Municipal, water conservancy, traffic engineering building structure safety early warning system and early warning method

Abstract

The application discloses a municipal, water conservancy, traffic engineering building structure safety early warning system and early warning method, aiming at solving the problems of poor adaptability, low early warning precision and process disconnection of the existing management and control mode. The system comprises a perception layer, a transmission layer, a data layer and an application layer. The perception layer differentiates and deploys sensing devices to collect multi-dimensional engineering structure operation data. The transmission layer transmits data through a mixed transmission network. The data layer processes data through cleaning and fusion. The application layer realizes data visualization, intelligent analysis, early warning release and emergency dispatch. The early warning method adopts threshold early warning method, trend early warning method and intelligent diagnosis early warning method for linkage analysis, and follows a closed-loop process of data collection, transmission, processing, analysis and disposal. The scheme is suitable for the needs of three types of engineering in multiple scenes, improves the real-time and precision of early warning, guarantees the safety of engineering structures, reduces the management and control cost, and has practicality and popularization value.

Description

Technical Field

[0001] This invention relates to the field of structural safety in municipal, water conservancy, and transportation engineering projects, specifically to early warning systems and methods for structural safety in municipal, water conservancy, and transportation engineering projects. Background Technology

[0002] Municipal engineering, water conservancy, and transportation engineering are core components of infrastructure construction, and the structural safety of their structures is directly related to the safety of public life and property and the stable operation of the social economy. Bridges, pipelines, and roads in municipal engineering, dams, sluices, and aqueducts in water conservancy projects, and highways, railway bridges, and tunnels in transportation engineering are exposed to complex outdoor environments for extended periods. They are susceptible to factors such as load changes, natural erosion, and geological shifts, which can lead to safety hazards such as cracks, settlement, and abnormal seepage. If these hazards are not detected and addressed in a timely manner, they may cause structural collapse, leakage, and other safety accidents.

[0003] Currently, existing safety management methods rely heavily on manual inspections and single monitoring devices, which have significant limitations. Manual inspections are inefficient, highly subjective, and difficult to achieve 24 / 7 coverage, and lack the ability to identify hidden hazards. Single monitoring devices can only be adapted to specific types of projects, have poor compatibility, and cannot achieve cross-domain data exchange, resulting in isolated monitoring information silos.

[0004] Meanwhile, existing early warning methods are mostly based on single indicator thresholds, lacking multi-method linkage analysis, which easily leads to false alarms and missed alarms. Furthermore, early warning and emergency response are disconnected, making it difficult to form a closed-loop management system. With the upgrading of infrastructure operation and maintenance needs, traditional management and control methods can no longer meet the precise and intelligent requirements of safety management throughout the entire life cycle of three types of engineering structures. There is an urgent need for a safety early warning system and methods that are widely adaptable, accurate in early warning, and have a closed-loop process to overcome existing technical bottlenecks. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the defects of the above-mentioned technologies and provide a safety early warning system and method for municipal, water conservancy and transportation engineering building structures.

[0006] To address the aforementioned technical problems, the present invention provides a safety early warning system and method for municipal, water conservancy, and transportation engineering building structures: The safety early warning system for municipal, water conservancy, and transportation engineering building structures includes a perception layer, a transmission layer, a data layer, and an application layer. These layers work in a coordinated manner from top to bottom to form a closed-loop control system. The perception layer is equipped with differentiated sensing devices, deployed according to the structural characteristics of municipal, water conservancy, and transportation engineering projects, for real-time capture of multi-dimensional engineering structure operation data. The transmission layer constructs a hybrid transmission network to transmit the engineering structure operation data captured by the perception layer to the data layer at high speed and stably. The data layer stores, cleans, and fuses the received engineering structure operation data. The application layer, as the core application module, analyzes, provides early warnings for, and coordinates emergency response to the processed engineering structure operation data, achieving all-weather control of engineering structure safety.

[0007] As an improvement, the differentiated sensing devices include strain sensors, displacement sensors, settlement monitoring instruments, piezometers, water level gauges, tilt sensors, vibration sensors, crack monitoring instruments, and temperature and humidity sensors. The strain sensors, displacement sensors, and settlement monitoring instruments are deployed in municipal engineering projects to monitor bridge beam stress, pipeline deformation, and road settlement. The piezometers, water level gauges, and tilt sensors are deployed in water conservancy projects to collect data on dam seepage, sluice gate opening, and aqueduct deflection. The vibration sensors, crack monitoring instruments, and temperature and humidity sensors are deployed in transportation engineering projects to monitor tunnel surrounding rock stability, railway bridge vibration amplitude, and highway pavement crack development.

[0008] As an improvement, the hybrid transmission network adopts a combination of Internet of Things (IoT) technology, fifth-generation mobile communication (5G) technology, and fiber optic network. The IoT technology is used to transmit the engineering structure operation data captured by the differentiated sensing devices to the regional acquisition gateway over short distances. The 5G technology and fiber optic network are used to upload the data received by the regional acquisition gateway to the cloud platform over long distances. The transmission layer is also equipped with a data encryption module, which is used to encrypt the engineering structure operation data during transmission to prevent data leakage and tampering.

