Tunnel vehicle-mounted lithium battery fire monitoring early warning and linkage fire extinguishing system

Abstract

The invention discloses a tunnel vehicle-mounted lithium battery fire monitoring early warning and linkage fire extinguishing system, and the system comprises an image obtaining unit which is used for obtaining the image information of a first vehicle driving into a target tunnel, and is also used for obtaining the image information of a second vehicle driving out of the target tunnel; the electric vehicle identification unit is used for determining electric vehicle distribution information and other vehicle distribution information in the target tunnel based on a vehicle identification model according to the first vehicle picture information and the second vehicle picture information; the tunnel environment collection unit is used for acquiring tunnel environment information of the target tunnel; the risk prediction unit is used for determining a risk prediction level based on a risk prediction model according to the electric vehicle distribution information, the other vehicle distribution information and the tunnel environment information; and the control unit is used for controlling the waiting response level of the linkage fire extinguishing system based on the risk prediction level.

Description

Technical Field

[0001] The present invention relates to the field of emergency response, and more specifically, to a tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system. Background Art

[0002] With the widespread use of electric vehicles (such as electric cars and electric trucks) in transportation, the operational safety of electric vehicles in tunnels has gradually attracted widespread attention. As the core component of electric vehicles, lithium batteries may cause fires under conditions of high temperature, impact, or abnormal charging and discharging. Especially in a closed tunnel environment, once a fire occurs, it is very likely to cause serious consequences. Traditional tunnel fire monitoring and fire extinguishing systems mostly rely on a single environmental monitoring method, such as smoke detectors, temperature sensors, etc., and do not conduct risk assessment and processing for the particularity of electric vehicles. In addition, the presence of special vehicles (such as dangerous goods transport vehicles) may also increase the risk of fire, but the existing system lacks refined management and monitoring methods for different types of vehicles.

[0003] Existing tunnel fire monitoring systems usually rely on fire detectors at fixed locations, which trigger alarms by detecting parameters such as temperature and smoke concentration in the tunnel. However, this method often has problems such as delayed response and inaccurate positioning. In particular, for fire hazards of electric vehicle batteries, traditional fire detectors are difficult to perceive risks in advance. The existing system lacks real-time monitoring of electric vehicles and special vehicles, and cannot effectively deal with the fire risks caused by different types of vehicles. At the same time, the fire extinguishing system usually responds only based on simple environmental data, lacks a dynamic and comprehensive risk assessment mechanism, and cannot adjust the fire extinguishing strategy in time according to different fire risk levels, making it difficult to provide accurate fire extinguishing solutions.

[0004] Therefore, it is necessary to propose a tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system to at least solve some of the above problems. Summary of the invention

[0005] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0006] In the first aspect, the present application proposes a tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system, comprising: An image acquisition unit, the image acquisition unit is used to acquire image information of a first vehicle entering a target tunnel, and the image acquisition unit is also used to acquire image information of a second vehicle exiting a target tunnel; An electric vehicle identification unit, used to determine electric vehicle distribution information and other vehicle distribution information in a target tunnel based on a vehicle identification model according to the first vehicle image information and the second vehicle image information, wherein the electric vehicle distribution information includes electric vehicle quantity information, electric vehicle model information and electric vehicle location information in the tunnel, and the other vehicle distribution information includes special vehicle quantity information, special vehicle type information and special vehicle location information in the tunnel; A tunnel environment collection unit, used to obtain tunnel environment information of the target tunnel; A risk prediction unit, configured to determine a risk prediction level based on a risk prediction model according to the electric vehicle distribution information, the other vehicle distribution information and the tunnel environment information; A control unit is used to control the waiting response level of the linkage fire extinguishing system based on the above risk prediction level.

[0007] In a feasible implementation manner, the specific steps of the electric vehicle identification unit determining the electric vehicle distribution information in the target tunnel include: Determine the existing vehicle information in the target tunnel based on the first vehicle picture information, the second vehicle picture information and the picture shooting time information; Determine the electric vehicle quantity information, the special vehicle quantity information, the electric vehicle model information and the special vehicle type information based on the existing vehicle information; Based on the existing vehicle information, the speed information of the existing vehicle entering the tunnel and the picture shooting time information, the position information of the electric vehicle in the tunnel and the position information of the special vehicle in the tunnel are determined.

[0008] In a feasible implementation manner, it is characterized in that the determining of the electric vehicle quantity information, the special vehicle quantity information, the electric vehicle model information and the special vehicle type information based on the existing vehicle information includes: Performing a preprocessing operation on the image information corresponding to the existing vehicle information to obtain preprocessed image information; Inputting the preprocessed image information into a first recognition module to obtain the electric vehicle quantity information and the special vehicle quantity information, wherein the first recognition module is established based on the Faster R-CNN model; The pre-processed image information is input into a second recognition module to obtain the electric vehicle model information and the special vehicle type information, wherein the second recognition module is established based on a SVM model.

[0009] In a feasible implementation manner, the determining of the position information of the electric vehicle in the tunnel and the position information of the special vehicle in the tunnel based on the existing vehicle information, the speed information of the existing vehicle entering the tunnel, and the picture shooting time information includes: Sending the first existing vehicle information whose speed information is less than the preset speed to the first prediction module to obtain a first predicted position corresponding to the first existing vehicle information, wherein the first prediction module is established based on the Kalman filter algorithm; Sending the second existing vehicle information whose speed information is greater than or equal to the preset speed to a second prediction module to obtain a second predicted position corresponding to the second existing vehicle information, wherein the second prediction module is established based on a long short-term memory network; Establishing integrated position information based on the first predicted position and the second predicted position; The position information of the electric vehicle and the special vehicle in the tunnel are determined based on the integrated position information and existing vehicle information about the vehicle type, lane and sequence information entering the tunnel.

[0010] In a feasible implementation, the risk prediction model includes a density risk prediction module, an environmental risk prediction module and a risk fusion module; The specific steps of determining the risk prediction level by the risk prediction unit based on the risk prediction model according to the electric vehicle distribution information, the other vehicle distribution information and the tunnel environment information include: Inputting the electric vehicle distribution information and the other vehicle distribution information into the density risk prediction module to obtain a density risk factor; Inputting the above tunnel environmental information into the above environmental risk prediction module to obtain environmental risk factors; The density risk factor and the environmental risk factor are input into the risk fusion module to obtain the risk prediction level.

[0011] In a feasible implementation manner, the electric vehicle distribution information and the other vehicle distribution information are input into the density risk prediction module to obtain a density risk factor, including: Performing grid processing on the target tunnel to obtain grid information of the target tunnel; Establishing vehicle distribution grid information based on the target tunnel grid information, the electric vehicle distribution information and the other vehicle distribution information; Determine density weight information for different vehicle types; The density risk factor is determined based on the vehicle distribution grid information and the density weight information.

[0012] In a feasible implementation manner, the density weight information of the electric vehicle is obtained by weighted fusion based on the battery type information and collision test data information of the electric vehicle.

[0013] In a feasible implementation manner, the tunnel environment information includes temperature information, humidity information, ventilation condition information and air quality information; The above-mentioned tunnel environmental information is input into the above-mentioned environmental risk prediction module to obtain environmental risk factors, including: The environmental risk factors are obtained by weighted fusion based on the temperature information, the humidity information, the ventilation condition information and the air quality information.

