A linkage control method and system based on interval floodgate state

Abstract

The application relates to a linkage control method and system based on interval floodgate states, and belongs to the technical field of intelligent protection control. The linkage control method comprises the following steps: collecting real-time states of floodgates in each interval of underground facilities, external water level data and real-time rainfall data; inputting the external water level data and the real-time rainfall data into a pre-trained risk warning model to obtain a risk warning level; determining corresponding intervals to be closed according to the risk warning level; determining intervals to be closed whose floodgates are in an open state according to the real-time states of the floodgates in each interval to be closed, and obtaining an interval to be closed list; sorting the interval to be closed list based on a preset interval closing priority; and generating a step-by-step closing control instruction according to the sorted interval to be closed list. The application can flexibly meet the closing requirements of each interval, and fully guarantees the closing safety of important intervals and the reliability of personnel evacuation during disaster diffusion.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent protection control, in particular to a linkage control method and system based on interval floodgate state. BACKGROUND

[0002] In underground transportation facilities and underground complexes, flood prevention and flood control are very important safety protection issues. Underground facilities often have large-scale personnel flow and equipment storage areas. Once threatened by heavy rainfall or floods, rising water levels can cause water to flow back, leading to serious consequences such as casualties, equipment damage, and operational disruptions. Therefore, floodgates are usually installed in underground facilities. These floodgates can quickly close in emergency situations to prevent floodwater from entering important areas.

[0003] However, common floodgate control systems usually rely on a single water level sensor or meteorological data feedback to initiate closure operations, making it difficult to accurately assess real-time risks. For long-distance underground facilities such as subway intervals and underground tunnels, it is difficult to meet the closure needs of each interval flexibly when facing different risk situations, leading to difficulties in ensuring the priority protection of high-risk intervals and the reliability of the closure safety and personnel evacuation of important intervals during disaster spread. SUMMARY

[0004] To improve safety and protection reliability, the present application provides a linkage control method and system based on interval floodgate state.

[0005] In a first aspect, the present application provides a linkage control method based on interval floodgate state, which adopts the following technical solution:

[0006] A linkage control method based on interval floodgate state, the linkage control method comprises:

[0007] Collecting real-time states of floodgates in each interval of an underground facility, as well as external water level data and real-time rainfall data;

[0008] Inputting the external water level data and real-time rainfall data into a pre-trained risk warning model for comprehensive analysis to obtain a risk warning level;

[0009] Determining corresponding intervals to be closed according to the risk warning level;

[0010] According to the real-time state of the floodgate of each interval to be closed, determining the interval to be closed whose floodgate is in an open state to obtain a list of intervals to be closed;

[0011] Sorting the list of intervals to be closed based on a pre-set interval closure priority;

[0012] According to the sorted list of the to-be-closed intervals, a step-by-step closing control instruction is generated, wherein the step-by-step closing control instruction is used to control the floodgate in each to-be-closed interval in the list of to-be-closed intervals to close step by step.

[0013] By using the above technical solution, the data inside and outside the underground facility is collected in real time, the risk comprehensive analysis is performed by using the risk early warning model, the more accurate risk assessment result is provided, the to-be-closed intervals that need to be closed are determined and are sorted according to the priority, and the priority protection of the high-risk intervals or important intervals is realized. At the same time, the step-by-step closing strategy avoids the "one-size-fits-all" control of the traditional method, which not only ensures the safe closing of the high-priority intervals, but also provides more flexible scheduling for personnel evacuation and subsequent protection, thereby realizing the intelligent linkage control of the interval floodgate, improving the accuracy and timeliness of the flood control emergency response, and effectively protecting the safety of personnel and the integrity of the facility.

[0014] Optionally, the control method further includes a training step of the risk early warning model, and the training step includes:

[0015] acquiring a historical sample data set, wherein the historical sample data set includes historical external water level data, historical rainfall data, and pre-labeled risk early warning level labels;

[0016] performing data preprocessing on the historical sample data set;

[0017] dividing the preprocessed historical sample data set into a training set, a validation set, and a test set;

[0018] initial training a pre-constructed long short-term memory network model based on the training set, and verifying and optimizing the model parameters of the initial trained long short-term memory network model based on the validation set and the test set to obtain the risk early warning model.

[0019] By using the above technical solution, the system can learn the rules and patterns of the risk early warning level from the time series data of the water level and the rainfall, and the advantage of the LSTM model in processing time series data makes it particularly suitable for the risk early warning needs of the underground facility, which can accurately predict the risk level at different time steps and provide efficient support for the closing control and early warning response of the floodgate.

[0020] Optionally, the step of initial training a pre-constructed long short-term memory network model based on the training set, and verifying and optimizing the model parameters of the initial trained long short-term memory network model based on the validation set and the test set to obtain the risk early warning model includes:

[0021] inputting the training set into a pre-constructed long short-term memory network model for training, optimizing model parameters and calculating a combined loss function of the model until the combined loss function meets a preset condition, to obtain the trained risk early warning model; wherein the combined loss function comprises a prediction error and a regularization term;

[0022] verifying the risk early warning model according to the verification set, evaluating the performance of the risk early warning model and adjusting the hyperparameters of the risk early warning model;

[0023] testing the prediction accuracy of the adjusted risk early warning model according to the test set.

