A method, system, equipment, and medium for generating a liquid nitrogen fire extinguishing scheme for cable trenches.

Abstract

This invention provides a method, system, equipment, and medium for generating liquid nitrogen fire extinguishing schemes in cable trenches, belonging to the field of intelligent fire prevention and control. It includes acquiring structural data and real-time sensor monitoring data of the cable trench to obtain prediction results of corresponding fire spread trend data, liquid nitrogen cooling temperature field change data, and oxygen concentration replacement data. Based on the prediction results, a target optimization algorithm is used to search for parameter combinations to obtain the optimal parameter combination. Real-world environmental data of the fire scene is acquired, and the measured data is dynamically compared with the prediction results for correction feedback. Based on the corrected prediction results, the target optimization algorithm is used to recalculate and obtain a real-time adjusted fire extinguishing scheme. This achieves accurate fire identification, adaptive fire extinguishing control, and optimized resource allocation, significantly improving fire extinguishing efficiency and reducing equipment damage risk.

Description

Technical Field

[0001] This invention belongs to the field of intelligent fire prevention and control, specifically relating to a method, system, equipment, and medium for generating a liquid nitrogen fire extinguishing scheme for cable trenches. Background Technology

[0002] Cable trenches, as core channels for urban power transmission, are densely packed with cables in an enclosed environment. Once a fire breaks out, it can easily trigger a series of chain reactions, including widespread power outages and equipment explosions. Furthermore, the fire is often concealed and difficult to extinguish. Traditional water-based firefighting methods can easily cause short circuits and secondary damage to equipment, threatening public safety and the stable operation of the power grid.

[0003] Liquid nitrogen possesses typical fire extinguishing characteristics such as rapid cooling, total flooding and oxygen-free asphyxiation, and no toxic residue after extinguishing, making it a highly efficient fire extinguishing medium for cable trench fires. However, existing liquid nitrogen fire extinguishing systems for cable trenches mostly employ fixed threshold triggering mechanisms, resulting in static response defects, including limited data dimensions, inconsistent spray ranges, low alarm accuracy, and high delays. These systems cannot adapt to real-time dynamic changes in the fire situation, leading to resource waste and low fire extinguishing efficiency. Summary of the Invention

[0004] To address the limitations of existing liquid nitrogen fire extinguishing technologies for cable trenches, this invention provides a method, system, equipment, and medium for generating liquid nitrogen fire extinguishing solutions for cable trenches.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A method for generating a liquid nitrogen fire extinguishing scheme for cable trenches includes the following steps:

[0007] The structural data of the cable trench and the real-time monitoring data of the sensors are acquired. Based on the structural data of the cable trench and the real-time monitoring data of the sensors, fire prediction is performed to obtain the prediction results of fire spread trend data, liquid nitrogen cooling temperature field change data and oxygen concentration replacement data.

[0008] Based on the prediction results, a parameter combination search is performed using an objective optimization algorithm to obtain a Pareto solution. The objective function values ​​of all candidate solutions in the Pareto solution are calculated to obtain the optimal parameter combination. A fire extinguishing scheme is obtained based on the optimal parameter combination. The optimal parameter combination includes the location and number of nitrogen injection ports, the flow rate of each nitrogen injection port, and the injection duration and sequence.

[0009] The system acquires environmental measurement data from the fire scene and dynamically compares the measured data with the prediction results. If the deviation between the prediction results and the measured data exceeds a set value, a feedback correction mechanism is triggered. Based on the measured data, the system re-predicts the fire spread trend data, liquid nitrogen cooling temperature field change data, and oxygen concentration replacement data to obtain the corrected prediction results. Based on the corrected prediction results, the system recalculates using a target optimization algorithm to obtain a real-time adjusted fire extinguishing plan.

[0010] Preferably, fire prediction is performed based on the structural data of the cable trench and the real-time monitoring data of the sensors to obtain prediction results for fire spread trend data, liquid nitrogen cooling temperature field change data, and oxygen concentration replacement data. Specifically, the real-time monitoring data of the sensors is input into the fire spread prediction model to obtain the prediction results for the fire spread trend data; the structural data of the cable trench and the real-time monitoring data of the sensors are input into the liquid nitrogen diffusion cooling model to obtain the prediction results for the liquid nitrogen cooling temperature field change data; and the structural data of the cable trench is input into the oxygen concentration replacement model to obtain the prediction results for the oxygen concentration replacement data.