[0014] In a feasible implementation manner, the inputting of the density risk factor and the environmental risk factor into the risk fusion module to obtain the risk prediction level includes: Determine first weight information corresponding to the density risk factor and second weight information corresponding to the environmental risk factor based on historical fire risk information; Calculate a risk score based on the density risk factor, the environmental risk factor, the first weight information, and the second weight information; The above risk levels are determined based on the above risk scores.

[0015] In a feasible implementation manner, the specific steps of the control unit controlling the waiting response level of the linkage fire extinguishing system based on the risk prediction level include: Based on the above risk prediction level, the wind speed information, temperature monitoring frequency information, fire detection detector sensitivity information and fire extinguishing equipment status information of the ventilation system of the linked fire extinguishing system are controlled, wherein the above fire extinguishing equipment status information includes automatic fire extinguishing device operation status information, fire extinguishing area division status information and fire extinguishing agent injection quantity status information.

[0016] In summary, the present application realizes real-time identification and monitoring of electric vehicles and special vehicles in the target tunnel through the image acquisition unit and the electric vehicle identification unit. Compared with the traditional fire detection system that only relies on fixed detectors, the present application can accurately obtain the specific information of vehicles in the tunnel, including the number of electric vehicles, electric vehicle models, location information and related information of special vehicles. This allows the system to identify the distribution of electric vehicles and special vehicles in advance, so as to more accurately assess the potential fire risk. The present application specifically considers the fire risk of electric vehicle batteries, and can locate and monitor the location of high-risk vehicles in combination with vehicle distribution and environmental conditions. This targeted monitoring greatly improves the accuracy of fire risk assessment. The tunnel environment collection unit can obtain information such as temperature, humidity, ventilation conditions and air quality in the tunnel in real time. Compared with traditional technology that only relies on a single smoke detection or temperature sensor, the present system integrates multiple environmental factors, and integrates environmental information and vehicle distribution information through the risk prediction unit to conduct a more comprehensive fire risk assessment. By integrating environmental and vehicle information, the system can dynamically assess the probability of fire in the tunnel, making risk prediction more accurate. The combination of environmental data and vehicle data enables the system to not only detect potential fire hazards, but also adjust the monitoring strategy according to the specific tunnel conditions. For example, when the temperature in the tunnel rises abnormally but the ventilation conditions are good, the system can reduce the sensitivity of the fire risk warning to avoid unnecessary false alarms. This application calculates the vehicle density and environmental risk factors respectively through the density risk prediction module and the environmental risk prediction module, and performs a comprehensive risk assessment in the risk fusion module. Unlike traditional fire detection systems, this system can dynamically adjust the accuracy of fire prediction based on density information such as vehicle type, quantity, and location, combined with the environmental conditions of the tunnel. In addition, different weight information is set for different types of vehicles (such as electric vehicles and special vehicles) in the application, making the risk prediction more accurate, especially the battery type and collision test data of electric vehicles are also introduced into the setting of risk weights, so as to better deal with battery fire risks. This method effectively avoids the shortcomings of traditional fire systems that cannot distinguish vehicle types and cannot adjust risk levels according to actual conditions. The control unit in this system can accurately control various parameters of the linkage fire extinguishing system based on the real-time risk prediction level, including the wind speed of the ventilation system, the frequency of temperature monitoring, the sensitivity of the fire detector, and the status of the fire extinguishing equipment. Compared with the traditional system that passively waits for a fire to occur before triggering fire extinguishing, this application can actively adjust the response level of the fire extinguishing system according to the predicted fire risk to achieve precise fire extinguishing. When the fire risk level increases, the system can not only activate the fire extinguishing device, but also select the appropriate type and injection amount of fire extinguishing agent according to the specific vehicle distribution and environmental conditions, realize zoned fire extinguishing and intelligent scheduling, thereby minimizing the damage of the fire to the tunnel and vehicles.Compared with the existing technology, the tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system of this application can not only accurately monitor the vehicle distribution and environmental information in the tunnel and conduct a comprehensive fire risk assessment, but also intelligently control the response measures of the fire extinguishing equipment according to the predicted fire risk level. Its advantages are reflected in dynamic and real-time fire monitoring, intelligent risk assessment and active fire extinguishing response, which effectively improves the safety and efficiency of fire prevention and control of electric vehicles and special vehicles in tunnels.

[0017] The artificial intelligence-based intelligent analysis and control system and method for network information proposed in this application, and other advantages, objectives and features of this application will be reflected in part through the following description, and in part will also be understood by technical personnel in this field through research and practice of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 A structural schematic diagram of a tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system provided in an embodiment of the present application; Figure 2 A schematic diagram of a specific process of an electric vehicle identification unit determining electric vehicle distribution information in a target tunnel provided in an embodiment of the present application; Figure 3 A schematic diagram of the specific steps for determining the number of electric vehicles, the number of special vehicles, the model information of electric vehicles and the type information of special vehicles based on the existing vehicle information provided in the embodiment of the present application; Figure 4 A schematic diagram of a process for determining the position information of an electric vehicle and a special vehicle in a tunnel provided in an embodiment of the present application; Figure 5 A schematic diagram of a process for predicting risk levels provided in an embodiment of the present application; Figure 6 A schematic diagram of a process for obtaining a density risk factor provided in an embodiment of the present application; Figure 1 The corresponding relationship between the reference numerals and the names of the drawings is as follows: 10 tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system; 101 image acquisition unit; 102 electric vehicle identification unit; 103 tunnel environment collection unit; 104 risk prediction unit; 105 control unit. DETAILED DESCRIPTION

[0019] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0020] See also Figure 1 , is a structural schematic diagram of a tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system 10 provided in an embodiment of the present application, which may specifically include: An image acquisition unit 101, the image acquisition unit is used to acquire image information of a first vehicle entering a target tunnel, and the image acquisition unit is also used to acquire image information of a second vehicle exiting a target tunnel; The electric vehicle identification unit 102 is used to determine the electric vehicle distribution information and other vehicle distribution information in the target tunnel based on the vehicle identification model according to the first vehicle image information and the second vehicle image information, wherein the electric vehicle distribution information includes the number of electric vehicles, the model of electric vehicles and the location of electric vehicles in the tunnel, and the other vehicle distribution information includes the number of special vehicles, the type of special vehicles and the location of special vehicles in the tunnel; The tunnel environment collecting unit 103 is used to obtain the tunnel environment information of the target tunnel; The risk prediction unit 104 is used to determine the risk prediction level based on the risk prediction model according to the electric vehicle distribution information, the other vehicle distribution information and the tunnel environment information; The control unit 105 is used to control the waiting response level of the linkage fire extinguishing system based on the above risk prediction level.

[0021] Exemplarily, the image acquisition unit 101 is used to acquire image information of vehicles in the tunnel. Specifically, it can acquire image information of a first vehicle entering the target tunnel and image information of a second vehicle exiting the target tunnel. These image information provide data support for subsequent vehicle identification and distribution information analysis. Through these image data, the vehicles entering and exiting the tunnel can be monitored in real time.

[0022] The electric vehicle identification unit 102 processes the first vehicle image information and the second vehicle image information provided by the image acquisition unit 101 based on a preset vehicle identification model to determine the electric vehicle distribution information and other vehicle distribution information in the target tunnel.

