Battery car charging system with fire catching, recognizing and early warning functions and early warning method

By integrating the fire capture and recognition warning function in the charging system of the battery car, the convolutional neural network is used to identify the fire and automatically cut off the power supply, the problem of low fire detection rate during charging of the battery car is solved, and the timeliness and safety of fire rescue is improved.

CN118928094APending Publication Date: 2024-11-12BEIJING HAILAN YUNLIAN TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411251183.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-06
Publication Date
2024-11-12

Smart Images

  • Figure CN118928094A_ABST
    Figure CN118928094A_ABST
Patent Text Reader

Abstract

The invention provides a battery car charging system with a fire catching, recognizing and early warning function and an early warning method. The system comprises a charging pile, a fire catching and recognizing system, a charging pile controller, a cloud control platform and a mobile terminal platform. The fire capturing and identifying system is in communication connection with the charging pile; the fire capture and identification system is used for identifying fire information in the range of a charging port to which the charging pile belongs and transmitting the identified fire information to the charging pile controller; the charging pile controller cuts off the power supply of each charging port of the charging pile after receiving the fire information of the fire capture and identification system, and transmits the fire information to the cloud control platform; and the cloud control platform is used for transmitting the fire information to the mobile terminal platform. According to the invention, fire catching identification and early warning are carried out on the battery car charging system, the fire identification rate is improved, the fire discovery real-time performance in the battery car charging process is improved, the fire rescue time is won for, and the loss is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of charging systems, and in particular to a battery vehicle charging system with fire capture, identification and warning functions and a warning method thereof. Background Art

[0002] With the development of society, electric bicycles and electric tricycles have solved the needs of people for short-distance travel in their lives and shortened people's travel time. People pay more and more attention to the safe charging of electric vehicles. When there is a risk of fire during charging, it is extremely important to extinguish the fire in time to reduce people's property losses. This system came into being.

[0003] The use of electric bicycles is inseparable from charging. Currently, electric bicycles are charged by using an electric bicycle charging system. Users scan codes or pay via APP and charge after connecting to the power connection port. For charging electric bicycles with non-removable batteries, due to the limited charging locations in the community and the situation where fully charged electric bicycles occupy the charging positions, there are insufficient charging piles. Users can only park their electric bicycles at home or in the corridor for charging. Due to the aging of the batteries of electric bicycles and irregular charging, electric bicycles often spontaneously combust while charging, posing a danger to the property and personal safety of residents. Therefore, how to realize fire capture, identification and early warning for the electric bicycle charging system, improve the fire identification rate, improve the real-time nature of fire detection during the charging process of electric bicycles, gain time for fire rescue, and reduce losses is a technical problem that urgently needs to be solved. Summary of the invention

[0004] The purpose of this application is to provide an electric vehicle charging system with fire capture, identification and warning functions and its warning method, so as to realize fire capture, identification and warning for the electric vehicle charging system, improve the fire recognition rate, improve the real-time fire detection during the charging process of the electric vehicle, gain fire rescue time and reduce losses.

[0005] To achieve the above-mentioned purpose, as the first aspect of the present application, the present application provides an electric vehicle charging system with a fire capture, identification and warning function, the system comprising: a charging pile, a fire capture and identification system, a charging pile controller, a cloud control platform, and a mobile terminal platform; the fire capture and identification system is communicatively connected to the charging pile; the fire capture and identification system is used to identify the fire information within the range of the charging port to which the charging pile belongs, and transmit the identified fire information to the charging pile controller; the charging pile controller, after receiving the fire information from the fire capture and identification system, cuts off the power supply of each charging port of the charging pile, and transmits the fire information to the cloud control platform; the cloud control platform is used to transmit the fire information to the mobile terminal platform.

[0006] As described above, the battery vehicle charging system with fire capture, identification and warning functions, wherein the system also includes: a monitoring module, which is used to monitor the charging pile controller for abnormalities. When an abnormality is detected in the charging pile controller, an alarm is issued and maintenance personnel are notified to perform maintenance. Otherwise, the charging pile controller continues to be monitored.