[0009] As an improvement, the data layer adopts a dual storage mode of cloud database and local server. The cloud database is used to store massive historical engineering structure operation data and real-time engineering structure operation data, while the local server is used to back up core engineering structure operation data. The data layer removes outliers and missing values ​​from the engineering structure operation data through data cleaning algorithms, and then integrates multi-source engineering structure operation data through data fusion technology to establish a unified data standard and realize cross-engineering data interoperability and sharing.

[0010] As an improvement, the application layer includes a data visualization module, an intelligent analysis module, an early warning release module, and an emergency dispatch module. The data visualization module is used to display the operating parameters of the engineering structure and the status of differentiated sensing devices in real time, supporting simultaneous monitoring of multiple projects and multiple indicators. The intelligent analysis module relies on intelligent algorithm models to analyze data change patterns and identify structural safety hazards. The early warning release module automatically releases early warning information according to the hazard level. The emergency dispatch module links with emergency plans to provide hazard handling suggestions and process guidance.

[0011] The method for early warning of structural safety in municipal, water conservancy, and transportation engineering projects includes the following steps: First, data acquisition: Real-time capture of structural operation data of municipal, water conservancy, and transportation engineering projects using differentiated sensing devices in the perception layer. These differentiated sensing devices are adapted to complex outdoor working conditions, ensuring the accuracy and reliability of the collected structural operation data. Second, data transmission: Encrypted transmission of the collected structural operation data to the data layer via a hybrid transmission network in the transmission layer, avoiding bottlenecks in single-network transmission and ensuring the timeliness and security of data transmission. Third, data processing: The data layer uses a dual-storage mode to store data, and processes the data through data cleaning and fusion techniques, eliminating invalid data and integrating multi-source data. Fourth, intelligent analysis: The application layer uses threshold early warning, trend early warning, and intelligent diagnostic early warning methods to analyze the processed data and determine whether an early warning is triggered. Fifth, early warning response: Based on the analysis results, corresponding level early warning information is issued, and the emergency dispatch module is linked to complete the handling and feedback of potential hazards, forming a closed-loop management system.

[0012] As an improvement, the threshold warning method is based on the current national engineering safety standards and combines engineering design parameters and operational experience to set four warning thresholds for each monitoring indicator. The four warning thresholds are blue warning threshold, yellow warning threshold, orange warning threshold and red warning threshold. The monitoring data is compared with the corresponding warning threshold in real time. When the monitoring data exceeds the corresponding warning threshold, the corresponding level of warning is immediately activated.

[0013] As an improvement, the trend early warning method uses a time series analysis algorithm to fit and analyze historical monitoring data and real-time monitoring data to predict the changing trend of monitoring indicators; for slowly changing indicators, a linear regression model is used to predict the trajectory of data changes; for abruptly changing indicators, a sliding window algorithm is used to capture abnormal fluctuations in data; if the predicted value is close to or exceeds the early warning threshold, an early warning information is issued in advance.

[0014] As an improvement, the intelligent diagnosis and early warning method introduces machine learning algorithms to construct an engineering structure safety diagnosis model, including random forest algorithm and neural network algorithm; the diagnosis model is optimized by training a large amount of historical hidden danger data, including data on the correlation between bridge crack expansion and collapse, and data on the correlation between abnormal seepage and piping in dams; the diagnosis model realizes multi-indicator linkage diagnosis, and the risk level is determined and the early warning level is adjusted according to the linkage of indicators.

[0015] As an improvement, the early warning information is simultaneously pushed to the management personnel through three methods: SMS, platform pop-up window, and audible and visual alarm. After the hidden danger is dealt with, the management personnel enter the handling results into the system, and the system updates the corresponding engineering structure operation data file, continuously optimizes the early warning model parameters, and improves the accuracy of subsequent early warnings.

[0016] The advantages of this invention compared with the prior art are as follows: First, it has strong adaptability and wide versatility. The early warning system deploys various sensing devices in a differentiated manner through the perception layer, and combines the unified standard of the data layer with the flexible configuration of the application layer. It can simultaneously meet the different structural monitoring needs of municipal engineering, water conservancy engineering and transportation engineering. There is no need to build a separate system, which greatly reduces equipment investment and operation and maintenance costs, and facilitates promotion and application.

[0017] Secondly, the early warning is accurate, real-time and efficient. The four-layer collaborative architecture realizes the connection of the entire process of data collection, transmission, analysis and early warning. The threshold early warning method, trend early warning method and intelligent diagnosis early warning method work together to reduce false alarms and missed alarms, capture hidden dangers in advance and reserve time for handling, and provide reliable protection for the safety of engineering structures.

[0018] Third, it boasts excellent data security and system stability. The data encryption module at the transmission layer ensures data security, and the dual storage mode of cloud database and local server prevents data loss. The software and hardware are adaptable to complex working conditions and can learn and optimize themselves, ensuring the continuity of management and control processes.

