A monitoring and early warning method and system for highway traffic protection facilities

Abstract

The application relates to the technical field of monitoring of protective facilities, in particular to a monitoring and early warning method and system for highway traffic protective facilities, which comprises the following steps: collecting running state data of different node positions of the highway traffic protective facilities in real time, pre-processing the running state data to obtain to-be-analyzed data, analyzing the to-be-analyzed data to obtain damage prediction values corresponding to the different node positions of the highway traffic protective facilities, performing safety evaluation on the highway traffic protective facilities according to the node positions and the damage prediction values, and determining whether to perform early warning on the node positions of the highway traffic protective facilities according to the safety evaluation result; if early warning is needed on the node positions of the highway traffic protective facilities, early warning signals are generated according to the node positions and the safety evaluation result, and the early warning signals are sent to target terminals. The application improves the accuracy of monitoring and early warning of the highway traffic protective facilities.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of monitoring of protective facilities, and in particular to a monitoring and early warning method and system for highway traffic protective facilities. BACKGROUND

[0002] Highway traffic, as an important infrastructure in modern society, carries a large amount of passenger and freight transportation tasks, and its safety and stability are directly related to the safety of the lives and property of the general public. However, due to the complexity and variability of the highway traffic environment, various natural disasters and human factors can cause damage to highway traffic protective facilities, thereby affecting the normal traffic and driving safety of the highway. Therefore, it is particularly important to develop an efficient and accurate monitoring and early warning method to monitor the state of highway traffic protective facilities in real time and to provide early warning of potential safety hazards.

[0003] Currently, the monitoring method of highway traffic protective facilities mainly relies on manual inspection and regular detection. These methods are not only inefficient, but also difficult to achieve real-time monitoring and early warning of highway traffic protective facilities. In addition, due to the complexity and variability of the highway traffic environment, the current monitoring method often fails to accurately capture the small changes in the state of the facilities, thereby failing to provide timely early warning of potential safety hazards. SUMMARY

[0004] In order to solve at least one of the above technical problems, the present application provides a monitoring and early warning method and system for highway traffic protective facilities.

[0005] In a first aspect, the present application provides a monitoring and early warning method for highway traffic protective facilities, which adopts the following technical solution:

[0006] Real-time collection of operation state data of different node positions of the highway traffic protective facilities;

[0007] Data preprocessing of the operation state data to obtain analysis data;

[0008] Data analysis of the analysis data to obtain damage prediction values corresponding to different node positions of the highway traffic protective facilities;

[0009] Safety evaluation of the highway traffic protective facilities according to the node positions and damage prediction values, and determination of whether to provide early warning for the node positions of the highway traffic protective facilities according to the safety evaluation results;

[0010] If early warning is needed for the node positions of the highway traffic protective facilities, an early warning signal is generated according to the node positions and safety evaluation results, and the early warning signal is sent to a target terminal.

[0011] By adopting the technical scheme, the running state data of different node positions of the highway traffic protection facility is collected in real time, so that the timeliness and accuracy of the data are ensured. The subsequent data preprocessing is provided with a solid foundation, so that the state monitoring of the highway traffic protection facility is more comprehensive and meticulous. The to-be-analyzed data obtained after the data preprocessing removes noise and redundancy, and improves the efficiency and accuracy of data analysis. In-depth data analysis on the to-be-analyzed data can accurately calculate the damage prediction value of different node positions of the highway traffic protection facility. The internal law of the data is effectively utilized, and a scientific basis is provided for safety evaluation. According to the safety evaluation based on the node position and the damage prediction value, the safety condition of the facility can be accurately reflected, and strong support is provided for early warning decision. On the basis of safety evaluation, it is determined whether to early warn the node position of the highway traffic protection facility according to the evaluation result. Not only unnecessary resource waste is avoided, but also the timeliness and pertinence of early warning are ensured. If early warning is needed, the early warning signal generated according to the node position and the safety evaluation result can be quickly conveyed to the target terminal, and timely warning information is provided for relevant personnel, so that potential safety hazards are effectively prevented, and the monitoring and early warning efficiency of the highway traffic protection facility is improved.

[0012] In a possible implementation manner, the data preprocessing on the running state data to obtain to-be-analyzed data comprises:

[0013] The running state data is decomposed into data modal components with different frequencies based on a preset modal number;

[0014] The data modal components are subjected to noise elimination processing, and the eliminated data modal components are superimposed to obtain the to-be-analyzed data.

[0015] By adopting the technical scheme, the running state data is decomposed into data modal components with different frequencies based on a preset modal number when the data preprocessing is performed on the running state data. Thus, the complex running state data can be effectively divided according to frequency characteristics, so that the subsequent processing is more targeted. Then, the decomposed data modal components are subjected to noise elimination processing, so that the interference information in the data can be significantly reduced, and the purity of the data is improved. Finally, the data modal components after noise elimination are superimposed to obtain the to-be-analyzed data, which makes the data more concentrated and reflects the essential characteristics of the running state, and provides a more accurate data basis for subsequent analysis.

[0016] In a possible implementation manner, the data analysis on the to-be-analyzed data to obtain the damage prediction value corresponding to different node positions of the highway traffic protection facility comprises:

[0017] The to-be-analyzed data is subjected to time series transformation analysis to obtain time series analysis data;

[0018] collecting environmental data around the highway traffic protection facilities, and constructing a three-dimensional environmental feature map of the highway traffic protection facilities in different time periods based on the environmental data;

[0019] determining a first damage prediction value corresponding to different node positions of the highway traffic protection facilities according to the time series analysis data and the three-dimensional environmental feature map;

[0020] performing cluster analysis on the to-be-analyzed data to obtain irregular items, regular items, and regular development item data of the to-be-analyzed data;

[0021] performing prediction and deduction processing on the irregular items, the regular items, and the regular development item data to obtain a second damage prediction value;

[0022] superimposing and calculating the first damage prediction value and the second damage prediction value to obtain a damage prediction value corresponding to different node positions of the highway traffic protection facilities.

[0023] By using the above technical solution, time series transformation analysis is performed on the to-be-analyzed data, which can effectively capture the trend of the running state of the highway traffic protection facilities changing with time. This step not only reveals the time correlation of the data, but also provides a time sequence basis for subsequent analysis. The three-dimensional environmental feature map constructed in combination with the collected surrounding environmental data can intuitively reflect the actual running environment of the highway traffic protection facilities in different time periods, thereby enhancing the environmental adaptability of the damage prediction. In combination with the above, the determined first damage prediction value is closer to the actual situation, and the accuracy and reliability of the prediction are improved. Cluster analysis is performed on the to-be-analyzed data, which can deeply mine the internal rules and patterns in the data. Cluster analysis divides the to-be-analyzed data into irregular items, regular items, and regular development items. This classification not only simplifies the data structure, but also provides a clear data framework for subsequent prediction and deduction. Prediction and deduction processing is performed on the three types of data to obtain a second damage prediction value that fully considers the diversity and complexity of the data, further improving the accuracy and comprehensiveness of the prediction. Finally, the first damage prediction value and the second damage prediction value are superimposed and calculated, the advantages of the two are combined, and the obtained damage prediction value is more accurate and comprehensive, providing strong data support for the maintenance and management of the highway traffic protection facilities.

