Civil air defense project remote management system based on multi-dimensional data intelligent analysis

Abstract

The invention discloses a civil air defense project remote management system based on multi-dimensional data intelligent analysis. The system comprises a multi-dimensional data acquisition module, a data transmission module, a data storage and management module, a multi-dimensional data intelligent analysis module, an intelligent decision and remote control module and a user interface and interaction module. Through real-time acquisition and analysis of multi-dimensional data, comprehensive and real-time monitoring of the civil air defense project is realized, the workload and time cost of manual inspection are reduced, and the management efficiency is improved. Potential risks and fault hidden dangers in the civil air defense project can be found in time, early warning information is sent out in advance, a corresponding solution is provided, accidents are effectively avoided, and the safety of the civil air defense project is enhanced. Based on intelligent analysis of multi-dimensional data, scientific and accurate decision support is provided for managers, and the managers are helped to formulate more reasonable and effective management strategies and measures.

Description

Technical Field

[0001] The present invention relates to the technical field of remote management systems for civil air defense projects, and particularly to a remote management system for civil air defense projects based on intelligent analysis of multi-dimensional data. Background Art

[0002] As an important part of the urban defense system, the safe and stable operation of civil air defense projects is of crucial importance. The traditional management methods of civil air defense projects mainly rely on manual inspections and simple monitoring devices, which have problems such as low management efficiency, untimely data processing, and inability to accurately predict potential risks. With the development of information technology, although some regions have introduced information-based management means, most of them only stay at the level of simple data collection and display, failing to fully explore the value behind multi-dimensional data and making it difficult to achieve refined and intelligent management of civil air defense projects.

[0003] Therefore, there is an urgent need for a remote management system for civil air defense projects based on intelligent analysis of multi-dimensional data. Summary of the Invention

[0004] The purpose of the present invention is to provide a remote management system for civil air defense projects based on intelligent analysis of multi-dimensional data to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: A remote management system for civil air defense projects based on intelligent analysis of multi-dimensional data, including a multi-dimensional data acquisition module, a data transmission module, a data storage and management module, a multi-dimensional data intelligent analysis module, an intelligent decision-making and remote control module, and a user interface and interaction module;

[0006] The multi-dimensional data acquisition module includes:

[0007] The environmental data acquisition sub-module is used to collect environmental data such as temperature, humidity, air quality, and harmful gas concentration in the project in real time;

[0008] The equipment status data acquisition sub-module collects the operation status data of various equipment in the civil air defense project through equipment interfaces and sensors;

[0009] The structural safety data acquisition sub-module monitors the structural deformation, stress changes, and crack development of the civil air defense project in real time to obtain data related to structural safety;

[0010] The personnel activity data acquisition sub-module is used to collect data such as the time, location, and number of personnel entering and leaving the civil air defense project, as well as the activity trajectory data of personnel in the project;

[0011] The data transmission module uses a combination of wired and wireless communication methods to transmit the data collected by the multi-dimensional data acquisition module to the remote management center in real time;

[0012] The data storage and management module includes:

[0013] The database construction sub-module builds a multi-dimensional database, including an environmental database, an equipment status database, a structural safety database, and a personnel activity database, and classifies and stores the collected data for management;

[0014] The data backup and recovery sub-module is used to regularly back up the data in the database to prevent data loss;

[0015] The multi-dimensional data intelligent analysis module includes:

[0016] The data preprocessing sub-module performs preprocessing operations such as cleaning, filtering, and normalization on the collected raw data, removing noise and outliers, and improving data quality;

[0017] The feature extraction sub-module uses data mining and machine learning algorithms to extract representative features from the preprocessed data;

[0018] The association analysis sub-module analyzes the association relationships between data in different dimensions, such as the association between environmental data and equipment operation status, the association between personnel activities and structural safety, etc., and mines the potential laws behind the data;

[0019] The model establishment and training sub-module builds various prediction and diagnosis models, such as equipment failure prediction models, structural safety assessment models, environmental quality prediction models, etc., based on historical data and feature extraction results, and uses a large amount of data to train and optimize the models to improve the accuracy and reliability of the models;

[0020] The real-time analysis and early warning sub-module: inputs the real-time collected data into the trained model for analysis, and judges the operation status and potential risks of the civil air defense project in real time; when an abnormal situation is detected, it issues early warning information in a timely manner, such as equipment failure early warning, structural safety hidden danger early warning, environmental quality exceeding standard early warning, etc.;

[0021] The intelligent decision-making and remote control module includes:

[0022] The intelligent decision-making support sub-module provides intelligent decision-making support for managers according to the analysis results of the multi-dimensional data intelligent analysis module. For example, when an equipment failure early warning occurs, the system automatically generates maintenance suggestions and emergency plans; when the environmental quality exceeds the standard, the system provides measures and solutions to improve the environment;