[0019] Fourth, a closed-loop management and control mechanism is established to achieve full life-cycle coverage of safety management and control, link emergency dispatch modules to standardize handling procedures, reduce reliance on manual labor and management and control costs, improve the level of intelligent management, extend the service life of the project, and achieve significant social and economic benefits. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the safety early warning system for municipal, water conservancy, and transportation engineering building structures according to the present invention.

[0022] Figure 2 This is a schematic diagram of the method for early warning of structural safety in municipal, water conservancy, and transportation engineering projects according to the present invention. Detailed Implementation

[0023] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings, which illustrate embodiments of the present application. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of this application will be thorough and complete.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0025] It is understood that spatial relation terms such as "below," "under," "below," "below," "above," "over," etc., can be used here to describe the relationship between one element or feature shown in the figure and other elements or features. It should be understood that, in addition to the orientation shown in the figure, spatial relation terms also include different orientations of the device in use and operation. For example, if the device in the figure is flipped, the element or feature described as "below" or "under" or "below" of the other element or feature will be oriented "over" the other element or feature. Therefore, the exemplary terms "below" and "under" can include both upper and lower orientations. Furthermore, the device may also include other orientations, such as being rotated 90 degrees or other orientations, and the spatial descriptive terms used herein will be interpreted accordingly.

[0026] It should be noted that when one element is considered to be "connected" to another element, it can be directly connected to the other element or connected to the other element through an intermediary element. In the following embodiments, "connection" should be understood as "electrical connection," "communication connection," etc., if the connected circuits, modules, units, etc., have the transmission of electrical signals or data between them.

[0027] When used herein, the singular forms of “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising,” “including,” or “having,” etc., specify the presence of the stated feature, whole, step, operation, component, part, or combination thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof.

[0028] Referring to the attached diagram, the municipal, water conservancy, and transportation engineering building structure safety early warning system and method are described. The municipal, water conservancy, and transportation engineering building structure safety early warning system includes a perception layer, a transmission layer, a data layer, and an application layer. The perception layer, transmission layer, data layer, and application layer work in a coordinated manner from top to bottom to form a closed-loop control system. The perception layer is equipped with differentiated sensing devices, which are deployed according to the structural characteristics of municipal, water conservancy, and transportation engineering projects to capture multi-dimensional engineering structure operation data in real time. The transmission layer constructs a hybrid transmission network to transmit the engineering structure operation data captured by the perception layer to the data layer at high speed and stably. The data layer is used to store, clean, and fuse the received engineering structure operation data. The application layer, as the core application module, is used to analyze, provide early warnings, and coordinate emergency response for the processed engineering structure operation data, achieving all-weather control of engineering structure safety.

[0029] The differentiated sensing devices include strain sensors, displacement sensors, settlement monitoring instruments, piezometers, water level gauges, tilt sensors, vibration sensors, crack monitoring instruments, and temperature and humidity sensors. The strain sensors, displacement sensors, and settlement monitoring instruments are deployed in municipal engineering projects to monitor bridge beam stress, pipeline deformation, and road settlement. The piezometers, water level gauges, and tilt sensors are deployed in water conservancy projects to collect data on dam seepage, sluice gate opening, and aqueduct deflection. The vibration sensors, crack monitoring instruments, and temperature and humidity sensors are deployed in transportation engineering projects to monitor tunnel surrounding rock stability, railway bridge vibration amplitude, and highway pavement crack development.

[0030] The hybrid transmission network adopts a combination of Internet of Things (IoT) technology, fifth-generation mobile communication (5G) technology, and fiber optic network. The IoT technology is used to transmit the engineering structure operation data captured by the differentiated sensing devices to the regional acquisition gateway over short distances. The 5G technology and fiber optic network are used to upload the data received by the regional acquisition gateway to the cloud platform over long distances. The transmission layer is also equipped with a data encryption module, which is used to encrypt the engineering structure operation data during transmission to prevent data leakage and tampering.

[0031] The data layer adopts a dual storage mode of cloud database and local server. The cloud database is used to store massive historical engineering structure operation data and real-time engineering structure operation data, while the local server is used to back up core engineering structure operation data. The data layer removes outliers and missing values ​​from the engineering structure operation data through data cleaning algorithms, and then integrates multi-source engineering structure operation data through data fusion technology to establish a unified data standard and realize cross-engineering data interoperability and sharing.

[0032] The application layer includes a data visualization module, an intelligent analysis module, an early warning release module, and an emergency dispatch module. The data visualization module is used to display the operating parameters of the engineering structure and the status of differentiated sensing devices in real time, supporting simultaneous monitoring of multiple projects and multiple indicators. The intelligent analysis module relies on intelligent algorithm models to analyze data change patterns and identify structural safety hazards. The early warning release module automatically releases early warning information according to the hazard level. The emergency dispatch module links with emergency plans and provides hazard handling suggestions and process guidance.