[0024] In a possible implementation manner, the determination of the first damage prediction value corresponding to different node positions of the highway traffic protection facilities according to the time series analysis data and the three-dimensional environmental feature map includes:

[0025] obtaining facility damage information and damage environment information corresponding to the facility damage information in a historical time period, and determining facility damage positions and damage time sequence data of each same damage type according to the facility damage information, the damage time sequence data being damage development data of the facility damage positions within a preset time period before and after the damage occurs;

[0026] determining damage environment data corresponding to the facility damage positions according to the damage environment information;

[0027] performing matrix correlation between the damage environment data and the damage development data to obtain a damage environment development matrix;

[0028] determining node environment data corresponding to different node positions of the highway traffic protection facility according to the three-dimensional environment feature map;

[0029] determining state change data of the different node positions of the highway traffic protection facility within a certain time period according to the time sequence analysis data;

[0030] performing screening on the damage environment development matrix according to the state change data and the node environment data to determine whether there is a matching data segment matching the state change data and the node environment data, and if there is, determining a first damage prediction value corresponding to the different node positions of the highway traffic protection facility according to the matching data segment.

[0031] By adopting the above technical solution, firstly, the facility damage information and the corresponding damage environment information in a historical time period are obtained, which provides a rich historical data basis for subsequent damage prediction. By determining the facility damage positions and the damage time sequence data of each same damage type, the development trajectory of the facility damage can be clearly depicted. Meanwhile, the damage environment data is determined in combination with the damage environment information, the damage environment and the damage development are correlated in matrix, and the damage environment development matrix is formed, which reveals the complex relationship between the damage and the environment. This processing process not only enhances the correlation between the data, but also provides a more detailed data model for subsequent prediction. The node environment data of the different node positions of the highway traffic protection facility is determined according to the three-dimensional environment feature map, so that the prediction process can fully consider the specific environment of the facility, and the environmental adaptability of the prediction is improved. Meanwhile, the state change data is determined in combination with the time sequence analysis data, and the damage environment development matrix is screened, which not only simplifies the complexity of data processing, but also quickly locates the historical data segment matching the current facility state. If there is a matching data segment, the first damage prediction value determined according to these data segments will be closer to the actual situation, and the prediction result will be more accurate and reliable, which provides strong data support for the maintenance and management of the highway traffic protection facility.

[0032] In a possible implementation manner, the prediction and deduction processing on the irregular item, the regular item and the regular development item data obtains a second damage prediction value, and the prediction and deduction processing includes:

[0033] determining the highest parameter value and the lowest parameter value corresponding to the irregular item in the to-be-analyzed data;

[0034] performing time sequence-free arrangement on the regular item and the regular development item data to obtain a regular item data matrix;

[0035] inputting the regular item data matrix into a trained vector extraction model to perform vector feature extraction to obtain a regular item dimension, and performing data combination processing on the obtained regular item dimension, the highest parameter value, the lowest parameter value and the regular data matrix to generate a comprehensive data matrix;

[0036] performing data processing on the data contained in the comprehensive data matrix to obtain comprehensive development data;

[0037] inputting the obtained comprehensive development data into a preset algorithm model to perform data calculation to obtain future development data;

[0038] inputting the future development data into a trained damage model to perform training to obtain a second damage prediction value.

[0039] By adopting the technical solution, the highest parameter value and the lowest parameter value of the irregular item in the to-be-analyzed data are determined, which provides a key boundary condition for subsequent data processing and helps to more accurately grasp the fluctuation range of the data. Then, the regular item and the regular development item data are subjected to time sequence-free arrangement to form a regular item data matrix, which lays a foundation for subsequent vector feature extraction. This series of steps effectively integrates the effective information in the data and provides data support for subsequent prediction. The regular item data matrix is input into a trained vector extraction model to efficiently extract the vector features of the data to form a regular item dimension. This step reduces the dimension of the high-dimensional data, which is convenient for subsequent processing. Meanwhile, the extracted regular item dimension is combined with the highest parameter value, the lowest parameter value and the regular data matrix to generate a comprehensive data matrix, which further enriches the dimension and depth of the data and improves the accuracy of data prediction. The data in the comprehensive data matrix is subjected to data processing to obtain comprehensive development data, which mines the potential law of the data and provides a reliable basis for future data prediction. Subsequently, the comprehensive development data is input into a preset algorithm model to perform data calculation to obtain future development data, which reasonably predicts the future trend based on historical data. Finally, the future development data is input into a trained damage model to perform training to obtain a second damage prediction value, which realizes accurate prediction of the damage condition and provides strong support for subsequent repair and maintenance.

[0040] In a possible implementation, the generating a warning signal according to the node position and the safety evaluation result and sending the warning signal to the target terminal comprises:

[0041] scoring the damage prediction value to obtain a facility hazard score;

[0042] determining whether the facility hazard score is greater than a preset hazard score, and if so, generating a maintenance cycle frequency and a maintenance item according to the damage prediction value, and sending the facility hazard score, the maintenance cycle frequency and the maintenance item to the target device.

[0043] By adopting the above technical solution, the warning signal is accurately generated according to the node position and the safety evaluation result, ensuring the timeliness and pertinence of the warning. Then, the warning signal is rapidly sent to the target terminal, so that the relevant personnel can obtain the warning information in the first time, thereby gaining valuable time for subsequent processing measures. This series of operations not only improves the efficiency of the warning, but also enhances the practicability of the warning, thereby providing a strong guarantee for the safe operation of the facility. After the warning signal is sent, the damage prediction value is further scored to obtain a facility hazard score. The damage degree caused by the damage is quantitatively evaluated, thereby providing a scientific basis for subsequent maintenance decision-making. At the same time, by determining whether the facility hazard score is greater than a preset hazard score, the facility that needs to be focused on can be intelligently identified, thereby avoiding the waste of resources and misjudgment. This process not only improves the pertinence of the maintenance, but also optimizes the allocation of maintenance resources. In the case that the facility hazard score is greater than the preset hazard score, the maintenance cycle frequency and the maintenance item are automatically generated according to the damage prediction value. The intelligent formulation of the maintenance plan is realized, thereby avoiding the interference of human factors and improving the accuracy and efficiency of the maintenance. At the same time, the facility hazard score, the maintenance cycle frequency and the maintenance item are sent to the target device, so that the relevant personnel can comprehensively understand the current state and maintenance demand of the facility, thereby providing comprehensive guidance for subsequent maintenance work. Not only the scientificity and standardization of the maintenance work are improved, but also a solid foundation is laid for the long-term safe operation of the facility.