[0023] Electric vehicle distribution information: including the number and model information of electric vehicles in the target tunnel and the specific location information of electric vehicles in the tunnel. Other vehicle distribution information: mainly including the number and type information of special vehicles and the specific location information of these vehicles in the tunnel. Special vehicles may include dangerous goods transport vehicles, rescue vehicles, etc., which have a significant impact on fire risks.

[0024] The tunnel environment collection unit 103 is used to obtain tunnel environment information of the target tunnel. Such environment information generally includes key information such as temperature, humidity, ventilation conditions, and air quality. Environmental factors in the tunnel may directly affect the fire risk, so the collection of environmental data is crucial for accurately assessing the risk.

[0025] The risk prediction unit 104 conducts a comprehensive assessment of the fire risk based on the risk prediction model, combined with the electric vehicle distribution information, other vehicle distribution information and tunnel environment information, and determines the risk prediction level. The risk prediction level can reflect the current fire risk in the tunnel and is divided into multiple levels such as low, medium and high. The unit provides real-time risk prediction by integrating multiple data sources such as vehicle density and environmental conditions, providing a basis for the automated control of subsequent fire extinguishing measures.

[0026] The control unit 105 controls the response behavior of the entire system according to the risk prediction level output by the risk prediction unit 104, specifically, controls the waiting response level of the linkage fire extinguishing system. The control parameters may include: Wind speed information of the ventilation system: Adjust the ventilation speed in the tunnel according to the risk level to ensure that smoke and harmful gases are quickly discharged.

[0027] Temperature monitoring frequency information: When the risk level increases, the frequency of temperature monitoring is increased to detect abnormal temperature changes in a timely manner.

[0028] Fire detector sensitivity information: As the risk level increases, the sensitivity of the fire detectors will be increased appropriately to allow for a quicker response to potential signs of a fire.

[0029] Fire extinguishing equipment status information: When the risk reaches a certain level, the fire extinguishing system will enter different preparatory states. Automated operations include pre-loading of extinguishing agent, division of fire extinguishing areas and adjustment of extinguishing agent injection volume.

[0030] In summary, the present application realizes real-time identification and monitoring of electric vehicles and special vehicles in the target tunnel through the image acquisition unit and the electric vehicle identification unit. Compared with the traditional fire detection system that only relies on fixed detectors, the present application can accurately obtain the specific information of vehicles in the tunnel, including the number of electric vehicles, electric vehicle models, location information and related information of special vehicles. This allows the system to identify the distribution of electric vehicles and special vehicles in advance, so as to more accurately assess the potential fire risk. The present application specifically considers the fire risk of electric vehicle batteries, and can locate and monitor the location of high-risk vehicles in combination with vehicle distribution and environmental conditions. This targeted monitoring greatly improves the accuracy of fire risk assessment. The tunnel environment collection unit can obtain information such as temperature, humidity, ventilation conditions and air quality in the tunnel in real time. Compared with traditional technology that only relies on a single smoke detection or temperature sensor, the present system integrates multiple environmental factors, and integrates environmental information and vehicle distribution information through the risk prediction unit to conduct a more comprehensive fire risk assessment. By integrating environmental and vehicle information, the system can dynamically assess the probability of fire in the tunnel, making risk prediction more accurate. The combination of environmental data and vehicle data enables the system to not only detect potential fire hazards, but also adjust the monitoring strategy according to the specific tunnel conditions. For example, when the temperature in the tunnel rises abnormally but the ventilation conditions are good, the system can reduce the sensitivity of the fire risk warning to avoid unnecessary false alarms. This application calculates the vehicle density and environmental risk factors respectively through the density risk prediction module and the environmental risk prediction module, and performs a comprehensive risk assessment in the risk fusion module. Unlike traditional fire detection systems, this system can dynamically adjust the accuracy of fire prediction based on density information such as vehicle type, quantity, and location, combined with the environmental conditions of the tunnel. In addition, different weight information is set for different types of vehicles (such as electric vehicles and special vehicles) in the application, making the risk prediction more accurate, especially the battery type and collision test data of electric vehicles are also introduced into the setting of risk weights, so as to better deal with battery fire risks. This method effectively avoids the shortcomings of traditional fire systems that cannot distinguish vehicle types and cannot adjust risk levels according to actual conditions. The control unit in this system can accurately control various parameters of the linkage fire extinguishing system based on the real-time risk prediction level, including the wind speed of the ventilation system, the frequency of temperature monitoring, the sensitivity of the fire detector, and the status of the fire extinguishing equipment. Compared with the traditional system that passively waits for a fire to occur before triggering fire extinguishing, this application can actively adjust the response level of the fire extinguishing system according to the predicted fire risk to achieve precise fire extinguishing. When the fire risk level increases, the system can not only activate the fire extinguishing device, but also select the appropriate type and injection amount of fire extinguishing agent according to the specific vehicle distribution and environmental conditions, realize zoned fire extinguishing and intelligent scheduling, thereby minimizing the damage of the fire to the tunnel and vehicles.Compared with the existing technology, the tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system of this application can not only accurately monitor the vehicle distribution and environmental information in the tunnel and conduct a comprehensive fire risk assessment, but also intelligently control the response measures of the fire extinguishing equipment according to the predicted fire risk level. Its advantages are reflected in dynamic and real-time fire monitoring, intelligent risk assessment and active fire extinguishing response, which effectively improves the safety and efficiency of fire prevention and control of electric vehicles and special vehicles in tunnels.

[0031] In some examples, such as Figure 2 As shown, the specific steps of the electric vehicle identification unit determining the electric vehicle distribution information in the target tunnel include: S110, determining the existing vehicle information in the target tunnel based on the first vehicle picture information, the second vehicle picture information and the picture shooting time information; S120, determining the number information of the electric vehicles, the number information of the special vehicles, the model information of the electric vehicles and the type information of the special vehicles based on the existing vehicle information; S130. Determine the position information of the electric vehicle and the position information of the special vehicle in the tunnel based on the existing vehicle information, the speed information of the existing vehicle entering the tunnel, and the picture shooting time information.

[0032] Exemplarily, first, the electric vehicle identification unit determines the existing vehicle information in the target tunnel by analyzing the first vehicle image information and the second vehicle image information provided by the image acquisition unit and combining the image shooting time information. The existing vehicle information includes basic data such as image data and shooting time of all vehicles entering and exiting the tunnel. With these data, the system can identify all vehicles in the current tunnel as the basis for subsequent vehicle analysis.

[0033] Next, based on the existing vehicle information obtained above, the electric vehicle identification unit further analyzes the attributes of each vehicle to identify electric vehicles and special vehicles. The system determines the number of electric vehicles in the tunnel based on the vehicle appearance features (such as license plates, vehicle model identification, etc.) combined with the trained vehicle identification model, that is, the number of electric vehicles currently in the tunnel. At the same time, the system will also identify the number of special vehicles, including the number of special vehicles such as dangerous goods transport vehicles and rescue vehicles. Through this classification, the system can effectively distinguish different types of vehicles and provide detailed data for subsequent risk assessment.

[0034] Based on the existing vehicle information, the electric vehicle identification unit further identifies the specific electric vehicle model information and special vehicle type information through vehicle model analysis. The system uses a predefined vehicle model recognition library to accurately match the vehicle's appearance features (such as body shape, logo, license plate, etc.) to determine the specific model of the electric vehicle and further classify the type of special vehicles. The model information of electric vehicles is an important parameter for fire risk assessment, because different models of electric vehicles may use different battery types and have different fire risks. Similarly, the type information of special vehicles is also an important input parameter that can help the system identify special vehicles (such as vehicles transporting hazardous chemicals) and adjust fire prevention and control strategies accordingly.