[0033] The method for early warning of structural safety in municipal, water conservancy, and transportation engineering projects includes the following steps: First, data acquisition: Real-time capture of structural operation data of municipal, water conservancy, and transportation engineering projects using differentiated sensing devices in the perception layer. These differentiated sensing devices are adapted to complex outdoor working conditions, ensuring the accuracy and reliability of the collected structural operation data. Second, data transmission: Encrypted transmission of the collected structural operation data to the data layer via a hybrid transmission network in the transmission layer, avoiding bottlenecks in single-network transmission and ensuring the timeliness and security of data transmission. Third, data processing: The data layer uses a dual-storage mode to store data, and processes the data through data cleaning and fusion techniques, eliminating invalid data and integrating multi-source data. Fourth, intelligent analysis: The application layer uses threshold early warning, trend early warning, and intelligent diagnostic early warning methods to analyze the processed data and determine whether an early warning is triggered. Fifth, early warning response: Based on the analysis results, corresponding level early warning information is issued, and the emergency dispatch module is linked to complete the handling and feedback of potential hazards, forming a closed-loop management system.

[0034] The threshold warning method is based on current national engineering safety standards and combines engineering design parameters and operational experience to set four levels of warning thresholds for each monitoring indicator. The four levels of warning thresholds are blue warning threshold, yellow warning threshold, orange warning threshold and red warning threshold. The monitoring data is compared with the corresponding warning threshold in real time. When the monitoring data exceeds the corresponding warning threshold, the corresponding level of warning is immediately activated.

[0035] The trend early warning method uses a time series analysis algorithm to fit and analyze historical and real-time monitoring data to predict the trend of changes in monitoring indicators. For slowly changing indicators, a linear regression model is used to predict the trajectory of data changes, and for abruptly changing indicators, a sliding window algorithm is used to capture abnormal fluctuations in data. If the predicted value is close to or exceeds the early warning threshold, an early warning information is issued in advance.

[0036] The intelligent diagnosis and early warning method introduces machine learning algorithms to construct an engineering structure safety diagnosis model, including random forest algorithm and neural network algorithm; the diagnosis model is optimized by training a large amount of historical hidden danger data, including data on the correlation between bridge crack expansion and collapse, and data on the correlation between abnormal seepage and piping in dams; the diagnosis model realizes multi-indicator linkage diagnosis, and the risk level is determined and the early warning level is adjusted according to the linkage of indicators.

[0037] The early warning information is simultaneously pushed to the management personnel through three methods: SMS, platform pop-up window, and audible and visual alarm. After the hidden danger is dealt with, the management personnel enter the handling results into the system. The system updates the corresponding engineering structure operation data file, continuously optimizes the early warning model parameters, and improves the accuracy of subsequent early warnings.

[0038] System implementation configuration:

[0039] The municipal, water conservancy, and transportation engineering building structure safety early warning system constructed in this embodiment adopts a four-layer architecture: perception layer, transmission layer, data layer, and application layer. Devices and modules at each layer work together to achieve all-time, multi-dimensional safety control of the three types of engineering building structures. The following details the configuration of each layer, the implementation process of the early warning method, and key technical details, using specific engineering application scenarios. The mathematical formulas involved are used to accurately define the early warning judgment logic, ensuring the scientific validity and reliability of the early warning results.

[0040] Perception layer implementation configuration:

[0041] As the system's data acquisition terminal, the sensing layer deploys strain sensors, displacement sensors, settlement observation instruments, piezometers, water level gauges, tilt sensors, vibration sensors, crack monitoring instruments, and temperature and humidity sensors as described in the claims, based on the structural characteristics and monitoring needs of municipal engineering, water conservancy engineering, and transportation engineering. All sensing devices are adapted to complex outdoor working conditions and possess waterproof, anti-interference, and high and low temperature resistance properties to ensure the stability and accuracy of the acquired data.

[0042] In municipal engineering bridge monitoring scenarios, strain sensors are evenly distributed at key stress-bearing parts of the bridge beam to collect beam stress data; displacement sensors are deployed at bridge bearings to monitor bearing displacement; and settlement monitoring instruments are set up at bridge piers and surrounding ground to capture real-time pier and ground settlement data. In water conservancy dam monitoring scenarios, piezometers are deployed layer by layer along the dam body to collect seepage pressure data at different depths; water level gauges are installed on the upstream side of the dam to monitor water level changes in real time; and tilt sensors are fixed to the top of the dam to monitor the dam's tilt angle. In traffic engineering tunnel monitoring scenarios, vibration sensors are deployed on the tunnel surrounding rock surface to capture surrounding rock vibration signals; crack monitoring instruments are installed on the tunnel lining structure to monitor crack width and length changes; and temperature and humidity sensors are deployed inside the tunnel to collect environmental temperature and humidity data, providing a basis for subsequent data correction.