[0044] In a possible implementation, the method further comprises:

[0045] determining facility materials, facility construction parameters, facility environments and facility deformation states of different node positions of the highway traffic protection facility according to the operation state data;

[0046] The facility material, facility building parameter, facility environment and facility deformation state are data-fused by the digital twinning technology, a digital model of the highway traffic protection facility is constructed, and the digital model of the highway traffic protection facility is sent to the target terminal.

[0047] By adopting the above technical scheme, the facility material, facility building parameter, facility environment and facility deformation state of different node positions of the highway traffic protection facility are comprehensively and accurately determined according to the operation state data. This step provides detailed and reliable basic data for subsequent data fusion processing, and ensures the accuracy of the digital model. By comprehensively considering these key factors, the actual operation state of the facility can be more comprehensively reflected, and strong data support is provided for the maintenance and management of the facility. The facility material, facility building parameter, facility environment and facility deformation state are data-fused by the digital twinning technology, and a digital model of the highway traffic protection facility is constructed. Through highly integrated data processing technology, real-time simulation and accurate prediction of the operation state of the facility are realized. The digital model not only visually displays the structure and state of the facility, but also has strong data analysis and prediction capabilities, providing a scientific basis for maintenance decisions of the facility. The constructed digital model of the facility is sent to the target terminal. This step realizes the rapid transmission and sharing of information, so that relevant personnel can obtain the latest state information of the facility at any time and anywhere. At the same time, the target terminal can further analyze and process the data provided by the digital model, providing more comprehensive support for the maintenance and management of the facility. The implementation of this process not only improves the utilization rate of information, but also enhances the maintenance efficiency and management level of the facility.

[0048] In a second aspect, the application provides a monitoring and early warning system for a highway traffic protection facility, which adopts the following technical scheme:

[0049] A monitoring and early warning system for a highway traffic protection facility, comprising:

[0050] A data acquisition module for acquiring real-time operation state data of different node positions of a highway traffic protection facility;

[0051] A data processing module for data preprocessing of the operation state data to obtain analysis data;

[0052] A data analysis module for data analysis of the analysis data to obtain a damage prediction value corresponding to different node positions of the highway traffic protection facility;

[0053] A safety evaluation module for safety evaluation of the highway traffic protection facility according to the node position and damage prediction value, and determining whether to issue a warning for the node position of the highway traffic protection facility according to the safety evaluation result.

[0054] A facility early warning module is configured to generate an early warning signal based on the node position of the highway traffic protection facility and the safety evaluation result when early warning is needed for the node position of the highway traffic protection facility, and send the early warning signal to a target terminal.

[0055] In a possible implementation, when the data processing module performs data preprocessing on the running state data to obtain the to-be-analyzed data, the data processing module is specifically configured to:

[0056] decompose the running state data into data modal components with different frequencies based on a preset modal number;

[0057] perform noise elimination processing on the data modal components, and superimpose the data modal components after elimination to obtain the to-be-analyzed data.

[0058] In another possible implementation, when the data analysis module performs data analysis on the to-be-analyzed data to obtain the damage prediction value corresponding to different node positions of the highway traffic protection facility, the data analysis module is specifically configured to:

[0059] perform time series transformation analysis on the to-be-analyzed data to obtain time series analysis data;

[0060] collect environmental data around the highway traffic protection facility, and construct a three-dimensional environmental feature map of the highway traffic protection facility in different time periods based on the environmental data;

[0061] determine a first damage prediction value corresponding to different node positions of the highway traffic protection facility according to the time series analysis data and the three-dimensional environmental feature map;

[0062] perform clustering analysis on the to-be-analyzed data to obtain irregular items, regular items, and regular development item data of the to-be-analyzed data;

[0063] perform prediction and deduction processing on the irregular items, the regular items, and the regular development item data to obtain a second damage prediction value;

[0064] superimpose and calculate the first damage prediction value and the second damage prediction value to obtain the damage prediction value corresponding to different node positions of the highway traffic protection facility.

[0065] In another possible implementation, when the data analysis module determines a first damage prediction value corresponding to different node positions of the highway traffic protection facility according to the time series analysis data and the three-dimensional environmental feature map, the data analysis module is specifically configured to:

[0066] obtaining facility damage information in a historical time period and damage environment information corresponding to the facility damage information, and determining, according to the facility damage information, a facility damage position of each same damage type and damage time sequence data of the facility damage position in a preset time period before and after the damage;

[0067] determining damage environment data corresponding to the facility damage position according to the damage environment information;

[0068] performing matrix correlation between the damage environment data and the damage development data to obtain a damage environment development matrix;

[0069] determining node environment data corresponding to different node positions of the highway traffic protection facility according to the three-dimensional environment feature map;

[0070] determining state change data of the different node positions of the highway traffic protection facility in a certain time period according to the time sequence analysis data;

[0071] performing screening on the damage environment development matrix according to the state change data and the node environment data to determine whether there is matching data segment matched with the state change data and the node environment data, and if there is, determining a first damage prediction value corresponding to the different node positions of the highway traffic protection facility according to the matching data segment.

[0072] In another possible implementation, when the data analysis module performs prediction and deduction processing on the irregular item, the regular item and the regular development item data to obtain a second damage prediction value, the data analysis module is specifically configured to:

[0073] determine a highest parameter value and a lowest parameter value corresponding to the irregular item in the to-be-analyzed data;

[0074] perform time sequence-free arrangement on the regular item and the regular development item data to obtain a regular item data matrix;

[0075] input the regular item data matrix into a trained vector extraction model to perform vector feature extraction, obtain a regular item dimension, and perform data combination processing on the obtained regular item dimension, the highest parameter value, the lowest parameter value and the regular data matrix to generate a comprehensive data matrix;

[0076] perform data processing on data contained in the comprehensive data matrix to obtain comprehensive development data;

[0077] input the obtained comprehensive development data into a preset algorithm model to perform data calculation to obtain future development data;

[0078] The future development data is input into the trained damage model for training to obtain a second damage prediction value.

[0079] In another possible implementation, the system further includes a hazard evaluation module and a hazard judgment module, wherein,

[0080] The hazard evaluation module is configured to perform hazard degree scoring on the damage prediction value to obtain a facility hazard score.

[0081] The hazard judgment module is configured to judge whether the facility hazard score is greater than a preset hazard score, and if so, generate a maintenance cycle frequency and a maintenance item according to the damage prediction value, and send the facility hazard score, the maintenance cycle frequency and the maintenance item to the target device.

[0082] In another possible implementation, the system further includes a determination module and a model construction module, wherein,

[0083] The determination module is configured to determine facility materials, facility construction parameters, a facility environment and a facility deformation state of different node positions of the highway traffic protection facility according to the operation state data.