[0023] In the remote control sub-module, managers can remotely control the equipment in the civil air defense project through the remote management center, such as remotely turning on or off ventilation equipment, adjusting the flow of water supply and drainage equipment, controlling the switches of electrical equipment, etc., to achieve real-time regulation of the civil air defense project;

[0024] The user interface and interaction module includes:

[0025] The visualization display sub-module develops an intuitive and user-friendly interface, visualizing multi-dimensional data and analysis results in the form of charts, reports, and maps, facilitating managers to understand the operation status and various indicators of the civil air defense project in real time;

[0026] The interaction sub-module provides user interaction functions such as querying, statistics, filtering, and exporting, facilitating managers to conduct in-depth analysis and processing of data. At the same time, it supports users to perform parameter settings and permission management operations on the system.

[0027] Preferably, the environmental data collection sub-module specifically deploys temperature and humidity sensors, air quality sensors, and gas concentration sensors inside the civil air defense project to collect environmental data such as temperature, humidity, PM2.5, PM10, carbon monoxide, and carbon dioxide in the project in real time;

[0028] The operation status data collected by the equipment status data collection sub-module includes, but is not limited to, the wind speed, wind pressure, and motor current of ventilation equipment, the water level, flow rate, and pump operation status of water supply and drainage equipment, and the voltage, current, and power of electrical equipment;

[0029] The structural safety data collection sub-module installs displacement sensors, strain sensors, and crack sensors to monitor the structural deformation, stress changes, and crack development of the civil air defense project in real time and obtain data related to structural safety;

[0030] The personnel activity data collection sub-module specifically uses the access control system, video surveillance system, and personnel positioning system to collect data on the time, location, and number of personnel entering and leaving the civil air defense project, as well as the activity trajectories of personnel inside the project.

[0031] Preferably, for areas with short distances and convenient wiring, the data transmission module adopts wired transmission methods such as Ethernet and optical fiber to ensure the stability and reliability of data transmission; for areas with scattered distribution or difficult wiring, it adopts wireless transmission methods such as GPRS, 4G, and 5G to achieve real-time data upload.

[0032] Preferably, the data backup and recovery sub-module also has a data recovery function, which can quickly recover data in case of database failures to ensure the integrity and availability of data.

[0033] Preferably, the data preprocessing sub-module specifically uses data cleaning algorithms to remove duplicate, invalid, and incorrect data, filtering algorithms to remove noise and fluctuations in the data, and normalization algorithms to convert the data into a unified dimension and range for subsequent data analysis and processing;

[0034] The formula of the data cleaning algorithm is as follows:

[0035] X(cleaned) = X - Xduplicates - Xerrors - Xinvalid

[0036] Among them, X(cleaned) represents the data after cleaning, X represents the original data, Xduplicates represents duplicate data, Xerrors represents error data, and Xinvalid represents invalid data;

[0037] The filtering algorithm adopts the moving average filtering algorithm, and the algorithm formula is:

[0038] Y(t) = (1 / (2N + 1)) Σ(X(t + i)),

[0039] where i = -N to N, Y(t) represents the data after filtering at time t, X(t + i) represents the original data at time t + i, and N is the size of the filtering window;

[0040] The normalization algorithm linearly transforms the data into the range of [0, 1], and the algorithm formula is:

[0041] X'(i) = (X(i) - Xmin) / (Xmax - Xmin),

[0042] where X'(i) represents the result after normalizing the i-th data, X(i) represents the i-th original data, Xmax represents the maximum value in the data, and Xmin represents the minimum value in the data.

[0043] Preferably, the feature extraction sub-module specifically uses data mining algorithms such as principal component analysis PCA and linear discriminant analysis LDA, and machine learning algorithms such as support vector machine SVM and random forest RF to extract feature variables that have important impacts on the environment, equipment status, structural safety, and personnel activities from the preprocessed data; the algorithm formula is:

[0044] The PCA algorithm projects the data into a new feature space through linear transformation and retains the main features of the data. Its formula is:

[0045] Z = XTP

[0046] Among them, Z is the principal component score matrix, X is the preprocessed data matrix, and P is the principal component loading matrix, representing the projection of the original variables on the principal components;

[0047] The LDA algorithm finds the best projection direction by maximizing the ratio of the between-class scatter matrix to the within-class scatter matrix. Its formula is:

[0048] W = argmax(WTSBW / WTSWW)

[0049] Among them, W is the projection direction vector, SB is the between-class scatter matrix, and SW is the within-class scatter matrix;

[0050] The SVM algorithm separates data of different classes by finding a hyperplane and maximizes the minimum distance from the hyperplane to the two classes of data. Its decision function is:

[0051] f(x) = sign(Σ(αiyiK(xi,x)) + b)

[0052] Among them, αi is the Lagrange multiplier, yi is the sample label, K(xi,x) is the kernel function, and b is the bias term;

[0053] The RF algorithm classifies or regresses by constructing multiple decision trees and synthesizing their output results. Its formula is:

[0054] Y = 1 / NTree ΣTree(Yi)

[0055] Among them, Y is the final output result, NTree is the number of decision trees, and Yi is the output result of the i-th decision tree.