[0043] Transport layer implementation configuration:

[0044] The transmission layer employs a hybrid transmission network combining IoT technology, 5G mobile communication technology, and fiber optic networks as described in the claims, enabling high-speed and secure transmission of data collected by the sensing layer. In specific implementation, within a short distance, IoT technology is used to transmit the engineering structure operation data collected by each sensor device to a regional acquisition gateway. The coverage radius of each regional acquisition gateway is set according to the project scale to ensure effective coverage of all sensor signals. For long-distance transmission, 5G mobile communication technology and fiber optic networks are used to upload the data received by the regional acquisition gateway to a cloud platform, avoiding the bottleneck of a single network transmission and ensuring the timeliness of data transmission.

[0045] To prevent leakage and tampering during data transmission, the data encryption module configured in the transport layer employs a symmetric encryption algorithm. The specific encryption logic is defined by the following formula:

[0046]

[0047] in, This represents the encrypted ciphertext data, which is the data actually transmitted during the transmission process; This embodiment uses the Advanced Encryption Standard (AES) algorithm. This refers to the encryption key, which is generated uniformly by the system backend and updated regularly, and is only accessible to the receiving end of the transport layer and data layer. This represents the raw plaintext data collected by the perception layer. The function of this formula is to encrypt the raw data using a key, ensuring that only authorized receivers can decrypt and access the raw data, thus guaranteeing data transmission security.

[0048] Data layer implementation configuration:

[0049] The data layer adopts a dual storage mode of cloud database and local server as described in the claims to achieve secure storage and efficient processing of engineering structure operation data. The cloud database uses a distributed cloud storage architecture to store massive amounts of historical and real-time engineering structure operation data, supporting fast data query and batch processing. The local server is deployed at the engineering site control center to back up core engineering structure operation data. When the cloud network fails, the local server can independently store real-time data to avoid data loss.

[0050] During data processing, outliers and missing values ​​are first removed from the original data using data cleaning algorithms. The 3σ criterion is used to determine outliers, and the specific formula is as follows:

[0051]

[0052] in, Represents a single collected data value; This represents the average value of multiple collected data for the same monitoring indicator. This represents the standard deviation of multiple data points collected for the same monitoring indicator. The formula is used to define the scope of outlier data. When the absolute value of the difference between a single data point and the mean is greater than three times the standard deviation, the data is considered an outlier and is removed, thus improving data quality. After data cleaning, multi-source data is integrated using data fusion technology to establish a unified data standard, enabling cross-project data sharing and providing reliable data support for intelligent analysis at the application layer.

[0053] Application layer implementation configuration:

[0054] The application layer encompasses the data visualization module, intelligent analysis module, early warning release module, and emergency dispatch module described in the claims. These modules operate collaboratively to achieve data analysis, early warning, and emergency response coordination. The data visualization module displays real-time operating parameters of the engineering structure and the status of sensing devices through a graphical interface, supporting focused monitoring of single projects and batch monitoring of multiple projects. Managers can intuitively grasp the operational status of each engineering structure through the interface. The intelligent analysis module analyzes data using threshold early warning, trend early warning, and intelligent diagnostic early warning methods. The early warning release module automatically releases early warning information based on the level of hazard. The emergency dispatch module links with emergency plans, providing hazard handling suggestions and process guidance.

[0055] Specific implementation process of early warning methods:

[0056] The early warning method in this embodiment is based on the above-mentioned system and strictly follows the five-step process described in the claims, namely data collection, data transmission, data processing, intelligent analysis, and early warning response. Through the coordinated application of the three early warning methods, the accuracy of hazard identification is improved, and early detection and early response to structural safety hazards are achieved.

[0057] Implementation of the threshold-based early warning method:

[0058] The threshold-based early warning method, based on current national engineering safety standards and combined with engineering design parameters and operational experience, sets four levels of early warning thresholds for each monitoring indicator: blue, yellow, orange, and red. Taking the strain monitoring of municipal bridge beams as an example, the early warning threshold is calculated and determined using the following formula:

[0059] ( )

[0060] in, Indicates the first Level 1 warning threshold Corresponding to the blue warning threshold, Corresponding to the yellow warning threshold, Corresponding to the orange alert threshold, Corresponding to the red alert threshold; This indicates the maximum allowable strain value for the bridge girder design, which is determined by the engineering design documents. This represents the threshold coefficient, which is set based on engineering operation experience and safety level requirements. In this embodiment... , , , The purpose of this formula is to scientifically classify early warning levels based on the beam's design limits and safety factor, ensuring the rationality of the early warning thresholds. During implementation, the system compares the monitored beam strain values ​​with the early warning thresholds for each level in real time. When the strain value exceeds the corresponding threshold, the corresponding level of early warning is immediately activated.