[0024] By adopting the above technical solutions, the model parameters are optimized through the training set, the hyperparameters are adjusted through the verification set, and the generalization performance is tested through the test set in a multi-stage process, thereby constructing a robust LSTM risk early warning model. The model can effectively predict the risk level based on water level and rainfall, provide scientific support for risk early warning and protection of underground facilities, and ensure high accuracy and reliability of the model in actual application.

[0025] Optionally, the step of determining the corresponding interval closure range according to the risk early warning level comprises:

[0026] determining whether the risk early warning level exceeds a corresponding safety threshold; if yes, determining the corresponding interval closure range according to the risk early warning level;

[0027] generating an interval structure diagram according to interval structure information of each interval in the underground facility;

[0028] identifying each of the interval closure intervals in the interval structure diagram according to the interval closure range.

[0029] By adopting the above technical solutions, it is first determined whether the risk level exceeds the safety threshold, and if it exceeds, the interval closure range is set according to the early warning level, the structure diagram is generated and the interval to be closed is identified, thereby achieving the goal of dynamically adjusting the closure range and determining the priority closure interval according to different risk levels, effectively improving the flexibility and scientificity of emergency protection, and ensuring that critical areas can be quickly closed in a high-risk state, while reasonably scheduling resources to protect the safety of personnel and assets.

[0030] Optionally, after the step of sorting the interval closure interval list based on the preset interval closure priority, the method further comprises:

[0031] obtaining a real-time state of a floodgate of each interval to be closed in the interval closure interval list; wherein the real-time state of the floodgate comprises a communication state, a power state and a transmission system state;

[0032] determine whether the real-time state of each to-be-closed interval is abnormal, and if so, determine the to-be-closed interval with the abnormal real-time state of the floodgate as an abnormal interval;

[0033] increase the closure priority of the to-be-closed interval adjacent to the position of the abnormal interval in the to-be-closed interval list, and remove the abnormal interval from the to-be-closed interval list;

[0034] generate maintenance alarm information according to the position information and the type of the abnormal interval, and send the maintenance alarm information to a maintenance terminal.

[0035] By using the above technical solution, the state of the floodgate is detected before the closure instruction is generated, and the abnormal interval is screened out, so as to ensure that the closure operation only covers the interval with a normal state, and reduce the protection vacancy caused by the abnormal floodgate. Meanwhile, the steps of increasing the priority of the adjacent interval and sending the maintenance alarm further enhance the flexibility and emergency response capability of the system, so that the safety of the underground facility can be more stably ensured in an emergency.

[0036] Optionally, after the step of generating the maintenance alarm information and sending the maintenance alarm information to the maintenance terminal, the method further includes:

[0037] real-time receiving maintenance feedback information of the maintenance terminal and determining whether the maintenance is successful;

[0038] if so, restoring the abnormal interval to a to-be-closed interval and adding the to-be-closed interval to the to-be-closed interval list;

[0039] if not, modifying the abnormal interval to a to-be-monitored interval, and sending an emergency alarm signal to the maintenance terminal when the water level and the environmental state of the to-be-monitored interval are abnormal.

[0040] By using the above technical solution, the interval state is dynamically adjusted according to the real-time received maintenance feedback, and an emergency alarm mechanism is established, so that the system can quickly judge and process the maintenance result in the case of abnormal floodgate, and realize dynamic management of the interval. In addition, for the interval with failed maintenance, by setting the "to-be-monitored" state and real-time monitoring environmental data, the system can timely alarm and take measures when a sudden risk occurs. This technical solution significantly improves the flexibility, emergency response capability and protection efficiency of the system, and provides more stable protection for underground facilities.

[0041] Optionally, before the step of generating the step-by-step closure control instruction according to the sorted to-be-closed interval list, the method further includes:

[0042] real-time detecting personnel distribution data of each to-be-closed interval in the to-be-closed interval list;

[0043] determine a personnel density level of each interval to be closed according to the personnel distribution data;

[0044] determine a corresponding alarm level according to the personnel density level;

[0045] generate corresponding closing alarm information according to the alarm level, and send the closing alarm information to an alarm module of each interval to be closed; wherein the closing alarm information comprises a closing alarm prompt and a personnel evacuation route.

[0046] By adopting the above technical solutions, in the event of an emergency, clear closing alarm and explicit evacuation guidance can provide timely evacuation guidance for personnel, and through intelligent allocation of different alarm levels and evacuation routes, not only can the evacuation of people be guided to disperse and avoid unnecessary congestion, but also the orderliness of the evacuation process of underground facilities such as subways or tunnels can be ensured.

[0047] In a second aspect, the application provides a linkage control system based on the state of an interval flood gate, which adopts the following technical solutions:

[0048] A linkage control system based on the state of an interval flood gate, the linkage control system comprises:

[0049] collecting real-time states of flood gates of each interval in an underground facility, and external water level data and real-time rainfall data;

[0050] inputting the external water level data and real-time rainfall data into a pre-trained risk warning model for comprehensive analysis to obtain a risk warning level;

[0051] determining corresponding each interval to be closed according to the risk warning level;

[0052] determining, according to the real-time state of the flood gate of each interval to be closed, an interval to be closed whose flood gate is in an open state to obtain an interval to be closed list;

[0053] sorting the interval to be closed list based on a preset interval closing priority;

[0054] generating a step-by-step closing control instruction according to the sorted interval to be closed list; wherein the step-by-step closing control instruction is used to step-by-step control the flood gate of each interval to be closed in the interval to be closed list to close.

[0055] In a third aspect, the application provides a computer device, which adopts the following technical solutions:

[0056] A computer device comprises a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to realize the steps of the method of the first aspect.