[0056] Preferably, the association analysis sub-module uses the Apriori algorithm and the FP-Growth algorithm to analyze the association relationships between data of different dimensions and mine the potential rules and patterns between the data;

[0057] The Apriori algorithm generates association rules by iteratively searching for frequent item sets. Its formula is:

[0058] L(k) = C(k) ∩ D(k - 1)

[0059] Among them, L(k) is the k-item frequent item set, C(k) is the k-item candidate item set, and D(k - 1) is the (k - 1)-item frequent item set;

[0060] The FP-Growth algorithm directly mines frequent item sets by constructing a frequent pattern tree FP-Tree without generating candidate item sets. The process of constructing the FP-Tree includes: sorting the transaction data set, inserting the sorted transactions into the FP-Tree in turn. If the same prefix path already exists in the FP-Tree, increase the count; if not, create a new node and path;

[0061] The model establishment and training sub-module establishes prediction models such as support vector regression SVR and neural network NN, as well as rule-based fault diagnosis models and structural safety assessment models based on historical data and feature extraction results, and uses methods such as cross-validation and grid search to optimize and train the parameters of the models to improve the generalization ability and accuracy of the models;

[0062] The real-time analysis and early warning sub-module inputs the real-time collected data into the trained model for analysis, and judges the operation status and potential risks of the civil air defense project according to the preset thresholds and rules. When abnormal situations are detected, early warning information is sent out in a timely manner through text messages, emails, system messages, etc., to remind the management personnel to take corresponding measures for handling.

[0063] Preferably, the intelligent decision-making support sub-module specifically generates processing suggestions and emergency plans for equipment failures, environmental quality, structural safety, etc. according to the results of intelligent analysis of multi-dimensional data, combined with preset rules and strategies; for example, when the equipment failure early warning model predicts that a certain ventilation equipment is about to fail, the system automatically generates a maintenance work order, recommends corresponding maintenance personnel and spare parts, and at the same time generates an emergency plan to guide the management personnel to take temporary replacement measures and risk control during the equipment failure; when the environmental quality early warning model detects that the air quality in the civil air defense project exceeds the standard, the system provides suggestions for improving the environment, such as increasing the operation time of the ventilation equipment, turning on the air purification device, etc., and generates corresponding operation instructions to automatically adjust the equipment operation parameters to improve the environmental quality; the intelligent decision-making support sub-module can also predict the operation status and potential risks of the civil air defense project in a future period according to historical data and current situations, providing forward-looking decision-making support for the management personnel.

[0064] Preferably, the visual display sub-module specifically develops a Web-based visual interface, and uses various forms such as charts, dashboards, and maps to display the environmental data, equipment status, structural safety, and personnel activities information in the civil air defense project in real time; the charts include but are not limited to line charts, bar charts, pie charts, and scatter plots, which are used to display the trends, distributions, and proportions of data; the dashboard is used to intuitively display the current values and thresholds of key indicators, such as temperature, humidity, air quality index, etc.; the map visualizes the location, layout, and equipment distribution of the civil air defense project, facilitating the management personnel to quickly locate and analyze; at the same time, the visual display sub-module also supports dynamic refreshing and interactive operations of data. The management personnel can click, drag, and zoom to view and analyze various data in depth;

[0065] The interaction sub-module specifically provides functions of data query, statistical analysis, screening and filtering, and data export. The management personnel can customize query conditions according to needs, quickly obtain the required data, and generate corresponding reports and charts to provide a basis for decision-making; at the same time, it supports the management personnel to set the parameters of the system, including data collection frequency, early warning threshold, user permissions, to ensure the flexibility and security of the system.