[0084] The model construction module is configured to perform data fusion processing on the facility materials, the facility construction parameters, the facility environment and the facility deformation state by using a digital twinning technology, construct a facility digital model corresponding to the highway traffic protection facility, and send the facility digital model to the target terminal.

[0085] In a third aspect, the present application provides an electronic device, which adopts the technical scheme as follows:

[0086] at least one processor;

[0087] a memory;

[0088] at least one application program, wherein the at least one application program is stored in the memory and configured to be executed by the at least one processor, and the at least one application program is configured to execute the method for monitoring and early warning of the highway traffic protection facility according to any one of the first aspect.

[0089] In a fourth aspect, the present application provides a computer readable storage medium, which adopts the technical scheme as follows:

[0090] A computer readable storage medium, which stores a computer program, and when the computer program is executed in a computer, the computer is caused to execute the method for monitoring and early warning of the highway traffic protection facility according to any one of the first aspect.

[0091] In summary, the present application includes at least one of the following beneficial technical effects:

[0092] By adopting the above technical solution, the running state data of different node positions of the highway traffic protection facility is collected in real time, which can ensure the timeliness and accuracy of the data. It provides a solid foundation for subsequent data preprocessing, making the state monitoring of the highway traffic protection facility more comprehensive and meticulous. The data obtained after data preprocessing is to be analyzed, which removes noise and redundancy, improves the efficiency and accuracy of data analysis. In-depth data analysis of the data to be analyzed can accurately calculate the damage prediction value of different node positions of the highway traffic protection facility. The internal law of the data is effectively utilized, and a scientific basis is provided for safety evaluation. According to the safety evaluation of the node position and the damage prediction value, the safety condition of the facility can be accurately reflected, and strong support is provided for early warning decision. On the basis of safety evaluation, it is determined whether to give early warning to the node position of the highway traffic protection facility according to the evaluation result. It not only avoids unnecessary waste of resources, but also ensures the timeliness and pertinence of early warning. If early warning is needed, the early warning signal generated according to the node position and the safety evaluation result can be quickly transmitted to the target terminal, providing timely warning information for relevant personnel, thereby effectively preventing potential safety hazards and improving the monitoring and early warning efficiency of the highway traffic protection facility. BRIEF DESCRIPTION OF DRAWINGS

[0093] Figure 1 A flowchart of a monitoring and early warning method for a highway traffic protection facility is provided for the embodiments of the present application.

[0094] Figure 2 A structural diagram of a monitoring and early warning system for a highway traffic protection facility is provided for the embodiments of the present application.

[0095] Figure 3 A structural diagram of an electronic device is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0096] The following will be described in detail in combination with the accompanying Figures 1-3 The present application will be further described in detail.

[0097] The present embodiment is only an explanation of the present application, and is not a limitation of the present application. Those skilled in the art can make modifications to the present embodiment without creative contribution after reading the present specification, but as long as it is within the scope of the present application, it is protected by the patent law.

[0098] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0099] In addition, the term "and / or" in the present application is only used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in the present application generally represents an "or" relationship between the associated objects unless otherwise specified.

[0100] The embodiments of the present application will be described in further detail below with reference to the drawings of the specification.

[0101] The embodiments of the present application provide a method for monitoring and early warning of highway traffic protection facilities, which is executed by an electronic device. The electronic device can be an independent physical electronic device, an electronic device cluster or a distributed system composed of multiple physical electronic devices, or a cloud electronic device providing cloud computing services. The embodiments of the present application do not make any limitation here, for example, as shown in the figure, the method comprises: Figure 1

[0102] Step S10, real-time collection of operation state data of different node positions of highway traffic protection facilities.

[0103] Specifically, real-time collection means collecting immediately at the same time when data is generated, without delay or lag, to ensure the timeliness and accuracy of data. Highway traffic protection facilities refer to various facilities set to protect highway traffic safety, including but not limited to guardrails, crash cushions, signboards, reflectors, and isolation fences, etc., which together constitute the safety protection system of highways. Different node positions are used to represent specific position points on or around highway traffic protection facilities, which differ due to different types of facilities, functions or safety requirements. Operation state data refers to data reflecting the current working state or performance of highway traffic protection facilities, including information such as integrity, damage degree, reflection effect, anti-collision ability, and environmental parameters of the facilities.

[0104] ​In the embodiments of the present application, sensor technology and unmanned aerial vehicle inspection technology are adopted. First, sensors such as vibration sensors, pressure sensors, optical sensors, etc. are installed at key node positions to monitor the stress conditions and reflection effects of the facilities; second, the data collected by the sensors are transmitted to the data center through wired or wireless means, and the data center processes and analyzes the data to generate a report on the operating status of the facilities. Then the flight route of the unmanned aerial vehicle is planned to ensure that all key node positions are covered, and the unmanned aerial vehicle is equipped with high-definition cameras, infrared thermal imagers and other equipment to take pictures and videos of the facilities; finally, the collected images and videos are processed by image recognition technology and data analysis software to identify damage and abnormal conditions of the facilities.

[0105] Step S11, data preprocessing is performed on the operating status data to obtain the to-be-analyzed data.

[0106] Specifically, the operating status data is decomposed into data modal components with different frequencies based on a preset modal number. The data modal components are subjected to noise removal processing, and the removed data modal components are superimposed to obtain the to-be-analyzed data.

[0107] Specifically, the preset modal number represents a value preset according to actual requirements or experience before data decomposition, which determines how many data modal components with different frequencies the data is decomposed into. The setting of this value is usually related to the characteristics of the data, the purpose of analysis, and the requirements of subsequent processing. The data modal component refers to each component obtained by decomposing the operating status data according to the frequency characteristics, each component representing a specific frequency range and reflecting the characteristics of the data in that frequency range. Noise removal processing refers to removing unwanted noise components that interfere with analysis from the data modal components to improve the accuracy and reliability of the data. Noise is caused by errors in the data collection process, environmental interference, etc. For example, if the operating status data contains a high-frequency noise component, the high-frequency noise component needs to be removed from the data in the noise removal processing to avoid interference with subsequent analysis.

[0108] In the embodiments of the present application, the wavelet transform method is adopted. According to the preset modal number, a suitable wavelet basis function and decomposition level are selected, and then the operating status data is subjected to wavelet transform to obtain data modal components with different frequencies. Then, each data modal component is subjected to noise removal processing, including but not limited to threshold method, soft threshold method or hard threshold method to remove noise. Finally, the data modal components after noise removal are reconstructed or superimposed to obtain the to-be-analyzed data.

[0109] Step S12, data analysis is performed on the to-be-analyzed data to obtain the damage prediction value corresponding to different node positions of the highway traffic protection facilities.