[0011] Preferably, before inputting the structural data of the cable trench and the real-time monitoring data of the sensors into the fire spread prediction model, the liquid nitrogen diffusion cooling model, and the oxygen concentration replacement model, the method further includes acquiring historical sensor monitoring data and historical fire case data; using the historical sensor monitoring data as input features and the fire spread trend data of the historical fire case data as output, training an LSTM time series model to obtain a fire spread prediction model; using the structural data of the cable trench and the historical sensor monitoring data as input, and the liquid nitrogen cooling temperature field change data of the historical fire case data as output, training a random forest model to obtain a liquid nitrogen diffusion cooling model; using the structural data of the cable trench as input and the oxygen replacement data of the historical fire case data as output, training a support vector regression or random forest regression model to obtain an oxygen concentration replacement model.

[0012] Preferably, acquiring the structural data of the cable trench specifically includes:

[0013] The cable trench structure was reconstructed using FDS and CFD numerical simulation software to obtain a numerical simulation model of the cable trench.

[0014] The structural data of the cable trench were obtained based on the numerical simulation model.

[0015] Preferably, the fire spread trend data specifically refers to the flame spread path and the spread rate per unit time; the liquid nitrogen cooling temperature field change data specifically refers to the temperature gradient change and the decrease in oxygen concentration per unit time; and the oxygen replacement data specifically refers to the local oxygen volume.

[0016] Preferably, the method further includes using a Realizable k-ε turbulence model and a deformable component model to simulate and obtain data on the oxygen concentration decrease rate and temperature gradient change during the liquid nitrogen diffusion and transport process in liquid nitrogen fire extinguishing. The oxygen concentration decrease rate is used to train the oxygen concentration replacement model, and the temperature gradient change data is used to train the liquid nitrogen diffusion cooling model.

[0017] Preferably, the method further includes constructing a multi-objective loss function with the optimization objectives of shortest fire extinguishing time, minimum liquid nitrogen usage, and minimum overall loss, and using the loss function to calculate the objective function value; the multi-objective loss function is specifically as follows:

[0018] ;

[0019] in, This indicates the time it takes for the fire to be effectively controlled to a safe threshold during firefighting. Indicates the total amount of liquid nitrogen used; This represents the overall loss value;

[0020] The objective function for the shortest fire extinguishing time is as follows:

[0021] ;

[0022] in, Represents any point in space within the cable trench; This represents the temperature at position x at time t; This indicates the set safe temperature threshold. This represents the volume fraction of oxygen at position x at time t. This indicates the safe oxygen concentration threshold required for fire extinguishing.

[0023] The objective function for minimizing liquid nitrogen usage is:

[0024] ;

[0025] in, Indicates the number of liquid nitrogen injection nozzles; This represents the liquid nitrogen injection flow rate at the i-th injection port at time t; This indicates the duration of continuous injection from the i-th nozzle;

[0026] The objective function for minimizing the overall loss is:

[0027] ;

[0028] in, Indicates the critical temperature that the cable or equipment can withstand; Represents the carbon monoxide concentration field; This indicates the upper limit of the safe concentration of carbon monoxide; This represents the weighting coefficients for losses caused by exceeding temperature and gas limits.

[0029] This invention also provides a liquid nitrogen fire extinguishing scheme generation system for cable trenches, specifically comprising:

[0030] The data prediction module is used to acquire structural data of the cable trench and real-time monitoring data from sensors. Based on the structural data of the cable trench and the real-time monitoring data from sensors, fire prediction is performed to obtain prediction results of fire spread trend data, liquid nitrogen cooling temperature field change data, and oxygen concentration replacement data.

[0031] The fire extinguishing scheme generation module is used to perform parameter combination search based on the prediction results using a target optimization algorithm to obtain a Pareto solution, calculate the objective function value of all candidate solutions in the Pareto solution to obtain the optimal parameter combination, and obtain a fire extinguishing scheme based on the optimal parameter combination. The optimal parameter combination includes the location and number of nitrogen injection ports, the flow rate of each nitrogen injection port, and the injection duration and sequence.

