A tunnel new energy vehicle operation risk monitoring and early warning method and system

Abstract

The application relates to the technical field of new energy automobile risk monitoring, and discloses a tunnel new energy automobile operation risk monitoring and early warning method and system, which comprises the following steps: at a tunnel entrance, a camera is used to acquire license plate information of a vehicle entering the tunnel, and it is determined whether the vehicle is a new energy automobile; based on a battery health parameter, a battery health index of the new energy automobile is calculated; if the battery health index is less than or equal to a preset threshold, an infrared thermal imaging all-in-one machine arranged in the tunnel is used to monitor temperature data of a battery pack of the new energy automobile in real time, and the battery health index and the temperature data are input into a preset risk research and judgment model to obtain a comprehensive risk probability and a risk level of the new energy automobile; and according to the risk level, corresponding early warning measures are executed. The scheme can monitor the risk condition of the new energy automobile in real time, accurately warn and take measures, and significantly improves the initiative and effectiveness of tunnel safety management.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of new energy vehicle risk monitoring, and particularly relates to a tunnel new energy vehicle operation risk monitoring and early warning method and system. BACKGROUND

[0002] With the continuous development of the automobile industry, the proportion of new energy vehicles in the composition of traffic vehicles is increasing year by year. When a new energy vehicle catches fire in a tunnel, the heat release rate is fast, the smoke production is large, and the fire spreads more rapidly in a confined space. Conventional fire-fighting facilities cannot effectively control the battery fire, and fire rescue is also difficult to extinguish it. Therefore, the risk monitoring of new energy vehicles is extremely important.

[0003] The existing tunnel monitoring system is mainly designed for traditional fuel vehicles and lacks special monitoring capability for new energy vehicle battery fire risks. The system cannot effectively identify the identity of new energy vehicles, and cannot obtain the core battery health status historical data, resulting in the inability to early screen potential risks such as battery aging. In terms of monitoring, traditional flame detectors or ordinary video monitoring cannot non-contact real-time measure the battery pack temperature, and cannot capture the early temperature rise signs of thermal runaway. In terms of analysis, the existing system relies on simple single threshold alarm and cannot fuse multi-dimensional parameters for comprehensive risk assessment, and has no ability to distinguish risk dominant factors, resulting in single early warning information and lack of targeted response measures, making it difficult to implement effective intervention in the key window period before battery thermal runaway occurs.

[0004] Therefore, it is urgent to develop a tunnel new energy vehicle operation risk monitoring and early warning method and system, which can monitor the risk situation of new energy vehicles in real time and accurately warn and take measures, significantly improving the initiative and effectiveness of tunnel safety management. SUMMARY

[0005] In order to solve the above technical problems, the application provides a tunnel new energy vehicle operation risk monitoring and early warning method and system, which can monitor the risk situation of new energy vehicles in real time and accurately warn and take measures, significantly improving the initiative and effectiveness of tunnel safety management.

[0006] The application provides a tunnel new energy vehicle operation risk monitoring and early warning method, which comprises the following steps:

[0007] S1, at the tunnel entrance, the license plate information of the vehicle entering the tunnel is obtained through a camera, and it is determined whether the vehicle is a new energy vehicle. If the vehicle is a new energy vehicle, the battery health parameters are obtained according to the license plate information of the new energy vehicle, otherwise the monitoring of the vehicle is stopped;

[0008] S2, calculate the battery health index of the new energy vehicle based on the battery health parameter; if the battery health index is less than or equal to a preset threshold, proceed to the next step; otherwise, stop monitoring the vehicle;

[0009] S3, use the infrared thermal imaging all-in-one machine arranged in the tunnel to monitor the temperature data of the battery pack of the new energy vehicle in real time, input the battery health index and the temperature data into a preset risk judgment model, and obtain the comprehensive risk probability and the risk level of the new energy vehicle;

[0010] S4, according to the risk level, execute corresponding warning measures.

[0011] Further, in S1, the battery health parameter includes at least one of the current battery state of charge, the total number of battery cycles, and the maximum temperature difference between the single cells in the battery pack.

[0012] Further, in S2, based on the battery health parameter, the battery health index of the new energy vehicle is calculated, including:

[0013] Based on the ratio of the total number of battery cycles to the maximum allowed number of cycles, the ratio of the maximum temperature difference between the single cells in the battery pack to the maximum allowed temperature difference, and the deviation of the current battery state of charge from the ideal state of charge, weighted calculation is performed to obtain the battery health index of the new energy vehicle.

