A fire warning system and method for new energy vehicles based on narrowband Internet of Things

Abstract

The present invention relates to the technical field of fire warning for new energy vehicles, and in particular to a fire warning system and method for new energy vehicles based on narrowband Internet of Things, including: a sensing module for obtaining battery status data, environmental data, charging data and driving data of new energy vehicles; an Internet of Things module for transmitting the battery status data, environmental data, charging data and driving data to a cloud service module through the narrowband Internet of Things, and setting the Internet of Things module according to the real-time status of the new energy vehicle; a cloud service module for pre-processing the battery status data, environmental data, charging data and driving data, judging the fire situation of the new energy vehicle, and outputting a fire response plan according to the judgment result; and a fire management module for handling the fire according to the fire response plan. The present invention improves the efficiency of fire warning for new energy vehicles.

Description

Technical Field

[0001] The present invention relates to the technical field of fire warning for new energy vehicles, and in particular to a fire warning system and method for new energy vehicles based on narrowband Internet of Things. Background Art

[0002] With the continuous development of my country's economy and society and the continuous improvement of people's income, the market share of new energy vehicles is also expanding. New energy vehicles, with their advantages of environmental protection, energy saving and low carbon, have gradually become an important choice for people's travel. However, with the continuous increase in the number of new energy vehicles, their safety issues have become increasingly prominent, especially fire accidents, which have brought serious threats to people's lives and property safety. Traditional fire warning systems mainly rely on smoke sensors, temperature sensors and other equipment for fire monitoring, but these devices have limitations in new energy vehicle fire warning.

[0003] Chinese patent publication number: CN113284309A discloses a fire warning system for new energy vehicle charging piles, including a cloud platform, a mobile terminal, a fire execution module, an edge computing device module and a temperature detector; the temperature detector is used to collect temperature data near the charging pile; the edge computing device module is used to collect temperature data and upload it to the cloud platform, and predict and judge the temperature at the same time, and execute the fire execution module if it is judged that a fire has occurred; the cloud platform connects to multiple mobile terminals wirelessly, sends real-time temperature data to the mobile terminal, and sends alarm information to the mobile terminal after receiving the alarm signal. However, this solution only provides fire warning for new energy vehicle charging piles, and cannot provide warning when the new energy vehicle is not charging. Summary of the invention

[0004] To this end, the present invention provides a new energy vehicle fire warning system and method based on narrowband Internet of Things, so as to overcome the problems of narrow fire warning range and low warning efficiency in the prior art.

[0005] To achieve the above object, the present invention provides a new energy vehicle fire warning system based on narrowband Internet of Things, characterized in that the system comprises:

[0006] The sensing module is used to obtain the battery status data, environmental data, charging data and driving data of new energy vehicles;

[0007] The Internet of Things module is used to transmit battery status data, environmental data, charging data and driving data to the cloud service module through the narrowband Internet of Things, and to set the Internet of Things module according to the real-time status of the new energy vehicle;

[0008] The cloud service module is used to pre-process the battery status data, environmental data, charging data and driving data, and judge the fire situation of the new energy vehicle based on the pre-processed battery status data, environmental data, charging data and driving data, and output the fire response plan based on the judgment result;

[0009] The fire management module is used to handle fires according to the fire response plan.

[0010] Furthermore, when the Internet of Things module transmits the battery status data, environmental data, charging data and driving data to the cloud service module through the narrowband Internet of Things, it obtains the real-time network status of the new energy vehicle, and sets the number of retransmissions W of the Internet of Things module according to the real-time network status of the new energy vehicle, wherein:

[0011] When the real-time network status of the new energy vehicle is stable, set the number of retransmissions W1 = 1;

[0012] When the real-time network status of the new energy vehicle is unstable, set the number of retransmissions W2 = 3 times;

[0013] The Internet of Things module also obtains the driving state of the new energy vehicle, judges the authenticity of the real-time network state of the new energy vehicle according to the driving state of the new energy vehicle, and adjusts the number of retransmissions W of the Internet of Things module according to the judgment result, wherein:

[0014] When the driving state of the new energy vehicle is vehicle stop, the authenticity of the real-time network state of the new energy vehicle is determined to be true and valid, and the number of retransmissions W is not adjusted;

[0015] When the driving state of the new energy vehicle is vehicle driving, the authenticity of the real-time network state of the new energy vehicle is determined to be invalid, and the number of retransmissions W1=1 is adjusted to W12=3;

[0016] The Internet of Things module also obtains the network transmission speed Q of the new energy vehicle, compares the network transmission speed Q of the new energy vehicle with the preset network transmission speed Q0, and optimizes the number of retransmissions W of the new energy vehicle in the driving state according to the comparison result, wherein:

[0017] When Q ≥ Q0, the number of retransmissions W of new energy vehicles in driving state is not optimized;

[0018] When Q<Q0, the retransmission optimization coefficient G is set, G=(Q0-Q) / Q0, and the number of retransmissions W12 is optimized according to the retransmission optimization coefficient G. The optimized number of retransmissions is set to Wg12, Wg12=W12+G.

[0019] Furthermore, the cloud service module includes:

[0020] A data preprocessing unit, used to preprocess the battery status data, environmental data, charging data and driving data to obtain the preprocessed battery status data, environmental data, charging data and driving data;

[0021] A model analysis unit is used to input the pre-processed battery status data, environmental data and charging data into the fire warning model for analysis to obtain battery status analysis results, environmental analysis results and charging analysis results;

[0022] The battery identification unit is used to judge the fire situation of new energy vehicles based on the battery status analysis results, and output the fire response plan based on the judgment results;

[0023] The environmental identification unit is used to judge the effectiveness of the fire situation judgment of the new energy vehicle by the battery identification unit according to the environmental analysis results, and adjust the fire response plan output by the battery identification unit according to the judgment results;

[0024] The charging identification unit is used to judge the charging status and charging pile status of the new energy vehicle according to the charging analysis results, and to correct the process of adjusting the fire response plan output by the battery identification unit according to the judgment results.