[0057] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the technical scheme as follows:

[0058] A computer-readable storage medium stores a computer program capable of being loaded and executed by a processor to perform any one of the methods in the first aspect.

[0059] In summary, the present application includes at least one of the following beneficial technical effects: by collecting the states of the flood prevention doors in each section of the underground facility and the external water level and rainfall data in real time, and based on the pre-trained risk warning model, the risk warning level is comprehensively analyzed and generated, so as to accurately identify the high-risk section that needs to be closed. The system sorts the closed sections according to the section closure priority, and generates step-by-step closure control instructions, ensuring that the flood prevention doors of high-priority sections are closed first, effectively reducing the risk of spreading, and improving the protection effect of the underground facility and the accuracy and efficiency of emergency response. BRIEF DESCRIPTION OF DRAWINGS

[0060] Figure 1 is a first flowchart of a linkage control method based on the states of the flood prevention doors in the sections according to an embodiment of the present application.

[0061] Figure 2 is a second flowchart of a linkage control method based on the states of the flood prevention doors in the sections according to an embodiment of the present application.

[0062] Figure 3 is a third flowchart of a linkage control method based on the states of the flood prevention doors in the sections according to an embodiment of the present application.

[0063] Figure 4 is a fourth flowchart of a linkage control method based on the states of the flood prevention doors in the sections according to an embodiment of the present application.

[0064] Figure 5 is a fifth flowchart of a linkage control method based on the states of the flood prevention doors in the sections according to an embodiment of the present application.

[0065] Figure 6 is a sixth flowchart of a linkage control method based on the states of the flood prevention doors in the sections according to an embodiment of the present application.

[0066] Figure 7 is a seventh flowchart of a linkage control method based on the states of the flood prevention doors in the sections according to an embodiment of the present application. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical scheme and advantages of the present application more clear, the following will be combined with the accompanying drawings to further describe the present application. Figures 1-7and the embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the application and should not be used in a limiting sense.

[0068] The embodiments of the application disclose a linkage control method based on interval floodgate state.

[0069] With reference to Figure 1 The linkage control method based on interval floodgate state comprises the following steps.

[0070] In step S101, real-time states of floodgates in each interval in underground facilities and external water level data and real-time rainfall data are collected.

[0071] The real-time state of the floodgate includes but is not limited to the opening and closing state of the door body, the communication state, the power state and the transmission system state and the like. The interval refers to the closed space between two points in the underground facilities, for example, between the subway stations, different paragraphs of the tunnel and the like. The interval floodgate refers to the flood prevention equipment arranged between these space paragraphs, which can be automatically controlled in linkage in the case of emergency such as flood and heavy rainfall.

[0072] Specifically, in the underground facilities (such as the subway or the tunnel), the opening and closing state data of the floodgate in each interval and the water level data and the rainfall data of the external environment are collected in real time by deploying a sensor network. The data collection module stores the collected information to the system database, so as to facilitate subsequent monitoring and analysis. Exemplarily, the sensors are arranged in the underground facilities to monitor the floodgate state of the A interval and the B interval in real time. The external water level data are monitored by the water level sensor, and the rainfall is received through the meteorological interface.

[0073] In step S102, the external water level data and the real-time rainfall data are input into a pre-trained risk warning model for comprehensive analysis to obtain a risk warning level.

[0074] Specifically, the water level data and the rainfall data are input into the risk warning model trained based on the historical data to evaluate the current risk warning level. The model can adopt a neural network algorithm, which can output the corresponding risk warning level by comprehensively considering the change trend of the water level and the rainfall.

[0075] It can be understood that the comprehensive analysis based on the multi-source data can realize more accurate risk warning, reduce the misjudgment caused by a single data, and improve the accuracy and timeliness of the warning.

[0076] In step S103, corresponding intervals to be closed are determined according to the risk warning level.

[0077] Among them, according to different risk warning levels, the system divides the interval into a closed interval and a monitoring interval, and a high risk level will trigger more closed intervals, and a low risk level will correspond to fewer closed intervals. For example, under the "high" warning level, the system determines that intervals A, B and C are all closed intervals; if the warning level is "medium", only intervals A and B are set as closed intervals.

[0078] It can be understood that through hierarchical closure control based on risk levels, the protection range is wider and the closure response is faster under high risk, enhancing the safety protection effect of the facility.

[0079] Step S104, according to the real-time state of the floodgate of each closed interval, determine the closed interval whose floodgate is in the open state, and obtain the closed interval list;

[0080] Among them, after determining the closed interval, the system further checks the real-time state of the floodgate of each interval, and filters and retains the closed interval in the "open" state in the closed interval list; for example, assuming that the floodgate state of closed interval A is "open", and the floodgate state of closed interval B is "closed", then only interval A is retained, and interval B does not need to be closed because it is already in the closed state.

[0081] It can be understood that by ensuring that the closure instruction is only sent to the interval that actually needs to be closed, unnecessary control instruction transmission is reduced, and control efficiency is improved.

[0082] Step S105, sort the closed interval list based on the preset interval closure priority;

[0083] Among them, in order to ensure personnel safety and asset protection, the system can preset the closure priority for each interval, and sort the closed interval list according to the priority, for example, high-risk or high-traffic intervals can be closed first;

[0084] For example, assuming that interval A is a key passage with a high priority, and interval B is a warehouse with a lower priority, the system will place interval A at the top of the closed interval list, so that the system can prioritize the protection of critical areas in the case of multiple closed intervals, optimizing the safety and timeliness of the closure process.