[0032] The correction module is used to acquire environmental measurement data of the fire scene, dynamically compare the measurement data with the prediction results, and if the deviation between the prediction results and the measurement data exceeds a set value, the feedback correction mechanism is triggered. Based on the measurement data, the fire spread trend data, liquid nitrogen cooling temperature field change data, and oxygen concentration replacement data are re-predicted to obtain the corrected prediction results. Based on the corrected prediction results, the target optimization algorithm is used to recalculate and obtain the real-time adjusted fire extinguishing plan.

[0033] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps described in the method for generating a liquid nitrogen fire extinguishing scheme for cable trenches.

[0034] The present invention also provides a computer-readable storage medium storing a computer program, which, when loaded by a processor, is capable of executing the steps described in the method for generating a liquid nitrogen fire extinguishing scheme for cable trenches.

[0035] The method for generating a liquid nitrogen fire extinguishing scheme for cable trenches provided by this invention has the following beneficial effects:

[0036] This invention improves upon traditional methods by integrating various data collected during cable trench firefighting to predict fire conditions, addressing the issue of limited data dimensions. Based on this fire condition prediction, a target optimization algorithm searches for optimal parameter combinations across multiple objectives. This optimal parameter combination yields the firefighting plan, mitigating the waste of liquid nitrogen resources caused by rigid firefighting range and dosage settings, and enabling intelligent optimization of liquid nitrogen injection strategies in complex scenarios. Simultaneously, a feedback correction mechanism is implemented based on real-time fire scene data to dynamically adjust the predicted fire condition values, ensuring the plan adapts to dynamic changes in the fire situation and enhancing the ability to respond to disturbances and sudden changes in real time. This achieves precise firefighting and optimized resource allocation in cable trench fires. Attached Figure Description

[0037] To more clearly illustrate the embodiments and design schemes of the present invention, the accompanying drawings required for this embodiment will be briefly described below. The drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating a method for generating a liquid nitrogen fire extinguishing scheme for cable trenches, as described in an embodiment of the present invention.

[0039] Figure 2 This is a flowchart illustrating a method for generating a liquid nitrogen fire extinguishing scheme for cable trenches, according to an embodiment of the present invention.

[0040] Figure 3 This is a numerical simulation model of a cable trench according to an embodiment of the present invention. Detailed Implementation

[0041] To enable those skilled in the art to better understand and implement the technical solutions of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be construed as limiting the scope of protection of the present invention.

[0042] Example

[0043] This invention provides a method for generating a liquid nitrogen fire extinguishing scheme for cable trenches, such as... Figure 1 and Figure 2 As shown, the specific steps include:

[0044] S1: Collect historical fire data, cable trench structural parameter data, and on-site sensor data for the cable trench. Specific data includes: cable trench structural dimensions, ventilation system information, cable distribution, cable type, voltage level, temperature and humidity, wind speed, oxygen concentration, fire source location, fire spread rate, and historical liquid nitrogen extinguishing effectiveness.

[0045] S11: Utilize web crawling and other technologies to acquire and aggregate historical fire case data for cable trenches from the internet, including data such as fire start time, fire spread time, fire severity, firefighting methods, and firefighting efficiency. The data is standardized and one-hot encoded to improve accuracy and address discretization issues.

[0046] S12: The DHT22 temperature and humidity sensor and GM8901 anemometer are used to collect temperature, humidity and wind speed data in the environment in real time at a sampling frequency of 1Hz. The CO concentration distributed in the environment is dynamically captured by the FLIR A615 infrared thermal imager and MQ-2 smoke sensor, and the obtained sensor data is cleaned.

[0047] S13: Import cable trench design drawings into BIM modeling software and extract its three-dimensional topology data, including geometric dimensions, ventilation coordinates, cable support distribution, coordinates of key nodes (turns, branches), obstacle locations, and distribution matrix of cable types and voltage levels.

[0048] S2: Perform FDS numerical simulation and CFD numerical simulation on the structural parameter data of the cable trench, and construct a liquid nitrogen fire extinguishing database for the cable trench by combining the historical fire data and on-site sensor data obtained in step 1. Save the acquired data in the data storage layer.