[0025] Furthermore, the model analysis unit inputs the preprocessed battery status data, environmental data and charging data into the fire warning model for analysis to obtain battery status analysis results, environmental analysis results and charging analysis results.

[0026] Furthermore, the battery identification unit determines the fire situation of the new energy vehicle according to the battery status analysis result, and outputs a fire response plan according to the judgment result, wherein:

[0027] When the battery status analysis result is that the battery status is safe, the fire situation of the new energy vehicle is determined to be Class A, and a Class A fire response plan is output;

[0028] When the battery status analysis result shows that the battery status is about to catch fire, the fire situation of the new energy vehicle is determined to be Class B, and a Class B fire response plan is output;

[0029] When the battery status analysis result shows that a fire has occurred in the battery, the fire situation of the new energy vehicle is determined to be Class C, and a Class C fire response plan is output.

[0030] Furthermore, the environment recognition unit judges the validity of the fire situation judgment result of the new energy vehicle by the battery recognition unit according to the environment analysis result, and adjusts the fire response plan output by the battery recognition unit according to the judgment result, wherein:

[0031] When the environmental analysis result is that the environment is not dangerous, the fire situation judgment result of the new energy vehicle by the battery identification unit is determined to be valid, and the fire response plan output by the battery identification unit is not adjusted;

[0032] When the environmental analysis result is an environmental hazard, the new energy vehicle fire situation judgment result of the battery identification unit is determined to be invalid, and the A-level fire response plan output by the battery identification unit is adjusted to an Ah-level fire response plan, the B-level fire response plan is adjusted to a Bh-level fire response plan, and the C-level fire response plan is adjusted to a Ch-level fire response plan.

[0033] Furthermore, the charging identification unit determines the correctness of the adjustment of the fire response plan according to the charging analysis result, and corrects the process of adjusting the fire response plan output by the battery identification unit according to the judgment result, wherein:

[0034] When the charging analysis result shows that the charging state of the new energy vehicle and the charging pile state are both normal, it is determined that the fire response plan is adjusted correctly, and the process of adjusting the fire response plan output by the battery identification unit is not corrected;

[0035] When the charging analysis result shows that the charging state of the new energy vehicle is normal, but the charging pile state is abnormal, it is determined that the fire response plan is adjusted incorrectly, and the process of adjusting the fire response plan output by the battery identification unit is corrected;

[0036] When the charging analysis result shows that both the charging state of the new energy vehicle and the charging pile state are abnormal, it is determined that the fire response plan is adjusted incorrectly, and the process of adjusting the fire response plan output by the battery identification unit is corrected;

[0037] When the charging analysis result shows that the charging state of the new energy vehicle is abnormal, but the charging pile state is normal, it is determined that the fire response plan is adjusted incorrectly, and the process of adjusting the fire response plan output by the battery identification unit is corrected.

[0038] Furthermore, when the charging identification unit corrects the process of adjusting the fire response plan output by the battery identification unit, the Ah-level fire response plan is corrected to the Ahd-level fire response plan, the Bh-level fire response plan is corrected to the Bhd-level fire response plan, and the Ch-level fire response plan is corrected to the Chd-level fire response plan.

[0039] Furthermore, the fire management module handles the new energy vehicle fire according to the fire response plan output by the cloud service module, wherein:

[0040] When the output of the cloud service module is a Class A fire response plan, no new energy vehicle fire will be handled;

[0041] When the output of the cloud service module is an Ah-level fire response plan, the environmental analysis results are sent to the vehicle owner terminal, and an alarm window is pushed to the vehicle owner terminal, and the vehicle owner terminal chooses whether to alarm. If the vehicle owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms and sends the current location of the new energy vehicle to the fire terminal;

[0042] When the output of the cloud service module is an Ahd-level fire response plan, the environmental analysis results and charging analysis results are sent to the car owner terminal, and an alarm window is pushed to the car owner terminal, and the car owner terminal chooses whether to alarm. If the car owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms, and the current location of the new energy vehicle is sent to the fire terminal, and the connection between the new energy vehicle and the charging pile is cut off;

[0043] When the output of the cloud service module is a Class B fire response plan, the battery status analysis results of the new energy vehicle are sent to the vehicle owner terminal, and an alarm window is pushed to the vehicle owner terminal, and the vehicle owner terminal chooses whether to alarm. If the vehicle owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms, and the current location of the new energy vehicle is sent to the fire terminal, and the new energy vehicle is parked in a safe location through unmanned driving technology;

[0044] When the output of the cloud service module is a Bh-level fire response plan, the battery status analysis results and environmental analysis results are sent to the car owner terminal, and an alarm window is pushed to the car owner terminal, and the car owner terminal chooses whether to alarm. If the car owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms, and the current location of the new energy vehicle is sent to the fire terminal, and the new energy vehicle is parked in a safe location through unmanned driving technology;

[0045] When the output of the cloud service module is a Bhd-level fire response plan, the battery status analysis results and environmental analysis results are sent to the car owner terminal, and an alarm window is pushed to the car owner terminal, and the car owner terminal chooses whether to alarm. If the car owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms, and the current location of the new energy vehicle is sent to the fire terminal, and the connection between the new energy vehicle and the charging pile is cut off;

[0046] When the output of the cloud service module is a Class C fire response plan, the fire management module will sound an alarm and send the current location of the new energy vehicle to the fire terminal, and at the same time, push an alarm prompt to the vehicle owner's terminal;

[0047] When the output of the cloud service module is a Ch-level fire response plan, the fire management module will sound an alarm and send the current location of the new energy vehicle to the fire terminal. At the same time, it will push an alarm prompt to the vehicle owner terminal and release the liquid non-aqueous fire extinguishing agent on the new energy vehicle;

[0048] When the output of the cloud service module is a Chd-level fire response plan, the fire management module will sound an alarm and send the current location of the new energy vehicle to the fire terminal. At the same time, it will cut off the connection between the new energy vehicle and the charging pile, push an alarm prompt to the owner's terminal, and release the liquid non-aqueous fire extinguishing agent on the new energy vehicle.