[0007] As described above, the battery vehicle charging system with fire capture, identification and warning functions, wherein the fire capture and identification system includes at least one camera or a monitoring device with a camera function.

[0008] As described above, the battery vehicle charging system with fire capture, identification and warning functions, wherein the fire capture and identification system adopts a convolutional neural network deep learning fire identification model with a twelve-layer residual network, which is used to perform multi-layer extraction of image features, detect different features of flames, and identify fire information.

[0009] The battery vehicle charging system with fire capture, identification and warning functions as described above, wherein the system further includes: a data processor, the data processor is used to calculate the fire severity value based on the identified fire information and the collected environmental data.

[0010] As described above, in the battery vehicle charging system with fire capture, identification and warning functions, when the cloud control platform receives fire information, the fire capture and identification system captures the scene image in real time and uploads it to the cloud control platform.

[0011] The battery vehicle charging system with fire capture, identification and early warning function as described above, wherein the system further comprises: an automatic fire extinguishing system,

[0012] Automatic fire extinguishing system, used for automatic fire extinguishing.

[0013] As a second aspect of the present application, the present application provides an early warning method for a battery vehicle charging system with a fire capture, identification and early warning function, the method comprising:

[0014] Identify fire information within the range of the charging pile to which the charging port belongs, and transmit the fire information to the charging pile controller;

[0015] After receiving the fire information, the charging pile controller cuts off the power supply of each charging port of the charging pile and transmits the fire information to the cloud control platform;

[0016] The charging pile controller is monitored for abnormalities. When an abnormality is detected in the charging pile controller, an alarm is issued and maintenance personnel are notified to perform maintenance. Otherwise, the charging pile controller continues to be monitored.

[0017] The early warning method for the battery vehicle charging system with fire capture, identification and early warning function as described above, wherein the method further comprises:

[0018] The cloud control platform transmits fire information to the mobile platform;

[0019] After receiving the fire information from the fire capture and identification system, the cloud control platform and mobile platform distribute the fire warning information according to the preset requirements.

[0020] The early warning method for the battery vehicle charging system with fire capture, identification and early warning function as described above, wherein the method further comprises:

[0021] When fire information is identified, environmental data is collected;

[0022] Calculate the fire severity value based on the identified fire information and the collected environmental data;

[0023] Based on the fire severity value, fire severity level and resource requirement data are issued to rescue personnel.

[0024] The beneficial effects achieved by this application are as follows:

[0025] (1) This application adopts pure visual fire recognition technology, using one or more cameras or monitoring equipment with camera functions to obtain scene information, and judge through the AI ​​system to obtain fire results. The results are transmitted to the charging pile terminal control system and to the back-end cloud platform and mobile terminal. The fire recognition system adopts a pure visual recognition method, and independently develops a large fire recognition model based on the characteristics of the battery vehicle charging system. The hardware cost of this system camera or monitoring equipment with camera function and recognition control system is low. The battery vehicle charging system with this fire capture, recognition and early warning system is suitable for large-scale promotion, which can greatly improve the real-time detection of fires during the charging process of battery vehicles, strive for fire rescue time, and reduce losses. The characteristics of this fire monitoring and early warning system use AI fire recognition large models, with low hardware costs and high fire recognition rate, which is suitable for large-scale promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For those skilled in the art, other drawings can also be obtained based on these drawings.

[0027] Figure 1 This is a structural schematic diagram of a battery vehicle charging system with fire capture, identification and warning functions according to an embodiment of the present application.

[0028] Figure 2 This is a structural principle diagram of a battery vehicle charging system with fire capture, identification and warning functions according to an embodiment of the present application.

[0029] Figure 3 This is a schematic diagram of the structure of a deep convolutional network according to an embodiment of the present application.