[0066] Compared with the prior art, the beneficial effects of the present invention are:

[0067] By collecting and analyzing multi-dimensional data in real time, it realizes comprehensive and real-time monitoring of civil air defense projects, reduces the workload and time cost of manual inspections, and improves management efficiency. It can timely detect potential risks and hidden troubles in civil air defense projects, send early warning information in advance, and provide corresponding solutions, effectively avoiding accidents and enhancing the safety of civil air defense projects. Based on the intelligent analysis of multi-dimensional data, it provides scientific and accurate decision-making support for managers, helping them formulate more reasonable and effective management strategies and measures. Managers can monitor and control civil air defense projects anytime and anywhere through the remote management center, without being restricted by time and region, improving the flexibility and convenience of management. Description of the Drawings

[0068] Figure 1 is the system schematic diagram of the present invention. Detailed Embodiments

[0069] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0070] Please refer to Figure 1 , the present invention provides a remote management system for civil air defense projects based on intelligent analysis of multi-dimensional data, including a multi-dimensional data collection module, a data transmission module, a data storage and management module, a multi-dimensional data intelligent analysis module, an intelligent decision-making and remote control module, and a user interface and interaction module;

[0071] The multi-dimensional data collection module includes:

[0072] The environmental data collection sub-module is used to collect environmental data such as temperature, humidity, air quality, and harmful gas concentration in the project in real time;

[0073] The equipment status data collection sub-module collects the operation status data of various equipment in the civil air defense project through equipment interfaces and sensors;

[0074] The structural safety data collection sub-module monitors the structural deformation, stress changes, and crack development of the civil air defense project in real time to obtain data related to structural safety;

[0075] The personnel activity data collection sub-module is used to collect the time, location, quantity of personnel entering and leaving the civil air defense project, and the activity trajectory data of personnel in the project;

[0076] The data transmission module uses a communication method that combines wired and wireless means to transmit the data collected by the multi-dimensional data acquisition module to the remote management center in real time;

[0077] The data storage and management module includes:

[0078] The database construction sub-module establishes a multi-dimensional database, including an environmental database, a device status database, a structural safety database, and a personnel activity database, and classifies, stores, and manages the collected data;

[0079] The data backup and recovery sub-module is used to regularly back up the data in the database to prevent data loss;

[0080] The multi-dimensional data intelligent analysis module includes:

[0081] The data preprocessing sub-module performs preprocessing operations such as cleaning, filtering, and normalization on the collected raw data to remove noise and outliers and improve data quality;

[0082] The feature extraction sub-module uses data mining and machine learning algorithms to extract representative features from the preprocessed data;

[0083] The association analysis sub-module analyzes the association relationships between data of different dimensions, such as the association between environmental data and device operating status, the association between personnel activities and structural safety, etc., and mines the potential laws behind the data;

[0084] The model establishment and training sub-module, based on historical data and feature extraction results, establishes various prediction and diagnosis models, such as equipment fault prediction models, structural safety assessment models, environmental quality prediction models, etc., and uses a large amount of data to train and optimize the models to improve the accuracy and reliability of the models;

[0085] The real-time analysis and early warning sub-module: inputs the real-time collected data into the trained models for analysis, and judges the operating status and potential risks of the civil air defense project in real time; when detecting abnormal situations, it issues early warning information in a timely manner, such as equipment fault early warning, structural safety hidden danger early warning, environmental quality exceeding standard early warning, etc.;

[0086] The intelligent decision-making and remote control module includes:

[0087] The intelligent decision-making support sub-module provides intelligent decision-making support for managers according to the analysis results of the multi-dimensional data intelligent analysis module. For example, when an equipment fault early warning occurs, the system automatically generates maintenance suggestions and emergency plans; when the environmental quality exceeds the standard, the system provides measures and solutions to improve the environment;

[0088] In the remote control sub-module, managers can remotely control the equipment in the civil air defense project through the remote management center, such as remotely turning on or off ventilation equipment, adjusting the flow rate of water supply and drainage equipment, controlling the switches of electrical equipment, etc., to achieve real-time regulation of the civil air defense project;

[0089] The user interface and interaction module includes:

[0090] The visual display sub-module develops an intuitive and friendly user interface, and visualizes multi-dimensional data and analysis results in the form of charts, reports, and maps, facilitating managers to understand the operation status and various indicators of the civil air defense project in real time;

[0091] The interaction sub-module provides user interaction functions such as querying, statistics, filtering, exporting, etc., facilitating managers to conduct in-depth analysis and processing of data. At the same time, it supports users to perform parameter settings and permission management operations on the system.

[0092] The environmental data collection sub-module specifically deploys temperature and humidity sensors, air quality sensors, and gas concentration sensors inside the civil air defense project to collect environmental data such as temperature, humidity, PM2.5, PM10, carbon monoxide, and carbon dioxide in the project in real time;

[0093] The operation status data collected by the equipment status data collection sub-module includes but is not limited to the wind speed, wind pressure, and motor current of ventilation equipment, the water level, flow rate, and pump operation status of water supply and drainage equipment, and the voltage, current, and power of electrical equipment;

[0094] The structural safety data collection sub-module installs displacement sensors, strain sensors, and crack sensors to monitor the structural deformation, stress changes, and crack development of the civil air defense project in real time, and obtains data related to structural safety;

[0095] The personnel activity data collection sub-module specifically uses the access control system, video surveillance system, and personnel positioning system to collect data on the time, location, quantity of personnel entering and leaving the civil air defense project, and the activity trajectories of personnel inside the project.