[0049] On the other hand, the present invention provides a new energy vehicle fire warning method based on narrowband Internet of Things, the method comprising:

[0050] Step S1, obtaining battery status data, environmental data, charging data and driving data of the new energy vehicle:

[0051] Step S2, setting the number of retransmissions according to the real-time status of the new energy vehicle;

[0052] Step S3, uploading the battery status data, environmental data, charging data and driving data to the cloud service end via the narrowband Internet of Things;

[0053] Step S4, preprocessing the battery status data, environmental data, charging data and driving data to obtain preprocessed battery status data, environmental data, charging data and driving data;

[0054] Step S5, inputting the pre-processed battery status data, environmental data and charging data into the fire warning model for analysis to obtain battery status analysis results, environmental analysis results and charging analysis results;

[0055] Step S6, judging the fire situation of the new energy vehicle according to the battery status analysis result, and outputting a fire response plan according to the judgment result;

[0056] Step S7, judging the effectiveness of the fire situation of the new energy vehicle according to the environmental analysis result, and adjusting the fire response plan according to the judgment result;

[0057] Step S8, judging the charging status of the new energy vehicle and the charging pile status according to the charging analysis result, and correcting the process of adjusting the fire response plan according to the judgment result.

[0058] Compared with the prior art, the beneficial effect of the present invention is that the system acquires the battery status data, environmental data, charging data and driving data of the new energy vehicle through the sensing module, so as to provide real-time warning for the fire of the new energy vehicle. The system uploads the data to the cloud service end through the Internet of Things module by taking advantage of the low power consumption and wide coverage of the narrowband Internet of Things, so as to realize the long endurance and high efficiency function of the new energy vehicle fire warning system, and sets the number of retransmissions to ensure the successful upload of the data, thereby improving the efficiency of the new energy vehicle fire warning. The system pre-processes the data through the cloud service module to improve the quality and availability of the data, and provides a reliable basis for subsequent data analysis. The system outputs a fire response plan according to the fire situation of the new energy vehicle, discovers the potential risk points and influencing factors of the new energy vehicle fire, and provides a scientific basis for the formulation of preventive measures and emergency treatment plans, reduces the incidence of new energy vehicle fires, reduces casualties and property losses, and further improves the efficiency of the new energy vehicle fire warning. The system handles the fire according to the fire response plan through the fire management module, improves the emergency response speed, and ensures that the emergency plan can be quickly activated and effective rescue work can be carried out when the fire occurs, thereby improving the efficiency of the new energy vehicle fire warning.

[0059] In particular, the Internet of Things module realizes the long battery life and high efficiency of the new energy vehicle fire warning system through the low power consumption and wide coverage of narrowband Internet of Things technology, and ensures the successful upload of data by setting the number of retransmissions.

[0060] In particular, the model analysis unit uses a random forest model to input into the fire warning model for analysis, thereby improving prediction accuracy, enhancing robustness, alleviating overfitting and underfitting, and supporting uncertainty estimation, thereby improving the efficiency and accuracy of new energy vehicle fire warning.

[0061] In particular, the battery identification unit judges the fire situation of the new energy vehicle based on the battery status analysis results, and outputs a fire response plan based on the judgment results, making a targeted fire response plan to avoid the need to invest more manpower, material resources and financial resources to extinguish the fire after the fire expands.

[0062] In particular, the environmental identification unit judges the validity of the fire situation judgment result of the battery identification unit of the new energy vehicle based on the environmental analysis result, and adjusts the fire response plan output by the battery identification unit according to the judgment result, so as to make a more accurate assessment of the fire risk, clarify the possibility and consequences of the fire, and thus more accurately locate the priority and focus of the response measures, and avoid additional losses caused by wrong decisions.

[0063] In particular, the charging identification unit judges the correctness of the adjustment of the fire response plan based on the charging analysis result, and corrects the process of adjusting the fire response plan output by the battery identification unit based on the judgment result, thereby ensuring the accuracy, completeness and effectiveness of the plan, thereby avoiding waste of resources, waste of time and potential risks caused by defects in the plan or improper implementation.

[0064] In particular, the fire management module handles new energy vehicle fires according to the fire response plan output by the cloud service module, and controls the spread of fire, protects personnel safety, and reduces economic losses through rapid response, emergency evacuation, power outage isolation, and professional rescue cooperation, thereby improving emergency response capabilities, enhancing safety awareness, and reducing social impact. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 This is a schematic diagram of the structure of a new energy vehicle fire warning system based on narrowband Internet of Things in this embodiment;

[0066] Figure 2 This is a schematic diagram of the structure of the cloud service module of this embodiment;

[0067] Figure 3 The figure is a flow chart of the fire warning method for new energy vehicles based on narrowband Internet of Things in this embodiment. DETAILED DESCRIPTION

[0068] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0069] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0070] It should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0071] See also Figure 1 As shown, it is a schematic diagram of the structure of the new energy vehicle fire warning system based on narrowband Internet of Things in this embodiment, and the system includes:

[0072] The sensing module is used to obtain the battery status data, environmental data, charging data and driving data of new energy vehicles;

[0073] The Internet of Things module is used to transmit battery status data, environmental data, charging data and driving data to the cloud service module through the narrowband Internet of Things, and the Internet of Things module is set according to the real-time status of the new energy vehicle. The Internet of Things module is connected to the perception module;

[0074] The cloud service module is used to pre-process the battery status data, environmental data, charging data and driving data, and judge the fire situation of the new energy vehicle based on the pre-processed battery status data, environmental data, charging data and driving data, and output the fire response plan based on the judgment result. The cloud service module is connected to the Internet of Things module;

[0075] The fire management module is used to handle fires according to the fire response plan. The fire management module is connected to the cloud service module.