[0061] Implementation of the trend early warning method:

[0062] The trend early warning method uses time series analysis algorithms to fit and analyze historical and real-time monitoring data to predict the changing trends of monitoring indicators. For slowly changing indicators such as road settlement and embankment displacement, a linear regression model is used to predict the trajectory of data changes. The specific prediction formula is as follows:

[0063]

[0064] in, This represents the predicted value of the monitoring indicator; This represents a time variable, with the unit being days. The regression coefficient represents the rate of change of the monitoring indicator over time. It represents the intercept, which is determined by fitting historical data. The function of this formula is to predict the changes in monitoring indicators within a certain period in the future through linear fitting. If the predicted value is close to or exceeds the warning threshold, warning information will be issued one to two cycles in advance to reserve time for potential hazard handling. For sudden change indicators such as tunnel surrounding rock vibration and bridge vibration, a sliding window algorithm is used to capture abnormal fluctuations in data. By setting a fixed time window, the fluctuation amplitude of the data within the window is calculated. When the fluctuation amplitude exceeds the set range, it is determined as an abnormal fluctuation and a warning is triggered.

[0065] Implementation of the intelligent diagnosis and warning method:

[0066] The intelligent diagnosis and warning method introduces the random forest algorithm and the neural network algorithm to construct an engineering structure safety diagnosis model. By training a large amount of historical potential hazard data, the model parameters are optimized to achieve multi-index linkage diagnosis. The output result of the model is expressed by the following formula:

[0067]

[0068] Among them, represents the risk level diagnosed by the model, and its value range is from 0 to 1. The closer the value is to 1, the higher the risk level; represents the number of decision trees in the random forest algorithm. In this embodiment ; represents the output result of the th decision tree;

[0069] represents the multi-dimensional monitoring index data input into the model, including index data such as strain, displacement, vibration, and seepage. The function of this formula is to integrate the output results of multiple decision trees to obtain the final risk level determination value, avoid diagnostic errors caused by a single decision tree, and improve the diagnostic accuracy. During implementation, when three indicators, namely, excessive surrounding rock displacement, abnormal vibration, and sudden change in temperature and humidity, are simultaneously triggered in a traffic tunnel, the system calculates the risk level

[0070] through the diagnosis model, determines it as a high risk of collapse, directly upgrades it to a red warning, and pushes the emergency response plan. At the same time, the model has the ability of self-learning, continuously compares the actual situation after potential hazard handling with the diagnosis result, optimizes the model parameters, and improves the subsequent warning accuracy.

[0071] Warning information is simultaneously pushed to management personnel through three methods as described in the claims: SMS, platform pop-ups, and audible and visual alarms. Different warning levels correspond to different handling procedures. A blue warning activates the daily inspection mechanism, with management personnel increasing the frequency of inspections of the corresponding structural parts and closely monitoring changes in indicators; a yellow warning activates the hidden danger investigation mechanism, organizing professional technicians to conduct a comprehensive investigation of the structural parts and analyze the causes of hidden dangers; an orange warning activates the emergency control mechanism, implementing flow restriction and traffic restriction measures in the project area to prevent the risk from escalating; a red warning activates the emergency response mechanism, immediately evacuating personnel, stopping project operations, and organizing professional teams to carry out hidden danger remediation.

[0072] After the hazard is dealt with, the management personnel will enter the results into the system. The system will then update the corresponding engineering structure operation data archives and optimize key indicators such as early warning threshold coefficients and model parameters based on the results. This will form a closed-loop management system of "collection-analysis-early warning-dealing-optimization" to continuously improve the system's early warning capabilities and the level of engineering structure safety management.

[0073] Implementation Results Description:

[0074] The system and early warning method of this embodiment have been piloted in a municipal bridge, a water conservancy dam, and a highway tunnel project. Through differentiated perception layer deployment, secure and efficient transmission layer configuration, accurate data processing, and multi-dimensional linkage early warning methods, the system has achieved effective identification and early warning of potential safety hazards in engineering structures. During the pilot project, the system successfully provided early warnings for several potential hazards, including abnormal strain in the beams of the municipal bridge, excessive seepage in the water conservancy dam, and the expansion of cracks in the lining of the highway tunnel. After timely handling, no safety accidents occurred, verifying the feasibility and practicality of the system and method of this invention, and demonstrating its ability to meet the actual needs of safety management and control of municipal, water conservancy, and transportation engineering structures.

[0075] Beneficial effects:

[0076] First, it achieves a unified approach to cross-domain adaptability and versatility, solving the problem that traditional early warning systems can only adapt to a single type of project and have poor compatibility. The early warning system of this invention, through differentiated deployment of sensing devices such as strain sensors, displacement sensors, piezometers, and vibration sensors at the perception layer, combined with unified data standards at the data layer and flexible configuration functions at the application layer, can simultaneously adapt to the different structural monitoring needs of municipal engineering, water conservancy engineering, and transportation engineering. It can meet the safety management and control needs of municipal bridges, pipelines, and roads, and also cover monitoring scenarios for water conservancy dams, sluices, aqueducts, and transportation highways, railway bridges, and tunnels. It eliminates the need to build separate systems for different projects, significantly reducing equipment investment and maintenance costs for project safety management and improving the applicability of the technical solution.