[0014] Further, in S3, the temperature data of the battery pack includes the real-time maximum temperature of the battery pack surface and the battery pack temperature rise rate.

[0015] Further, in S3, a multi-layer perception mechanism is used to build the preset risk judgment model, and the preset risk judgment model includes an input layer, a hidden layer and an output layer:

[0016] The input layer includes 3 nodes for receiving the real-time maximum temperature of the battery pack surface, the battery pack temperature rise rate and the battery health index;

[0017] The hidden layer uses a ReLU activation function;

[0018] The output layer includes two output branches, the first branch is a risk probability branch using a Sigmoid activation function, and the second branch is a risk dominant type branch using a Softmax activation function.

[0019] Further, the risk dominant type output by the second branch includes a thermal runaway risk probability, a mechanical damage probability and an electrical abnormality probability.

[0020] Further, in S4, according to the risk level, corresponding warning measures are executed, including:

[0021] When the risk level is low risk, no warning is needed, and the new energy vehicle is continuously monitored until it leaves the tunnel.

[0022] When the risk level is medium risk or high risk, the new energy vehicle is prompted to immediately drive out of the tunnel.

[0023] The application also provides a tunnel new energy vehicle operation risk monitoring and early warning system for executing the tunnel new energy vehicle operation risk monitoring and early warning method.

[0024] The data acquisition module is used for acquiring the license plate information of the vehicle entering the tunnel through the camera at the tunnel entrance, and determining whether the vehicle is a new energy vehicle; if the vehicle is a new energy vehicle, the battery health parameter is acquired according to the license plate information of the new energy vehicle, otherwise the vehicle is stopped from being monitored;

[0025] The health index calculation module is used for calculating the battery health index of the new energy vehicle based on the battery health parameter; if the battery health index is less than or equal to a preset threshold, the next step is entered; otherwise, the vehicle is stopped from being monitored;

[0026] The risk prediction module is used for monitoring the temperature data of the battery pack of the new energy vehicle in real time by using the infrared thermal imaging all-in-one machine arranged in the tunnel, and inputting the battery health index and the temperature data into a preset risk research and judgment model to obtain the comprehensive risk probability and the risk level of the new energy vehicle;

[0027] The early warning module is used for executing corresponding early warning measures according to the risk level.

[0028] The application has the following technical effects:

[0029] The application realizes early screening of the battery health state of the vehicle by capturing the license plate at the tunnel entrance and associating the remote data platform for data tracing, solves the problems of target identification and static risk assessment, and realizes the leap from static assessment to dynamic perception by using the infrared thermal imaging technology inside the tunnel, based on the thermal radiation measurement principle, for non-contact temperature monitoring of the battery pack of the vehicle in driving, and accurately capturing the two key precursor signals of surface temperature and temperature rise rate; the scheme adopts a specially designed double-branch neural network model as the intelligent analysis center, which is based on the multi-task learning principle and can deeply fuse the static health index and dynamic temperature data, on the one hand, outputs the comprehensive risk probability to realize risk grading, and on the other hand, researches and judges different risk dominant types such as thermal abuse, mechanical damage or electrical abnormality, which makes the system have the intelligent research and judgment ability of understanding the risk source, and surpasses the limitations of traditional single threshold alarm; finally, based on the accurate risk portrait, the system triggers the early warning response of classification, and starts the differentiated disposal measures for different levels and types of risks, such as targeted broadcast prompt or linkage of traffic control equipment, so as to realize the leap from general alarm to accurate strategy, and significantly improve the initiative and effectiveness of tunnel safety management. Attached Figure Description

[0030] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0031] Figure 1 This is a flowchart of a method for monitoring and early warning of operational risks of new energy vehicles in tunnels, provided by an embodiment of the present invention.

[0032] Figure 2 This is a schematic diagram of the structure of a system for monitoring and early warning of operational risks of new energy vehicles in tunnels, provided by an embodiment of the present invention. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0034] This invention provides a method for monitoring and early warning of operational risks of new energy vehicles in tunnels. Figure 1 This is a flowchart of a method for monitoring and early warning of operational risks of new energy vehicles in tunnels, provided by an embodiment of the present invention. (See also...) Figure 1 The method includes the following steps:

[0035] S1. At the tunnel entrance, cameras are used to obtain the license plate information of vehicles entering the tunnel and to determine whether the vehicles are new energy vehicles.