[0096] For areas that are relatively close and convenient for wiring, the data transmission module adopts wired transmission methods such as Ethernet and optical fiber to ensure the stability and reliability of data transmission; for areas that are relatively dispersed or difficult for wiring, it adopts wireless transmission methods such as GPRS, 4G, and 5G to achieve real-time data upload.

[0097] The data backup and recovery sub-module also has a data recovery function, which can quickly recover data when the database fails to ensure the integrity and availability of the data.

[0098] The data preprocessing sub-module specifically uses data cleaning algorithms to remove duplicate, invalid, and incorrect data, uses filtering algorithms to remove noise and fluctuations in the data, and uses normalization algorithms to convert the data into a unified dimension and range for subsequent data analysis and processing;

[0099] The formula for the data cleaning algorithm is:

[0100] X(cleaned) = X - Xduplicates - Xerrors - Xinvalid

[0101] Among them, X(cleaned) represents the data after cleaning, X represents the original data, Xduplicates represents duplicate data, Xerrors represents incorrect data, and Xinvalid represents invalid data;

[0102] The filtering algorithm uses a moving average filtering algorithm, and the algorithm formula is:

[0103] Y(t) = (1 / (2N + 1)) Σ(X(t + i)),

[0104] where i = -N to N, Y(t) represents the filtered data at time t, X(t + i) represents the original data at time t + i, and N is the size of the filtering window;

[0105] The normalization algorithm linearly transforms the data into the range [0, 1], and the algorithm formula is:

[0106] X'(i) = (X(i) - Xmin) / (Xmax - Xmin),

[0107] Among them, X'(i) represents the result of normalizing the i-th data, X(i) represents the i-th original data, Xmax represents the maximum value in the data, and Xmin represents the minimum value in the data.

[0108] The feature extraction sub-module specifically uses data mining algorithms such as principal component analysis (PCA) and linear discriminant analysis (LDA), as well as machine learning algorithms such as support vector machine (SVM) and random forest (RF) to extract feature variables that have important impacts on the environment, equipment status, structural safety, and personnel activities from the preprocessed data; the algorithm formula is:

[0109] The PCA algorithm projects the data into a new feature space through linear transformation, retaining the main features of the data, and its formula is:

[0110] Z = XTP

[0111] Among them, Z is the principal component score matrix, X is the preprocessed data matrix, and P is the principal component loading matrix, representing the projection of the original variables on the principal components;

[0112] The LDA algorithm finds the optimal projection direction by maximizing the ratio of the between-class scatter matrix to the within-class scatter matrix, and its formula is:

[0113] W = argmax(WTSBW / WTSWW)

[0114] where W is the projection direction vector, SB is the between-class scatter matrix, and SW is the within-class scatter matrix;

[0115] The SVM algorithm separates data of different classes by finding a hyperplane and maximizes the minimum distance from the hyperplane to the two classes of data. Its decision function is:

[0116] f(x) = sign(Σ(αiyiK(xi,x)) + b)

[0117] where αi is the Lagrange multiplier, yi is the sample label, K(xi,x) is the kernel function, and b is the bias term;

[0118] The RF algorithm classifies or regresses by constructing multiple decision trees and synthesizing their output results. Its formula is:

[0119] Y = 1 / NTree ΣTree(Yi)

[0120] where Y is the final output result, NTree is the number of decision trees, and Yi is the output result of the i-th decision tree.

[0121] The association analysis sub-module uses the Apriori algorithm and the FP-Growth algorithm to analyze the association relationships between data in different dimensions and mine the potential rules and patterns in the data;

[0122] The Apriori algorithm generates association rules by iteratively searching for frequent item sets. Its formula is:

[0123] L(k) = C(k) ∩ D(k - 1)

[0124] where L(k) is the k-item frequent item set, C(k) is the k-item candidate item set, and D(k - 1) is the (k - 1)-item frequent item set;

[0125] The FP-Growth algorithm directly mines frequent item sets by constructing a frequent pattern tree FP-Tree without generating candidate item sets. The process of constructing the FP-Tree includes: sorting the transaction dataset, inserting the sorted transactions into the FP-Tree in turn. If the same prefix path already exists in the FP-Tree, increment the count; if not, create a new node and path;

[0126] The model establishment and training sub-module establishes prediction models such as Support Vector Regression (SVR) and Neural Network (NN), as well as rule-based fault diagnosis models and structural safety assessment models based on historical data and feature extraction results, and uses methods such as cross-validation and grid search to optimize and train the model parameters to improve the generalization ability and accuracy of the model;

[0127] The real-time analysis and early warning sub-module inputs the real-time collected data into the trained model for analysis, and judges the operation status and potential risks of the civil air defense project according to the preset thresholds and rules. When abnormal situations are detected, early warning information is sent out in a timely manner by means of text messages, emails, system messages, etc., to remind the management personnel to take corresponding measures for handling.

