Combined emergency response method and system for bridge and tunnel geological disasters

Abstract

The invention provides a bridge and tunnel geological disaster combined emergency response method and system, and the method comprises the steps: installing a plurality of sensors at key positions of a target bridge and a target tunnel, and collecting the structural health data of the target bridge and the target tunnel and the environmental data of the positions of the target bridge and the target tunnel in real time through the sensors; removing noise and abnormal values of the structural health data and the environmental data to obtain preprocessed data; standardizing the preprocessed data to obtain a standard data set; inputting the standard data set into a preset geological disaster assessment model to obtain a disaster risk assessment result; according to a disaster risk assessment result, performing an emergency response decision in combination with historical disaster data and a historical emergency plan to obtain an emergency response scheme; and the emergency response scheme is transmitted to related departments and personnel in real time by using the information sharing platform. According to the invention, the capability of coping with geological disasters is remarkably improved, and the problems of low emergency response efficiency and untimely resource allocation are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge and tunnel engineering, and particularly to a method and system for joint emergency response to geological disasters of bridges and tunnels. Background Art

[0002] With the acceleration of the urbanization process, bridges and tunnels, as important transportation infrastructures, are undertaking an increasing transportation task. However, geological disasters (such as landslides, debris flows, earthquakes, etc.) pose a serious threat to the safety of bridges and tunnels. Traditional emergency response methods are often designed for a single structure (bridge or tunnel), lacking joint consideration of the two, resulting in low response efficiency and heavy losses during disasters.

[0003] In the prior art, sensors are used to monitor the structural health status of bridges and tunnels, but there is a lack of real-time early warning for geological disasters; the formulated emergency plans often lack coordination, resulting in untimely resource allocation during disasters; the monitoring data and emergency information of bridges and tunnels are often scattered, lacking a unified platform for integration and analysis.

[0004] Therefore, there is an urgent need for an emergency response mechanism that can effectively integrate bridges and tunnels to improve the ability to respond to geological disasters. Summary of the Invention

[0005] In order to overcome the deficiencies of the prior art, the purpose of the present invention is to provide a method and system for joint emergency response to geological disasters of bridges and tunnels. Through innovations in multiple aspects such as joint monitoring, data integration, real-time evaluation, coordinated decision-making, and information sharing, the ability to respond to geological disasters is significantly improved, the problems of low efficiency and untimely resource allocation existing in traditional emergency response methods are solved, and more effective protection is provided for the safety of bridges and tunnels.

[0006] To achieve the above purpose, the present invention provides the following solutions:

[0007] A method for joint emergency response to geological disasters of bridges and tunnels, comprising:

[0008] Install a variety of sensors at key positions of the target bridge and tunnel, and collect the structural health data of the target bridge and tunnel and the environmental data of the location where the target bridge and tunnel are located in real time through the sensors;

[0009] Remove the noise and outliers from the structural health data and the environmental data to obtain preprocessed data;

[0010] Perform standardization processing on the preprocessed data to obtain a standard data set;

[0011] Input the standard data set into a preset geological disaster assessment model to obtain a disaster risk assessment result;

[0012] According to the disaster risk assessment result, combine historical disaster data and historical emergency plans to make an emergency response decision and obtain an emergency response plan;

[0013] Use an information sharing platform to transmit the emergency response plan to relevant departments and personnel in real time.

[0014] Preferably, the structural health data includes: displacement data, strain data, acceleration data, crack monitoring data, and load data; the environmental data includes rainfall data, soil moisture data, surface water level data, wind speed and direction data, seismic data, and temperature change data.

[0015] Preferably, remove the noise and outliers from the structural health data and the environmental data to obtain preprocessed data, including:

[0016] For each type of collected data in the structural health data and the environmental data, calculate the weighted average of the collected data; the calculation formula for the weighted average is: where n is the number of data points of each type of collected data, D(t - i) is the collected data at time t - i, is the weighted average, t is the current time point, W(t - i) is the weight corresponding to time t - i, α(t) is the adaptive factor;

[0017] Remove the noise according to the weighted average and the corresponding weight to obtain the denoised data; the calculation formula for the denoised data is: where D clean (t) is the denoised data, and N(t) is the noise at time t;

[0018] For each type of the denoised data, group it according to a preset collection period to obtain multiple data groups;

[0019] Calculate the difference coefficient between the current data group and the previous data group in sequence;

[0020] Judge whether the value of the difference coefficient is within a preset range;

[0021] If the value of the difference coefficient is not within the preset range, remove the corresponding data group;

[0022] If the value of the difference coefficient is within the preset range, retain the corresponding data group until all data groups are traversed to obtain the preprocessed data.