[0030] Figure 4 Schematic diagram of the structure of the residual network of the embodiment of the present application.

[0031] Figure 5 This is a flow chart of an early warning method for an electric vehicle charging system with fire capture, identification and early warning functions according to an embodiment of the present application.

[0032] Figure numerals: 10 - charging pile; 20 - fire capture and identification system; 30 - charging pile controller; 40 - monitoring module; 50 - cloud control platform; 60 - mobile platform; 70 - data processor; 100 - battery vehicle charging system. DETAILED DESCRIPTION

[0033] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0034] Embodiment 1

[0035] like Figure 1 As shown, the present application provides a battery vehicle charging system 100 with a fire capture, identification and warning function, the system comprising: a charging pile 10, a fire capture and identification system 20, a charging pile controller 30, a cloud control platform 50, and a mobile terminal platform 60. The fire capture and identification system 20 is connected to the charging pile 10 in communication. Specifically, the fire capture and identification system 20 is connected to the charging pile 10 via wired communication. The charging pile 10 is connected to the cloud control platform 50 in communication, specifically, the charging pile 10 is connected to the cloud control platform 50 via wireless communication. The cloud control platform 50 is connected to the mobile terminal platform 60 in communication, specifically, the cloud control platform 50 is connected to the mobile terminal platform 60 via wireless communication.

[0036] The fire capture and identification system 20 is used to identify fire information within the range of the charging port of the charging pile 10, and transmit the identified fire information to the charging pile controller 30 via a wired manner.

[0037] The cloud control platform 50 is used to transmit the fire information to the mobile terminal platform 60 via wireless.

[0038] The fire capture and identification system 20 includes a camera or a monitoring device with a camera function, a fire identification controller and a communication line. The fire identification controller has a trained large fire model. The camera or the monitoring device with a camera function is used to monitor the range of the charging pile 10 in real time. The fire identification controller is used to identify fires in real time through the large fire model and transmit the identified fire warning information to the charging pile controller 30, the cloud control platform 50 and the mobile terminal platform 60.

[0039] The charging pile controller 30 is used to cut off the power supply of each charging port of the charging pile 10 after receiving the fire information from the fire capture and identification system 20, and transmit the fire information to the cloud control platform 50 via wireless.

[0040] Among them, the battery vehicle charging system with fire capture, identification and warning function also includes: a monitoring module 40, which is used to monitor the charging pile controller 30 for abnormalities. When an abnormality is detected in the charging pile controller 30, it is repaired in time. Otherwise, the charging pile controller 30 continues to be monitored to ensure that the charging pile controller 30 can work normally. After receiving the fire warning information, the power supply of each charging port of the charging pile 10 is cut off in time.

[0041] Specifically, the method for monitoring the abnormality of the charging pile controller 30 includes:

[0042] Step S310: continuously collect status monitoring data of the charging pile controller at regular intervals for a preset time period.

[0043] Among them, the status monitoring data of the charging pile controller includes: real-time voltage value, real-time resistance value and real-time temperature value;

[0044] Step S320, calculating the abnormal fluctuation value of the charging pile controller according to the status monitoring data of the charging pile controller.

[0045] Specifically, the calculation formula of the abnormal fluctuation value of the charging pile controller is as follows:

[0046]

[0047] Wherein, YS represents the abnormal fluctuation value of the charging pile controller; Q1 represents the influence weight of the power fluctuation of the charging pile controller on the abnormal fluctuation value of the charging pile controller; N represents the duration of continuous collection of the status monitoring data of the charging pile controller; t i represents the i-th moment of collecting the status monitoring data of the charging pile controller; t (i+1) Indicates the i+1th moment when the status monitoring data of the charging pile controller is collected; U(t) indicates the real-time voltage value of the charging pile controller at the tth moment; the value range of t is: t i ~t (i+1); R represents the resistance value of the charging pile controller; P represents the rated power of the charging pile controller; Q2 represents the weight of the temperature fluctuation of the charging pile controller on the abnormal fluctuation value of the charging pile controller; H represents the total number of times the real-time temperature value of the charging pile controller is greater than the standard temperature value during the time period of continuous collection of the status monitoring data of the charging pile controller; ms j represents the real-time temperature value of the charging pile controller at the jth moment that is greater than the standard temperature value; Mb represents the standard temperature value of the charging pile controller.