[0110] Specifically, time series transformation analysis is performed on the data to be analyzed to obtain time series analysis data, environmental data around the highway traffic protection facility is collected, and a three-dimensional environmental feature map of the highway traffic protection facility in different time periods is constructed based on the environmental data. According to the time series analysis data and the three-dimensional environmental feature map, a first damage prediction value corresponding to different node positions of the highway traffic protection facility is determined. The data to be analyzed is subjected to cluster analysis to obtain irregular items, regular items and regular development item data of the data to be analyzed. The irregular items, regular items and regular development item data are subjected to prediction and deduction processing to obtain a second damage prediction value. The first damage prediction value and the second damage prediction value are superimposed and calculated to obtain a damage prediction value corresponding to different node positions of the highway traffic protection facility.

[0111] In the embodiments of the present application, the time series analysis data is the converted feature data, for example, a frequency spectrum diagram of the vibration frequency of a certain bridge guardrail. The environmental data is used to represent dynamic information such as the meteorological conditions (temperature and humidity, wind speed) around the facility, traffic flow (vehicle density, vehicle type distribution), etc. The three-dimensional environmental feature map refers to a dynamic three-dimensional model constructed based on multi-source environmental data (such as laser radar point cloud, meteorological sensor data), which can intuitively display the space-time changes around the facility, for example, a three-dimensional thermal map of the water depth around a certain guardrail on a road section in heavy rain. The first damage prediction value is a node-level prediction result obtained by associating the time series analysis with the environmental features, for example, a fatigue damage prediction value of a certain guardrail column caused by long-term vibration. Cluster analysis refers to grouping data according to similarity, for example, grouping traffic flow data into three categories: peak, flat and trough. The irregular item represents abnormal data that cannot be fitted by a common model, such as instantaneous impact force data caused by sudden traffic accidents. The regular item and the regular development item refer to stable periodic data (such as diurnal temperature difference cycles) and trend data (such as material aging cumulative effects), respectively. The second damage prediction value is a weighted prediction result of abnormal, periodic and trend items based on the clustering results, for example, a comprehensive damage value obtained by combining the sudden event and long-term aging.

[0112] Specifically, the execution process is as follows:

[0113] Time series analysis stage: After denoising preprocessing of the original monitoring data (such as vibration, strain), time-frequency features are extracted by short-time Fourier transform to generate a frequency spectrum diagram containing main frequency components as time series analysis data.

[0114] Environment modeling stage: Synchronize the collection of temperature and humidity, wind speed, traffic flow and other environmental parameters, and use BIM model and real-time sensor data fusion to construct a three-dimensional environmental feature map with space-time labels (such as an hourly updated thermal-force coupled model).

[0115] First prediction calculation: input the time series features and the corresponding period's mechanical parameters (such as wind load) in the environmental model into the regression model to calculate the initial damage index of each node (such as the connection of the guardrail).

[0116] Data clustering stage: use DBSCAN algorithm to perform density clustering on the preprocessed data to be analyzed, and separate three types of data subsets: sudden impact (irregular items), periodic fluctuations (regular items), and linear degradation (regular development items).

[0117] Second prediction calculation: use LSTM network (handle time series dependence), ARIMA model (predict periodicity), and linear regression (fit degradation trend) to predict the three types of subsets, and obtain the second damage prediction value after weighting.

[0118] Result fusion: fuse the first prediction value driven by the physical model and the prediction value driven by the data through Bayesian estimation to generate the final node-level damage probability distribution map.

[0119] Step S13, according to the node position and the damage prediction value, safety evaluation is performed on the highway traffic protection facilities, and according to the safety evaluation result, it is judged whether to give a warning to the node position of the highway traffic protection facilities.

[0120] Specifically, the node position represents the key structural connection point or stress-sensitive area of the traffic protection facility, such as the column and beam welding of the bridge guardrail, the anchor point of the slope protection net. The damage prediction value is the damage probability quantitative value calculated by the time series analysis and data clustering method in the foregoing, the value range is usually 0 (no risk) to 1 (complete failure), for example, the prediction value of a certain guardrail node is 0.75, indicating that the failure probability is 75%. Safety evaluation refers to the comprehensive judgment process of the facility state based on the prediction value, design specification and safety threshold, for example, comparing the prediction value with the international bridge maintenance standard. Warning is used to represent the behavior of triggering risk prompt, which is divided into level (such as yellow / orange / red warning) and form (sound and light alarm, SMS notification, etc.), for example, when the prediction value of three consecutive nodes exceeds 0.8, a red warning is triggered. The judgment refers to the logical decision of whether to start the warning according to the evaluation result, which needs to consider the importance of the facility, traffic flow and other context factors, for example, the guardrail of the highway hub interchange adopts a more stringent judgment threshold.

[0121] For the embodiments of the present application, the data association stage: bind the damage prediction value with the facility node coordinates in the GIS system to generate a risk heat map with geographical labels, for example, mark the prediction values of 10 guardrail nodes at a tunnel entrance on the corresponding position of the three-dimensional map.

[0122] Threshold setting stage: set three-level warning thresholds according to industry standards (such as "Highway Bridge Technical Condition Evaluation Standard"):

[0123] Green (prediction value <0.3): Normal state, no intervention needed

[0124] Yellow (0.3≤ prediction value <0.7): Low risk, included in regular inspection list

[0125] Red (prediction value ≥0.7): High risk, trigger immediate warning

[0126] Multi-factor evaluation stage: Introduce environmental weight coefficient (such as reducing anchor warning threshold by 20% under heavy rain) and traffic impact coefficient (such as increasing guardrail warning priority by 50% during peak hours), dynamically adjust the decision criteria.

[0127] Decision execution stage:

[0128] For red warning nodes, start emergency plan: Call unmanned aerial vehicle inspection system to obtain real-time images, dispatch maintenance team for on-site verification.

[0129] For yellow warning nodes, generate maintenance work order: Include in the next quarter's maintenance plan, and give priority to non-destructive testing.

[0130] For green nodes, maintain regular monitoring: Extend data sampling interval to 2 hours per time.

[0131] Step S14, if it is necessary to warn the node position of the highway traffic protection facility, a warning signal is generated according to the node position and the safety evaluation result, and the warning signal is sent to the target terminal.

[0132] In the embodiments of the present application, the target terminal is a terminal device applied by maintenance personnel, including but not limited to mobile phones, tablets and other terminal devices.