[0036] In some embodiments, a high-definition video snapshot of the incoming vehicle is taken by an industrial-grade pan-tilt camera mounted on the portal frame at the tunnel entrance, the license plate number is identified in real time, and it is determined whether the vehicle is a new energy vehicle according to the license plate color and number rules. If the vehicle is a new energy vehicle, the system will initiate a query request to the vehicle manufacturer's data platform or authorized third-party service platform through a pre-set, privacy regulation-compliant secure channel to obtain the battery health parameters. The query process is anonymized and does not involve the vehicle owner's personal information. It is worth noting that the vehicle manufacturer's data platform or authorized third-party service platform will have obtained the authorization of the new energy vehicle user in advance and will send the battery health parameters to the monitoring and early warning system involved in the present application. For example, an option "Do you agree that the tunnel monitoring and early warning system obtains the battery health parameters for battery health monitoring?" is set on the data platform or third-party service platform for the user to choose. If the user checks this option, it is considered that the user agrees to the system monitoring the battery health of the vehicle. If the vehicle is not a new energy vehicle, the monitoring of the vehicle is stopped.

[0037] Among them, obtaining the battery health parameters includes:

[0038] The current state of charge of the battery, which represents the percentage of the remaining battery capacity, a high SOC state means that the battery energy is high and the potential risk of thermal runaway increases;

[0039] The total number of battery cycles, which means that one cycle refers to the process of discharging from full to full, and this value directly reflects the historical use intensity and aging degree of the battery;

[0040] The maximum temperature difference between the single cells in the battery pack is a key indicator for judging the internal consistency of the battery pack, the efficiency of the cooling system, and whether there is an internal short circuit fault, and a large temperature difference is an important precursor of thermal runaway.

[0041] In some embodiments, other key parameters can also be obtained, such as the vehicle model, which is used to match the inherent risk characteristics in the knowledge base; the battery type (such as ternary lithium, iron phosphate lithium), different types of batteries have different thermal runaway mechanisms, etc.

[0042] S2, based on the battery health parameters, calculate the battery health index of the new energy vehicle.

[0043] In some embodiments, based on the ratio of the total number of battery cycles to the maximum allowed number of cycles, the ratio of the maximum temperature difference between the single cells in the battery pack to the maximum allowed temperature difference, and the deviation of the current state of charge of the battery from the ideal state of charge, a weighted calculation is performed to obtain the battery health index of the new energy vehicle, and the calculation formula is as follows:

[0044] ;

[0045] BHI, where BHI represents the battery health index, the value range is 0-1, the closer to 1, the better the battery health, the closer to 0, the higher the risk of battery aging or failure, Cycle 总 represents the total number of cycles of the battery, Cycle max represents the maximum allowable number of cycles of the battery under safety specifications, which is a preset value, derived from the technical specifications or historical database of the battery manufacturer, ΔT cell represents the maximum temperature difference between the single cells in the battery pack, ΔT max represents the maximum allowable temperature difference allowed by the battery of this model, a temperature difference exceeding this value indicates that the battery pack has a serious internal consistency problem, F SOC represents the SOC state scoring function, which is an empirical function, when the SOC is in the ideal range of 20%-80%, the function output value is higher (close to 1), close to 0% or 100%, the function output value is lower, because the extreme SOC state will accelerate the battery aging and increase the safety risk, SOC represents the current state of charge of the battery, α, β, γ represent the weight coefficients, satisfying α+β+γ=1, according to the influence degree of each parameter on aging, for example, α=0.5, β=0.3, γ=0.2.

[0046] If the battery health index is less than or equal to the preset threshold, it indicates that the battery of the new energy vehicle has significant aging or potential failure, and is identified as a high-risk target, entering the next step; if the battery health index is greater than the preset threshold, the battery health of the new energy vehicle is good, and the current risk of running in the tunnel is low, the system marks it as a "low-risk vehicle" and ends the special monitoring process of the vehicle; wherein the preset threshold is set according to the actual situation, and exemplarily can be set to 0.6.