[0076] Specifically, the system is applied to new energy vehicles and fire warning management. The system obtains battery status data, environmental data, charging data and driving data of new energy vehicles, and uploads the data to the cloud for processing through narrowband Internet of Things technology. The cloud makes warnings to facilitate efficient warnings and timely responses, thereby reducing fire risks and losses. The system obtains battery status data, environmental data, charging data and driving data of new energy vehicles through a sensing module to facilitate real-time warnings of new energy vehicle fires. The system uploads data to the cloud service end through the Internet of Things module by taking advantage of the low power consumption and wide coverage of the narrowband Internet of Things, and sets the number of retransmissions to ensure that the data is successfully uploaded to achieve long battery life and high efficiency of the new energy vehicle fire warning system. Function, thereby improving the efficiency of new energy vehicle fire warning. The system pre-processes data through the cloud service module to improve the quality and availability of data, provide a reliable basis for subsequent data analysis, and output fire response plans based on the new energy vehicle fire situation, discover potential risk points and influencing factors of new energy vehicle fires, and provide a scientific basis for formulating preventive measures and emergency response plans, reduce the incidence of new energy vehicle fires, reduce casualties and property losses, and further improve the efficiency of new energy vehicle fire warning. The system handles fires according to the fire response plan through the fire management module, improves the emergency response speed, and ensures that the emergency plan can be quickly activated and effective rescue work can be carried out when a fire occurs, thereby improving the efficiency of new energy vehicle fire warning.

[0077] Specifically, when acquiring the battery status data, environmental data, charging data and driving data of the new energy vehicle, the perception module acquires the driving data through the on-board sensors and China's Beidou satellite navigation system, acquires the environmental data through the environmental perception device, acquires the battery status data through the on-board diagnostic system, and acquires the charging data through the charging management system.

[0078] Specifically, the driving data includes speed, acceleration, location information, driving distance, direction, timestamp and driving mode, such as economic mode and sports mode; the environmental data includes weather conditions, light intensity, road conditions, traffic flow and air quality; the battery status data includes battery power, battery voltage, battery current, battery temperature, battery health status and battery balancing status; the charging data includes charging start time and charging end time, charging amount, charging power, charging current, charging voltage, charging efficiency, and charging status; the on-board sensor refers to a device installed on the vehicle for detecting vehicle status or external environmental information, such as: speed sensor, acceleration sensor, GPS sensor, temperature sensor, camera, lidar and ultrasonic sensor; the China Beidou Satellite Navigation System refers to a global satellite navigation system independently developed by China that provides global positioning, navigation and timing services; the environmental perception device refers to a device used to detect and analyze the environment around the vehicle; the on-board diagnostic system refers to a self-diagnostic system on the vehicle for monitoring and reporting the performance and emission status of the vehicle; the charging management system refers to a system and equipment used to manage and control the vehicle charging process.

[0079] Specifically, when the Internet of Things module transmits the battery status data, environmental data, charging data and driving data to the cloud service module through the narrowband Internet of Things, it obtains the real-time network status of the new energy vehicle and sets the number of retransmissions W of the Internet of Things module according to the real-time network status of the new energy vehicle, where:

[0080] When the real-time network status of the new energy vehicle is stable, set the number of retransmissions W1 = 1;

[0081] When the real-time network status of the new energy vehicle is unstable, the number of retransmissions is set to W2 = 3 times.

[0082] Specifically, the Internet of Things module also obtains the driving state of the new energy vehicle, judges the authenticity of the real-time network state of the new energy vehicle according to the driving state of the new energy vehicle, and adjusts the number of retransmissions W of the Internet of Things module according to the judgment result, wherein:

[0083] When the driving state of the new energy vehicle is vehicle stop, the authenticity of the real-time network state of the new energy vehicle is determined to be true and valid, and the number of retransmissions W is not adjusted;

[0084] When the driving state of the new energy vehicle is vehicle driving, the authenticity of the real-time network state of the new energy vehicle is determined to be invalid, and the number of retransmissions W1=1 is adjusted to W12=3.

[0085] Specifically, the Internet of Things module also obtains the network transmission speed Q of the new energy vehicle, compares the network transmission speed Q of the new energy vehicle with the preset network transmission speed Q0, and optimizes the number of retransmissions W of the new energy vehicle in the driving state according to the comparison result, wherein:

[0086] When Q ≥ Q0, the number of retransmissions W of new energy vehicles in driving state is not optimized;

[0087] When Q<Q0, set the retransmission optimization coefficient G, G=(Q0-Q) / Q0, optimize the number of retransmissions W12 according to the retransmission optimization coefficient G, and set the optimized number of retransmissions to Wg12, Wg12=W12+G, where the value of G is an integer, for example, when G=0.4, G=0, and when G=0.5, G=1.

[0088] Specifically, the narrowband Internet of Things refers to a low-power, wide-coverage, low-cost Internet of Things technology. The number of retransmissions W refers to the number of times the sender resends the data packet when the data packet is not correctly received by the receiver due to loss, error or other reasons in network communication. The new energy vehicle network transmission speed Q refers to the rate at which new energy vehicles transmit data through the communication network.