[0085] Step S106, generate a step-by-step closure control instruction according to the sorted closed interval list; wherein the step-by-step closure control instruction is used to gradually control the floodgate of each closed interval in the closed interval list to close.

[0086] Specifically, according to the ranked interval list, the system generates step-by-step closure control instructions, which are sent to the execution module of the corresponding floodgate in priority order, ensuring that the closure process is carried out in priority order, helping to protect important areas one by one in an emergency, and improving the safety and rationality of the linkage control.

[0087] In the above embodiments, real-time data inside and outside the underground facility is collected, a risk early warning model is used for comprehensive risk analysis, a more accurate risk assessment result is provided to determine the intervals to be closed and rank them according to priority, and the priority protection of high-risk intervals or important intervals is achieved; at the same time, the step-by-step closure strategy avoids the "one-size-fits-all" control of traditional methods, ensuring the safe closure of high-priority intervals and providing more flexible scheduling for personnel evacuation and subsequent protection, thereby realizing intelligent linkage control of the interval floodgate, improving the accuracy and timeliness of the flood control emergency response, and effectively protecting personnel safety and facility integrity.

[0088] Reference Figure 2 As an embodiment of the risk early warning model, the training steps of the risk early warning model include:

[0089] Step S201, obtaining a historical sample data set;

[0090] The historical sample data set includes historical external water level data, historical rainfall data, and pre-labeled risk early warning level labels.

[0091] In some embodiments, the risk early warning level labels are pre-labeled according to the actual risk situation caused by different water levels and rainfall in historical events, providing an effective learning goal for the model.

[0092] It can be understood that the acquisition of historical sample data provides the risk situation in the actual environment for the model, enabling the model to learn the risk assessment standard through real data and providing high-quality training samples for early warning level prediction.

[0093] Step S202, data preprocessing of the historical sample data set;

[0094] Specifically, since the historical sample data may contain noise, missing values, or abnormal data, the data preprocessing step can ensure the quality of the data input to the model; the data preprocessing usually includes missing value filling, abnormal value processing, normalization, etc., so that the data meets the unified numerical range and format standard before being input to the model.

[0095] For example, if some water level data is missing in the sample data, the system can fill it in by interpolation, normalize all water level values and rainfall data to the 0-1 interval, and ensure that different data magnitudes do not affect model training.

[0096] Step S203, the pre-processed historical sample data set is divided into a training set, a validation set and a test set;

[0097] The training set is used for model learning, the validation set is used for model parameter adjustment, and the test set is used for evaluating the performance of the model on unseen data to avoid model overfitting. For example, 70% of the sample data can be allocated as the training set, 15% as the validation set, and 15% as the test set.

[0098] Step S204, the pre-constructed long short-term memory network model is initially trained based on the training set, and the long short-term memory network model after initial training is verified and the model parameters are optimized based on the validation set and the test set, to obtain a risk warning model.

[0099] Specifically, the long short-term memory network (LSTM) is a relatively optimal neural network model selection, which is good at processing time series data and can well capture the trend and pattern of water level and rainfall over time, and is very suitable for the risk warning scenario based on water level and rainfall in the present application.

[0100] The network structure of the risk warning model obtained based on the long short-term memory network in the present application includes an input layer, an LSTM layer, a fully connected layer and an output layer. The input layer is mainly used to receive time series data, including historical water level data and rainfall data, and each time step corresponds to a set of features (for example, the combination of water level and rainfall). The LSTM layer includes one or more LSTM units, which is responsible for processing the time series relationship of the input data and can effectively understand the trend of the current risk level by remembering the water level and rainfall information of the previous steps. The fully connected layer is used to pass the output of the LSTM layer to the fully connected layer and convert the time series output to an output space suitable for classification tasks. The output layer is used to output the probability distribution of different risk warning levels (such as “low”, “medium” and “high”).

[0101] During the training process, the data of the training set is input into the LSTM model according to the time step, and the model gradually adjusts the network parameters through back propagation and gradient descent algorithm, so that the output risk warning level is closer to the label. The LSTM layer can extract patterns in multi-step time data through memory and forgetting mechanism to realize prediction of the current risk level. After training, the system evaluates the accuracy of the model through the validation set, and optimizes the model performance by adjusting the learning rate, regularization parameters, etc. Finally, the generalization effect of the model on unknown data is evaluated through the test set to ensure the performance of the model in the actual environment.

[0102] In the above embodiments, the system can learn the rules and patterns of risk warning levels from the time series data of water levels and rainfall, and the advantages of LSTM models in processing time series data make them particularly suitable for the risk warning needs of underground facilities, enabling accurate prediction of risk levels at different time steps and providing efficient support for the closing control and warning response of flood prevention gates.

[0103] With reference to Figure 3 As an embodiment of step S204, the pre-constructed long short-term memory network model is initially trained based on the training set, and the long short-term memory network model after initial training is verified and the model parameters are optimized based on the verification set and the test set to obtain the risk warning model.

[0104] Step S301, input the training set into the pre-constructed long short-term memory network model for training, optimize the model parameters and calculate the combined loss function of the model until the combined loss function meets the preset condition, and obtain the trained risk warning model.

[0105] The combined loss function includes a prediction error and a regularization term.