[0077] Secondly, it enhances the real-time performance and accuracy of structural safety early warnings, effectively avoiding the drawbacks of traditional manual monitoring, such as high latency and high false alarm / missed alarm rates. The early warning system employs a four-layer collaborative architecture: perception, transmission, data, and application. The perception layer uses high-precision sensors to capture multi-dimensional structural operation data in real time. This data is then transmitted at high speed with encrypted transmission via a hybrid network in the transmission layer. The data layer cleanses and integrates the data to remove invalid data. Finally, the application layer utilizes three interconnected early warning methods for analysis, achieving efficient integration of the entire process from data collection and transmission to analysis and early warning. Specifically, the threshold-based early warning method accurately determines the level of hazard based on scientifically set four-level warning thresholds; the trend-based early warning method predicts the trajectory of indicator changes in advance, allowing time for intervention; and the intelligent diagnostic early warning method reduces the limitations of single-indicator analysis through multi-indicator linkage diagnosis. The combination of these three methods significantly reduces the false alarm rate, ensuring early detection, early assessment, and early intervention of hazards, providing reliable technical support for structural safety.

[0078] Third, strengthen data security and system stability to ensure the integrity of engineering structure operation data and the continuity of management processes. The data encryption module configured in the transmission layer encrypts the engineering structure operation data using a symmetric encryption algorithm, effectively preventing leakage and tampering during data transmission and ensuring data transmission security. The data layer adopts a dual storage mode of cloud database and local server, which not only achieves secure storage of massive historical and real-time data, but also allows for independent storage of core data on the local server in the event of cloud network failure, avoiding data loss. At the same time, the system hardware uses sensing devices adapted to complex outdoor working conditions, and the software has self-learning optimization capabilities, which can continuously adjust the early warning threshold coefficient and model parameters based on engineering operation feedback, improving the system's operational stability and long-term adaptability in different environments.

[0079] Fourth, a closed-loop management and control system is constructed to achieve full lifecycle coverage and intelligent upgrade of engineering structure safety management and control. The early warning method follows a complete process of data collection, data transmission, data processing, intelligent analysis, and early warning response. After an early warning is issued, the emergency dispatch module provides response suggestions and process guidance. After the hazard is handled, the results are entered into the system to update the data archive, forming a closed-loop mechanism of "collection-analysis-early warning-response-optimization." This mechanism breaks down the traditional disconnect between early warning and response, enabling managers to not only monitor the operational status of engineering structures in real time but also to achieve standardized and efficient hazard response through the system. Simultaneously, through data accumulation and model optimization, the accuracy of subsequent early warnings and the level of control are continuously improved, extending the service life of municipal, water conservancy, and transportation engineering structures, reducing the incidence of safety accidents, and ensuring the safety of public life and property and the safe operation of engineering projects, resulting in significant social and economic benefits.

[0080] Fifth, this invention reduces reliance on manual labor and management costs, and enhances the intelligence level of engineering safety management. By replacing traditional manual inspections with automated sensing equipment, it achieves 24 / 7 uninterrupted collection and monitoring of engineering structure operation data, significantly reducing the workload and labor costs of manual inspections. It also avoids monitoring errors caused by subjective judgment and environmental limitations during manual monitoring. The system's data visualization module supports simultaneous monitoring of multiple projects and multiple indicators. Managers can intuitively grasp the operational status of each engineering structure through a graphical interface, eliminating the need for on-site inspections and improving management efficiency. The emergency dispatch module links with emergency plans, enabling rapid dissemination of response solutions, shortening the response time for hazard handling, and further reducing losses caused by safety accidents.

[0081] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. A structural safety early warning system for municipal, water conservancy, and transportation engineering projects, characterized by: The system comprises a perception layer, a transmission layer, a data layer, and an application layer. These layers work in tandem from top to bottom to form a closed-loop control system. The perception layer is equipped with differentiated sensing devices, deployed according to the structural characteristics of municipal engineering, water conservancy engineering, and transportation engineering projects, to capture multi-dimensional operational data of the engineering structures in real time. The transmission layer constructs a hybrid transmission network to transmit the operational data captured by the perception layer to the data layer at high speed and stably. The data layer stores, cleans, and fuses the received operational data. The application layer, as the core application module, analyzes, provides early warnings, and coordinates emergency response to the processed operational data, achieving all-weather control of engineering structure safety.

2. The municipal, water conservancy, and transportation engineering building structure safety early warning system according to claim 1, characterized in that: The differentiated sensing devices include strain sensors, displacement sensors, settlement monitoring instruments, piezometers, water level gauges, tilt sensors, vibration sensors, crack monitoring instruments, and temperature and humidity sensors. The strain sensors, displacement sensors, and settlement monitoring instruments are deployed in municipal engineering projects to monitor bridge beam stress, pipeline deformation, and road settlement. The piezometers, water level gauges, and tilt sensors are deployed in water conservancy projects to collect data on dam seepage, sluice gate opening, and aqueduct deflection. The vibration sensors, crack monitoring instruments, and temperature and humidity sensors are deployed in transportation engineering projects to monitor tunnel surrounding rock stability, railway bridge vibration amplitude, and highway pavement crack development.