[0023] Preferably, the formula for calculating the coefficient of variation is:

[0024]

[0025] where p X,Y is the coefficient of variation, cov(X,Y) represents the covariance between the current data set X and the previous data set Y, α X represents the mean of the current data set X, and β Y represents the mean of the previous data set Y.

[0026] Preferably, the formula for calculating the adaptive factor is:

[0027]

[0028] where σ(t) is the standard deviation; ΔD(t) is the data change amount, ΔD(t) = |D(t) - D(t - 1)|; ∈ is a constant used to avoid the denominator being zero; β is the sensitivity control parameter.

[0029] Preferably, input the standard data set into a preset geological disaster assessment model to obtain the disaster risk assessment result, including:

[0030] Obtain a preset structural health data set and an environmental data data set;

[0031] Construct a deep learning model;

[0032] Train the deep learning model according to the structural health data set and the environmental data data set respectively to obtain a trained first classifier and a second classifier;

[0033] Use the first classifier to evaluate the disaster probability in the structural health data set to obtain the first disaster probability confidence level, and use the second classifier to identify the disaster probability in the environmental data data set to obtain the second disaster probability confidence level;

[0034] Select the largest data among the first disaster probability confidence level and the second disaster probability confidence level as the training threshold data, and retrain the classifier corresponding to the other disaster probability confidence level so that the classification confidence level of each classifier is greater than or equal to the training threshold data, and finally cascade the trained classifiers to obtain a classification network;

[0035] Connect a trained LSTM neural network after the classification network to obtain a trained geological disaster assessment model;

[0036] Input the standard data set into the geological disaster assessment model to obtain the disaster risk assessment result.

[0037] Preferably, according to the disaster risk assessment result, combine historical disaster data and historical emergency plans to make emergency response decisions, and obtain an emergency response plan, including:

[0038] Apply data analysis techniques to analyze the disaster risk assessment result and the historical disaster data to identify historical disaster patterns and influencing factors related to the current disaster risk assessment result;

[0039] Based on a decision support system, match the historical emergency plan according to historical disaster patterns and influencing factors to obtain multiple alternative plans to be optimized;

[0040] Evaluate each of the alternative plans to be optimized through simulation drills and an expert engine to obtain the emergency response plan.

[0041] Preferably, the emergency response plan includes resource allocation, personnel arrangement, and evacuation routes.

[0042] A combined emergency response system for geological disasters of bridges and tunnels includes:

[0043] A data acquisition unit, configured to install a variety of sensors at key positions of the target bridge and tunnel, and collect the structural health data of the target bridge and tunnel and the environmental data of the location where the target bridge and tunnel are located in real time through the sensors;

[0044] A data processing unit, configured to remove the noise and outliers from the structural health data and the environmental data to obtain preprocessed data;

[0045] A standardization unit, configured to perform standardization processing on the preprocessed data to obtain a standard data set;

[0046] A disaster assessment unit, configured to input the standard data set into a preset geological disaster assessment model to obtain a disaster risk assessment result;

[0047] A decision-making unit, configured to make emergency response decisions according to the disaster risk assessment result, combine historical disaster data and historical emergency plans, and obtain an emergency response plan;

[0048] A plan transmission unit, configured to use an information sharing platform to transmit the emergency response plan to relevant departments and personnel in real time.