[0128] The intelligent decision-making support sub-module specifically generates processing suggestions and emergency plans for equipment failures, environmental quality, structural safety, etc. according to the results of intelligent analysis of multi-dimensional data, combined with preset rules and strategies; for example, when the equipment failure early warning model predicts that a certain ventilation equipment is about to fail, the system automatically generates a maintenance work order, recommends the corresponding maintenance personnel and spare parts, and at the same time generates an emergency plan to guide the management personnel to take temporary replacement measures and risk control during the equipment failure; when the environmental quality early warning model detects that the air quality in the civil air defense project exceeds the standard, the system provides suggestions for measures to improve the environment, such as increasing the operation time of ventilation equipment, turning on the air purification device, etc., and generates corresponding operation instructions to automatically adjust the equipment operation parameters to improve the environmental quality; the intelligent decision-making support sub-module can also predict the operation status and potential risks of the civil air defense project in a future period according to historical data and current situations, providing forward-looking decision-making support for the management personnel.

[0129] The visualization display sub-module specifically develops a Web-based visualization interface, which uses various forms such as charts, dashboards, and maps to display in real-time the environmental data, equipment status, structural safety, and personnel activities information in the civil air defense project; the charts include but are not limited to line charts, bar charts, pie charts, and scatter plots, which are used to display the trends, distributions, and proportions of data; the dashboard is used to intuitively display the current values and thresholds of key indicators, such as temperature, humidity, air quality index, etc.; the map visualizes the location, layout, and equipment distribution of the civil air defense project, facilitating the management personnel to quickly locate and analyze; at the same time, the visualization display sub-module also supports dynamic refreshing and interactive operations of data, and the management personnel can click, drag, and zoom to view and analyze various data in depth;

[0130] The interactive sub-module specifically provides functions such as data query, statistical analysis, filtering, and data export. Managers can customize query conditions according to their needs, quickly obtain the required data, and generate corresponding reports and charts to provide a basis for decision-making. At the same time, it supports managers to set system parameters, including data collection frequency, warning thresholds, and user permissions, to ensure the flexibility and security of the system.

[0131] In specific use, managers log in to the remote management center through the user interface of the interactive module. The first thing that catches their eye is the intuitive interface provided by the visual display sub-module. On the interface, information such as the environmental data, equipment status, structural safety, and personnel activities of the civil air defense project is clearly visible. Managers can quickly understand the current status of key indicators through the dashboard, such as whether the temperature and humidity are within the appropriate range and whether the air quality meets the standards. If a certain indicator approaches or exceeds the preset threshold, the dashboard will prompt with a prominent color to attract the attention of managers.

[0132] Furthermore, managers can use the functions provided by the interactive sub-module to conduct in-depth analysis and processing of the data. They can customize query conditions according to their needs, filter out data for a specific time period or specific area, and conduct detailed statistical analysis. At the same time, the system also supports exporting the data in formats such as Excel and PDF, which is convenient for managers to perform subsequent processing and report writing.

[0133] In terms of the intelligent decision-making and remote control module, when the multi-dimensional data intelligent analysis module detects an abnormal situation, the intelligent decision-making support sub-module will automatically generate processing suggestions and emergency plans. Managers can view these suggestions through the interface and decide whether to take corresponding measures according to the actual situation. If remote control of equipment is required, managers only need to click the corresponding button or enter commands on the interface to achieve real-time control of the equipment in the civil air defense project.

[0134] In addition, the entire system also has high flexibility and scalability. Managers can set and adjust system parameters according to actual needs, such as data collection frequency, warning thresholds, etc. At the same time, with the development of the civil air defense project and the change of requirements, the system can also be continuously upgraded and expanded to adapt to new application scenarios and requirements.