[0048] Step S330, compare the abnormal fluctuation value of the charging pile controller with the preset danger threshold. If the abnormal fluctuation value of the charging pile controller is greater than the preset danger threshold, there is an abnormality in the charging pile controller, and the charging pile controller is repaired and inspected; otherwise, continue to monitor the abnormality of the charging pile controller.

[0049] After receiving the fire information from the fire capture and identification system 20, the cloud control platform 50 and the mobile terminal platform 60 distribute the fire warning information according to the preset requirements. The distribution of the fire warning information includes distributing the fire warning information to rescue personnel and residents near the fire.

[0050] As a specific embodiment of the present invention, the fire capture and identification system 20 may include one or more cameras. One camera can complete the fire capture function, and multiple cameras can be used to avoid information loss caused by damage to a single camera.

[0051] As other specific embodiments of the present invention, the fire capture and identification system 20 may use one or more monitoring devices with a camera function. One monitoring device with a camera function can complete the fire capture function. Using multiple monitoring devices with a camera function can avoid information loss caused by damage to a single monitoring device.

[0052] like Figure 2 As shown, this is a structural schematic diagram of an electric vehicle charging system with fire capture, identification and warning functions according to an embodiment of the present application. The charging pile is connected to a community transformer and multiple charging ports; the charging pile is communicated with a cloud server; the cloud server is communicated with an AI recognition controller; the AI ​​recognition controller is connected to the charging pile and the community transformer; and the linkage fire extinguishing system is communicated with the cloud server.

[0053] The fire capture and identification system 20 adopts a twelve-layer residual network convolutional neural network deep learning fire identification large model or a twelve-layer residual network convolutional neural network deep learning fire identification model, which has fast recognition speed and high accuracy.

[0054] The fire capture and identification system 20 inputs image data from one or more cameras, which can be color or black and white. The convolutional neural network deep learning fire identification large model with a twelve-layer residual network performs multi-layer extraction of image features, detects different features of the flame, and identifies fire information.

[0055] The convolutional neural network of the twelve-layer residual network deep learning fire recognition large model includes input layer, convolution layer, pooling layer, fully connected layer and output layer.

[0056] The input layer is an H*W*C image of the charging station site, where H refers to the length of the image, W is the width of the image, and C refers to the number of channels of the image. Generally, the number of channels of a grayscale image is 1, and the number of channels of a color image is 3.

[0057] The convolution layer divides the image into many small areas. The entire original input image is weighted according to one area to obtain a feature map. Each element of each feature map is the result of the convolution at the corresponding position. The calculation is performed by using the inner product (multiplication of corresponding positions) and then adding the bias. The calculation process of a single convolution kernel with an image of 3 channels is used (where +1 is the bias).

[0058] Among them, the parameters in the convolution layer are:

[0059] Sliding window step size S, convolution kernel size K, edge padding P.

[0060] Among them, the number of convolution kernels is equal to the number of feature maps.

[0061] The pooling operation uses the overall statistical features of the adjacent area of ​​a certain position in the input matrix as the output of that position, which is the compression of the feature map. This reduces the number of parameters in the network, reduces the consumption of computing resources, and can effectively control overfitting.

[0062] It should be explained that the fire recognition model uses a multi-layer deep convolutional network, which has strong ability to describe complex features. Each layer recognizes different features and learns image features layer by layer.