[0049] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0050] The present invention provides a method and system for joint emergency response to geological disasters of bridges and tunnels. The method includes: installing a variety of sensors at key positions of the target bridge and tunnel, and collecting real-time structural health data of the target bridge and tunnel and environmental data of the location where the target bridge and tunnel are located through the sensors; removing noise and outliers from the structural health data and the environmental data to obtain preprocessed data; performing standardization processing on the preprocessed data to obtain a standard data set; inputting the standard data set into a preset geological disaster assessment model to obtain a disaster risk assessment result; making an emergency response decision based on the disaster risk assessment result, combining historical disaster data and historical emergency plans to obtain an emergency response plan; and using an information sharing platform to transmit the emergency response plan to relevant departments and personnel in real time. Through innovations in multiple aspects such as joint monitoring, data integration, real-time assessment, coordinated decision-making, and information sharing, the present invention significantly improves the ability to respond to geological disasters, solves the problems of low efficiency and untimely resource allocation existing in traditional emergency response methods, and provides a more effective guarantee for the safety of bridges and tunnels. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0052] Figure 1 It is a flowchart of the method provided by the embodiment of the present invention;

[0053] Figure 2 It is a schematic structural diagram of the system provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0055] The purpose of the present invention is to provide a method and system for joint emergency response to geological disasters of bridges and tunnels, which solves the problems of low efficiency and untimely resource allocation existing in traditional emergency response methods and provides a more effective guarantee for the safety of bridges and tunnels.

[0056] To make the above objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0057] Figure 1 It is a flowchart of the method provided by the embodiment of the present invention. As Figure 1 shown, the present invention provides a combined emergency response method for geological disasters of bridges and tunnels, including:

[0058] Step 100: Install a variety of sensors at key positions of the target bridge and tunnel, and collect the structural health data of the target bridge and tunnel and the environmental data of the location where the target bridge and tunnel are located in real time through the sensors;

[0059] Step 200: Remove the noise and outliers from the structural health data and environmental data to obtain preprocessed data;

[0060] Step 300: Perform standardization processing on the preprocessed data to obtain a standard data set;

[0061] Step 400: Input the standard data set into a preset geological disaster assessment model to obtain a disaster risk assessment result;

[0062] Step 500: Make an emergency response decision based on the disaster risk assessment result, combined with historical disaster data and historical emergency plans, to obtain an emergency response plan;

[0063] Step 600: Use the information sharing platform to transmit the emergency response plan to relevant departments and personnel in real time.

[0064] Preferably, the structural health data includes: displacement data, strain data, acceleration data, crack monitoring data, and load data; the environmental data includes rainfall data, soil moisture data, surface water level data, wind speed and direction data, earthquake data, and temperature change data.

[0065] Specifically, step 100 of this embodiment includes:

[0066] According to the structural characteristics of the bridge and tunnel and the potential geological disaster risks, select appropriate sensor types. For structural health monitoring, preferred sensors include displacement sensors, strain gauges, accelerometers, crack sensors, and load sensors. These sensors are reasonably arranged according to the key parts of the structure, such as at the supports, main girders, and joints of the bridge, and at the crown and sidewalls of the tunnel, etc., to ensure that the health status of the structure can be comprehensively monitored. At the same time, environmental data sensors such as rain gauges, soil moisture sensors, surface water level sensors, wind speed and direction meters, earthquake monitors, and temperature sensors should also be arranged at appropriate positions to obtain real-time data of the surrounding environment.

[0067] After determining the layout of the sensors, the actual installation work is carried out. During the installation process, it is necessary to ensure that the sensors are firmly fixed to avoid affecting the accuracy of data collection due to vibration or external forces. After installation, system debugging is carried out to ensure that each sensor can work properly and accurately collect data. During the debugging process, simulation tests can be used to verify the response ability of the sensors and the stability of data transmission, ensuring that all sensors can operate normally within the predetermined working range.

[0068] To achieve real-time data collection, a data collection system is built in this embodiment. This system can centralize the data of each sensor onto a unified platform. Wireless transmission technologies (such as LoRa, Zigbee, etc.) are used to transmit sensor data to the central control system in real time, or wired networks are used for data transmission. The data collection system should have the capabilities of data storage, processing, and analysis, be able to monitor the status of sensors in real time, and record and store the collected structural health data and environmental data in a timely manner.

[0069] In this embodiment, a data monitoring and analysis platform is also established to monitor and analyze the real-time collected data. This platform should have the function of data visualization, be able to intuitively display the structural health status and environmental changes. Through data analysis, potential risks and abnormal situations can be identified and early warnings can be issued in a timely manner. In addition, the platform should also support the storage and retrospective analysis of historical data for subsequent research and decision-making support, ensuring that rapid responses and corresponding measures can be taken when geological disasters occur.