[0135] Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A remote management system for civil air defense projects based on multi-dimensional data intelligent analysis, characterized in that: It includes multi-dimensional data acquisition module, data transmission module, data storage and management module, multi-dimensional data intelligent analysis module, intelligent decision-making and remote control module and user interface and interaction module; The multi-dimensional data acquisition module includes: The environmental data collection submodule is used to collect environmental data such as temperature, humidity, air quality, and harmful gas concentration in the project in real time; The equipment status data collection submodule collects the operating status data of various equipment in the civil air defense project through equipment interfaces and sensors; The structural safety data acquisition submodule monitors the structural deformation, stress changes, and crack development of civil air defense projects in real time to obtain data related to structural safety; The personnel activity data collection submodule is used to collect the time, location, number of personnel entering and leaving the civil air defense project, as well as the activity trajectory data of personnel within the project; The data transmission module adopts a communication method combining wired and wireless to transmit the data collected by the multi-dimensional data collection module to the remote management center in real time; The data storage and management module includes: The database construction submodule establishes a multi-dimensional database, including an environmental database, an equipment status database, a structural safety database, and a personnel activity database, and classifies, stores, and manages the collected data; The data backup and recovery submodule is used to regularly back up the data in the database to prevent data loss; The multi-dimensional data intelligent analysis module includes: The data preprocessing submodule performs preprocessing operations such as cleaning, filtering, and normalization on the collected raw data to remove noise and outliers and improve data quality; The feature extraction submodule uses data mining and machine learning algorithms to extract representative features from the preprocessed data; The association analysis submodule analyzes the associations between data of different dimensions and explores the potential rules behind the data; The model building and training submodule builds various prediction and diagnosis models based on historical data and feature extraction results, and uses a large amount of data to train and optimize the models to improve the accuracy and reliability of the models; Real-time analysis and early warning submodule: input the real-time collected data into the trained model for analysis, and judge the operation status and potential risks of civil air defense projects in real time; when abnormal conditions are detected, issue early warning information in a timely manner; The intelligent decision-making and remote control module includes: The intelligent decision support submodule provides intelligent decision support for managers based on the analysis results of the multi-dimensional data intelligent analysis module; In the remote control submodule, managers can remotely control the equipment in the civil air defense project through the remote management center, realizing real-time regulation of the civil air defense project; The user interface and interaction module include: The visualization submodule develops an intuitive and user-friendly interface to visualize multi-dimensional data and analysis results in the form of charts, reports, and maps, making it easier for managers to understand the operating status and various indicators of civil air defense projects in real time; The interactive submodule provides user interaction functions and supports users to set system parameters and perform permission management operations.

2. The remote management system for civil air defense projects based on multi-dimensional data intelligent analysis according to claim 1, characterized in that: The environmental data acquisition sub-module is specifically to deploy temperature and humidity sensors, air quality sensors and gas concentration sensors inside the civil air defense project to collect environmental data such as temperature, humidity, PM2.5, PM10, carbon monoxide and carbon dioxide in the project in real time; The operation status data collected by the equipment status data acquisition sub-module includes but is not limited to the wind speed, wind pressure, and motor current of the ventilation equipment, the water level, flow rate, and pump operation status of the water supply and drainage equipment, and the voltage, current, and power of the electrical equipment; The structural safety data acquisition sub-module installs displacement sensors, strain sensors, and crack sensors to monitor the structural deformation, stress changes, and crack development of the civil air defense project in real time and obtain data related to structural safety; The personnel activity data acquisition sub-module is specifically to use the access control system, video surveillance system, and personnel positioning system to collect data on the time, location, number of personnel entering and leaving the civil air defense project, and the activity trajectories of personnel inside the project.

3. The remote management system for civil air defense projects based on multi-dimensional data intelligent analysis according to claim 1 is characterized in that: For areas with a short distance and convenient wiring, the data transmission module adopts wired transmission methods such as Ethernet and optical fiber to ensure the stability and reliability of data transmission; for areas with a more dispersed distribution or difficult wiring, it adopts wireless transmission methods such as GPRS, 4G, and 5G to realize real-time data upload.

4. The remote management system for civil air defense projects based on multi-dimensional data intelligent analysis according to claim 1, characterized in that: The data backup and recovery sub-module also has a data recovery function, which can quickly recover data when the database fails to ensure the integrity and availability of the data.

5. The remote management system for civil air defense projects based on multi-dimensional data intelligent analysis according to claim 1, wherein: The data preprocessing sub-module specifically uses data cleaning algorithms to remove duplicate, invalid, and incorrect data, uses filtering algorithms to remove noise and fluctuations in the data, and uses normalization algorithms to convert the data into a unified dimension and range for subsequent data analysis and processing; The formula for the data cleaning algorithm is: X(cleaned) = X - Xduplicates - Xerrors - Xinvalid Among them, X(cleaned) represents the data after cleaning, X represents the original data, Xduplicates represents duplicate data, Xerrors represents error data, and Xinvalid represents invalid data; The filtering algorithm adopts the moving average filtering algorithm, and the algorithm formula is: Y(t) = (1 / 2N + 1) Σ(X(t + i)), where i = -N to N, Y(t) represents the data after filtering at time t, X(t + i) represents the original data at time t + i, and N is the size of the filtering window; The normalization algorithm linearly transforms the data into the range of [0, 1], and the algorithm formula is: X'(i) = (X(i) - Xmin) / (Xmax - Xmin), where X'(i) represents the result of normalizing the i-th data, X(i) represents the i-th original data, Xmax represents the maximum value in the data, and Xmin represents the minimum value in the data.