[0063] like Figure 3 As shown, the convolution layer, the pooling layer and the fully connected layer include: convolution layer 1, pooling layer 1, convolution layer 2, pooling layer 2, fully connected layer 1, fully connected layer 2, convolution layer 1, pooling layer 1, convolution layer 2, pooling layer 2, fully connected layer 1, and fully connected layer 2 are connected in sequence.

[0064] Specifically, the convolutional neural network deep learning fire recognition model with twelve layers of residual network adopts ResNet residual network to optimize the numerical stability problem in deep neural network and solve the degradation problem of network model. Figure 4As shown in the figure: The learning target is f(x), and x is the output of the shallow layer. The dotted box is the newly added layer. The newly added layer learns f(x)-x. When outputting, the two are added to get f(x). In other words, f(x) is the ideal mapping and f(x)-x is the residual mapping.

[0065] The fire capture and identification system 20 also sends fire warning information to the cloud control platform 50 via wireless.

[0066] The automatic fire extinguishing system is installed in an extended manner, and the fire capture and identification system 20 can drive the automatic fire extinguishing system to automatically extinguish the fire.

[0067] When the cloud control platform 50 receives the fire information, click on the on-site confirmation, and the fire capture and identification system 20 can capture the on-site image in real time and upload it to the cloud control platform 50 for manual confirmation.

[0068] As a specific embodiment of the present invention, the system further comprises a data processor 70, which is used to calculate a fire severity value based on the identified fire information and the collected environmental data, and to issue a fire severity level to rescue personnel based on the fire severity value.

[0069] Specifically, the fire information includes flame characteristic data, which includes color, brightness, temperature, etc. The environmental data includes environmental temperature and environmental wind speed.

[0070] Specifically, the calculation formula for the fire severity value is:

[0071]

[0072] Where Y represents the fire severity value; x1 represents the influence weight of flame characteristic data on the fire severity value; U represents the total number of types of flame characteristic data; μ k represents the weight of the kth flame characteristic data; e = 2.718; St k Indicates the characteristic value of the k-th flame characteristic data; Tzh k It represents the corresponding environmental data when collecting the k-th flame characteristic data; if the flame characteristic data is a color value, the corresponding environmental data is the environmental color value; if the flame characteristic data is a brightness value, the corresponding environmental data is the environmental brightness value; if the flame characteristic data is a temperature value, the corresponding environmental data is the environmental temperature value; x2 represents the influence weight of the environmental temperature on the fire severity value; Tc represents the ambient temperature when collecting the flame characteristic data; x3 represents the influence weight of the ambient wind speed on the fire severity value; Vf represents the ambient wind speed value when collecting the flame characteristic data.

[0073] Embodiment 2

[0074] like Figure 5As shown, the present application provides an early warning method for a battery vehicle charging system with a fire capture, identification and early warning function, the method comprising:

[0075] Step S1, identifying fire information within the range of the charging pile to which the charging port belongs, and transmitting the fire information to the charging pile controller.

[0076] Step S2: After receiving the fire information, the charging pile controller cuts off the power supply of each charging port of the charging pile and transmits the fire information to the cloud control platform.

[0077] Step S3, monitor the charging pile controller for abnormalities. When an abnormality is detected in the charging pile controller, an alarm is issued and maintenance personnel are notified to perform maintenance. Otherwise, the charging pile controller continues to be monitored.

[0078] Specifically, the method for monitoring abnormalities of the charging pile controller includes:

[0079] Step S310: continuously collect status monitoring data of the charging pile controller at regular intervals for a preset time period.

[0080] Among them, the status monitoring data of the charging pile controller includes: real-time voltage value, real-time resistance value and real-time temperature value;

[0081] Step S320, calculating the abnormal fluctuation value of the charging pile controller according to the status monitoring data of the charging pile controller.