[0070] Preferably, noise and outliers are removed from the structural health data and the environmental data to obtain preprocessed data, including:

[0071] For each type of collected data in the structural health data and the environmental data, calculate the weighted average value of the collected data; the calculation formula for the weighted average value is: where n is the number of data points of each type of collected data, D(t - i) is the collected data at time t - i, is the weighted average value, t is the current time point, W(t - i) is the weight corresponding to time t - i, α(t) is the adaptive factor;

[0072] Remove noise according to the weighted average value and the corresponding weight to obtain the denoised data; the calculation formula for the denoised data is: where D clean (t) is the denoised data, and N(t) is the noise at time t;

[0073] For each type of the denoised data, group them according to a preset acquisition period to obtain a plurality of data groups;

[0074] Calculate the difference coefficient between the current data group and the previous data group in sequence;

[0075] Determine whether the value of the difference coefficient is within a preset range;

[0076] If the value of the difference coefficient is not within the preset range, remove the corresponding data group;

[0077] If the value of the difference coefficient is within the preset range, retain the corresponding data group until all data groups are traversed to obtain the preprocessed data.

[0078] Preferably, the formula for calculating the difference coefficient is:

[0079]

[0080] where p X,Y is the difference coefficient, cov(X,Y) represents the covariance between the current data group X and the previous data group Y, α X represents the mean of the current data group X, and β Y represents the mean of the previous data group Y.

[0081] Specifically, due to the influence of their own parameters or environmental factors, each sensor may cause a large deviation between the measured value collected at a certain moment and the actual value. Therefore, in this embodiment, the difference coefficient can be used to screen out abnormal monitoring values, thereby ensuring the accuracy of the data.

[0082] Furthermore, in this embodiment, an adaptive factor and a dynamic weight mechanism are introduced to calculate the weighted average of the structural health data and the environmental data, so as to achieve more accurate noise removal. Traditional weighted average calculations usually use fixed weights and cannot effectively cope with the influence brought by data fluctuations and environmental changes. However, this method dynamically adjusts the weights in real time and combines the adaptive factor, enabling the weights to be dynamically adjusted according to the reliability and change degree of the data during the data acquisition process, thereby improving the accuracy and flexibility of the denoising effect. The innovative method of this embodiment not only enhances the intelligent level of data processing, but also provides a more reliable data basis for the real-time monitoring and early warning system, and improves the response ability to potential risks.

[0083] Preferably, the formula for calculating the adaptive factor is:

[0084]

[0085] where σ(t) is the standard deviation; ΔD(t) is the data change amount, and ΔD(t) = |D(t) - D(t - 1)|; ∈ is a constant used to avoid the denominator being zero; β is the sensitivity control parameter.

[0086] Specifically, in this embodiment, the adaptive factor is dynamically calculated by combining the standard deviation and the data change amount, so as to achieve a sensitive response to data volatility. Traditional methods often use a fixed adaptive factor and cannot effectively adapt to changes in different environments and data characteristics. However, this solution can automatically adjust the value of the adaptive factor according to the actual situation by analyzing the volatility and change degree of the data in real time, enhancing the ability to identify abnormal situations. In addition, the introduction of a constant to avoid the denominator being zero and the sensitivity control parameter makes the calculation of the adaptive factor more robust, ensuring good performance in various situations. This innovative design not only improves the accuracy of data processing, but also provides a stronger adaptability for real-time monitoring and warning systems, significantly enhancing the response efficiency to geological disasters.

[0087] Exemplarily, in the health monitoring of bridge structures, the sensitivity control parameter can be used to adjust the calculation of the adaptive factor so as to reflect the health status of the bridge in real time under different traffic loads and environmental conditions. For example, when there is heavy vehicle traffic or extreme weather (such as strong wind or heavy rain) on the bridge, the sensitivity control parameter can increase the weight of the adaptive factor, making the monitoring system more sensitive to data changes, so as to timely identify potential structural damage or abnormal situations. This flexible adjustment mechanism ensures the safety of the bridge under various dynamic conditions and can effectively prevent accidents from occurring.