[0035] Finally, the electric vehicle identification unit determines the location information of each electric vehicle and special vehicle in the tunnel based on the existing vehicle information, combined with the speed information of the existing vehicles when entering the tunnel and the time information of the picture shooting. By analyzing the time point when the vehicle enters the tunnel, the driving speed and the change in the vehicle position, the system can accurately estimate the specific location of the current vehicle in the tunnel. This step is particularly important for the subsequent regional division and fire fighting response of fire prevention and control.

[0036] Speed ​​information: The speed data of the vehicle when entering the tunnel is obtained through vehicle sensors or external monitoring systems as the basis for position estimation.

[0037] Image shooting time information: Combined with the time point when the image was taken, the system can calculate the distance traveled by the vehicle based on the speed information, thereby determining the vehicle's exact position in the tunnel.

[0038] In summary, the electric vehicle identification unit can accurately obtain the number, type, model and distribution location information of electric vehicles and special vehicles in the tunnel. This information provides key input data for the system's fire monitoring and early warning and linkage fire extinguishing system, ensuring that the system can respond accurately and promptly based on the distribution of vehicles and fire risks.

[0039] In some examples, such as Figure 3 As shown, S120 determines the electric vehicle quantity information, the special vehicle quantity information, the electric vehicle model information and the special vehicle type information based on the existing vehicle information, including: S1201, preprocessing the image information corresponding to the existing vehicle information to obtain preprocessed image information; S1202, inputting the pre-processed image information into a first recognition module to obtain the electric vehicle quantity information and the special vehicle quantity information, wherein the first recognition module is established based on a Faster R-CNN model; S1203. Input the pre-processed image information into a second recognition module to obtain the electric vehicle model information and the special vehicle type information, wherein the second recognition module is established based on a SVM model.

[0040] Exemplarily, first, the image information corresponding to the existing vehicle information is preprocessed to obtain preprocessed image information. This operation is intended to improve the recognition accuracy and efficiency of the subsequent vehicle recognition module. The preprocessing steps may include image denoising, image enhancement, size adjustment, etc. By preprocessing the image information, it is possible to ensure that the quality of the image data input to the subsequent recognition module meets the requirements, thereby ensuring the accuracy of recognition.

[0041] After completing the preprocessing operation, the system inputs the preprocessed image information into the first recognition module to obtain information on the number of electric vehicles and special vehicles. Specifically, the first recognition module is based on the Faster R-CNN model. By processing the preprocessed image information, the Faster R-CNN model can detect the vehicle targets appearing in the picture and perform preliminary identification of the vehicle category. During this identification process, the model will identify the number of electric vehicles in the current picture, that is, detect the number of targets belonging to electric vehicles in the picture. At the same time, the model will also identify the number of special vehicles, that is, detect the number of targets belonging to special vehicles in the picture. Through the target detection and classification capabilities of the Faster R-CNN model, the system can automatically analyze vehicle pictures and generate quantity information of electric vehicles and special vehicles. This step is the basis for the system to further refine the identification.

[0042] After completing the identification of the number of vehicles, the system will further input the same pre-processed image information into the second identification module to obtain the electric vehicle model information and special vehicle type information. The second identification module is established based on the SVM model (support vector machine). The system further extracts the model information of each electric vehicle by inputting the vehicle image in the pre-processed image information into the SVM model. Different models of electric vehicles may use different battery types and have different safety, so accurate identification of model information is particularly important for fire risk assessment. At the same time, the SVM model will also identify the type information of special vehicles, such as different types of special vehicles such as dangerous goods transport vehicles and rescue vehicles. The type information of special vehicles will also serve as an important reference for fire risk prediction.

[0043] Specifically, the purpose of image preprocessing is to improve the accuracy of the recognition module, which usually includes but is not limited to the following operations: Use Gaussian filtering, mean filtering or median filtering to remove noise from the image. Improve image quality by adjusting brightness, contrast or applying histogram equalization. Scale the image to a suitable size to meet the input requirements of the subsequent recognition module, such as 600×600 pixels. Through these preprocessing steps, the system generates high-quality preprocessed image information to ensure that the image data input to the recognition module is stable.

[0044] The structure of Faster R-CNN is divided into the following parts: Convolutional neural networks (CNNs) are used to extract features of images. Commonly used backbone networks include ResNet, VGG, etc.

[0045] The calculation formula of the convolutional layer is: ; Among them, I is the input image, W is the convolution kernel, ∗ represents the convolution operation, b is the bias term, σ is the activation function (such as ReLU), and F is the extracted feature.

[0046] The Region Proposal Network (RPN) is used to generate candidate regions, predict whether each region contains an object, and generate its bounding box.

[0047] The loss function of RPN includes the classification loss L cls and the bounding box regression loss L reg : ; Among them, pi is the predicted classification probability, pi ∗ is the true category, ti is the predicted bounding box, is the ground-truth bounding box, and λ is the balance coefficient.

[0048] ROI Pooling is used to perform ROI pooling on the candidate regions generated by RPN and fix the output feature size for subsequent classification and regression.

[0049] The candidate regions are classified and bounding boxes are fine-tuned. Faster R-CNN classifies and predicts the number of vehicles and gives the corresponding category (electric vehicle or special vehicle).

[0050] Classification loss: ; in, is the true category, p i is the predicted probability.

[0051] Bounding Box Regression Loss: ; Among them, t i is the prediction box, For the real frame.

[0052] With the above structure, the Faster R-CNN model can identify the number of electric vehicles and special vehicles in the picture.

[0053] SVM (Support Vector Machine) is a model used to identify electric vehicle models and special vehicle types. The structure and identification process of SVM are as follows: Feature extraction: The preprocessed image information is used to extract features through image processing algorithms, such as HOG (Histogram of Oriented Gradients) features.

[0054] HOG feature calculation: ; Among them, Gx and Gy are the gradients of the image.

[0055] SVM Classifier: SVM performs classification by maximizing the margin between classes.

[0056] Classification function: ; Among them, w is the weight vector, x is the feature vector, and b is the bias term.

[0057] Training objective: Train the SVM model by optimizing the following loss function: Loss function (hinge loss): ; Among them, y i is the label of the sample and f(xi) is the predicted value.

[0058] Through this process, SVM can accurately identify the models of electric vehicles and types of special vehicles based on the characteristics of the vehicles.

[0059] By preprocessing the existing vehicle information, and using the first recognition module based on the Faster R-CNN model and the second recognition module based on the SVM model, the automatic recognition and extraction of the number of electric vehicles, the number of special vehicles, the model of electric vehicles, and the type of special vehicles in the tunnel are realized. This method can effectively improve the recognition accuracy of the system and provide accurate basic data support for subsequent fire risk prediction and fire extinguishing system response.