[0106] In one embodiment of the present application, the training set data is input into the pre-constructed LSTM model for initial training. The training process uses a gradient descent algorithm to gradually optimize the model parameters through backpropagation. The model measures the gap between the predicted value and the actual label by calculating the combined loss function (which specifically includes a prediction error and a regularization term). The value of the combined loss function is used to evaluate the performance of the model. The system continuously adjusts the model parameters until the combined loss function reaches the preset condition (i.e., the loss function value is less than a certain threshold or there is no significant decrease after multiple iterations) to ensure the convergence of the model error.

[0107] Step S302, verify the risk warning model according to the verification set, evaluate the performance of the risk warning model and adjust the hyperparameters of the risk warning model.

[0108] Specifically, after initial training is complete, the system inputs the verification set data into the model for verification, the purpose of which is to evaluate the generalization ability of the model on unseen data. During the verification process, the system evaluates the performance indicators (such as accuracy, recall rate, F1 score, etc.) of the model to determine the suitability of the model. If the model performance does not meet expectations, the system can optimize the model performance by adjusting the hyperparameters (such as learning rate, LSTM unit number, regularization coefficient, etc.) of the model to reduce overfitting or underfitting.

[0109] Step S303, test the prediction accuracy of the adjusted risk warning model according to the test set.

[0110] Specifically, after the hyperparameter adjustment is completed, the system uses the test set to perform a final evaluation on the model, testing the prediction accuracy of the model on unseen data. The test set data does not participate in the training and validation process, ensuring that the evaluation results reflect the performance of the model in actual application, and confirming the prediction accuracy and stability of the model by analyzing the test results. In some embodiments, the test indicators can include accuracy, recall, mean square error, etc.

[0111] In the above implementation, the multi-stage process of optimizing model parameters through the training set, adjusting hyperparameters through the validation set, and testing generalization performance through the test set builds a robust LSTM risk warning model. This model can effectively predict the risk level based on water level and rainfall, providing scientific support for risk warning and protection of underground facilities, and ensuring that the model has high accuracy and reliability in actual application.

[0112] Referring to Figure 4 As an embodiment of step S103, the step of determining the corresponding interval to be closed according to the risk warning level includes:

[0113] Step S401, determine whether the risk warning level exceeds the corresponding safety threshold; if yes, jump to step S402; if no, do not perform any operation;

[0114] Among them, after receiving the latest risk warning level, the system first determines whether the level exceeds the preset safety threshold. The risk warning level is generated based on real-time monitoring of water level, rainfall and other environmental data. If the risk warning level is higher than the safety threshold, it indicates that there is a high potential risk in the current situation, and more stringent closure measures need to be taken to ensure the safety of the facility.

[0115] Step S402, determine the interval closure range according to the risk warning level;

[0116] Specifically, when the risk warning level exceeds the safety threshold, the system determines the specific interval closure range according to the warning level. High risk levels usually correspond to larger closure intervals to cover areas with higher potential risks and prevent water flow or other disasters from spreading to adjacent areas.

[0117] Step S403, generate an interval structure diagram according to the interval structure information of each interval in the underground facility;

[0118] Among them, the system retrieves the structure information of each interval in the underground facility from the database, including the adjacent relationship of the interval, the connection of the channel, the main function (such as the channel, the storage area, etc.), the personnel flow and the importance level, etc. According to these data, the interval structure diagram is generated to clearly show the position relationship and connection of each interval, providing support for subsequent closure decision-making.

[0119] Step S404, identifying each interval to be closed in the interval structure diagram according to the interval closure range.

[0120] The system combines the determined closure range with the interval structure diagram, and identifies each interval to be closed on the structure diagram. The identification information of each interval to be closed includes its position and adjacent relationship with other intervals.

[0121] In the above embodiment, first, it is judged whether the risk level exceeds the safety threshold. If it exceeds, the interval closure range is set according to the warning level, the structure diagram is generated, and the interval to be closed is identified. Thus, the goal of dynamically adjusting the closure range and determining the priority closure interval according to different risk levels is achieved, which effectively improves the flexibility and scientificity of emergency protection, ensures that the key area can be quickly closed in a high-risk state, and reasonably allocates resources to protect the safety of personnel and assets.

[0122] With reference to Figure 5 As a further embodiment of the linkage control method, after the step of sorting the list of intervals to be closed based on the preset interval closure priority, the method further includes:

[0123] Step S501, acquiring the real-time state of the floodgate in each interval to be closed in the list of intervals to be closed;

[0124] The real-time state of the floodgate includes the communication state, the power state, and the transmission system state.

[0125] Specifically, after sorting the list of intervals to be closed by priority, the system further acquires the real-time state information of the floodgate in each interval to be closed, to ensure that the system has a comprehensive understanding of the operability of the floodgate before performing the closure operation, and to ensure that the closure operation will not fail due to floodgate failure; wherein the real-time state of the floodgate includes the communication state, the power state, and the transmission system state.

[0126] For example, assuming that intervals A, B, and C are determined as intervals to be closed, the system acquires the communication state (whether online), the power state (sufficiency of power or power switching condition), and the transmission system state (whether there is abnormality such as jamming or resistance when opening or closing) of the floodgate in these intervals.

[0127] Step S502, respectively judging whether the real-time state of the floodgate in each interval to be closed is abnormal, if yes, jumping to step S503; if no, returning to step S502 to continue judging the real-time state of the floodgate in the next interval to be closed;

[0128] Step S503, determining the interval to be closed whose real-time state of the floodgate is abnormal as an abnormal interval;

[0129] If the communication state shows offline, the power state is abnormal, or the transmission system fails, the system marks the floodgate as "abnormal state". By identifying potential abnormal floodgates in time, it ensures that problems can be found before the closure operation, thereby avoiding operation failure in actual closure.