3. The municipal, water conservancy, and transportation engineering building structure safety early warning system according to claim 1, characterized in that: The hybrid transmission network adopts a combination of Internet of Things (IoT) technology, fifth-generation mobile communication (5G) technology, and fiber optic network. The IoT technology is used to transmit the engineering structure operation data captured by the differentiated sensing devices to the regional acquisition gateway over short distances. The 5G technology and fiber optic network are used to upload the data received by the regional acquisition gateway to the cloud platform over long distances. The transmission layer is also equipped with a data encryption module, which is used to encrypt the engineering structure operation data during transmission to prevent data leakage and tampering.

4. The municipal, water conservancy, and transportation engineering building structure safety early warning system according to claim 1, characterized in that: The data layer adopts a dual storage mode of cloud database and local server. The cloud database is used to store massive historical engineering structure operation data and real-time engineering structure operation data, while the local server is used to back up core engineering structure operation data. The data layer removes outliers and missing values ​​from the engineering structure operation data through data cleaning algorithms, and then integrates multi-source engineering structure operation data through data fusion technology to establish a unified data standard and realize cross-engineering data interoperability and sharing.

5. The municipal, water conservancy, and transportation engineering building structure safety early warning system according to claim 1, characterized in that: The application layer includes a data visualization module, an intelligent analysis module, an early warning release module, and an emergency dispatch module. The data visualization module is used to display the operating parameters of the engineering structure and the status of differentiated sensing devices in real time, and supports simultaneous monitoring of multiple projects and multiple indicators. The intelligent analysis module relies on intelligent algorithm models to analyze data change patterns and identify potential structural safety hazards. The early warning release module automatically releases early warning information based on the level of hazard; the emergency dispatch module links with the emergency plan to provide suggestions and process guidance for hazard handling.

6. A method for early warning of structural safety in municipal, water conservancy, and transportation engineering projects based on the system described in any one of claims 1-5, characterized in that: Includes the following steps: The first step is data acquisition. Real-time structural operation data for municipal engineering, water conservancy, and transportation engineering is captured using differentiated sensing devices in the perception layer. These devices are adapted to complex outdoor conditions, ensuring the accuracy and reliability of the collected structural operation data. The second step is data transmission. The collected structural operation data is encrypted and transmitted to the data layer via a hybrid transmission network in the transmission layer, avoiding bottlenecks in single-network transmission and ensuring the timeliness and security of data transmission. The third step is data processing. The data layer uses a dual-storage mode to store data and processes it through data cleaning and fusion techniques, eliminating invalid data and integrating multi-source data. The fourth step is intelligent analysis. The application layer uses threshold warning, trend warning, and intelligent diagnostic warning methods to analyze the processed data and determine whether a warning is triggered. The fifth step is early warning and response. Based on the analysis results, early warning information of the corresponding level is issued, and the emergency dispatch module is linked to complete the handling and feedback of potential hazards, forming a closed-loop management system.

7. The method for early warning of structural safety in municipal, water conservancy, and transportation engineering projects according to claim 6, characterized in that: The threshold warning method is based on current national engineering safety standards and combines engineering design parameters and operational experience to set four levels of warning thresholds for each monitoring indicator. The four levels of warning thresholds are blue warning threshold, yellow warning threshold, orange warning threshold and red warning threshold. The monitoring data is compared with the corresponding warning threshold in real time. When the monitoring data exceeds the corresponding warning threshold, the corresponding level of warning is immediately activated.

8. The method for early warning of structural safety in municipal, water conservancy, and transportation engineering projects according to claim 6, characterized in that: The trend early warning method uses a time series analysis algorithm to fit and analyze historical and real-time monitoring data to predict the trend of changes in monitoring indicators. For slowly changing indicators, a linear regression model is used to predict the trajectory of data changes, and for abruptly changing indicators, a sliding window algorithm is used to capture abnormal fluctuations in data. If the predicted value is close to or exceeds the early warning threshold, an early warning information is issued in advance.

9. The method for early warning of structural safety in municipal, water conservancy, and transportation engineering projects according to claim 6, characterized in that: The intelligent diagnosis and early warning method introduces machine learning algorithms to construct an engineering structure safety diagnosis model, including random forest algorithm and neural network algorithm; the diagnosis model is optimized by training a large amount of historical hidden danger data, including data on the correlation between bridge crack expansion and collapse, and data on the correlation between abnormal seepage and piping in dams; the diagnosis model realizes multi-indicator linkage diagnosis, and the risk level is determined and the early warning level is adjusted according to the linkage of indicators.

10. The method for early warning of structural safety in municipal, water conservancy, and transportation engineering projects according to claim 6, characterized in that: The early warning information is simultaneously pushed to the management personnel through three methods: SMS, platform pop-up window, and audible and visual alarm. After the hidden danger is dealt with, the management personnel enter the handling results into the system. The system updates the corresponding engineering structure operation data file, continuously optimizes the early warning model parameters, and improves the accuracy of subsequent early warnings.

Images