[0089] See also Figure 2 As shown in FIG. 1 , a schematic diagram of the structure of the cloud service module of this embodiment is shown, and the cloud service module includes:

[0090] A data preprocessing unit, used to preprocess the battery status data, environmental data, charging data and driving data to obtain the preprocessed battery status data, environmental data, charging data and driving data;

[0091] A model analysis unit is used to input the pre-processed battery status data, environmental data and charging data into the fire warning model for analysis to obtain battery status analysis results, environmental analysis results and charging analysis results. The model analysis unit is connected to the data pre-processing unit;

[0092] A battery identification unit is used to judge the fire situation of the new energy vehicle according to the battery status analysis result, and output a fire response plan according to the judgment result. The battery identification unit is connected to the model analysis unit;

[0093] An environmental identification unit is used to judge the effectiveness of the fire situation judgment of the new energy vehicle by the battery identification unit according to the environmental analysis result, and to adjust the fire response plan output by the battery identification unit according to the judgment result. The environmental identification unit is connected to the battery identification unit;

[0094] The charging identification unit is used to judge the charging status and charging pile status of the new energy vehicle according to the charging analysis results, and to calibrate the process of adjusting the fire response plan output by the battery identification unit according to the judgment results. The charging identification unit is connected to the environmental identification unit.

[0095] Specifically, the data preprocessing unit performs missing value processing on the battery status data, environmental data, charging data and driving data through linear interpolation, and performs feature importance evaluation on the battery status data, environmental data, charging data and driving data after missing value processing through a feature screening model, and outputs the preprocessed battery status data, environmental data, charging data and driving data.

[0096] Specifically, the linear interpolation method refers to a method of using a straight line connecting two known quantities to determine the value of an unknown quantity between the two known quantities. The missing value processing refers to the process of processing missing or incomplete values ​​in a data set during data analysis or data preprocessing. The feature screening model refers to a convolutional neural network model that meets the preprocessing accuracy and is trained based on preset preprocessing data. The preset preprocessing data refers to a pre-acquired data set for training the convolutional neural network model. The convolutional neural network model refers to a feedforward neural network that includes convolution calculations and has a deep structure. This embodiment does not train the convolutional neural network model. The method is limited, and relevant technical personnel in the field can freely set it according to actual needs, and only need to meet the needs of feature importance evaluation of battery status data, environmental data, charging data and driving data. For example, the training method of the convolutional neural network model can be set to divide the preset preprocessed data into 70% training set and 30% validation set, and the training set is input into the convolutional neural network model for training, and the validation set is input into the trained convolutional neural network model, and the parameters of the convolutional neural network model are optimized until the accuracy of the output result of the convolutional neural network model reaches 90%, and then the convolutional neural network model is output as a feature screening model.

[0097] Specifically, the model analysis unit inputs the pre-processed battery status data, environmental data and charging data into the fire warning model for analysis to obtain battery status analysis results, environmental analysis results and charging analysis results.

[0098] Specifically, the fire warning model refers to a random forest model that meets the analysis accuracy and is trained based on historical new energy vehicle fire data. The convolutional neural network model refers to a deep learning model for data classification and recognition tasks. The random forest model is an ensemble learning algorithm based on a classification tree that improves the prediction accuracy of the model by constructing multiple decision trees and aggregating their prediction results. The gradient boosting tree model refers to a machine learning model that optimizes the target value of the loss function by iteratively adding new decision trees. This embodiment does not limit the training method of the random forest model. For example, the training method of the random forest model can be set to divide the historical new energy vehicle fire data into a 75% training set and a 25% validation set, input the training set into the random forest model for training, and input the validation set into the trained random forest model. The parameters of the random forest model are optimized until the accuracy of the output result of the random forest model reaches 98%, and the random forest model is output as a fire warning model. The historical new energy vehicle fire data refers to statistical information on the number, causes, characteristics, etc. of fire accidents involving new energy vehicles in different time periods.

[0099] Specifically, the battery identification unit determines the fire situation of the new energy vehicle according to the battery status analysis result, and outputs a fire response plan according to the judgment result, wherein:

[0100] When the battery status analysis result is that the battery status is safe, the fire situation of the new energy vehicle is determined to be Class A, and a Class A fire response plan is output;

[0101] When the battery status analysis result shows that the battery status is about to catch fire, the fire situation of the new energy vehicle is determined to be Class B, and a Class B fire response plan is output;

[0102] When the battery status analysis result shows that a fire has occurred in the battery, the fire situation of the new energy vehicle is determined to be Class C, and a Class C fire response plan is output.

[0103] Specifically, the environment recognition unit judges the validity of the fire situation judgment result of the battery recognition unit according to the environment analysis result, and adjusts the fire response plan output by the battery recognition unit according to the judgment result, wherein:

[0104] When the environmental analysis result is that the environment is not dangerous, the fire situation judgment result of the new energy vehicle by the battery identification unit is determined to be valid, and the fire response plan output by the battery identification unit is not adjusted;

[0105] When the environmental analysis result is an environmental hazard, the new energy vehicle fire situation judgment result of the battery identification unit is determined to be invalid, and the A-level fire response plan output by the battery identification unit is adjusted to an Ah-level fire response plan, the B-level fire response plan is adjusted to a Bh-level fire response plan, and the C-level fire response plan is adjusted to a Ch-level fire response plan.