[0049] S21: Reconstruct the cable trench structure data using FDS and CFD numerical simulation software, and build a structure such as... Figure 3 The numerical simulation model shown retains key structures such as ventilation openings, cable supports, and fireproof partitions. Cable bundles are treated as equivalent structures (cables with a diameter ≥ 20mm are modeled separately, while the rest are simplified to cuboid obstacles based on volume equivalents).

[0050] S22: Unstructured meshes are used to refine the mesh in the local fire source area and near the nitrogen injection port. Specifically, the mesh size in the fire source area is 0.05m x 0.05m x 0.05m, the mesh size in the liquid nitrogen diffusion area is 0.1m x 0.1m x 0.1m, and the maximum mesh size for the remaining areas is ≤0.3m. For FDS fire spread simulation, a heat release rate of 500 kW / m² is used. 2 The fire source was replaced by the fire source on the surface of the cable. At the same time, thermocouples and slices were used to detect data such as temperature and carbon monoxide concentration around the fire source, so as to obtain temperature field distribution data, smoke concentration distribution data and heat radiation flux in the fire field during the fire spread process.

[0051] S23: For the diffusion and transport process of liquid nitrogen, the Euler-Lagrange method is used: a Realizable k-ε turbulence model is employed to simulate the turbulent flow characteristics of the continuous phase (air), and a Deformable Part Model (DPM) is used to simulate the motion and evaporation process of the discrete phase (liquid nitrogen droplets). The DPM model parameters are specifically set as follows: particle size distribution 50-200 μm. The liquid nitrogen physical properties are set as follows: density: 808 kg / m³. 3 (Liquid). 1.25 kg / m³ 3 (Gaseous state, -196℃); latent heat of vaporization: 199 KJ / kg; specific heat capacity: 2.04 kJ / kg•K (gaseous state). The environmental impact of liquid nitrogen evaporation cooling and dilution during fire extinguishing was predicted using a combined Realizable k-ε turbulence model and a DPM model. Specifically, the rate of oxygen concentration decrease and temperature gradient changes during liquid nitrogen fire extinguishing were obtained through CFD numerical simulation.

[0052] S24: Based on the data obtained from the above FDS and CFD numerical simulations, construct a fire feature vector database, and combine it with the data collected in S101 to complete the liquid nitrogen fire extinguishing database for cable trenches.

[0053] S3: Based on the liquid nitrogen fire extinguishing database for cable trenches, construct a fire spread prediction model, a liquid nitrogen diffusion cooling model, and an oxygen concentration replacement model for parameter prediction.

[0054] S31: Using temperature distribution, smoke concentration, and fire source location collected by sensors as input features, and flame spread path and spread rate per unit time as output labels, an LSTM (Long Short-Term Memory) network is trained to obtain a fire spread prediction model. The core objective of the fire spread prediction model is to predict the propagation path, speed, and time point of the flame in the cable trench based on different ignition locations and trench structure conditions.

[0055] The model is trained and validated using simulated data from a database, with five-fold cross-validation used to optimize parameters during training. It provides real-time assessment of fire spread risk, exhibits good generalization ability, and is widely applicable to fire prediction in various trench structures.

[0056] S32: Based on the physical diffusion characteristics of liquid nitrogen, the cable trench is divided into regular grid cells to simulate the cooling coverage area of ​​the low-temperature expansion boundary after single-injection nitrogen, which changes over time. Using the injection port location, injection rate, ambient temperature, and obstacle distribution as inputs, and the temperature gradient change and oxygen concentration decrease per unit time as outputs, a random forest model is trained to obtain a liquid nitrogen diffusion cooling model. This quantitatively simulates the diffusion path, cooling effect, and cooling duration of liquid nitrogen within the cable trench. The cable trench liquid nitrogen fire extinguishing database, based on large-scale CFD simulations, collects temperature field evolution data under different injection parameters (flow rate, pressure, nozzle arrangement) and trench structure combinations, covering thousands of samples from the entire process of liquid nitrogen injection to vaporization and heat exchange.