[0082] Specifically, the calculation formula of the abnormal fluctuation value of the charging pile controller is as follows:

[0083]

[0084] Wherein, YS represents the abnormal fluctuation value of the charging pile controller; Q1 represents the influence weight of the power fluctuation of the charging pile controller on the abnormal fluctuation value of the charging pile controller; N represents the duration of continuous collection of the status monitoring data of the charging pile controller; t i Indicates the i-th moment of collecting the status monitoring data of the charging pile controller; U(t) indicates the real-time voltage value at the t-th moment; R indicates the resistance value of the charging pile controller; P indicates the rated power of the charging pile controller; Q2 indicates the weight of the influence of the temperature fluctuation of the charging pile controller on the abnormal fluctuation value of the charging pile controller; J indicates the total number of moments when the real-time temperature value of the charging pile controller is greater than the standard temperature value during the time of continuously collecting the status monitoring data of the charging pile controller; ms j represents the real-time temperature value of the charging pile controller at the jth moment that is greater than the standard temperature value; Mb represents the standard temperature value of the charging pile controller.

[0085] The present application calculates the abnormal fluctuation value of the charging pile controller, improves the accuracy of the abnormal fluctuation value of the charging pile controller, and improves the safety of the charging pile controller.

[0086] Step S330, compare the abnormal fluctuation value of the charging pile controller with the preset danger threshold. If the abnormal fluctuation value of the charging pile controller is greater than the preset danger threshold, there is an abnormality in the charging pile controller, and the charging pile controller is repaired and inspected; otherwise, continue to monitor the abnormality of the charging pile controller.

[0087] Step S4: The cloud control platform transmits the fire information to the mobile platform.

[0088] Step S5: After receiving the fire information from the fire capture and identification system, the cloud control platform and the mobile terminal platform distribute the fire warning information according to the preset requirements.

[0089] Specifically, distributing the fire warning information includes distributing the fire warning information to rescue personnel and residents near the fire.

[0090] Step S6, after the fire information is identified, environmental data is collected.

[0091] Step S7, calculating the fire severity value based on the identified fire information and the collected environmental data.

[0092] Specifically, the fire information includes flame characteristic data, which includes color, brightness, temperature, etc. The environmental data includes environmental temperature and environmental wind speed.

[0093] Specifically, the calculation formula for the fire severity value is:

[0094]

[0095] Where Y represents the fire severity value; x1 represents the influence weight of flame characteristic data on the fire severity value; U represents the total number of types of flame characteristic data; μ k represents the weight of the kth flame characteristic data; e = 2.718; St k Indicates the characteristic value of the k-th flame characteristic data; Tzh k It represents the corresponding environmental data when collecting the k-th flame characteristic data; if the flame characteristic data is a color value, the corresponding environmental data is the environmental color value; if the flame characteristic data is a brightness value, the corresponding environmental data is the environmental brightness value; if the flame characteristic data is a temperature value, the corresponding environmental data is the environmental temperature value; x2 represents the influence weight of the environmental temperature on the fire severity value; Tc represents the ambient temperature when collecting the flame characteristic data; x3 represents the influence weight of the ambient wind speed on the fire severity value; Vf represents the ambient wind speed value when collecting the flame characteristic data.

[0096] This application calculates the fire severity value, improves the accuracy of fire severity value calculation, and promptly releases fire severity level and resource demand data to rescue personnel based on the fire severity value, thereby improving the timeliness and reliability of fire rescue.

[0097] Step S8: issuing fire severity level and resource requirement data to rescue personnel according to the fire severity value.

[0098] Specifically, according to the different sizes of the flame severity values, the corresponding fire severity levels and resource demand data (for example, the corresponding recommended number of rescue personnel and rescue vehicles, etc.) are matched.

[0099] The present application also provides a computer storage medium, the computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the address mapping method of the large-capacity solid-state hard disk. The computer storage medium contains one or more program instructions, and the one or more program instructions are used by the processor to execute an early warning method for a battery vehicle charging system with a fire capture, identification and early warning function.

[0100] The embodiment disclosed in the present invention provides a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are executed on a computer, the computer executes the above-mentioned early warning method for an electric battery vehicle charging system with fire capture, identification and early warning functions.