[0060] In some examples, such as Figure 4As shown, S130 determines the position information of the electric vehicle in the tunnel and the position information of the special vehicle in the tunnel based on the existing vehicle information, the speed information of the existing vehicle entering the tunnel, and the picture shooting time information, including: S1301, sending the first existing vehicle information whose speed information is less than a preset speed to a first prediction module to obtain a first predicted position corresponding to the first existing vehicle information, wherein the first prediction module is established based on a Kalman filter algorithm; S1302, sending the second existing vehicle information whose speed information is greater than or equal to the preset speed to a second prediction module to obtain a second predicted position corresponding to the second existing vehicle information, wherein the second prediction module is established based on a long short-term memory network; S1303, establishing integrated position information according to the first predicted position and the second predicted position; S1304, determining the position information of the electric vehicle and the special vehicle in the tunnel according to the integrated position information and the existing vehicle information, the type, lane and sequence information of the vehicle entering the tunnel.

[0061] Exemplarily, first, the system performs speed analysis on the existing vehicle information of all vehicles and compares the speed information. If the speed information of some vehicles is less than the preset speed, these vehicles will be classified as low-speed vehicles, that is, the first existing vehicle information. These vehicle information will be sent to the first prediction module for predicting its position.

[0062] The first prediction module is built based on the Kalman filter algorithm. Kalman filtering is a linear estimation method for continuous time series, especially suitable for the position prediction of vehicles with low speed or steady movement. Kalman filtering performs recursive estimation based on the existing vehicle speed information, time information and the previous position of the vehicle, and finally obtains the first predicted position corresponding to the first existing vehicle information.

[0063] For vehicles whose speed information is greater than or equal to the preset speed, the system classifies them as high-speed vehicles, that is, the second existing vehicle information. This vehicle information will be sent to the second prediction module. The second prediction module is based on the long short-term memory network (LSTM). LSTM is a recursive neural network that can handle long-term dependencies and is particularly suitable for vehicles with nonlinear and complex motion trajectories. The LSTM model can predict the future motion trajectory of high-speed vehicles through historical time series data (such as vehicle speed changes and position at the previous moment). The system uses the LSTM model to predict the future positions of these high-speed vehicles, and then obtains the second predicted position corresponding to the second existing vehicle information.

[0064] The system obtains results from the first predicted position predicted by the Kalman filter algorithm and the second predicted position predicted by the LSTM algorithm respectively. Next, the system combines the first predicted position (the predicted position of the low-speed vehicle) with the second predicted position (the predicted position of the high-speed vehicle) to establish integrated position information.

[0065] Finally, the system combines the integrated position information with the information on the vehicle types, lanes, and order of the existing vehicles entering the tunnel to further accurately determine the position information of the electric vehicles in the tunnel and the position information of the special vehicles in the tunnel.

[0066] The vehicle type information enables the system to identify electric vehicles and special vehicles and determine their specific positions in the tunnel respectively. The lane information is used to determine the driving trajectory of the vehicle to ensure that the system can accurately locate the vehicle according to the specific lane where the vehicle is located. The order information is used to determine the order in which vehicles enter the tunnel. Through this information, the system can dynamically track the movement path of the vehicle and further correct the predicted position to ensure that the position information determined by the system matches the actual situation.

[0067] Specifically, the system first obtains the speed information of all vehicles and classifies the vehicles into two categories: The first category: low-speed vehicles, with speed information vi < vth (where vth is the preset speed threshold), that is, the first existing vehicle information.

[0068] The second category: high-speed vehicles, with speed information vi ≥ vth, that is, the second existing vehicle information.

[0069] Low-speed vehicle position prediction (based on Kalman filter) Kalman filter is a recursive algorithm used to estimate the current position of low-speed vehicles. The steps are as follows: The state equation is: xk+1 = Ax k + Bu k + w k where x k is the state vector of the vehicle at time k, including position and speed, A is the state transition matrix, B is the control input matrix, u k is the control input, and w k is the process noise.

[0070] The observation equation: zk = Hx k + v k where z k is the observation value obtained at time k (such as the current vehicle position and speed information), H is the observation matrix, and v k is the observation noise.

[0071] The Kalman filter process includes two steps: prediction and update: Prediction steps: ; where P is the state covariance matrix and Q is the process noise covariance.

[0072] Update steps: ; Among them, K k is the Kalman gain and R is the observation noise covariance.

[0073] Finally, the system obtains the predicted position of the low-speed vehicle through the Kalman filter algorithm .

[0074] For high-speed vehicles, the LSTM model is used to capture complex speed changes and nonlinear motion trajectories. The input of LSTM includes the historical speed information and position information of the vehicle, and the output is the predicted future position of the vehicle.

[0075] The update equation of LSTM is as follows: Input Gate: ; Forget Gate: ; Candidate memory cells: ; Output Gate: ; Memory unit update: ; Hide status updates:

[0076] Among them, x t is the input (historical speed and position), h t is the hidden state, C t The memory unit status.

[0077] By training the LSTM model, the system can predict the future position of high-speed vehicles .

[0078] This solution uses the first prediction module based on the Kalman filter algorithm and the second prediction module based on the long short-term memory network (LSTM) to predict the position of vehicles at different speeds, and finally accurately determines the position information of electric vehicles and special vehicles in the tunnel by integrating the predicted position, combining the vehicle type, lane and sequence information. This method can not only make personalized predictions based on the speed characteristics of the vehicle, but also provide more accurate vehicle positioning information on the basis of integration, providing reliable data support for subsequent fire monitoring and early warning.

[0079] In some examples, the risk prediction model includes a density risk prediction module, an environmental risk prediction module, and a risk fusion module; like Figure 5 As shown, the risk prediction unit determines the risk prediction level based on the risk prediction model according to the electric vehicle distribution information, the other vehicle distribution information and the tunnel environment information, and the specific steps include: S210, inputting the electric vehicle distribution information and the other vehicle distribution information into the density risk prediction module to obtain a density risk factor; S220, inputting the tunnel environmental information into the environmental risk prediction module to obtain environmental risk factors; S230, inputting the density risk factor and the environmental risk factor into the risk fusion module to obtain the risk prediction level.

[0080] Exemplarily, the system inputs the electric vehicle distribution information and other vehicle distribution information into the density risk prediction module to calculate the density-related fire risk factors. The electric vehicle distribution information includes the number and model of electric vehicles in the target tunnel and their specific locations in the tunnel. Other vehicle distribution information includes the number, type and location of special vehicles in the tunnel. The density risk prediction module evaluates the vehicle density in the tunnel based on the distribution of vehicles, especially the gathering of electric vehicles and special vehicles. If the vehicles in a certain area are too dense, or vehicles with higher risks such as electric vehicles and dangerous goods transport vehicles are concentrated in a specific area, the system will calculate the corresponding density risk factor based on the degree of density.

[0081] The system inputs tunnel environmental information into the environmental risk prediction module to evaluate the impact of tunnel environmental conditions on fire risk. Tunnel environmental information usually includes but is not limited to: Temperature information: Temperature changes in the tunnel, especially areas with abnormally high temperatures.

[0082] Humidity information: Humidity data in the tunnel. Too low humidity may increase the possibility of fire.

[0083] Ventilation status information: The operation status of the ventilation system in the tunnel. Good ventilation can quickly expel harmful gases and heat, reducing the risk of fire.

[0084] Air quality information: data such as smoke and carbon dioxide concentration that reflect air pollution or potential fire hazards.

[0085] The environmental risk prediction module evaluates the safety of the tunnel based on these environmental parameters, and generates corresponding environmental risk factors through comprehensive calculation of data such as temperature, humidity, ventilation and air quality. For example, when the temperature in the tunnel is abnormally high and the ventilation is poor, the environmental risk factor will be high.