[0057] In the model construction process, a three-dimensional channel structure mesh model is first constructed using CFD software. Liquid nitrogen injection conditions are then set and simulated to extract its temperature control capability over the heat source region. Based on these structured simulation data, a mapping relationship between input parameters and temperature change response is established using supervised learning methods (such as XGBoost or multilayer perceptron). The final model can quickly output key indicators such as cooling coverage radius, minimum temperature zone, and cooling duration after inputting the injection nozzle location, flow rate, and channel structure. This model is widely used in the optimization of fire extinguishing scheme parameters.

[0058] S33: The liquid nitrogen fire extinguishing database for cable trenches integrates key data such as nitrogen diffusion paths, oxygen concentration time series under different injection methods, and oxygen replacement rates obtained from FDS and CFD simulations.

[0059] The model uses a component transport equation to describe the diffusion behavior between nitrogen and air. Based on a large dataset, it trains Support Vector Regression (SVR) or Random Forest Regression (RFR) using a mapping model between inputs (injection parameters, injection time, initial oxygen concentration, and channel structure) and outputs (local oxygen volume change over time) to obtain an oxygen concentration replacement model. This model examines how the nitrogen-rich environment formed within the channel affects the local oxygen volume distribution and determines whether asphyxiation extinguishing conditions are met. It can not only predict whether the extinguishing oxygen concentration threshold (e.g., 12%–15%) has been reached, but also supports dynamic adjustments based on on-site sensor data during actual fires. Through deep learning of gas diffusion experimental and simulation data in the database, the model can flexibly adapt to fire extinguishing strategy simulations and extrapolations under different operating conditions.

[0060] S4: Based on the data predicted by the fire spread prediction model, liquid nitrogen diffusion cooling model and oxygen concentration replacement model, the optimal parameter combination searched by the multi-objective optimization algorithm is used to obtain the fire extinguishing plan, and dynamic adjustment is achieved according to the measured data collected by the sensor.

[0061] After the fire spread prediction model, liquid nitrogen diffusion cooling model, and oxygen concentration replacement model are constructed, the fire extinguishing plan is generated, optimized, and dynamically corrected based on the fire feature vector information of the current fire scene. This includes the following steps:

[0062] First, the acquired feature vector of the current fire scene is input into the three models mentioned above to obtain predictions of the fire spread trend, changes in the liquid nitrogen cooling temperature field, and the effect of oxygen concentration replacement. Based on this, a non-dominated sorting genetic algorithm (NSGA-II) or other multi-objective optimization algorithms are used, with the shortest extinguishing time, minimum liquid nitrogen usage, and minimum overall loss as the optimization objective functions, to jointly optimize the following key control parameters: the spatial layout and number of liquid nitrogen injection ports; the injection flow rate of each injection port; the injection duration; and the response delay time of the extinguishing system.

[0063] With the goal of minimizing fire extinguishing time, the objective function is as follows:

[0064] ;

[0065] in, This indicates the time required for the fire to be effectively controlled to a safe threshold. Represents any point in space within the cable trench; This represents the temperature at position x at time t (predicted by the liquid nitrogen cooling model). This indicates the set safe temperature threshold. This represents the oxygen volume fraction at position x at time t (predicted by the displacement model). This indicates the safe oxygen concentration threshold required for fire extinguishing.

[0066] With the goal of minimizing liquid nitrogen usage, the objective function is as follows:

[0067] ;

[0068] in, This indicates the total liquid nitrogen consumption; Indicates the number of liquid nitrogen injection nozzles; This represents the liquid nitrogen injection flow rate at the i-th injection port at time t; This represents the duration of continuous injection from the i-th injection port.

[0069] With the goal of minimizing the overall loss, the objective function is as follows:

[0070] ;

[0071] in, This represents the estimated total loss. Indicates the critical temperature that the cable or equipment can withstand; This indicates the carbon monoxide concentration value (a fire smoke indicator that can be calculated from fire prediction models). This indicates the upper limit of the safe concentration of carbon monoxide; This represents the weighting coefficients for losses caused by exceeding temperature and gas limits.

[0072] A non-dominated sorting genetic algorithm is used to construct a multi-objective loss function for optimization, which integrates the above multi-objective objectives.