[0088] In the tunnel environment monitoring, the application of the sensitivity control parameter can help the system better cope with sudden geological changes or environmental factors. For example, when rainfall or an earthquake occurs in the tunnel, the sensitivity control parameter can be set to a higher value to enhance the response ability to environmental data (such as soil moisture, surface water level, etc.). This adjustment enables the monitoring system to quickly capture the impact of environmental changes and issue early warnings in a timely manner to ensure the safe operation of the tunnel. Through the dynamic adjustment of the sensitivity control parameter, the tunnel monitoring system can maintain high-efficiency monitoring and warning capabilities in a complex geological environment.

[0089] Preferably, input the standard data set into a preset geological disaster assessment model to obtain a disaster risk assessment result, including:

[0090] Obtain a preset structural health data set and an environmental data set;

[0091] Construct a deep learning model;

[0092] Train the deep learning model according to the structural health data set and the environmental data set respectively to obtain a trained first classifier and a second classifier;

[0093] Use the first classifier to evaluate the disaster probability in the structural health data set to obtain a first disaster probability confidence level, and use the second classifier to identify the disaster probability in the environmental data data set to obtain a second disaster probability confidence level;

[0094] Select the largest data among the first disaster probability confidence level and the second disaster probability confidence level as the training threshold data, and retrain the classifier corresponding to the other disaster probability confidence level so that the classification confidence level of each classifier is greater than or equal to the training threshold data, and finally cascade the trained classifiers to obtain a classification network;

[0095] Connect a trained LSTM neural network after the classification network to obtain a trained geological disaster assessment model;

[0096] Input the standard data set into the geological disaster assessment model to obtain a disaster risk assessment result.

[0097] Specifically, in the training process of this embodiment, the cross-entropy loss function and an appropriate optimization algorithm (such as Adam or SGD) are used to minimize the prediction error of the model to ensure that the classifier can accurately identify the disaster probability. After training, use the first classifier to evaluate the disaster probability in the structural health data set to obtain a first disaster probability confidence level. At the same time, use the second classifier to identify the disaster probability in the environmental data set to obtain a second disaster probability confidence level. These two confidence levels will provide an important basis for subsequent decisions to help judge the current disaster risk level. After obtaining the first and second disaster probability confidence levels, select the largest value of these two confidence levels as the training threshold data. This threshold will be used to guide the subsequent classifier training to ensure that the model can achieve the expected classification performance in practical applications. According to this threshold, retrain the other classifier to improve its classification confidence level to be greater than or equal to the selected training threshold data. After completing the retraining, cascade the trained first classifier and the second classifier to form a comprehensive classification network. This classification network can simultaneously consider the impacts of structural health and environmental factors on disaster risks, thereby providing a more accurate disaster risk assessment result. The cascade design enables the model to perform feature extraction and decision-making at different levels, enhancing the overall classification ability.

[0098] Optionally, a trained long short-term memory (LSTM) neural network is connected after the classification network to capture the dynamic changes in time series data. The LSTM network can effectively process time-dependent data and further improve the accuracy of disaster risk assessment. The standard dataset is input into the final geological disaster assessment model, and after being processed by the classification network and LSTM, the final disaster risk assessment result is obtained, providing a scientific basis for decision-making.

[0099] Furthermore, the assessment results of this embodiment will provide the occurrence probabilities of different types of disasters, such as landslides, debris flows, earthquakes, etc., presented in the form of confidence levels, helping decision-makers understand the risk levels of various disasters. Secondly, the assessment results will also include a specific description of the affected areas, including the health status of affected facilities (such as bridges and tunnels), environmental factors (such as rainfall, soil moisture, etc.), and the risk of possible secondary disasters. The assessment results of this embodiment also include the analysis of historical disaster data to provide a reference basis for future risk management and decision-making. Through this information, relevant departments can better formulate prevention and emergency response strategies and reduce the losses caused by disasters. The manifestation form of the specific assessment results is shown as follows:

[0100] Assessment date: February 27, 2025

[0101] Assessment area: Bridge and tunnel systems in City A

[0102] 1. Disaster types and occurrence probabilities:

[0103] Landslide: The occurrence probability is 30% (confidence level: 0.85)

[0104] Debris flow: The occurrence probability is 20% (confidence level: 0.75)

[0105] Earthquake: The occurrence probability is 10% (confidence level: 0.90)

[0106] 2. Health status of affected facilities:

[0107] Bridge X: The structural health index is 0.7 (full score 1.0), there are slight cracks, and regular monitoring is required.

[0108] Tunnel Y: The structural health index is 0.9, in good condition, but the change in surrounding soil moisture needs to be monitored.