[0086] Finally, the system inputs the density risk factor obtained from the density risk prediction module and the environmental risk factor obtained from the environmental risk prediction module into the risk fusion module. The function of the risk fusion module is to weight and fuse the risk factors from different modules to generate a comprehensive fire risk assessment result. The module weights the density risk factor and the environmental risk factor separately according to the weights set by historical data or by real-time adjustment. The specific weights can be dynamically adjusted according to the historical fire events in the tunnel, the vehicle type and the current environmental conditions.

[0087] Finally, the risk fusion module generates a comprehensive risk prediction level that reflects the severity of the current fire risk in the tunnel and is used to guide the response of the linked fire extinguishing system.

[0088] This solution uses the cooperation of three modules (density risk prediction module, environmental risk prediction module and risk fusion module). The system first calculates the density risk factor related to vehicle density based on the distribution information of electric vehicles and other vehicles. Then, the system generates the corresponding environmental risk factor based on tunnel environmental information such as tunnel temperature, humidity, ventilation conditions and air quality. Finally, the system inputs the two risk factors into the risk fusion module and obtains the risk prediction level of the current tunnel through weighted processing. This risk prediction level is used to judge the level of fire risk and help the system to make reasonable fire extinguishing responses under different fire risk levels.

[0089] In some examples, such as Figure 6 As shown, S210 inputs the electric vehicle distribution information and the other vehicle distribution information into the density risk prediction module to obtain density risk factors, including: S2101, gridding the target tunnel to obtain gridding information of the target tunnel; S2102, establishing vehicle distribution grid information based on the target tunnel grid information, the electric vehicle distribution information and the other vehicle distribution information; S2103, determining density weight information of different vehicle types; S2104. Determine the density risk factor based on the vehicle distribution grid information and the density weight information.

[0090] Exemplarily, the system performs gridding processing on the target tunnel to obtain the gridding information of the target tunnel. The purpose of the gridding processing is to divide the tunnel into multiple grid areas of equal size, each grid representing a location segment in the tunnel. Through such gridding, the distribution of vehicles in the tunnel can be refined to facilitate subsequent risk analysis. For example, the system can divide the length and width of the tunnel according to a predetermined resolution, and the size of each grid is determined according to the actual size of the tunnel and the monitoring accuracy. The gridding information of the target tunnel describes the location, number and distribution of these grids in the tunnel.

[0091] After obtaining the grid information of the target tunnel, the system then establishes the vehicle distribution grid information based on this information as well as the electric vehicle distribution information and other vehicle distribution information. The electric vehicle distribution information includes the number and model of electric vehicles and their specific locations in the tunnel. The system will classify the electric vehicles into the corresponding grids based on their location information. Other vehicle distribution information includes the number and type of special vehicles and their locations in the tunnel. Similarly, the system will distribute these vehicles to the corresponding grids based on their location information. The vehicle distribution grid information is based on the specific distribution of vehicles in each grid in the tunnel after gridding. This information includes the number of electric vehicles and special vehicles in each grid, and is distinguished according to different vehicle types.

[0092] Next, the system sets density weight information for different types of vehicles. The density weight information is set based on the degree of impact of different vehicle types on fire risk.

[0093] Electric vehicles have different safety levels due to their different types of lithium batteries.

[0094] Special vehicles, such as those transporting hazardous materials, also have a higher density weight because the cargo they carry may pose an increased risk of fire or explosion.

[0095] By setting corresponding density weight information for each type of vehicle, the system can more accurately assess the impact of different vehicle types on the overall risk in the tunnel. For example, electric vehicles can be weighted higher than ordinary vehicles, while dangerous goods transport vehicles may have a higher weight to better reflect their risks in the density analysis.

[0096] In some examples, density weight information of electric vehicles is obtained by weighted fusion based on battery type information and collision test data information of the electric vehicles.

[0097] For example, first, the system sets a preliminary weight value for the electric vehicle based on the battery type information of the electric vehicle. Different battery types play different roles in fire risk, and some batteries are more susceptible to ambient temperature or collision impact, and have a higher risk of fire.

[0098] Lithium-ion batteries: Lithium-ion batteries are widely used in electric vehicles. They have high energy density but are prone to thermal runaway at high temperatures or under overcharge. Therefore, electric vehicles equipped with lithium-ion batteries usually have a higher risk weight.

[0099] Lithium iron phosphate battery: This type of battery has higher thermal stability and is relatively less prone to thermal runaway, so its weighting will be lower than that of lithium-ion batteries.

[0100] Solid-state batteries: Solid-state batteries have a lower risk of fire because they do not have liquid electrolytes, so the system assigns a lower risk weight to electric vehicles using solid-state batteries.

[0101] By identifying the battery type information of each electric vehicle, the system can set initial weight values ​​for electric vehicles with different types of batteries to reflect their impact on fire risk.

[0102] It should be noted that the battery type information is determined based on a fixed matching relationship between the electric vehicle type information and the battery type.

[0103] Next, the system will further adjust the weight of electric vehicles based on the collision test data information. The collision test data is an important indicator for evaluating the safety of electric vehicles in collision events. The structural strength and battery protection performance of electric vehicles in collisions directly affect their fire risk.

[0104] Collision level classification: Based on the collision test data of different electric vehicles, the system divides them into different collision levels. A higher collision level indicates that the vehicle has better safety performance in the event of a collision, while a lower collision level means that the battery may be more easily damaged in an accident, increasing the risk of fire.

[0105] Electric vehicles with higher collision levels will have lower weight values ​​because their vehicle structures and battery protection measures are more complete and the risk of fire is lower.

[0106] Electric vehicles with lower crash ratings will have a higher weighting because the battery may be more likely to be damaged and cause a fire in an accident.

[0107] Source of collision data: Collision test data can come from standardized vehicle safety testing organizations, such as NCAP and other safety testing and rating organizations, to ensure the reliability and scientific nature of the data.

[0108] Based on the collision test data information of electric vehicles, the system can further adjust the weight of electric vehicles to accurately reflect their risk contribution in vehicle density.

[0109] In some examples, the tunnel environment information includes temperature information, humidity information, ventilation condition information, and air quality information; The above-mentioned tunnel environmental information is input into the above-mentioned environmental risk prediction module to obtain environmental risk factors, including: The environmental risk factors are obtained by weighted fusion based on the temperature information, the humidity information, the ventilation condition information and the air quality information.

[0110] For example, first, the system evaluates the fire risk in the tunnel based on the real-time monitored temperature information. High temperature may be a direct sign of fire hazard, especially in a closed environment such as a tunnel, where abnormal temperature rise is usually a risk factor that needs to be focused on.

[0111] The system uses multi-point temperature sensors to obtain temperature information at different locations in the tunnel, including current temperature and temperature change trends. For areas with excessively high temperatures or rapid temperature rise, the system will set a high risk weight because these areas may have battery overheating or other high temperature risks.

[0112] The risk weight of temperature information, Wtemp, is adjusted according to the extent to which the temperature exceeds the safety threshold and the rate of temperature change.

[0113] Humidity plays an important role in the occurrence and spread of fire. Monitoring humidity information in tunnels helps to assess the possibility of fire. The system obtains humidity information of the air in the tunnel through humidity sensors. Usually, too low humidity can easily lead to dry air, thereby increasing the probability of fire.