[0073] ;

[0074] The variables include the location and number of liquid nitrogen injection ports, the flow rate per port, the injection time, and the delayed response time. Constraints include structural safety, fire extinguishing effectiveness, and equipment protection requirements.

[0075] A set of Pareto solutions, i.e., a set of liquid nitrogen injection schemes, was obtained using the NSGA-II multi-objective optimization algorithm. The Pareto optimal solution for each set was obtained based on the weight settings of the objective function. The fire extinguishing scheme was then derived from the parameter combinations corresponding to the optimal solutions, guiding actual fire extinguishing response operations.

[0076] The fire extinguishing system incorporating the method of this invention maintains data interconnection with environmental monitoring terminals deployed inside cable trenches. These terminals include, but are not limited to, temperature sensors, smoke concentration sensors, oxygen concentration detectors, and image acquisition devices, capable of collecting real-time fire scene data and uploading it to the central processing module. The central system dynamically compares the current measured data with the predicted values ​​from various models. If a significant deviation is detected between the actual fire development trajectory, cooling temperature distribution, or oxygen concentration change trend and the predicted value, the system automatically triggers a feedback correction mechanism. The feedback correction mechanism includes the following steps:

[0077] (1) Based on the current fire monitoring data and combined with historical similar fire scenarios in the database, a lightweight simulation module is called to perform rapid modeling and recalculation, and the fire spread trend and liquid nitrogen diffusion status corresponding to the current fire situation are updated.

[0078] (2) Based on the corrected simulation results, the multi-objective optimization algorithm module is restarted, and the parameters such as liquid nitrogen injection flow rate, injection time, and nozzle activation sequence are quickly re-optimized under the constraints of remaining response time and liquid nitrogen resources.

[0079] (3) Based on the optimization results, the system automatically adjusts the on-site liquid nitrogen injection plan, including starting the backup injection port, adjusting the injection rate, extending or advancing the injection time, etc. The action module realizes the linkage control and real-time correction of the fire extinguishing strategy.

[0080] Furthermore, the system further constructs an adaptive strategy evolution mechanism, automatically storing the optimized solutions, adjustment records, and final effect feedback information of each fire response process into the cable trench liquid nitrogen extinguishing database, thereby achieving knowledge accumulation and reuse of historical data. The aforementioned strategy evolution module works in conjunction with the on-site automatic control unit, supporting the sending of control commands to equipment such as liquid nitrogen control valves, injection mechanisms, and safety early warning systems, achieving fully automated response throughout the entire process.

[0081] The system can also perform 3D visualization simulations, including:

[0082] (1) Based on the three-dimensional cable trench model, the fire spread and liquid nitrogen diffusion process are dynamically visualized.

[0083] (2) Mark the nitrogen injection area coverage boundary, temperature contour lines, personnel evacuation routes and remaining safety time windows at key time points.

[0084] This invention also provides a liquid nitrogen fire extinguishing scheme generation system for cable trenches, specifically comprising:

[0085] The data prediction module is used to acquire structural data of the cable trench and real-time monitoring data from sensors. Based on the structural data of the cable trench and the real-time monitoring data from sensors, fire prediction is performed, and prediction results are obtained for fire spread trend data, liquid nitrogen cooling temperature field change data, and oxygen concentration replacement data.

[0086] The fire extinguishing scheme generation module is used to perform parameter combination search based on the prediction results using an objective optimization algorithm to obtain the Pareto solution, calculate the objective function value of all candidate solutions in the Pareto solution, and obtain the optimal parameter combination; the fire extinguishing scheme is obtained based on the optimal parameter combination; the optimal parameter combination includes the location and number of nitrogen injection ports, the flow rate of each nitrogen injection port, and the injection duration and sequence.

[0087] The correction module is used to acquire environmental measurement data of the fire scene and dynamically compare the measurement data with the prediction results. If the deviation between the prediction results and the measurement data exceeds the set value, the feedback correction mechanism is triggered. Based on the measurement data, the fire spread trend data, liquid nitrogen cooling temperature field change data, and oxygen concentration replacement data are re-predicted to obtain the corrected prediction results. Based on the corrected prediction results, the target optimization algorithm is used to recalculate and obtain the real-time adjusted fire extinguishing plan.