6. The remote management system for civil air defense projects based on multi-dimensional data intelligent analysis according to claim 1, wherein: The feature extraction sub-module specifically uses data mining algorithms such as principal component analysis (PCA) and linear discriminant analysis (LDA), as well as machine learning algorithms such as support vector machine (SVM) and random forest (RF) to extract feature variables that have important impacts on the environment, equipment status, structural safety, and personnel activities from the preprocessed data. The algorithm formulas are as follows: The PCA algorithm projects the data into a new feature space through linear transformation, retaining the main features of the data. Its formula is: Z = XTP where Z is the principal component score matrix, X is the preprocessed data matrix, and P is the principal component loading matrix, representing the projection of the original variables on the principal components; The LDA algorithm finds the optimal projection direction by maximizing the ratio of the between-class scatter matrix to the within-class scatter matrix. Its formula is: W = argmax(WTSBW / WTSWW) where W is the projection direction vector, SB is the between-class scatter matrix, and SW is the within-class scatter matrix; The SVM algorithm separates data of different classes by finding a hyperplane and maximizes the minimum distance from the hyperplane to the two classes of data. Its decision function is: f(x) = sign(Σ(αiyiK(xi,x)) + b) where αi is the Lagrange multiplier, yi is the sample label, K(xi,x) is the kernel function, and b is the bias term; The RF algorithm classifies or regresses by constructing multiple decision trees and integrating their output results. Its formula is: Y = 1 / NTree ΣTree(Yi) where Y is the final output result, NTree is the number of decision trees, and Yi is the output result of the i-th decision tree.

7. The remote management system for civil air defense projects based on multi-dimensional data intelligent analysis according to claim 1, characterized in that: The association analysis sub-module uses the Apriori algorithm and the FP-Growth algorithm to analyze the association relationships between data of different dimensions and mine the potential rules and patterns in the data; The Apriori algorithm iteratively searches for frequent item sets and generates association rules using the frequent item sets. Its formula is: L(k) = C(k) ∩ D(k - 1) where L(k) is the k-item frequent item set, C(k) is the k-item candidate item set, and D(k - 1) is the (k - 1)-item frequent item set; The FP-Growth algorithm directly mines frequent item sets by constructing a frequent pattern tree (FP-Tree) without generating candidate item sets. The process of constructing the FP-Tree includes: sorting the transaction data set, inserting the sorted transactions into the FP-Tree in sequence. If the same prefix path already exists in the FP-Tree, increase the count; if not, create a new node and path; The model establishment and training sub-module establishes prediction models such as support vector regression (SVR) and neural network (NN) based on historical data and feature extraction results, as well as rule-based fault diagnosis models and structural safety assessment models, and uses methods such as cross-validation and grid search to optimize and train the model parameters to improve the generalization ability and accuracy of the model; The real-time analysis and early warning sub-module inputs the real-time collected data into the trained model for analysis, and judges the operation status and potential risks of the civil air defense project according to the preset thresholds and rules. When abnormal situations are detected, early warning information is sent out in a timely manner by means of text messages, emails, system messages, etc., to remind the management personnel to take corresponding measures for handling.

8. The remote management system for civil air defense projects based on multi-dimensional data intelligent analysis according to claim 1, characterized in that: The intelligent decision-making support sub-module specifically generates handling suggestions and emergency plans for equipment failures, environmental quality, structural safety, etc. according to the results of intelligent analysis of multi-dimensional data, combined with the preset rules and strategies; the intelligent decision-making support sub-module can also predict the operation status and potential risks of the civil air defense project in a future period according to historical data and current situations, providing forward-looking decision-making support for the management personnel.

9. The remote management system for civil air defense projects based on multi-dimensional data intelligent analysis according to claim 1, characterized in that: The visual display sub-module specifically develops a Web-based visual interface, and uses various forms such as charts, dashboards, and maps to display in real time the environmental data, equipment status, structural safety, and personnel activities information in the civil air defense project; the charts include but are not limited to line charts, bar charts, pie charts, and scatter plots, which are used to display the trends, distributions, and proportions of data; the dashboard is used to intuitively display the current values and thresholds of key indicators; the map visualizes the location, layout, and equipment distribution of the civil air defense project, facilitating the management personnel to quickly locate and analyze; at the same time, the visual display sub-module also supports the dynamic refresh and interactive operations of data. The management personnel can deeply view and analyze various data through operations such as clicking, dragging, and zooming; The interaction sub-module specifically provides functions of data query, statistical analysis, screening and filtering, and data export. The management personnel can customize query conditions according to needs, quickly obtain the required data, and generate corresponding reports and charts to provide a basis for decision-making; at the same time, it supports the management personnel to set the parameters of the system, including data collection frequency, early warning thresholds, and user permissions, to ensure the flexibility and security of the system.

Images