[0106] Specifically, the charging identification unit determines the correctness of the adjustment of the fire response plan according to the charging analysis result, and corrects the process of adjusting the fire response plan output by the battery identification unit according to the judgment result, wherein:

[0107] When the charging analysis result shows that the charging state of the new energy vehicle and the charging pile state are both normal, it is determined that the fire response plan is adjusted correctly, and the process of adjusting the fire response plan output by the battery identification unit is not corrected;

[0108] When the charging analysis result shows that the charging state of the new energy vehicle is normal, but the charging pile state is abnormal, it is determined that the fire response plan is adjusted incorrectly, and the process of adjusting the fire response plan output by the battery identification unit is corrected;

[0109] When the charging analysis result shows that both the charging state of the new energy vehicle and the charging pile state are abnormal, it is determined that the fire response plan is adjusted incorrectly, and the process of adjusting the fire response plan output by the battery identification unit is corrected;

[0110] When the charging analysis result shows that the charging state of the new energy vehicle is abnormal, but the charging pile state is normal, it is determined that the fire response plan is adjusted incorrectly, and the process of adjusting the fire response plan output by the battery identification unit is corrected.

[0111] Specifically, when the charging identification unit corrects the process of adjusting the fire response plan output by the battery identification unit, the Ah-level fire response plan is corrected to the Ahd-level fire response plan, the Bh-level fire response plan is corrected to the Bhd-level fire response plan, and the Ch-level fire response plan is corrected to the Chd-level fire response plan.

[0112] Specifically, the fire management module handles the new energy vehicle fire according to the fire response plan output by the cloud service module, wherein:

[0113] When the output of the cloud service module is a Class A fire response plan, no new energy vehicle fire will be handled;

[0114] When the output of the cloud service module is an Ah-level fire response plan, the environmental analysis results are sent to the vehicle owner terminal, and an alarm window is pushed to the vehicle owner terminal, and the vehicle owner terminal chooses whether to alarm. If the vehicle owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms and sends the current location of the new energy vehicle to the fire terminal;

[0115] When the output of the cloud service module is an Ahd-level fire response plan, the environmental analysis results and charging analysis results are sent to the car owner terminal, and an alarm window is pushed to the car owner terminal, and the car owner terminal chooses whether to alarm. If the car owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms, and the current location of the new energy vehicle is sent to the fire terminal, and the connection between the new energy vehicle and the charging pile is cut off;

[0116] When the output of the cloud service module is a Class B fire response plan, the battery status analysis results of the new energy vehicle are sent to the vehicle owner terminal, and an alarm window is pushed to the vehicle owner terminal, and the vehicle owner terminal chooses whether to alarm. If the vehicle owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms, and the current location of the new energy vehicle is sent to the fire terminal, and the new energy vehicle is parked in a safe location through unmanned driving technology;

[0117] When the output of the cloud service module is a Bh-level fire response plan, the battery status analysis results and environmental analysis results are sent to the car owner terminal, and an alarm window is pushed to the car owner terminal, and the car owner terminal chooses whether to alarm. If the car owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms, and the current location of the new energy vehicle is sent to the fire terminal, and the new energy vehicle is parked in a safe location through unmanned driving technology;

[0118] When the output of the cloud service module is a Bhd-level fire response plan, the battery status analysis results and environmental analysis results are sent to the car owner terminal, and an alarm window is pushed to the car owner terminal, and the car owner terminal chooses whether to alarm. If the car owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms, and the current location of the new energy vehicle is sent to the fire terminal, and the connection between the new energy vehicle and the charging pile is cut off;

[0119] When the output of the cloud service module is a Class C fire response plan, the fire management module will sound an alarm and send the current location of the new energy vehicle to the fire terminal, and at the same time, push an alarm prompt to the vehicle owner's terminal;

[0120] When the output of the cloud service module is a Ch-level fire response plan, the fire management module will sound an alarm and send the current location of the new energy vehicle to the fire terminal. At the same time, it will push an alarm prompt to the vehicle owner terminal and release the liquid non-aqueous fire extinguishing agent on the new energy vehicle;

[0121] When the output of the cloud service module is a Chd-level fire response plan, the fire management module will sound an alarm and send the current location of the new energy vehicle to the fire terminal. At the same time, it will cut off the connection between the new energy vehicle and the charging pile, push an alarm prompt to the owner's terminal, and release the liquid non-aqueous fire extinguishing agent on the new energy vehicle.

[0122] Specifically, the liquid non-aqueous fire extinguishing agent refers to a substance that does not contain a large amount of water and can cover objects or areas during use, and reduces the combustion reaction by changing the surrounding environment, for example, perfluorohexanone and liquid nitrogen. The owner terminal refers to a device or software interface used by the owner to interact with the new energy vehicle. The fire terminal refers to a firefighter who has the ability to extinguish fires in new energy vehicles. This embodiment does not limit the methods of pushing alarm windows, pushing alarm prompts, sending the current location of the new energy vehicle to the fire terminal, cutting off the connection between the new energy vehicle and the charging pile, parking the new energy vehicle in a safe position through unmanned driving technology, and releasing the liquid non-aqueous fire extinguishing agent on the new energy vehicle. Relevant technical personnel in this field can It can be freely set according to actual needs, and only needs to meet the needs of handling new energy vehicle fires. For example, the method of pushing the alarm window and the method of pushing the alarm prompt can be set to send text messages to the owner's mobile phone through the cloud service module, and the method of sending the current location of the new energy vehicle to the fire terminal can be set to send text messages to the fire station through the cloud service module. The method of cutting off the connection between the new energy vehicle and the charging pile, parking the new energy vehicle in a safe position through unmanned driving technology, and releasing the liquid non-aqueous fire extinguishing agent on the new energy vehicle can be set to be operated through a remote control system. The remote control system refers to a system that can remotely monitor, control and manage new energy vehicles through wireless networks or other remote communication means.