[0114] If the humidity in the tunnel is too low, the system will set a higher risk weight Whumidity for the humidity information. Conversely, if the humidity is high, the fire risk is considered relatively low. By setting the risk threshold of humidity, the system can automatically adjust the humidity risk factor to ensure that the fire risk under different humidity conditions is properly assessed.

[0115] Ventilation information is another important factor in assessing fire risk. Good ventilation can reduce gas accumulation and high temperature accumulation in the tunnel, reducing the risk of fire. The system monitors ventilation information in real time through wind speed monitors installed in the tunnel. If ventilation is poor, the system will set a higher risk weight Wvent for the area. Poor ventilation will accelerate the accumulation of heat and smoke and increase the possibility of fire spread. Therefore, in the case of poor ventilation conditions, the system will increase the risk level of the corresponding area.

[0116] Air quality information includes smoke concentration, carbon dioxide content, and other harmful gas concentrations in the tunnel. Deterioration of air quality may be a precursor to an impending or ongoing fire. The system monitors the air composition in the tunnel, such as smoke concentration, carbon dioxide concentration, and other possible pollutants, through air quality sensors. If the air quality deteriorates sharply, especially if there is a significant increase in the concentration of smoke or harmful gases, the system will assign a higher risk weight Wair to the air quality information. Changes in air quality can directly reflect potential fire situations, so through real-time monitoring, the system can identify fire risks at an early stage.

[0117] Finally, the system will perform weighted fusion of the respective risk weights extracted from temperature information, humidity information, ventilation information, and air quality information to generate an environmental risk factor. The specific weighted fusion formula is as follows: ; Fenv represents the final calculated environmental risk factor.

[0118] w1, w2, w3 and w4 are the weight coefficients of each factor, which can be adjusted based on historical data, current environmental conditions and other factors to reflect the relative impact of different factors on fire risk.

[0119] In some examples, S230 inputs the density risk factor and the environmental risk factor into the risk fusion module to obtain the risk prediction level, including: S2301. Determine first weight information corresponding to the density risk factor and second weight information corresponding to the environmental risk factor based on historical fire risk information; S2302, calculating a risk score based on the density risk factor, the environmental risk factor, the first weight information, and the second weight information; S2303. Determine the risk level based on the risk score.

[0120] Exemplarily, first, the system refers to historical fire risk information to determine the relative importance of density risk factors and environmental risk factors in the comprehensive risk assessment.

[0121] The density risk factor reflects the density of vehicle distribution in the tunnel, especially the concentration of electric vehicles and special vehicles. Based on historical fire cases, the system can evaluate the correlation between vehicle density and fire occurrence, and then set the first weight information for the density risk factor. The environmental risk factor evaluates the impact of temperature, humidity, ventilation conditions and air quality in the tunnel on fire risk. By analyzing the relationship between previous fire incidents and environmental conditions, the system sets the second weight information for the environmental risk factor.

[0122] These weight information (first weight information and second weight information) are derived from statistical analysis of historical fire data and can be dynamically adjusted to ensure that density risks and environmental risks are appropriately reflected in different scenarios.

[0123] After obtaining the density risk factor, environmental risk factor and their respective weight information, the system will proceed to the next step, namely, calculating the risk score. The system multiplies the density risk factor with its corresponding first weight information to obtain the risk contribution value of the density part. Similarly, the system multiplies the environmental risk factor with the second weight information to obtain the contribution value of the environmental risk part.

[0124] The system calculates a comprehensive risk score by weighted summation, and the formula is as follows: ; Among them, R represents the final risk score.

[0125] Fdensity is the density risk factor, and Fenv is the environmental risk factor.

[0126] w1 and w2 are first weight information and second weight information respectively determined from historical fire risk information.

[0127] Through this weighted calculation, the system is able to derive an overall fire risk score for the current tunnel based on a combination of vehicle density and environmental conditions.

[0128] Finally, the system determines the risk prediction level within the tunnel based on the calculated risk score. The relationship between the risk score and the risk level is usually defined by a pre-set grading standard. The following is an exemplary risk level classification: In this solution, the system first sets corresponding first weight information and second weight information for density risk factor and environmental risk factor based on historical fire risk information. Then, the system combines density and environmental risk factors with their respective weights to calculate a comprehensive risk score. Finally, the system maps the risk score to different risk levels through preset standards, thereby providing accurate fire risk assessment and response solutions for the linkage fire extinguishing system.

[0129] In some examples, the specific steps of the control unit controlling the waiting response level of the linkage fire extinguishing system based on the risk prediction level include: Based on the above risk prediction level, the wind speed information, temperature monitoring frequency information, fire detection detector sensitivity information and fire extinguishing equipment status information of the ventilation system of the linked fire extinguishing system are controlled, wherein the above fire extinguishing equipment status information includes automatic fire extinguishing device operation status information, fire extinguishing area division status information and fire extinguishing agent injection quantity status information.

[0130] For example, according to the risk prediction level evaluated by the system in real time, the control unit dynamically adjusts the wind speed information of the ventilation system. The ventilation system plays an important role in air circulation, smoke emission, etc. in the tunnel.

[0131] When the risk prediction level is low, the system maintains the normal operation of the ventilation system and the wind speed is maintained at a standard level for regular air circulation. When the risk prediction level is raised to medium or high risk, the system will increase the wind speed according to actual needs to ensure smoother air circulation in the tunnel and reduce the accumulation of harmful gases or smoke. At this time, the wind speed information will be adjusted to a higher value to cope with potential fire risks.

[0132] Temperature monitoring frequency information is another important control parameter. As the risk prediction level increases, the system needs to monitor the temperature changes in the tunnel more frequently in order to promptly capture any temperature anomalies that may cause a fire. In low-risk situations, the system maintains a standard temperature monitoring frequency, such as taking temperature samples at regular intervals. When the risk prediction level rises, the system will speed up the frequency of temperature monitoring to ensure real-time updates of the temperature status in the tunnel. The frequency may be shortened from the conventional 10 minutes to 1 minute to ensure a faster response to temperature changes. In high or extremely high risk situations, the system can be set to continuous real-time monitoring to ensure that any slight temperature changes can be quickly detected.

[0133] Fire detector sensitivity information is used to adjust the sensitivity of fire detectors to signs of fire. The system dynamically adjusts the sensitivity of detectors according to different risk prediction levels. When the risk prediction level is low, the system maintains normal detection sensitivity, and the detectors respond to potential fire signals according to the normal sensitivity threshold. When the risk level increases, the system will increase the sensitivity of the detectors and lower their response thresholds to ensure that potential fire hazards are detected earlier. In high-risk situations, the sensitivity of the detectors reaches the highest level, and any increase in temperature, smoke or other signs of fire will be immediately captured by the system, triggering further fire response measures.

[0134] The system controls the status information of fire extinguishing equipment to ensure that the fire extinguishing equipment is in the corresponding standby state under different risk levels. Specifically: (1) Automatic fire extinguishing device operation status information: At lower risk, the fire extinguishing equipment is in standby mode, the pre-operation is not started, and the system only performs routine monitoring. As the risk prediction level increases, the system will gradually start automatic fire extinguishing pre-operation, including preparing fire extinguishing agent, checking pipeline pressure, preheating fire extinguishing equipment, etc., to ensure that the fire extinguishing system can be put into operation quickly when needed.