[0130] Step S504: Increase the closure priority of the interval adjacent to the abnormal interval in the list of intervals to be closed, and remove the abnormal interval from the list of intervals to be closed.

[0131] Specifically, once the real-time state of the floodgate is detected to be abnormal, the system removes the interval from the list of intervals to be closed and marks it as an "abnormal interval" to avoid the situation where the closure instruction cannot be executed due to the abnormal floodgate.

[0132] It can be understood that, since the floodgate of the abnormal interval cannot be normally closed, the system will increase the closure priority of the interval adjacent to it to form a replacement protection, thereby making up for the security gap of the abnormal interval by ensuring that the protection of the adjacent interval is completed earlier, which can effectively deal with the abnormal situation of a single interval.

[0133] For example, if interval A is an abnormal interval, the system will increase the closure priority of interval B adjacent to it from medium priority to high priority to ensure that the protection of interval B is completed earlier near the abnormal interval.

[0134] Step S505: Generate maintenance alarm information according to the position information and type of the abnormal interval and send it to the maintenance terminal.

[0135] The maintenance alarm information includes the position of the abnormal interval, the type of the abnormal interval (communication failure, power failure, or transmission failure, etc.), and the information is sent to the maintenance terminal to ensure that maintenance personnel can understand and take repair measures in time, providing support for subsequent closure operations and overall security protection.

[0136] In the above embodiments, the state of the floodgate is detected before the closure instruction is generated, and the abnormal interval is screened out to ensure that the closure operation only covers intervals with normal states, reducing the security gap caused by abnormal floodgates. At the same time, the steps of increasing the priority of adjacent intervals and sending maintenance alarms further enhance the flexibility and emergency response capability of the system, making it more stable to ensure the safety of underground facilities in emergency situations.

[0137] Referring to Figure 6 As a further embodiment of the linkage control method, after the step of generating maintenance alarm information and sending it to the maintenance terminal, the method further includes:

[0138] Step S601, real-time receiving maintenance feedback information of the maintenance terminal and judging whether the maintenance is successful; if yes, jumping to step S602; if no, jumping to step S603;

[0139] Specifically, the system monitors the feedback information of the maintenance terminal in real time after sending the maintenance alarm information. After the maintenance personnel complete the repair operation, the maintenance terminal feeds back the maintenance state (such as repair completion or repair failure). The system judges whether the normal function of the floodgate is successfully restored according to the feedback information, ensures the operability of the floodgate in emergency is effectively recovered, and lays a foundation for the subsequent closure instruction execution.

[0140] Illustratively, the floodgate drive system of the A interval is abnormal, and the maintenance personnel performs maintenance repair after receiving the alarm. After completing the repair, the maintenance personnel feeds back the “repair completion” state through the maintenance terminal. The system receives this feedback information and judges that the maintenance is successful.

[0141] Step S602, restoring the abnormal interval to the to-be-closed interval and adding it to the to-be-closed interval list;

[0142] Specifically, when the system judges that the maintenance is successful, the abnormal interval is automatically marked as “to-be-closed interval” again, and is added to the to-be-closed interval list to perform closure control according to the original or updated priority order. This process ensures that the interval after repair can restore the normal closure function, and improves the overall protection ability of the system.

[0143] Step S603, modifying the abnormal interval to the to-be-monitored interval, and sending an emergency alarm signal to the maintenance terminal when the water level and environmental state of the to-be-monitored interval are abnormal.

[0144] Specifically, if the system receives the “repair failure” feedback information from the maintenance terminal, the interval is marked as “to-be-monitored interval”, indicating that the interval cannot restore the closure function under the current conditions and needs to be transferred to the monitoring state. By timely adjusting the state of the interval that cannot be restored, the system can focus on resources to protect other closable intervals, improve the resource utilization efficiency of the system, and reduce invalid operations. For example, if the floodgate of the A interval fails in the repair of the drive system, the system marks the A interval as “to-be-monitored interval” and does not issue a closure instruction to it.

[0145] It should be noted that for the to-be-monitored interval in an abnormal state and unable to be maintained in time, the water level and environmental state (such as humidity data) in the tracking interval should be monitored in real time, and when the water level continuously rises or the humidity exceeds the set threshold, an emergency alarm is triggered to the maintenance terminal, so as to timely upgrade the closure priority of the adjacent interval or set temporary protection and the like according to the risk change. For example, temporary protection equipment such as an emergency water pump, a temporary water baffle and the like can be deployed in advance near the to-be-monitored interval, so as to control the water level in the interval within an acceptable range or prevent the water from spreading to the adjacent interval in an emergency, which helps to improve the emergency response capability of the whole system.

[0146] In the above embodiment, the interval state is dynamically adjusted according to the real-time received maintenance feedback, and an emergency alarm mechanism is established, so that in the case of abnormality of the flood prevention door, the system can quickly judge and process the maintenance result, and realize dynamic management of the interval. In addition, for the interval with failed maintenance, by setting the "to-be-monitored" state and monitoring the environmental data in real time, the system can timely alarm and take measures when a sudden risk occurs. This technical scheme significantly improves the flexibility, emergency response capability and protection efficiency of the system, and provides more robust protection for underground facilities.