[0123] See also Figure 3 As shown, it is a flow chart of a new energy vehicle fire warning method based on narrowband Internet of Things in this embodiment, and the method includes:

[0124] Step S1, obtaining battery status data, environmental data, charging data and driving data of the new energy vehicle:

[0125] Step S2, setting the number of retransmissions according to the real-time status of the new energy vehicle;

[0126] Step S3, uploading the battery status data, environmental data, charging data and driving data to the cloud service end via the narrowband Internet of Things;

[0127] Step S4, preprocessing the battery status data, environmental data, charging data and driving data to obtain preprocessed battery status data, environmental data, charging data and driving data;

[0128] Step S5, inputting the pre-processed battery status data, environmental data and charging data into the fire warning model for analysis to obtain battery status analysis results, environmental analysis results and charging analysis results;

[0129] Step S6, judging the fire situation of the new energy vehicle according to the battery status analysis result, and outputting a fire response plan according to the judgment result;

[0130] Step S7, judging the effectiveness of the fire situation of the new energy vehicle according to the environmental analysis result, and adjusting the fire response plan according to the judgment result;

[0131] Step S8, judging the charging status of the new energy vehicle and the charging pile status according to the charging analysis result, and correcting the process of adjusting the fire response plan according to the judgment result.

[0132] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A new energy vehicle fire warning system based on narrowband Internet of Things, characterized in that: The system includes: a sensing module for acquiring battery status data, environmental data, charging data and driving data of the new energy vehicle; The Internet of Things module is used to transmit battery status data, environmental data, charging data and driving data to the cloud service module through the narrowband Internet of Things, and to set the Internet of Things module according to the real-time status of the new energy vehicle; The cloud service module is used to pre-process the battery status data, environmental data, charging data and driving data, and judge the fire situation of the new energy vehicle based on the pre-processed battery status data, environmental data, charging data and driving data, and output the fire response plan based on the judgment result; Fire management module, used to handle fire according to fire response plan; The cloud service module includes: a data preprocessing unit, which is used to preprocess the battery status data, environmental data, charging data and driving data to obtain the preprocessed battery status data, environmental data, charging data and driving data; A model analysis unit is used to input the pre-processed battery status data, environmental data and charging data into the fire warning model for analysis to obtain battery status analysis results, environmental analysis results and charging analysis results; The battery identification unit is used to judge the fire situation of new energy vehicles based on the battery status analysis results, and output the fire response plan based on the judgment results; The environmental identification unit is used to judge the effectiveness of the fire situation judgment of the new energy vehicle by the battery identification unit according to the environmental analysis results, and adjust the fire response plan output by the battery identification unit according to the judgment results; The charging identification unit is used to judge the charging status and charging pile status of the new energy vehicle according to the charging analysis results, and to correct the process of adjusting the fire response plan output by the battery identification unit according to the judgment results.

2. The fire warning system for new energy vehicles based on narrowband Internet of Things according to claim 1 is characterized in that: When the Internet of Things module transmits the battery status data, environmental data, charging data and driving data to the cloud service module through the narrowband Internet of Things, the real-time network status of the new energy vehicle is obtained, and the number of retransmissions W of the Internet of Things module is set according to the real-time network status of the new energy vehicle, wherein: when the real-time network status of the new energy vehicle is stable, the number of retransmissions W1 is set to 1; When the real-time network status of the new energy vehicle is unstable, set the number of retransmissions W2 = 3 times; The Internet of Things module also obtains the driving state of the new energy vehicle, judges the authenticity of the real-time network state of the new energy vehicle according to the driving state of the new energy vehicle, and adjusts the number of retransmissions W of the Internet of Things module according to the judgment result, wherein: when the driving state of the new energy vehicle is that the vehicle is stopped, the authenticity of the real-time network state of the new energy vehicle is judged to be true and valid, and the number of retransmissions W is not adjusted; When the driving state of the new energy vehicle is vehicle driving, the authenticity of the real-time network state of the new energy vehicle is determined to be invalid, and the number of retransmissions W1=1 is adjusted to W12=3; The Internet of Things module also obtains the network transmission speed Q of the new energy vehicle, compares the network transmission speed Q of the new energy vehicle with the preset network transmission speed Q0, and optimizes the number of retransmissions W of the new energy vehicle in the driving state according to the comparison result, wherein: when Q≥Q0, the number of retransmissions W of the new energy vehicle in the driving state is not optimized; When Q<Q0, the retransmission optimization coefficient G is set, G=(Q0-Q) / Q0, and the number of retransmissions W12 is optimized according to the retransmission optimization coefficient G. The optimized number of retransmissions is set to Wg12, Wg12=W12+G.

3. The fire warning system for new energy vehicles based on narrowband Internet of Things according to claim 1 is characterized in that: The battery identification unit determines the fire situation of the new energy vehicle according to the battery status analysis result, and outputs a fire response plan according to the judgment result, wherein: when the battery status analysis result is that the battery status is safe, the fire situation of the new energy vehicle is determined to be Class A, and the Class A fire response plan is output; When the battery status analysis result shows that the battery status is about to catch fire, the fire situation of the new energy vehicle is determined to be Class B, and a Class B fire response plan is output; When the battery status analysis result shows that a fire has occurred in the battery, the fire situation of the new energy vehicle is determined to be Class C, and a Class C fire response plan is output.

4. The new energy vehicle fire warning system based on narrowband Internet of Things according to claim 1 is characterized in that: The environment identification unit judges the validity of the fire situation judgment result of the new energy vehicle by the battery identification unit according to the environment analysis result, and adjusts the fire response plan output by the battery identification unit according to the judgment result, wherein: when the environment analysis result is that the environment is not dangerous, the fire situation judgment result of the new energy vehicle by the battery identification unit is determined to be valid, and the fire response plan output by the battery identification unit is not adjusted; When the environmental analysis result is an environmental hazard, the new energy vehicle fire situation judgment result of the battery identification unit is determined to be invalid, and the A-level fire response plan output by the battery identification unit is adjusted to an Ah-level fire response plan, the B-level fire response plan is adjusted to a Bh-level fire response plan, and the C-level fire response plan is adjusted to a Ch-level fire response plan.