[0133] The embodiment of the application provides a monitoring and early warning method for highway traffic protection facilities, which can collect the running state data of different node positions of the highway traffic protection facilities in real time, and can ensure the timeliness and accuracy of the data. The method provides a solid foundation for subsequent data preprocessing, so that the state monitoring of the highway traffic protection facilities is more comprehensive and detailed. The to-be-analyzed data obtained after data preprocessing removes noise and redundancy, and improves the efficiency and accuracy of data analysis. In-depth data analysis on the to-be-analyzed data can accurately calculate the damage prediction value of different node positions of the highway traffic protection facilities. The method effectively utilizes the internal law of data and provides a scientific basis for safety evaluation. The safety evaluation according to the node position and the damage prediction value can accurately reflect the safety condition of the facilities and provide strong support for early warning decision. On the basis of safety evaluation, whether the node position of the highway traffic protection facilities needs to be warned is determined according to the evaluation result. The method not only avoids unnecessary waste of resources, but also ensures the timeliness and pertinence of the warning. If the warning is needed, the warning signal generated according to the node position and the safety evaluation result can be quickly conveyed to the target terminal, so as to provide timely warning information for relevant personnel, thereby effectively preventing potential safety hazards and improving the monitoring and early warning efficiency of the highway traffic protection facilities.

[0134] Further, the first damage prediction value corresponding to different node positions of the highway traffic protection facilities is determined according to the time sequence analysis data and the three-dimensional environment feature map, including: obtaining facility damage information and damage environment information corresponding to the facility damage information in a historical time period, and determining the facility damage position and damage time sequence data of each same damage type according to the facility damage information, the damage time sequence data being damage development data of the facility damage position in a preset time period before and after the damage. The damage environment data corresponding to the facility damage position is determined according to the damage environment information, the damage environment data is associated with the damage development data in a matrix to obtain a damage environment development matrix, the node environment data corresponding to different node positions of the highway traffic protection facilities is determined according to the three-dimensional environment feature map, and the state change data of the different node positions of the highway traffic protection facilities in a certain time period is determined according to the time sequence analysis data. The damage environment development matrix is screened according to the state change data and the node environment data to determine whether there is matching data segment matched with the state change data and the node environment data, and if there is, the first damage prediction value corresponding to different node positions of the highway traffic protection facilities is determined according to the matching data segment.

[0135] Further, the irregular item, the regular item and the regular development item data are predicted and deduced to obtain a second damage prediction value, including: determining the highest parameter value and the lowest parameter value corresponding to the irregular item in the to-be-analyzed data, performing time sequence-free arrangement on the regular item and the regular development item data to obtain a regular item data matrix. The regular item data matrix is input into a trained vector extraction model to perform vector feature extraction to obtain a regular item dimension, and the obtained regular item dimension, the highest parameter value, the lowest parameter value and the regular data matrix are combined to generate a comprehensive data matrix. The data contained in the comprehensive data matrix is processed to obtain comprehensive development data. The obtained comprehensive development data is input into a preset algorithm model to perform data calculation to obtain future development data. The future development data is input into a trained damage model to obtain the second damage prediction value.

[0136] In the embodiments of the present application, the highest / lowest parameter value is used to represent the extreme value of the irregular item in a certain dimension, for example, the maximum displacement of a certain sensor in an abnormal period is 15 mm and the minimum temperature is -20℃. The regular item refers to a data subset that conforms to periodic or trend characteristics, such as the bimodal distribution pattern of daily traffic flow. The regular development item data represents a derived index of the evolution of the regular item over time, such as the correlation data between the weekly average traffic flow and the quarterly GDP growth rate. Time sequence-free arrangement refers to a data reconstruction operation that eliminates the dependence on time stamp. The regular item data matrix represents a multi-dimensional data structure after arrangement, with rows representing characteristic dimensions (such as temperature, humidity, traffic flow) and columns representing observation samples, for example, a matrix with a shape of [5x1000]. The vector extraction model is a neural network module for automatic feature learning, such as a Transformer-based encoder. The regular item dimension represents a low-dimensional representation vector output by the model, for example, compressing 50-dimensional original features into a 10-dimensional semantic vector. The comprehensive data matrix is a mathematical representation of multi-dimensional information, such as an enhanced tensor formed by splicing the extreme value parameters and the model output. Data processing includes normalization, noise reduction, missing value filling and other operations, for example, using Min-Max standardization on temperature data. The preset algorithm model refers to a pre-defined mathematical operation framework, such as an ARIMA time series prediction model or an LSTM neural network. The future development data represents the prediction value of the future period output by the model, for example, a traffic flow prediction curve for the next 12 months. The damage model is a machine learning model for evaluating structural damage, such as a random forest classifier. The second damage prediction value represents the updated prediction result after combining multiple source data, and the value range is usually 0 (no damage) to 1 (complete failure).

[0137] Further, the early warning signal is generated according to the node position and the safety evaluation result, and the early warning signal is sent to the target terminal. After that, it further includes: scoring the damage prediction value to obtain a facility hazard score. It is judged whether the facility hazard score is greater than a preset hazard score. If it is greater, the maintenance cycle frequency and the maintenance project are generated according to the damage prediction value, and the facility hazard score, the maintenance cycle frequency and the maintenance project are sent to the target device.

[0138] Further, the facility material, the facility building parameter, the facility environment and the facility deformation state of different node positions of the highway traffic protection facility are determined according to the running state data. The facility material, the facility building parameter, the facility environment and the facility deformation state are processed by data fusion through digital twin technology, a facility digital model corresponding to the highway traffic protection facility is constructed, and the facility digital model is sent to the target terminal.

[0139] Specifically, the facility material represents the attribute of the raw material constituting the protection facility, for example, the yield strength of Q235 steel is greater than or equal to 235MPa, and the density of HDPE plastic is 0.95g / cm³. The facility building parameter refers to the geometric design index in the construction process, such as the plate width of the wave-shaped guardrail is 310mm, the column spacing is 4m, and the burial depth is 1.2m. The facility environment covers meteorological data such as temperature, humidity, rainfall, wind speed and sunshine intensity, as well as surrounding topographic features. The facility deformation state is used to represent the degree of structural deformation, such as the transverse displacement amount of the wave-shaped guardrail, the column inclination angle, and the loosening degree of the connecting bolt. The digital twin technology is an information technology framework that maps the virtual model to the physical entity, including data-driven modeling, real-time synchronization, simulation prediction and other functional modules. Data fusion processing refers to the integration and analysis method of multi-source heterogeneous data, for example, Kalman filter fusion of accelerometer and GPS data. The facility digital model is a three-dimensional visualization model with dynamic updating capability, which can display engineering parameters such as facility stress distribution and fatigue life, for example: the collision response process of the wave-shaped guardrail is displayed through the BIM model.