[0147] Reference Figure 7 As a further embodiment of the linkage control method, before the step of generating the step-by-step closure control instruction according to the sorted to-be-closed interval list, the method further comprises:

[0148] Step S701, detecting personnel distribution data of each to-be-closed interval in the to-be-closed interval list in real time;

[0149] The personnel distribution data of each interval is collected in real time by the personnel detection sensor arranged in each to-be-closed interval, and these data will be used to judge the personnel distribution density in each interval, and provide basis for subsequent evacuation decision.

[0150] It can be understood that when the subway or tunnel encounters rising water level or sudden flood, the personnel density in each interval is directly related to the evacuation demand, and real-time detection of personnel data can enable the system to timely understand the personnel situation of each interval, and provide key support for subsequent alarm and evacuation, to ensure the safety of passengers and staff.

[0151] Step S702, determining the personnel density level of each to-be-closed interval according to the personnel distribution data;

[0152] The division of the personnel density level enables the system to distinguish the personnel density of each interval, so as to accurately issue a closure alarm, especially in high-density areas, through a higher alarm level to remind personnel to evacuate, which can effectively avoid congestion and ensure the safety and order of the evacuation process.

[0153] Step S703, determining the corresponding alarm level according to the personnel density level;

[0154] Specifically, the system sets an alarm level for each to-be-closed section according to the personnel density level, for example, the alarm level is divided into low, medium and high, corresponding to different alarm modes and intensities, to ensure that the personnel in the high-density area can obtain clear alarm information in the first time, thereby effectively reminding the personnel in the high-density area to evacuate quickly, ensuring the safety of the high-density area, avoiding resource waste, reducing excessive alarm in the low-density area, and preventing panic from spreading.

[0155] Step S704, generating corresponding closure alarm information according to the alarm level, and sending the closure alarm information to the alarm module of each to-be-closed section;

[0156] The closure alarm information includes closure alarm prompts and personnel evacuation routes.

[0157] Specifically, the system generates corresponding closure alarm information according to different alarm levels, and the alarm information includes closure prompts and evacuation routes. The closure prompts can be issued to the personnel in the to-be-closed section through sound and light alarms, voice broadcasts, and on-screen text, and the evacuation routes provide the best evacuation direction for the personnel according to the current traffic state.

[0158] For example, when the A section triggers a medium-level alarm, the system issues a sound and light alarm in the A section and displays closure prompts and evacuation route guidance; the B section triggers a low-level alarm and only displays closure prompts and evacuation directions, and the C section does not make any prompts. Through hierarchical alarm and intelligent evacuation guidance, the application can greatly improve the safety and emergency efficiency of the protection system, and is particularly suitable for underground facilities such as subways and tunnels where personnel are concentrated.

[0159] In the above embodiments, in the event of an emergency, clear closure alarms and explicit evacuation guidance can provide timely evacuation guidance for personnel. Through intelligent allocation of different alarm levels and evacuation routes, not only can the evacuation of the crowd be guided to avoid unnecessary congestion, but also the orderliness of the evacuation process of underground facilities such as subways and tunnels can be ensured.

[0160] In actual application, the application has important practical significance in flood and flood prevention management of underground facilities. By accurately analyzing real-time water level and rainfall data, dynamically determining risks and linking control of the closing sequence of the flood prevention door, the high-risk section is preferentially protected, the timeliness and accuracy of emergency response are improved, and the safety of facilities and personnel is ensured in the event of a disaster, reducing the loss caused by floods or sudden floods to underground facilities.

[0161] The application also discloses a linkage control system based on the state of the section flood prevention door.

[0162] A linkage control system based on the state of interval floodgate, the linkage control system comprises:

[0163] Collecting the real-time state of the floodgate of each interval in the underground facility, and external water level data and real-time rainfall data;

[0164] Inputting the external water level data and real-time rainfall data into a pre-trained risk warning model for comprehensive analysis to obtain a risk warning level;

[0165] Determining corresponding intervals to be closed according to the risk warning level;

[0166] According to the real-time state of the floodgate of each interval to be closed, determining the interval to be closed whose floodgate is in an open state to obtain a list of intervals to be closed;

[0167] Sorting the list of intervals to be closed based on a preset interval closing priority;

[0168] Generating a step-by-step closing control instruction according to the sorted list of intervals to be closed; wherein the step-by-step closing control instruction is used to gradually control the floodgate of each interval to be closed in the list of intervals to be closed to close.

[0169] In the above embodiment, by collecting the state of the floodgate of each interval in the underground facility, and external water level and rainfall data in real time, a risk warning level is generated based on a pre-trained risk warning model for comprehensive analysis, thereby accurately identifying high-risk intervals that need to be closed. The system sorts the intervals to be closed according to the interval closing priority and generates a step-by-step closing control instruction to ensure that the floodgates of high-priority intervals are closed first, effectively reducing the risk of spreading and improving the protection effect of the underground facility and the accuracy and efficiency of emergency response.

[0170] The linkage control system based on the state of interval floodgate according to the embodiment of the present application can implement any of the above linkage control methods based on the state of interval floodgate, and the specific working process of each module in the linkage control system can refer to the corresponding process in the above method embodiment.

[0171] In several embodiments provided in the present application, it should be understood that the provided methods and systems can be implemented in other ways. For example, the above-described system embodiments are only illustrative; for example, the division of a certain module is only a logical functional division, and actual implementation can have another division manner, for example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0172] The embodiment of the present application also discloses a computer device.

[0173] The computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the interval floodgate state-based linkage control method when executing the computer program.

[0174] The application further discloses a computer readable storage medium.