[0088] The modules in the aforementioned liquid nitrogen fire extinguishing system for cable trenches can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0089] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps in an embodiment of a method for generating a liquid nitrogen fire extinguishing scheme for cable trenches. Specific implementation methods can be found in the method embodiments, and will not be repeated here.

[0090] Furthermore, the present invention also provides a non-transitory computer-readable storage medium containing instructions, on which a computer program is stored. For example, a memory containing instructions that can be executed by a processor of a computer device to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc. When the computer program is executed by the processor, it can implement the steps in an embodiment of a method for generating a liquid nitrogen fire extinguishing scheme for cable trenches. Specific implementation methods can be found in the method embodiments, which will not be repeated here.

[0091] Those skilled in the art will understand that embodiments of the present invention can provide methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0093] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0094] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0095] It should be noted that the specific embodiments described above enable those skilled in the art to more fully understand the present invention, but do not limit the present invention in any way. Therefore, although the present invention has been described in detail in this specification and embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the present invention; and all technical solutions and improvements that do not depart from the spirit and scope of the present invention are covered within the protection scope of the present invention patent. No reference numerals in the claims should be construed as limiting the scope of the claims. Any simple variations or equivalent substitutions of technical solutions that can be readily obtained by those skilled in the art within the scope of the technology disclosed in the present invention are within the protection scope of the present invention.

Claims

1. A method for generating a liquid nitrogen fire extinguishing scheme for cable trenches, characterized in that, Includes the following steps: The structural data of the cable trench and the real-time monitoring data of the sensors are acquired. Based on the structural data of the cable trench and the real-time monitoring data of the sensors, fire prediction is performed to obtain the prediction results of fire spread trend data, liquid nitrogen cooling temperature field change data and oxygen concentration replacement data. Based on the prediction results, a parameter combination search is performed using an objective optimization algorithm to obtain a Pareto solution. The objective function values ​​of all candidate solutions in the Pareto solution are calculated to obtain the optimal parameter combination. A fire extinguishing scheme is obtained based on the optimal parameter combination. The optimal parameter combination includes the location and number of nitrogen injection ports, the flow rate of each nitrogen injection port, and the injection duration and sequence. The system acquires environmental measurement data from the fire scene and dynamically compares the measured data with the prediction results. If the deviation between the prediction results and the measured data exceeds a set value, a feedback correction mechanism is triggered. Based on the measured data, the system re-predicts the fire spread trend data, liquid nitrogen cooling temperature field change data, and oxygen concentration replacement data to obtain the corrected prediction results. Based on the corrected prediction results, the system recalculates using a target optimization algorithm to obtain a real-time adjusted fire extinguishing plan.

2. The method for generating a liquid nitrogen fire extinguishing scheme for cable trenches according to claim 1, characterized in that, Fire prediction is performed based on the structural data of the cable trench and real-time monitoring data from sensors to obtain prediction results for fire spread trend data, liquid nitrogen cooling temperature field change data, and oxygen concentration replacement data. Specifically, the real-time monitoring data from sensors is input into a fire spread prediction model to obtain prediction results for fire spread trend data; the structural data of the cable trench and the real-time monitoring data from sensors are input into a liquid nitrogen diffusion cooling model to obtain prediction results for liquid nitrogen cooling temperature field change data; and the structural data of the cable trench is input into an oxygen concentration replacement model to obtain prediction results for oxygen concentration replacement data.

3. The method for generating a liquid nitrogen fire extinguishing scheme for cable trenches according to claim 2, characterized in that, Before inputting the structural data of the cable trench and the real-time monitoring data from sensors into the fire spread prediction model, the liquid nitrogen diffusion cooling model, and the oxygen concentration replacement model, the process includes acquiring historical sensor monitoring data and historical fire case data; using the historical sensor monitoring data as input features and the fire spread trend data from the historical fire case data as output, training an LSTM time series model to obtain the fire spread prediction model; using the structural data of the cable trench and the historical sensor monitoring data as input, and the liquid nitrogen cooling temperature field change data from the historical fire case data as output, training a random forest model to obtain the liquid nitrogen diffusion cooling model; using the structural data of the cable trench as input and the oxygen replacement data from the historical fire case data as output, training a support vector regression or random forest regression model to obtain the oxygen concentration replacement model.