[0140] Next, a kind of monitoring and early warning system for highway traffic protection facilities provided by the embodiment of the application will be introduced, the monitoring and early warning system for highway traffic protection facilities described in the following and the monitoring and early warning method for highway traffic protection facilities described in the preceding can be mutually corresponding, please refer to Figure 2 , Figure 2 It is a structure schematic view of a kind of monitoring and early warning system 20 for highway traffic protection facilities provided by the embodiment of the application, including:

[0141] Data acquisition module 21, for real-time acquisition of the running state data of different node positions of highway traffic protection facilities;

[0142] a data processing module 22, configured to perform data preprocessing on the running state data to obtain to-be-analyzed data;

[0143] a data analysis module 23, configured to perform data analysis on the to-be-analyzed data to obtain a damage prediction value corresponding to different node positions of the highway traffic protection facility;

[0144] a safety evaluation module 24, configured to perform safety evaluation on the highway traffic protection facility according to the node position and the damage prediction value, and determine whether to perform early warning on the node position of the highway traffic protection facility according to a safety evaluation result;

[0145] a facility early warning module 25, configured to, when it is necessary to perform early warning on the node position of the highway traffic protection facility, generate an early warning signal according to the node position and the safety evaluation result, and send the early warning signal to a target terminal.

[0146] In a possible implementation of the embodiment, when the data processing module 22 performs data preprocessing on the running state data to obtain the to-be-analyzed data, the data processing module 22 is specifically configured to:

[0147] decompose the running state data into data modal components with different frequencies based on a preset modal number;

[0148] perform noise elimination processing on the data modal components, and superimposes the data modal components after elimination to obtain the to-be-analyzed data.

[0149] In another possible implementation of the embodiment, when the data analysis module 23 performs data analysis on the to-be-analyzed data to obtain the damage prediction value corresponding to different node positions of the highway traffic protection facility, the data analysis module 23 is specifically configured to:

[0150] perform time series transformation analysis on the to-be-analyzed data to obtain time series analysis data;

[0151] collect environmental data around the highway traffic protection facility, and construct a three-dimensional environmental feature map of the highway traffic protection facility in different time periods based on the environmental data;

[0152] determine a first damage prediction value corresponding to different node positions of the highway traffic protection facility according to the time series analysis data and the three-dimensional environmental feature map;

[0153] perform clustering analysis on the to-be-analyzed data to obtain irregular items, regular items and regular development item data of the to-be-analyzed data;

[0154] perform prediction and deduction processing on the irregular items, the regular items and the regular development item data to obtain a second damage prediction value;

[0155] Superimpose the first damage prediction value and the second damage prediction value to obtain the damage prediction value corresponding to different node positions of the highway traffic protection facility.

[0156] In another possible implementation of the embodiment, the data analysis module 23 is specifically configured to:

[0157] Obtain facility damage information and damage environment information corresponding to the facility damage information in a historical time period, and determine facility damage positions and damage time sequence data of each same damage type according to the facility damage information, the damage time sequence data being damage development data of the facility damage positions within a preset time period before and after the damage occurs;

[0158] Determine damage environment data corresponding to the facility damage positions according to the damage environment information;

[0159] Matrix correlate the damage environment data and the damage development data to obtain a damage environment development matrix;

[0160] Determine node environment data corresponding to different node positions of the highway traffic protection facility according to the three-dimensional environment feature map;

[0161] Determine state change data of different node positions of the highway traffic protection facility within a certain time period according to the time sequence analysis data;

[0162] Filter the damage environment development matrix according to the state change data and the node environment data to determine whether there is matching data segment matching the state change data and the node environment data, and if there is, determine the first damage prediction value corresponding to different node positions of the highway traffic protection facility according to the matching data segment.

[0163] In another possible implementation of the embodiment, the data analysis module 23 is specifically configured to:

[0164] Determine the highest parameter value and the lowest parameter value corresponding to the irregular item in the to-be-analyzed data;

[0165] Perform time sequence-free arrangement on the regular item and the regular development item data to obtain a regular item data matrix;

[0166] Input the regular item data matrix into the trained vector extraction model to extract vector features, obtain a regular item dimension, and perform data combination processing on the obtained regular item dimension, the highest parameter value, the lowest parameter value, and the regular data matrix to generate a comprehensive data matrix;

[0167] The data contained in the comprehensive data matrix is processed to obtain comprehensive development data;

[0168] The obtained comprehensive development data is input into a preset algorithm model for data calculation to obtain future development data;

[0169] The future development data is input into the trained damage model for training to obtain a second damage prediction value.

[0170] Another possible implementation of the embodiment of the application, the system 20 further comprises: a hazard evaluation module and a hazard judgment module, wherein,

[0171] The hazard evaluation module is configured to score the damage prediction value according to the degree of hazard to obtain a facility hazard score;

[0172] The hazard judgment module is configured to determine whether the facility hazard score is greater than a preset hazard score, and if so, generate a maintenance cycle frequency and a maintenance item according to the damage prediction value, and send the facility hazard score, the maintenance cycle frequency and the maintenance item to the target device.

[0173] Another possible implementation of the embodiment of the application, the system 20 further comprises: a determination module and a model construction module, wherein,

[0174] The determination module is configured to determine the facility material, the facility building parameter, the facility environment and the facility deformation state of different node positions of the highway traffic protection facility according to the running state data;

[0175] The model construction module is configured to perform data fusion processing on the facility material, the facility building parameter, the facility environment and the facility deformation state by digital twinning technology, construct a facility digital model corresponding to the highway traffic protection facility, and send the facility digital model to the target terminal.

[0176] The embodiment of the application provides an electronic device, as shown in Figure 3 The structure of the electronic device provided by the embodiment of the application is shown in Figure 3 The electronic device 300 shown in the structure of the electronic device provided by the embodiment of the application is shown in Figure 3 The electronic device 300 shown in the structure of the electronic device provided by the embodiment of the application is shown in

[0177] The processor 301 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic device, transistor logic device, hardware component, or any combination thereof. The processor 301 can implement or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure of the embodiments of the present application. The processor 301 can also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0178] The bus 302 can include a path for transmitting information between the above-mentioned components. The bus 302 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 302 can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 3 In the figure, only one thick line is used to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0179] The memory 303 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0180] The memory 303 is used to store application program code for implementing the embodiments of the present application, and is controlled by the processor 301 to execute. The processor 301 is used to execute the application program code stored in the memory 303 to realize the content shown in the foregoing method embodiments.

[0181] The electronic device includes, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a car terminal (for example, a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. Figure 3 The illustrated electronic device is merely an example and should not impose any limitation on the function and use range of the embodiments of the present application.

[0182] A computer readable storage medium provided by the embodiments of the present application is described below. The computer readable storage medium described below can be referred to the method described above.

[0183] The embodiments of the present application provide a computer readable storage medium, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the steps of the method for monitoring and early warning of highway traffic protection facilities.

[0184] Since the embodiments of the computer readable storage medium part correspond to the embodiments of the method part, the embodiments of the computer readable storage medium part are described with reference to the description of the embodiments of the method part.

[0185] It should be understood that, although each step in the flowchart of the accompanying drawings is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other orders. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0186] The above is only some embodiments of the present application. It should be pointed out that, for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should also be considered as the protection scope of the present application.

