard value Zbz, the material strength Cqd and the construction accuracy Sjd from the multi-source data, performs dimensionless processing, and calculates the construction quality index Sgzls by the following formula: The safety index calculation subunit extracts the safety score Aqz of the current environmental condition and the environmental condition preset safety threshold Yaqz based on the analysis of the related data of the environment in the multi-source data by the decision tree model, and calculates the environmental safety index Hjaqs, and the specific formula is as follows: Finally, the engineering progress index Cgjs, the construction quality index Sgzls and the environmental safety index Hjaqs are transmitted to the quality evaluation module.

7. The big data based engineering project supervision quality monitoring management system according to claim 1, characterized in that: The quality evaluation module comprises a comprehensive quality calculation unit, a quality comparison unit and a risk assessment unit: The comprehensive quality calculation unit calculates the comprehensive quality coefficient Zzqs by the following formula: The quality comparison unit compares and evaluates the comprehensive quality coefficient Zzqs by presetting a first comprehensive quality threshold Q1 and a second comprehensive quality threshold Q2, where the first comprehensive quality threshold Q1 > the second comprehensive quality threshold Q2, and the specific evaluation content is as follows: If the comprehensive quality coefficient Zzqs is greater than or equal to the first comprehensive quality threshold Q1, it indicates that the engineering quality is qualified and meets or exceeds the standard threshold, at which time the current standard and quality control measures are maintained and a first judgment result is generated; If the first comprehensive quality threshold Q1 > the comprehensive quality coefficient Zzqs > the second comprehensive quality threshold Q2, it indicates that the engineering quality is qualified, but only meets the minimum qualified standard threshold, at which time further quality improvement and inspection are carried out, including calculating and evaluating the risk evaluation coefficient Fxps, identifying potential problems and developing an improvement plan, while generating a second judgment result; If the second comprehensive quality threshold Q2 > the comprehensive quality coefficient Zzqs, it indicates that the engineering quality is unqualified, at which time emergency measures are taken to solve the quality problem, and detailed investigation and analysis are carried out, including re-evaluating and improving the engineering design, construction and quality management process, while generating a third judgment result.

8. The big data based engineering project supervision quality monitoring management system according to claim 7, characterized in that: The risk evaluation unit is used to further calculate and evaluate the risk evaluation coefficient Fxps according to the second judgment result; by extracting the rainfall Gjy, real-time water level Ssw, soil moisture Trs, equipment maintenance frequency Swx and accident frequency Scs in a fixed period from multi-source data and performing dimensionless processing, the risk evaluation coefficient Fxps is calculated by the following formula: In the formula, w1, w2, w3, w4 and w5 represent the weight coefficients of the rainfall Gjy, real-time water level Ssw, soil moisture Trs, equipment maintenance frequency Swx and accident frequency Scs in a fixed period, respectively, and 0 < w1 ≤ 1, 0 < w2 ≤ 1, 0 < w3 ≤ 1, 0 < w4 ≤ 1, 0 < w5 ≤ 1, w1 + w2 + w3 + w4 + w5 = 1, wi represents the weight coefficient of the i-th parameter; The risk evaluation coefficient Fxps is evaluated by presetting a first risk threshold E1 and a second risk threshold E2, and the first risk threshold E1 > the second risk threshold E2, and the specific evaluation content is as follows: If the risk evaluation coefficient Fxps > the first risk threshold E1, a first risk result is generated, indicating that there are serious potential problems and hidden dangers in the water conservancy project, at which time countermeasures are taken, including adjusting the monitoring frequency, implementing a comprehensive maintenance plan, conducting on-site evaluation and starting an emergency response scheme; If the first risk threshold E1 ≥ the risk evaluation coefficient Fxps > the second risk threshold E2, a second risk result is generated, further monitoring and checking the water conservancy project If the second risk threshold E2 ≥ the risk evaluation coefficient Fxps, a third risk result is generated, continuing the regular monitoring and maintenance work, and maintaining the current engineering operation state. 9.The big data-based engineering project supervision quality monitoring management system according to claim 1, characterized in that: The decision support module includes a risk tolerance calculation unit and a graphical display unit; The risk tolerance calculation unit is configured to obtain the risk tolerance Rrld by associating the environment safety index Hjaqs, the comprehensive quality coefficient Zzqs and the risk assessment coefficient Fxps, and performing dimensionless processing, and specifically in the following manner: In the formula, Hjaqs represents the environment safety index, V represents a second correction constant, F1 and F2 are weight coefficients, 0 10. The big data based engineering project supervision quality monitoring management system according to claim 9, characterized in that: The graphical display unit comprises a data visualization subunit and a decision suggestion generation subunit. The data visualization subunit is configured to display the calculated risk tolerance Rrld to the supervisor through a graphical interface. The decision suggestion generation subunit compares the risk tolerance Rrld with a preset first risk tolerance threshold R1 and a second risk tolerance threshold R2 to generate a decision suggestion and a warning measure, and specifically in the following manner: If the risk tolerance Rrld is greater than the first risk tolerance threshold R1, a problem causing a serious risk is handled in priority, the monitoring frequency of the risk factors is adjusted, and a red warning is issued; If the first risk tolerance threshold R1 is greater than or equal to the risk tolerance Rrld and the risk tolerance Rrld is greater than the second risk tolerance threshold R2, the inspection frequency is adjusted, the risk points are monitored, and preventive measures are taken, and a yellow warning is issued; If the second risk tolerance threshold R2 is greater than or equal to the risk tolerance Rrld, the normal operation process is continued, no additional measures are taken immediately, and no warning is given.

Images