4. The method for generating a liquid nitrogen fire extinguishing scheme for cable trenches according to claim 1, characterized in that, The acquisition of the structural data of the cable trench specifically includes: The cable trench structure was reconstructed using FDS and CFD numerical simulation software to obtain a numerical simulation model of the cable trench. The structural data of the cable trench were obtained based on the numerical simulation model.

5. The method for generating a liquid nitrogen fire extinguishing scheme for cable trenches according to claim 1, characterized in that, The fire spread trend data specifically refers to the flame spread path and spread rate per unit time; the liquid nitrogen cooling temperature field change data specifically refers to the temperature gradient change and the decrease in oxygen concentration per unit time; the oxygen replacement data specifically refers to the local oxygen volume.

6. The method for generating a liquid nitrogen fire extinguishing scheme for cable trenches according to claim 3, characterized in that, It also includes data on the oxygen concentration decrease rate and temperature gradient change during the liquid nitrogen diffusion and transport process when liquid nitrogen is used to simulate the liquid nitrogen diffusion and transport process using a Realizable k-ε turbulence model and a deformable component model. The oxygen concentration decrease rate is used to train the oxygen concentration replacement model, and the temperature gradient change data is used to train the liquid nitrogen diffusion cooling model.

7. The method for generating a liquid nitrogen fire extinguishing scheme for cable trenches according to claim 1, characterized in that, It also includes constructing a multi-objective loss function with the optimization objectives of shortest fire extinguishing time, minimum liquid nitrogen usage, and minimum overall loss, and using the loss function to calculate the objective function value; the multi-objective loss function is specifically as follows: ； in, This indicates the time it takes for the fire to be effectively controlled to a safe threshold during firefighting. Indicates the total amount of liquid nitrogen used; This represents the overall loss value; The objective function for the shortest fire extinguishing time is as follows: ； in, Represents any point in space within the cable trench; This represents the temperature at position x at time t; This indicates the set safe temperature threshold. This represents the volume fraction of oxygen at position x at time t. This indicates the safe oxygen concentration threshold required for fire extinguishing. The objective function for minimizing liquid nitrogen usage is: ； in, Indicates the number of liquid nitrogen injection nozzles; This represents the liquid nitrogen injection flow rate at the i-th injection port at time t; This indicates the duration of continuous injection from the i-th nozzle; The objective function for minimizing the overall loss is: ； in, Indicates the critical temperature that the cable or equipment can withstand; Represents the carbon monoxide concentration field; This indicates the upper limit of the safe concentration of carbon monoxide; This represents the weighting coefficients for losses caused by exceeding temperature and gas limits.

8. A liquid nitrogen fire extinguishing scheme generation system for cable trenches, characterized in that, include: The data prediction module is used to acquire structural data of the cable trench and real-time monitoring data from sensors, and to predict the fire situation based on the structural data of the cable trench and the real-time monitoring data from sensors, so as to obtain prediction results of fire spread trend data, liquid nitrogen cooling temperature field change data and oxygen concentration replacement data. The fire extinguishing scheme generation module is used to perform parameter combination search based on the prediction results using an objective optimization algorithm to obtain a Pareto solution, calculate the objective function value of all candidate solutions in the Pareto solution to obtain the optimal parameter combination, and obtain a fire extinguishing scheme based on the optimal parameter combination; the optimal parameter combination includes the location and number of nitrogen injection ports, the flow rate of each nitrogen injection port, and the injection duration and sequence; The correction module is used to acquire environmental measurement data of the fire scene, dynamically compare the measurement data with the prediction results, and if the deviation between the prediction results and the measurement data exceeds a set value, the feedback correction mechanism is triggered. Based on the measurement data, the fire spread trend data, liquid nitrogen cooling temperature field change data, and oxygen concentration replacement data are re-predicted to obtain the corrected prediction results. Based on the corrected prediction results, the target optimization algorithm is used to recalculate and obtain the real-time adjusted fire extinguishing plan.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is loaded by the processor, it is able to perform the steps of the method according to any one of claims 1 to 7.

Images