Claims

1. A monitoring and early warning method for highway traffic protection facilities, characterized in that, The method comprises the following steps: real-time acquisition of operation state data of different node positions of a highway traffic protection facility; data preprocessing of the operation state data to obtain analysis data; data analysis of the analysis data to obtain a damage prediction value corresponding to different node positions of the highway traffic protection facility; the data analysis of the analysis data to obtain the damage prediction value corresponding to different node positions of the highway traffic protection facility comprises: time series transformation analysis of the analysis data to obtain time series analysis data; acquisition of environmental data around the highway traffic protection facility, and construction of a three-dimensional environmental feature map of the highway traffic protection facility in different time periods based on the environmental data; determination of a first damage prediction value corresponding to different node positions of the highway traffic protection facility according to the time series analysis data and the three-dimensional environmental feature map; clustering analysis of the analysis data to obtain irregular items, regular items and regular development item data of the analysis data; prediction and deduction processing of the irregular items, the regular items and the regular development item data to obtain a second damage prediction value; superimposed calculation of the first damage prediction value and the second damage prediction value to obtain the damage prediction value corresponding to different node positions of the highway traffic protection facility; safety evaluation of the highway traffic protection facility according to the node positions and the damage prediction value, and determination of whether to issue a warning for the node positions of the highway traffic protection facility according to the safety evaluation result; if a warning is needed for the node positions of the highway traffic protection facility, a warning signal is generated according to the node positions and the safety evaluation result, and the warning signal is sent to a target terminal.

2. The method for monitoring and early warning of highway traffic protection facilities according to claim 1, characterized in that, The data preprocessing of the operation state data to obtain analysis data comprises: decomposition of the operation state data into data modal components with different frequencies based on a preset modal number; noise elimination processing of the data modal components, and superimposition of the eliminated data modal components to obtain analysis data.

3. The method for monitoring and early warning of highway traffic protection facilities according to claim 1, characterized in that, The determination of a first damage prediction value corresponding to different node positions of the highway traffic protection facility according to the time series analysis data and the three-dimensional environmental feature map comprises: acquisition of facility damage information and damage environment information corresponding to the facility damage information in a historical time period, and determination of facility damage positions and damage time series data of each same damage type according to the facility damage information, the damage time series data being damage development data of the facility damage positions within a preset time period before and after damage; determination of damage environment data corresponding to the facility damage positions according to the damage environment information; matrix correlation of the damage environment data and the damage development data to obtain a damage environment development matrix; determination of node environment data corresponding to different node positions of the highway traffic protection facility according to the three-dimensional environmental feature map; determination of state change data of different node positions of the highway traffic protection facility within a certain time period according to the time series analysis data; Screen the damage environment development matrix according to the state change data and the node environment data, determine whether there is matching data segment matching the state change data and the node environment data, if there is, determine the first damage prediction value corresponding to different node positions of the highway traffic protection facilities according to the matching data segment.

4. The method for monitoring and early warning of highway traffic protection facilities according to claim 1, characterized in that, The prediction and deduction processing of the irregular item, the regular item and the regular development item data includes: Determine the highest parameter value and the lowest parameter value corresponding to the irregular item in the to-be-analyzed data; Perform time sequence arrangement on the regular item and the regular development item data to obtain a regular item data matrix; Input the regular item data matrix into a trained vector extraction model for vector feature extraction to obtain a regular item dimension, and perform data combination processing on the obtained regular item dimension, the highest parameter value, the lowest parameter value and the regular item data matrix to generate a comprehensive data matrix; Perform data processing on the data contained in the comprehensive data matrix to obtain comprehensive development data; Input the obtained comprehensive development data into a preset algorithm model for data calculation to obtain future development data; Input the future development data into the trained damage model for training to obtain a second damage prediction value.

5. The method for monitoring and early warning of highway traffic protection facilities according to claim 1, characterized in that, The method further includes: Determine the facility material, facility building parameter, facility environment and facility deformation state of different node positions of the highway traffic protection facilities according to the running state data; Perform data fusion processing on the facility material, facility building parameter, facility environment and facility deformation state by digital twinning technology, construct a facility digital model corresponding to the highway traffic protection facilities, and send the facility digital model to the target terminal.

6. The method for monitoring and early warning of highway traffic protection facilities according to claim 1, characterized in that, The method further includes: Determine the facility material, facility building parameter, facility environment and facility deformation state of different node positions of the highway traffic protection facilities according to the running state data; Perform data fusion processing on the facility material, facility building parameter, facility environment and facility deformation state by digital twinning technology, construct a facility digital model corresponding to the highway traffic protection facilities, and send the facility digital model to the target terminal.

7. A monitoring and warning system for highway traffic protection installations, characterized in that, The method further includes: A data acquisition module for acquiring running state data of different node positions of highway traffic protection facilities in real time; A data processing module for pre-processing the running state data to obtain to-be-analyzed data; A data analysis module for analyzing the to-be-analyzed data to obtain a damage prediction value corresponding to different node positions of the highway traffic protection facilities; The data analysis module, when analyzing the to-be-analyzed data to obtain a damage prediction value corresponding to different node positions of the highway traffic protection facilities, is specifically configured to: Perform time sequence transformation analysis on the to-be-analyzed data to obtain time sequence analysis data; Collecting environmental data around the highway traffic protection facilities, and constructing a three-dimensional environmental feature map of the highway traffic protection facilities in different time periods based on the environmental data; Determining a first damage prediction value corresponding to different node positions of the highway traffic protection facilities according to the time series analysis data and the three-dimensional environmental feature map; Performing cluster analysis on the to-be-analyzed data to obtain irregular items, regular items, and regular development item data of the to-be-analyzed data; Performing prediction and deduction processing on the irregular items, the regular items, and the regular development item data to obtain a second damage prediction value; Superimposing and calculating the first damage prediction value and the second damage prediction value to obtain a damage prediction value corresponding to different node positions of the highway traffic protection facilities; A safety evaluation module configured to perform safety evaluation on the highway traffic protection facilities according to the node positions and the damage prediction value, and determine whether to perform early warning on the node positions of the highway traffic protection facilities according to a safety evaluation result; A facility early warning module configured to, when it is necessary to perform early warning on the node positions of the highway traffic protection facilities, generate an early warning signal according to the node positions and the safety evaluation result, and send the early warning signal to a target terminal.

8. An electronic device, comprising: The electronic device includes: at least one processor; a memory; at least one application program, wherein the at least one application program is stored in the memory and is configured to be executed by the at least one processor, and the at least one application program is configured to perform the method for monitoring and early warning of highway traffic protection facilities according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, including: a computer program stored in the memory and capable of being loaded and executed by the processor to perform the method for monitoring and early warning of highway traffic protection facilities according to any one of claims 1-6.

Images