5. The new energy vehicle fire warning system based on narrowband Internet of Things according to claim 1 is characterized in that: The charging identification unit determines the correctness of the adjustment of the fire response plan according to the charging analysis result, and corrects the process of adjusting the fire response plan output by the battery identification unit according to the judgment result, wherein: when the charging analysis result shows that the charging state of the new energy vehicle and the charging pile state are both normal, it is determined that the fire response plan is adjusted correctly, and the process of adjusting the fire response plan output by the battery identification unit is not corrected; When the charging analysis result shows that the charging state of the new energy vehicle is normal, but the charging pile state is abnormal, it is determined that the fire response plan is adjusted incorrectly, and the process of adjusting the fire response plan output by the battery identification unit is corrected; When the charging analysis result shows that both the charging state of the new energy vehicle and the charging pile state are abnormal, it is determined that the fire response plan is adjusted incorrectly, and the process of adjusting the fire response plan output by the battery identification unit is corrected; When the charging analysis result shows that the charging state of the new energy vehicle is abnormal, but the charging pile state is normal, it is determined that the fire response plan is adjusted incorrectly, and the process of adjusting the fire response plan output by the battery identification unit is corrected.

6. The fire warning system for new energy vehicles based on narrowband Internet of Things according to claim 5 is characterized in that: When the charging identification unit corrects the process of adjusting the fire response plan output by the battery identification unit, the Ah-level fire response plan is corrected to the Ahd-level fire response plan, the Bh-level fire response plan is corrected to the Bhd-level fire response plan, and the Ch-level fire response plan is corrected to the Chd-level fire response plan.

7. The fire warning system for new energy vehicles based on narrowband Internet of Things according to claim 6 is characterized in that: The fire management module processes the new energy vehicle fire according to the fire response plan output by the cloud service module, wherein: when the output of the cloud service module is a Class A fire response plan, the new energy vehicle fire is not processed; When the output of the cloud service module is an Ah-level fire response plan, the environmental analysis results are sent to the vehicle owner terminal, and an alarm window is pushed to the vehicle owner terminal, and the vehicle owner terminal chooses whether to alarm. If the vehicle owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms and sends the current location of the new energy vehicle to the fire terminal; When the output of the cloud service module is an Ahd-level fire response plan, the environmental analysis results and charging analysis results are sent to the car owner terminal, and an alarm window is pushed to the car owner terminal, and the car owner terminal chooses whether to alarm. If the car owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms, and the current location of the new energy vehicle is sent to the fire terminal, and the connection between the new energy vehicle and the charging pile is cut off; When the output of the cloud service module is a Class B fire response plan, the battery status analysis results of the new energy vehicle are sent to the vehicle owner terminal, and an alarm window is pushed to the vehicle owner terminal, and the vehicle owner terminal chooses whether to alarm. If the vehicle owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms, and the current location of the new energy vehicle is sent to the fire terminal, and the new energy vehicle is parked in a safe location through unmanned driving technology; When the output of the cloud service module is a Bh-level fire response plan, the battery status analysis results and environmental analysis results are sent to the car owner terminal, and an alarm window is pushed to the car owner terminal, and the car owner terminal chooses whether to alarm. If the car owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms, and the current location of the new energy vehicle is sent to the fire terminal, and the new energy vehicle is parked in a safe location through unmanned driving technology; When the output of the cloud service module is a Bhd-level fire response plan, the battery status analysis results and environmental analysis results are sent to the car owner terminal, and an alarm window is pushed to the car owner terminal, and the car owner terminal chooses whether to alarm. If the car owner terminal does not make a choice on the alarm window within 10 seconds, the alarm window automatically alarms, and the current location of the new energy vehicle is sent to the fire terminal, and the connection between the new energy vehicle and the charging pile is cut off; When the output of the cloud service module is a Class C fire response plan, the fire management module will sound an alarm and send the current location of the new energy vehicle to the fire terminal, and at the same time, push an alarm prompt to the vehicle owner's terminal; When the output of the cloud service module is a Ch-level fire response plan, the fire management module will sound an alarm and send the current location of the new energy vehicle to the fire terminal. At the same time, it will push an alarm prompt to the vehicle owner terminal and release the liquid non-aqueous fire extinguishing agent on the new energy vehicle; When the output of the cloud service module is a Chd-level fire response plan, the fire management module will sound an alarm and send the current location of the new energy vehicle to the fire terminal. At the same time, it will cut off the connection between the new energy vehicle and the charging pile, push an alarm prompt to the owner's terminal, and release the liquid non-aqueous fire extinguishing agent on the new energy vehicle.

8. A method applied to the fire warning system for new energy vehicles based on narrowband Internet of Things as described in any one of claims 1 to 7, characterized in that: The method comprises: step S1, acquiring battery status data, environmental data, charging data and driving data of the new energy vehicle; step S2, setting the number of retransmissions according to the real-time status of the new energy vehicle; Step S3, uploading the battery status data, environmental data, charging data and driving data to the cloud service end via the narrowband Internet of Things; Step S4, preprocessing the battery status data, environmental data, charging data and driving data to obtain preprocessed battery status data, environmental data, charging data and driving data; Step S5, inputting the pre-processed battery status data, environmental data and charging data into the fire warning model for analysis to obtain battery status analysis results, environmental analysis results and charging analysis results; Step S6, judging the fire situation of the new energy vehicle according to the battery status analysis result, and outputting a fire response plan according to the judgment result; Step S7, judging the effectiveness of the fire situation of the new energy vehicle according to the environmental analysis result, and adjusting the fire response plan according to the judgment result; Step S8, judging the charging status of the new energy vehicle and the charging pile status according to the charging analysis result, and correcting the process of adjusting the fire response plan according to the judgment result.

Images