[0109] 3. Environmental factors:

[0110] Rainfall: The rainfall in the past 24 hours was 50 mm, and the rainfall is expected to reach 80 mm in the next 48 hours.

[0111] Soil moisture: The current soil moisture is 30%, higher than the normal level (20%).

[0112] Earthquake data: 2 minor earthquakes (magnitude ≤ 3.0) occurred in the last 24 hours.

[0113] 4. Secondary disaster risks:

[0114] Due to recent increased rainfall, the risk of landslides and mudslides has increased significantly, especially in the hillside area near Bridge X.

[0115] 5. Recommended emergency response measures:

[0116] Carry out a detailed inspection of Bridge X and restrict traffic if necessary.

[0117] Set up warning signs in landslide risk areas and arrange special personnel to monitor changes in soil moisture.

[0118] Activate emergency plans and prepare to respond to possible mudslides and landslides.

[0119] 6. Analysis of historical disaster data:

[0120] In the past five years, there have been three landslides in the area, all of which were related to heavy rainfall. It is recommended to strengthen rainfall monitoring and early warning.

[0121] Through the above assessment results, relevant departments can clearly understand the current disaster risk situation and take corresponding prevention and emergency measures to reduce potential losses.

[0122] Preferably, based on the disaster risk assessment results, combined with historical disaster data and historical emergency plans, emergency response decisions are made to obtain emergency response plans, including:

[0123] Applying data analysis techniques to analyze the disaster risk assessment results and the historical disaster data to identify historical disaster patterns and influencing factors related to the current disaster risk assessment results;

[0124] Based on the decision support system, the historical emergency plans are matched according to historical disaster patterns and influencing factors to obtain multiple plans to be optimized;

[0125] Each of the schemes to be optimized is evaluated through simulation exercises and an expert engine to obtain the emergency response plan.

[0126] Specifically, this embodiment utilizes data analysis techniques to deeply analyze the current disaster risk assessment results and historical disaster data. Through machine learning algorithms (such as clustering analysis, association rule mining, etc.), historical disaster patterns similar to the current risk assessment results are identified. For example, if the current assessment result shows that there is a landslide risk in a certain area, the system will extract cases of similar landslide events that have occurred in the historical data and analyze their inducing factors, such as environmental factors like rainfall and soil moisture. In addition, this embodiment will also extract the influencing factors in these historical events, such as geological conditions and meteorological conditions, to provide a basis for subsequent decision-making.

[0127] Furthermore, based on the identified historical disaster patterns and influencing factors, the decision support system will automatically match historical emergency plans and generate multiple emergency response plans to be optimized. The decision support system includes a plan library that stores successful and failed cases of dealing with similar disasters in the past. The system will retrieve relevant emergency measures from the plan library according to the current disaster type, risk level, and impact scope, and generate a preliminary emergency response plan in combination with the current specific situation. For example, if historical data shows that a certain type of landslide event has a greater impact on traffic, the system will give priority to suggesting traffic control and evacuation measures.

[0128] Even further, to ensure the feasibility and effectiveness of the generated emergency response plan, the system will conduct simulation drills and invite experts for review. The simulation drills will be based on the current disaster risk assessment results and the generated emergency plan, simulate the emergency response process under different disaster scenarios, and evaluate the implementation efficiency and coverage of the plan. At the same time, the expert engine will evaluate the rationality, operability, and potential risks of the plan and put forward modification suggestions. For example, the expert engine will suggest increasing the monitoring frequency of certain key nodes or adjusting the evacuation route to avoid traffic congestion.

[0129] Exemplarily, according to the feedback from the simulation drills and the expert engine, the system will optimize the emergency response plan, adjust the unreasonable parts and supplement the necessary details. The optimized plan will be released to relevant departments in the form of an official report, and necessary warning information and response guidelines will be conveyed to the public through the emergency management platform. For example, the optimized plan may include specific time nodes, division of responsibilities, resource allocation plans, etc., to ensure that all parties can respond quickly and cooperate effectively. Finally, the emergency response plan will be implemented in a clear and operable form to minimize the losses caused by disasters.