[0047] S3, using the infrared thermal imaging all-in-one machine arranged in the tunnel to monitor the temperature data of the battery pack of the new energy vehicle in real time, and inputting the battery health index and the temperature data into the preset risk judgment model to obtain the comprehensive risk probability and risk level of the new energy vehicle.

[0048] Wherein, the temperature data of the battery pack includes the real-time maximum temperature of the battery pack surface and the temperature rise rate of the battery pack, the real-time maximum temperature of the battery pack surface is directly read by analyzing the infrared thermal imaging diagram.

[0049] In some embodiments, a multi-layer perception mechanism is used to build the preset risk judgment model, and the preset risk judgment model includes an input layer, a hidden layer and an output layer:

[0050] The input layer includes 3 nodes for receiving the real-time maximum temperature of the battery pack surface, the temperature rise rate of the battery pack and the battery health index;

[0051] Before inputting data, the original data needs to be normalized to fall within the range of [0, 1] or [-1, 1] to speed up model training and improve stability.

[0052] The hidden layer adopts a ReLU activation function.

[0053] The output layer includes two output branches. The first branch is a risk probability branch, which includes one node and adopts a Sigmoid activation function. The second branch is a risk dominant type branch, which includes three nodes and adopts a Softmax activation function.

[0054] The risk dominant type output by the second branch includes a thermal runaway risk probability, a mechanical damage probability, and an electrical abnormality probability. The type with the largest value is the dominant factor of the current risk. The thermal runaway risk probability indicates whether the current state is likely to develop into thermal runaway. The mechanical damage probability indicates whether poor battery health status (low BHI) is the main contributing factor of the current high risk, because aged batteries are more susceptible to damage due to slight mechanical stress. The electrical abnormality probability indicates whether a rapid temperature rise rate is the main contributing factor of the current high risk, because electrical abuse is usually characterized by a sharp temperature rise.

[0055] Further, the total loss function of the multi-layer perception is the weighted sum of the loss of the two branches. The regression loss function adopts a mean square error loss function:

[0056] ;

[0057] The classification loss function adopts a cross-entropy loss function:

[0058] ;

[0059] where i represents the sample index, j represents the risk dominant type index, represents the true risk probability of the ith sample, represents the risk probability of the ith sample predicted by the model, N represents the total number of samples, L regression represents the regression loss function, L classification represents the classification loss function, represents the true label of the ith sample in the jth risk dominant type, which is represented by one-hot encoding, for example, [1, 0, 0], represents the predicted probability of the ith sample in the jth risk dominant type.

[0060] Total loss function:

[0061] L total =a×L regression +b×L classification ;

[0062] wherein, L total represents the total loss function, a represents the weight of the regression loss function, which is set as 1 by default, and b represents the weight of the classification loss function, which is adjusted according to the importance of the task.

[0063] In some embodiments, according to the comprehensive risk probability P risk The risk level can be determined according to actual conditions, and in the present embodiment, the following division method is adopted:

[0064] If P risk ≤ 0.1, the risk level is low risk;

[0065] If 0.1 < P risk ≤ 0.5, the risk level is medium risk;

[0066] If P risk > 0.5, the risk level is high risk.

[0067] S4. According to the risk level, the corresponding warning measures are executed.

[0068] In some embodiments, the following can be included:

[0069] When the risk level is low risk, no warning is needed, and the new energy vehicle is continuously monitored until it leaves the tunnel;

[0070] When the risk level is medium risk or high risk, the new energy vehicle is prompted to immediately leave the tunnel.

[0071] Further, in some embodiments, the corresponding warning measures can be further determined in combination with the risk dominant type, for example:

[0072] When the risk level is low risk, no warning is needed, and the new energy vehicle is continuously monitored until it leaves the tunnel;

[0073] When the risk level is medium risk and the risk dominant type is thermal runaway risk or electrical abnormality, it indicates that the vehicle battery temperature is high or the temperature rises too fast, and further deterioration needs to be avoided, and the new energy vehicle can be prompted to "please drive smoothly and check after leaving the tunnel as soon as possible"; the emphasis is on "smooth driving" to avoid sudden acceleration leading to sudden increase of battery load; the goal is to let the vehicle leave the high-risk area (tunnel) before the risk escalates;