[0175] The computer readable storage medium stores a computer program capable of being loaded and executed by the processor to implement any one of the interval floodgate state-based linkage control methods.

[0176] The computer readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, device or apparatus; the program code contained in the computer readable medium can be transmitted by any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any appropriate combination of the above.

[0177] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0178] The above are preferred embodiments of the application, and are not intended to limit the protection scope of the application, any feature disclosed in the specification (including the abstract and the drawings) can be replaced by other equivalent or similar features unless specifically described, that is, each feature is only an example of a series of equivalent or similar features.

Claims

1. A linkage control method based on the status of flood prevention gates in a section, characterized in that, The linkage control method includes: Collect real-time status of floodgates in various sections of the underground facility, as well as external water level data and real-time rainfall data; The external water level data and real-time rainfall data are input into a pre-trained risk warning model for comprehensive analysis to obtain the risk warning level. The corresponding areas to be closed are determined based on the aforementioned risk warning levels; Based on the real-time status of the floodgates of each of the sections to be closed, determine the sections to be closed where the floodgates are in the open state, and obtain a list of sections to be closed. The list of intervals to be closed is sorted based on a preset interval closure priority. Based on the sorted list of sections to be closed, a gradual closure control instruction is generated; wherein, the gradual closure control instruction is used to gradually control the floodgates of each section to be closed in the list of sections to be closed to close. The control method further includes a training step for the risk warning model, the training step comprising: Obtain a historical sample dataset; wherein, the historical sample dataset includes historical external water level data and historical rainfall data, as well as pre-labeled risk warning level tags; The historical sample dataset is preprocessed. The preprocessed historical sample dataset is divided into a training set, a validation set, and a test set; The training set is input into a pre-built long short-term memory network model for training. The model parameters are optimized and the combined loss function of the model is calculated until the combined loss function meets the preset conditions, thus obtaining the trained risk warning model. The combined loss function includes prediction error and regularization term. The risk warning model is validated based on the validation set, its performance is evaluated, and its hyperparameters are adjusted. The prediction accuracy of the adjusted risk warning model is tested based on the test set.

2. The linkage control method based on the status of flood prevention gates in a section according to claim 1, characterized in that, The steps for determining the corresponding areas to be closed based on the risk warning level include: Determine whether the risk warning level exceeds the corresponding safety threshold; if so, determine the corresponding closed area based on the risk warning level. Generate a section structure diagram based on the section structure information of each section within the underground facility; Each interval to be closed is identified in the interval structure diagram according to the interval closure range.

3. The linkage control method based on the status of flood prevention gates in a section according to claim 2, characterized in that, After the step of sorting the list of intervals to be closed based on a preset interval closure priority, the method further includes: Obtain the real-time status of the floodgates of each section to be closed in the list of sections to be closed; wherein, the real-time status of the floodgates includes communication status, power status and transmission system status; Determine whether there is any abnormality in the real-time status of the floodgates in each section to be closed. If so, the section to be closed in which the real-time status of the floodgates is abnormal is identified as an abnormal section. Increase the closing priority of the intervals to be closed that are adjacent to the location of the abnormal interval in the list of intervals to be closed, and remove the abnormal interval from the list of intervals to be closed; Based on the location information and anomaly type of the abnormal range, maintenance alarm information is generated and sent to the maintenance terminal.

4. The linkage control method based on the status of flood prevention gates in a section according to claim 3, characterized in that, The process, following the step of generating maintenance alarm information and sending it to the maintenance terminal, also includes: Receive maintenance feedback information from the maintenance terminal in real time and determine whether the maintenance was successful; If so, the abnormal interval is restored to a pending interval and added to the pending interval list; If not, the abnormal range will be modified and marked as a monitoring range, and an emergency alarm signal will be sent to the maintenance terminal when there are abnormalities in the water level and environmental conditions of the monitoring range.

5. A linkage control method based on the status of a flood prevention gate according to any one of claims 1 to 4, characterized in that, Before the step of generating the progressive closure control instruction based on the sorted list of intervals to be closed, the following steps are also included: Real-time monitoring of personnel distribution data in each of the areas to be closed in the list of areas to be closed; The population density level of each area to be closed is determined based on the population distribution data. The corresponding alarm level is determined based on the personnel density level; Based on the alarm level, a corresponding closure alarm message is generated and sent to the alarm module of each area to be closed; wherein, the closure alarm message includes a closure alarm prompt and personnel evacuation routes.

6. A linkage control system based on the status of flood prevention gates in a section, characterized in that, A linkage control method based on the status of a flood prevention gate according to any one of claims 1 to 5, wherein the linkage control system comprises: Collect real-time status of floodgates in various sections of the underground facility, as well as external water level data and real-time rainfall data; The external water level data and real-time rainfall data are input into a pre-trained risk warning model for comprehensive analysis to obtain the risk warning level. The corresponding areas to be closed are determined based on the aforementioned risk warning levels; Based on the real-time status of the floodgates of each of the sections to be closed, determine the sections to be closed where the floodgates are in the open state, and obtain a list of sections to be closed. The list of intervals to be closed is sorted based on a preset interval closure priority. Based on the sorted list of sections to be closed, a gradual closure control instruction is generated; wherein, the gradual closure control instruction is used to gradually control the floodgates of each section to be closed in the list of sections to be closed to close.

7. A computer device, characterized in that: The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer program is stored that can be loaded by a processor and executed as described in any one of claims 1 to 5.

Images