[0130] Specifically, in this embodiment, a digital twin environment is constructed. Using Geographic Information System (GIS) and 3D modeling technology, the terrain, buildings, and infrastructure in the disaster-stricken area are accurately restored. In this virtual environment, through Monte Carlo simulation and multi-agent modeling technology, the behavior decisions of different participants (such as rescue workers, residents, and emergency commanders) are simulated, and random perturbations and complex interaction mechanisms are introduced. The expert engine adopts a knowledge graph-based reasoning system and machine learning algorithms to integrate historical disaster data, expert experience rules, and real-time risk assessment data, and dynamically generates decision-making suggestions. This embodiment also uses Bayesian networks and fuzzy inference technology to conduct risk assessment and confidence calculation on different emergency plans, and finally generates a comprehensive report containing multi-scenario and multi-dimensional evaluation results, providing a scientific basis for actual emergency decision-making. This computer simulation method can not only greatly reduce the cost and risk of actual drills but also repeatedly test and optimize emergency plans in a virtual environment, significantly improving the accuracy and efficiency of disaster response.

[0131] As an alternative implementation, the information sharing platform integrates multiple communication protocols (such as HTTP / HTTPS, WebSocket, MQTT, etc.) to support seamless access of different devices and systems. The emergency response plan is converted into a standardized data format (such as JSON or XML), and data security is ensured through encrypted transmission. The platform adopts a role-based access control (RBAC) mechanism to ensure that different departments and personnel can only access information related to their responsibilities. At the same time, the platform uses message queues (such as Kafka or RabbitMQ) to achieve asynchronous communication, ensuring fast information transfer even in high-concurrency situations. In addition, the platform supports multi-terminal access, including PC terminals, mobile terminals, and Internet of Things devices, and through multiple methods such as push notifications, text messages, and emails, ensures that relevant personnel can receive and respond to the emergency plan in a timely manner. Finally, the platform records the logs of all information transmissions for subsequent auditing and optimization, thus forming a closed-loop information sharing and feedback mechanism.

[0132] Corresponding to the above method, as Figure 2 shown, this embodiment also provides a joint emergency response system for geological disasters of bridges and tunnels, including:

[0133] A data acquisition unit for installing a variety of sensors at key positions of the target bridge and tunnel, and collecting the structural health data of the target bridge and tunnel and the environmental data of the location where the target bridge and tunnel are located in real time through the sensors;

[0134] A data processing unit for removing the noise and outliers from the structural health data and the environmental data to obtain preprocessed data;

[0135] A normalization unit for normalizing the preprocessed data to obtain a standard data set;

[0136] A disaster assessment unit for inputting the standard data set into a preset geological disaster assessment model to obtain a disaster risk assessment result;

[0137] A decision-making unit for making an emergency response decision based on the disaster risk assessment result in combination with historical disaster data and historical emergency plans to obtain an emergency response plan;

[0138] A plan transmission unit for using an information sharing platform to transmit the emergency response plan to relevant departments and personnel in real time.

[0139] In this specification, each embodiment is described in a progressive manner. The key point of each embodiment is the difference from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For the relevant parts, reference can be made to the description in the method part.

[0140] In this article, specific examples are used to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A joint emergency response method for bridge and tunnel geological disasters, characterized in that: include: Install a variety of sensors at key locations of target bridges and tunnels, and use the sensors to collect real-time structural health data of the target bridges and tunnels and environmental data of the locations of the target bridges and tunnels; removing noise and outliers from the structural health data and the environmental data to obtain preprocessed data; Performing standardization on the preprocessed data to obtain a standard data set; Inputting the standard data set into a preset geological disaster assessment model to obtain a disaster risk assessment result; Based on the disaster risk assessment results, combining historical disaster data and historical emergency plans, emergency response decisions are made to obtain emergency response plans; The emergency response plan is delivered to relevant departments and personnel in real time using the information sharing platform.

2. The bridge and tunnel geological disaster joint emergency response method according to claim 1 is characterized in that: The structural health data includes displacement data, strain data, acceleration data, crack monitoring data and load data; the environmental data includes rainfall data, soil moisture data, surface water level data, wind speed and direction data, earthquake data and temperature change data.