[0074] When the risk level is medium risk and the risk dominant type is mechanical damage, it indicates that the vehicle battery pack may become fragile due to aging or potential damage, and needs to avoid bumps or collisions, and the new energy vehicle can be prompted to "please drive smoothly and check slowly after passing through the tunnel"; the emphasis is on "smooth and slow", which aims to reduce the impact of road impact on the possibly damaged battery pack;

[0075] When the risk level is high risk and the risk dominant type is thermal runaway, it indicates that the vehicle battery is in a high temperature state, which may be caused by external fire or continuous overheating, and the prompt "please drive away immediately after the tunnel and check" can be given. In addition, the administrator can be contacted to notify the fire department, and a large amount of water source can be prepared, because the battery thermal runaway needs continuous cooling;

[0076] When the risk level is high risk and the risk dominant type is mechanical damage, it indicates that the vehicle battery pack structure is determined to be damaged, but there may be no open fire yet, and the disposal needs to avoid causing secondary short circuit. The prompt "please drive away from the tunnel immediately and park safely after turning off the engine" can be given. In addition, the administrator or the lane can be automatically closed to prevent rear-end collision and cause secondary collision. The prompt "smoothly" is to avoid emergency braking and other behaviors that aggravate the internal damage of the battery pack;

[0077] When the risk level is high risk and the risk dominant type is electrical abnormality, it indicates that the vehicle battery may be experiencing severe short circuit, with extremely fast temperature rise and possible explosion at any time. The prompt "please drive away from the tunnel immediately" can be given. In addition, the facilities in the tunnel can be linked to start the strongest ventilation mode and aim at the accident area to delay the battery temperature rise. Since the development speed of electrical abuse is extremely fast, it needs to be solved in seconds, and the response measures are the most aggressive.

[0078] After all the warning instructions are issued, the system continues to monitor the vehicle state and tunnel environment changes, and at the same time, the current executed plan, vehicle position and equipment state are clearly marked on the monitoring center interface. Until the vehicle risk is removed (such as safe driving away, risk being controlled) or handed over to the on-site rescue personnel, this warning task is completed, and the system state is reset, forming a "perception-judgment-decision-execution-feedback" closed loop.

[0079] The application realizes early screening of the battery health state of the vehicle by capturing the license plate at the tunnel entrance and associating the remote data platform for data tracing, solves the problems of target identification and static risk assessment, and realizes the leap from static assessment to dynamic perception by using infrared thermal imaging technology inside the tunnel, based on the principle of thermal radiation measurement, non-contact temperature monitoring of the battery pack of the vehicle in motion, and accurately capturing the two key precursor signals of thermal runaway, surface temperature and temperature rise rate; the scheme adopts a specially designed double-branch neural network model as the intelligent analysis center, which is based on the principle of multi-task learning and can deeply integrate static health index and dynamic temperature data, on the one hand, output comprehensive risk probability to realize risk grading, and on the other hand, judge different risk leading types such as thermal abuse, mechanical damage or electrical abnormality, which makes the system have intelligent judgment ability to understand the risk source, and surpasses the limitations of traditional single threshold alarm; finally, based on this accurate risk portrait, the system triggers the warning response of grading classification, and starts different disposal measures for different levels and types of risks, such as targeted broadcast prompt or linkage of traffic control equipment. Thus, the leap from general alarm to accurate strategy is realized, and the initiative and effectiveness of tunnel safety management are significantly improved.

[0080] The embodiment of the application also provides a tunnel new energy vehicle operation risk monitoring and early warning system for executing the tunnel new energy vehicle operation risk monitoring and early warning method, Figure 2 is a structural schematic diagram of a tunnel new energy vehicle operation risk monitoring and early warning system provided by the embodiment of the application, referring to Figure 2 The system comprises the following modules:

[0081] The data acquisition module is used for acquiring the license plate information of the vehicle entering the tunnel through a camera at the tunnel entrance, and determining whether the vehicle is a new energy vehicle; if the vehicle is a new energy vehicle, the battery health parameter is acquired according to the license plate information of the new energy vehicle, otherwise the vehicle is stopped from being monitored;

[0082] The health index calculation module is used for calculating the battery health index of the new energy vehicle based on the battery health parameter; if the battery health index is less than or equal to a preset threshold, the next step is entered; otherwise, the vehicle is stopped from being monitored;

[0083] The risk prediction module is used for monitoring the temperature data of the battery pack of the new energy vehicle in real time by using the infrared thermal imaging all-in-one machine arranged in the tunnel, and inputting the battery health index and the temperature data into a preset risk judgment model to obtain the comprehensive risk probability and the risk level of the new energy vehicle;

[0084] The early warning module is used for executing corresponding early warning measures according to the risk level.