[0135] (2) Fire extinguishing area division status information: The system divides the fire-fighting areas according to the risk prediction level and vehicle distribution information. When the risk is low, the system only makes a preliminary division of the high-risk areas and allocates potential fire-fighting equipment to each area. When the risk level increases, the system divides the fire-fighting areas in the tunnel in more detail to ensure that when a fire occurs, it can be accurately extinguished in a specific area to avoid wasting fire-fighting resources.

[0136] (3) Fire extinguishing agent injection quantity status information: According to the risk prediction level, the system will also control the state information of the injection amount of the fire extinguishing agent. In the case of lower risk, the injection amount of the fire extinguishing agent is in the lowest standby state, and the appropriate amount of fire extinguishing agent is prepared. When the risk increases, especially in high-risk situations, the system will increase the reserve amount of fire extinguishing agent according to the predicted possibility of fire to ensure that there is enough fire extinguishing agent to quickly extinguish the fire when it occurs. In the case of extremely high risk, the injection amount of the fire extinguishing agent will reach the preset maximum value to ensure that the fire extinguishing system can fully cover the entire high-risk area and quickly and effectively control the fire.

[0137] This embodiment uses a control unit to dynamically adjust the wind speed information of the ventilation system, the temperature monitoring frequency information, the fire detector sensitivity information, and the equipment status information of the fire extinguishing equipment based on the risk prediction level, thereby realizing intelligent and graded response to the linkage fire extinguishing system. The system can take corresponding fire prevention measures and fire extinguishing preparations according to different risk levels to ensure that the fire risk in the tunnel is optimally managed and responded to.

[0138] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system, characterized in that: include: An image acquisition unit, the image acquisition unit is used to acquire image information of a first vehicle entering a target tunnel, and the image acquisition unit is also used to acquire image information of a second vehicle exiting the target tunnel; an electric vehicle identification unit, configured to determine electric vehicle distribution information and other vehicle distribution information in a target tunnel based on a vehicle identification model according to the first vehicle image information and the second vehicle image information, wherein the electric vehicle distribution information includes electric vehicle quantity information, electric vehicle model information, and electric vehicle location information in the tunnel, and the other vehicle distribution information includes special vehicle quantity information, special vehicle type information, and special vehicle location information in the tunnel; A tunnel environment collection unit, used to obtain tunnel environment information of the target tunnel; A risk prediction unit, configured to determine a risk prediction level based on a risk prediction model according to the electric vehicle distribution information, the other vehicle distribution information and the tunnel environment information; A control unit is used to control the waiting response level of the linkage fire extinguishing system based on the risk prediction level.

2. The tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system according to claim 1 is characterized in that: The specific steps of the electric vehicle identification unit determining the electric vehicle distribution information in the target tunnel include: Determine the existing vehicle information in the target tunnel based on the first vehicle picture information, the second vehicle picture information and the picture shooting time information; Determine the electric vehicle quantity information, the special vehicle quantity information, the electric vehicle model information and the special vehicle type information based on the existing vehicle information; The position information of the electric vehicle in the tunnel and the position information of the special vehicle in the tunnel are determined based on the existing vehicle information, the speed information of the existing vehicle entering the tunnel and the picture shooting time information.

3. The tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system according to claim 2 is characterized in that: The determining, based on the existing vehicle information, the electric vehicle quantity information, the special vehicle quantity information, the electric vehicle model information and the special vehicle type information includes: Performing a preprocessing operation on the image information corresponding to the existing vehicle information to obtain preprocessed image information; Inputting the preprocessed image information into a first recognition module to obtain the electric vehicle quantity information and the special vehicle quantity information, wherein the first recognition module is established based on a Faster R-CNN model; The pre-processed image information is input into a second recognition module to obtain the electric vehicle model information and the special vehicle type information, wherein the second recognition module is established based on a SVM model.

4. The tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system according to claim 2 is characterized in that: The determining the position information of the electric vehicle in the tunnel and the position information of the special vehicle in the tunnel based on the existing vehicle information, the speed information of the existing vehicle entering the tunnel, and the picture shooting time information includes: Sending the first existing vehicle information whose speed information is less than the preset speed to the first prediction module to obtain a first predicted position corresponding to the first existing vehicle information, wherein the first prediction module is established based on a Kalman filter algorithm; Sending the second existing vehicle information whose speed information is greater than or equal to the preset speed to a second prediction module to obtain a second predicted position corresponding to the second existing vehicle information, wherein the second prediction module is established based on a long short-term memory network; Establishing integrated position information based on the first predicted position and the second predicted position; The position information of the electric vehicle and the special vehicle in the tunnel are determined based on the integrated position information and existing vehicle information about the type, lane and sequence of vehicles entering the tunnel.

5. The tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system according to claim 1 is characterized in that: The risk prediction model includes a density risk prediction module, an environmental risk prediction module and a risk fusion module; The specific steps of determining the risk prediction level by the risk prediction unit based on the risk prediction model according to the electric vehicle distribution information, the other vehicle distribution information and the tunnel environment information include: Inputting the electric vehicle distribution information and the other vehicle distribution information into the density risk prediction module to obtain a density risk factor; Inputting the tunnel environmental information into the environmental risk prediction module to obtain environmental risk factors; The density risk factor and the environmental risk factor are input into the risk fusion module to obtain the risk prediction level.

6. The tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system according to claim 5 is characterized in that: The step of inputting the electric vehicle distribution information and the other vehicle distribution information into the density risk prediction module to obtain a density risk factor includes: Performing grid processing on the target tunnel to obtain grid information of the target tunnel; Establishing vehicle distribution grid information based on the target tunnel grid information, the electric vehicle distribution information and the other vehicle distribution information; Determine density weight information for different vehicle types; The density risk factor is determined according to the vehicle distribution gridding information and the density weight information.

7. The tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system according to claim 6 is characterized in that: The density weight information of electric vehicles is obtained by weighted fusion based on the battery type information and collision test data information of the electric vehicles.

8. The tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system according to claim 5 is characterized in that: The tunnel environment information includes temperature information, humidity information, ventilation condition information and air quality information; The step of inputting the tunnel environment information into the environmental risk prediction module to obtain environmental risk factors includes: The environmental risk factor is obtained by performing weighted fusion based on the temperature information, the humidity information, the ventilation condition information and the air quality information.

9. According to the tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system of claim 5, the inputting of the density risk factor and the environmental risk factor into the risk fusion module to obtain the risk prediction level comprises: Determine first weight information corresponding to the density risk factor and second weight information corresponding to the environmental risk factor based on historical fire risk information; Calculating a risk score based on the density risk factor, the environmental risk factor, the first weight information, and the second weight information; The risk level is determined based on the risk score.

10. The tunnel vehicle-mounted lithium battery fire monitoring, early warning and linkage fire extinguishing system according to claim 1 is characterized in that: The specific steps of the control unit controlling the waiting response level of the linkage fire extinguishing system based on the risk prediction level include: Based on the risk prediction level, the wind speed information, temperature monitoring frequency information, fire detection detector sensitivity information and fire extinguishing equipment status information of the ventilation system of the linked fire extinguishing system are controlled, wherein the fire extinguishing equipment status information includes automatic fire extinguishing device operation status information, fire extinguishing area division status information and fire extinguishing agent injection amount status information.

Images