3. The bridge and tunnel geological disaster joint emergency response method according to claim 1 is characterized in that: Removing noise and outliers from the structural health data and the environmental data to obtain preprocessed data includes: For each type of collected data in the structural health data and the environmental data, a weighted average value of the collected data is calculated; the calculation formula of the weighted average value is: Where n is the number of data points of each type of collected data, D(ti) is the collected data at time ti, is the weighted average, t is the current time point, W(ti) is the weight corresponding to time ti, α(t) is the adaptive factor; The noise is removed according to the weighted average value and the corresponding weight to obtain the denoised data; the calculation formula of the denoised data is: Among them, D clean (t) is the denoised data, and N(t) is the noise at time t; For each type of the denoised data, grouping is performed according to a preset collection period to obtain multiple data groups; Calculate the difference coefficient between the current data group and the previous data group in sequence; Determine whether the value of the coefficient of difference is within a preset range; If the value of the difference coefficient is not within the preset range, the corresponding data group is removed; If the value of the difference coefficient is within a preset range, the corresponding data group is retained until all data groups are traversed to obtain the preprocessed data.

4. The bridge and tunnel geological disaster joint emergency response method according to claim 3 is characterized in that: The coefficient of difference calculation formula is: Among them, p X,Y is the coefficient of difference, cov(X,Y) represents the covariance between the current data set X and the previous data set Y, α X represents the mean of the current data set X, β Y Represents the mean of the previous data set Y.

5. The bridge and tunnel geological disaster joint emergency response method according to claim 3 is characterized in that: The calculation formula of the adaptive factor is: Where σ(t) is the standard deviation; ΔD(t) is the data change, ΔD(t)=|D(t)-D(t-1)|; ∈ is a constant used to avoid the situation where the denominator is zero; β is the sensitivity control parameter.

6. The bridge and tunnel geological disaster joint emergency response method according to claim 1 is characterized in that: The standard data set is input into the preset geological disaster assessment model to obtain the disaster risk assessment results, including: Obtaining a preset structural health data set and an environmental data data set; Build deep learning models; The deep learning model is trained according to the structural health data set and the environmental data data set to obtain a trained first classifier and a second classifier; Using the first classifier to evaluate the disaster probability in the structural health data set to obtain a first disaster probability confidence level, and using the second classifier to identify the disaster probability in the environmental data set to obtain a second disaster probability confidence level; Selecting the largest data of the first disaster probability confidence degree and the second disaster probability confidence degree as training threshold data, and retraining the classifiers corresponding to the other disaster probability confidence degrees so that the classification confidence of each classifier is greater than or equal to the training threshold data, and finally cascading the trained classifiers to obtain a classification network; Connecting the trained LSTM neural network after the classification network to obtain a trained geological disaster assessment model; The standard data set is input into the geological disaster assessment model to obtain a disaster risk assessment result.

7. The bridge and tunnel geological disaster joint emergency response method according to claim 1 is characterized in that: Based on the disaster risk assessment results, combined with historical disaster data and historical emergency plans, emergency response decisions are made to obtain emergency response plans, including: Applying data analysis techniques to analyze the disaster risk assessment results and the historical disaster data to identify historical disaster patterns and influencing factors related to the current disaster risk assessment results; Based on the decision support system, the historical emergency plans are matched according to historical disaster patterns and influencing factors to obtain multiple plans to be optimized; Each of the schemes to be optimized is evaluated through simulation exercises and an expert engine to obtain the emergency response plan.

8. The bridge and tunnel geological disaster joint emergency response method according to claim 7 is characterized in that: The emergency response plan includes resource deployment, personnel arrangement and evacuation routes.

9. A bridge and tunnel geological disaster joint emergency response system, characterized in that: include: A data acquisition unit is used to install a variety of sensors at key locations of target bridges and tunnels, and to collect structural health data of the target bridges and tunnels and environmental data of the locations of the target bridges and tunnels in real time through the sensors; A data processing unit, used to remove noise and abnormal values ​​from the structural health data and the environmental data to obtain preprocessed data; A standardization unit, used for performing standardization processing on the preprocessed data to obtain a standard data set; A disaster assessment unit, used for inputting the standard data set into a preset geological disaster assessment model to obtain a disaster risk assessment result; A decision-making unit, used to make emergency response decisions based on the disaster risk assessment results, combined with historical disaster data and historical emergency plans, to obtain an emergency response plan; The plan delivery unit is used to deliver the emergency response plan to relevant departments and personnel in real time using the information sharing platform.

Images