[0085] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions recorded in the above embodiments can still be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present application.

Claims

1. A tunnel new energy vehicle operation risk monitoring and early warning method, characterized in that, The method comprises the following steps: S1, at the entrance of the tunnel, acquiring the license plate information of the vehicle entering the tunnel through a camera, and determining whether the vehicle is a new energy vehicle; if the vehicle is a new energy vehicle, obtaining the battery health parameter according to the license plate information of the new energy vehicle, otherwise stopping monitoring the vehicle; S2, based on the battery health parameter, calculating the battery health index of the new energy vehicle; if the battery health index is less than or equal to a preset threshold, proceed to the next step; otherwise, stop monitoring the vehicle; S3, using the infrared thermal imaging all-in-one machine arranged in the tunnel to monitor the temperature data of the battery pack of the new energy vehicle in real time, and inputting the battery health index and the temperature data into a preset risk research model to obtain the comprehensive risk probability and risk level of the new energy vehicle; S4, according to the risk level, executing corresponding warning measures; In S1, the battery health parameter includes at least one of the current battery state of charge, the total battery cycle number and the maximum temperature difference between the single cells in the battery pack; In S2, based on the battery health parameter, the battery health index of the new energy vehicle is calculated, including: Based on the ratio of the total battery cycle number to the maximum allowed cycle number, the ratio of the maximum temperature difference between the single cells in the battery pack to the maximum allowed temperature difference, and the deviation of the current battery state of charge from the ideal state of charge, weighted calculation is performed to obtain the battery health index of the new energy vehicle. 2.The tunnel new energy vehicle operation risk monitoring and early warning method according to claim 1, characterized in that, In S3, the temperature data of the battery pack includes the real-time maximum temperature of the battery pack surface and the battery pack temperature rise rate. 3.The tunnel new energy vehicle operation risk monitoring and early warning method according to claim 2, characterized in that, In S3, the preset risk research model is built using a multi-layer perception mechanism, and the preset risk research model includes an input layer, a hidden layer and an output layer: The input layer includes 3 nodes for receiving the real-time maximum temperature of the battery pack surface, the battery pack temperature rise rate and the battery health index; The hidden layer adopts a ReLU activation function; The output layer includes two output branches, the first branch is a risk probability branch, which adopts a Sigmoid activation function, and the second branch is a risk dominant type branch, which adopts a Softmax activation function.

4. The tunnel new energy vehicle operation risk monitoring and early warning method according to claim 3, characterized in that, The risk dominant type output by the second branch includes thermal runaway risk, mechanical damage and electrical abnormality.

5. The tunnel new energy vehicle operation risk monitoring and early warning method according to claim 1, characterized in that, In S4, according to the risk level, corresponding warning measures are executed, including: When the risk level is low risk, no warning is needed, and the new energy vehicle is continuously monitored until it drives out of the tunnel; When the risk level is medium risk or high risk, the new energy vehicle is prompted to drive out of the tunnel immediately.

6. A tunnel new energy vehicle operation risk monitoring and early warning system for executing the tunnel new energy vehicle operation risk monitoring and early warning method of any one of claims 1-5, characterized in that, The system comprises the following modules: A data acquisition module is used to acquire the license plate information of the vehicle entering the tunnel through a camera at the entrance of the tunnel, and determine whether the vehicle is a new energy vehicle; if the vehicle is a new energy vehicle, obtain the battery health parameter according to the license plate information of the new energy vehicle, otherwise stop monitoring the vehicle; A health index calculation module is used to calculate the battery health index of the new energy vehicle based on the battery health parameter; If the battery health index is less than or equal to a preset threshold, proceed to the next step; Otherwise, stop monitoring the vehicle; A risk prediction module is configured to utilize an infrared thermal imaging all-in-one machine arranged in a tunnel to monitor temperature data of a battery pack of the new energy vehicle in real time, and input the battery health index and the temperature data into a preset risk research model to obtain a comprehensive risk probability and a risk level of the new energy vehicle; An early warning module is configured to perform corresponding early warning measures according to the risk level.

Images