[0101] An embodiment of the present invention provides a processor for processing the above-mentioned early warning method of an electric battery vehicle charging system with fire capture, identification and early warning functions.

[0102] In the embodiment of the present invention, the processor may be an integrated circuit chip having the ability to process signals. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0103] The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The processor reads the information in the storage medium and completes the steps of the above method in combination with its hardware.

[0104] The storage medium may be a memory, which may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0105] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct RAM bus random access memory (DRRAM).

[0106] The beneficial effects achieved by this application are as follows:

[0107] (1) This application adopts pure visual fire recognition technology, using one or more cameras or monitoring equipment with camera functions to obtain scene information, and judge through the AI ​​system to obtain fire results. The results are transmitted to the charging pile terminal control system and to the back-end cloud platform and mobile terminal. The fire recognition system adopts a pure visual recognition method, and independently develops a large fire recognition model based on the characteristics of the battery vehicle charging system. The hardware cost of this system camera or monitoring equipment with camera function and recognition control system is low. The battery vehicle charging system with this fire monitoring and early warning system is suitable for large-scale promotion, which can greatly improve the real-time detection of fires during the charging process of battery vehicles, strive for fire rescue time, and reduce losses. The characteristics of this fire monitoring and early warning system use AI fire recognition large models, with low hardware costs and high fire recognition rate, which is suitable for large-scale promotion.

[0108] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0109] In the description of the present application, the word "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0110] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A battery vehicle charging system with fire capture, identification and early warning function, characterized in that: The system includes: charging pile, fire capture and identification system, charging pile controller, cloud control platform, and mobile terminal platform; The fire capture and identification system is communicatively connected with the charging pile; The fire capture and identification system is used to identify fire information within the charging range to which the charging port belongs, and transmit the identified fire information to the charging pile controller; The charging pile controller, after receiving the fire information from the fire capture and identification system, cuts off the power supply of each charging port of the charging pile and transmits the fire information to the cloud control platform; The cloud control platform is used to transmit fire information to the mobile platform and simultaneously control various parameters of the charging pile.

2. The battery vehicle charging system with fire capture, identification and early warning function according to claim 1 is characterized in that: The system also includes: a monitoring module for performing abnormal monitoring on the charging pile controller. When an abnormality is detected in the charging pile controller, an alarm is issued and maintenance personnel are notified to perform maintenance. Otherwise, the charging pile controller continues to be monitored.

3. The battery vehicle charging system with fire capture, identification and early warning function according to claim 1 is characterized in that: The fire capture and identification system includes at least one camera or monitoring equipment with a camera function.

4. The battery vehicle charging system with fire capture, identification and early warning function according to claim 1 is characterized in that: The fire capture and identification system adopts a convolutional neural network deep learning fire identification model with a twelve-layer residual network to perform multi-layer extraction of image features, detect different features of flames, and identify fire information.

5. The battery vehicle charging system with fire capture, identification and early warning function according to claim 1 is characterized in that: The system also includes: a data processor, which is used to calculate the fire severity value based on the identified fire information and the collected environmental data.

6. The battery vehicle charging system with fire capture, identification and early warning function according to claim 1 is characterized in that: When the cloud control platform receives the fire information, the fire capture and identification system captures the on-site images in real time and uploads them to the cloud control platform.

7. The battery vehicle charging system with fire capture, identification and early warning function according to claim 1 is characterized in that: The system also includes: automatic fire extinguishing system, Automatic fire extinguishing system, used for automatic fire extinguishing.

8. An early warning method for a battery vehicle charging system with fire capture, identification and early warning functions, characterized in that: The method includes: Identify fire information within the range of the charging pile to which the charging port belongs, and transmit the fire information to the charging pile controller; After receiving the fire information, the charging pile controller cuts off the power supply of each charging port of the charging pile and transmits the fire information to the cloud control platform; The charging pile controller is monitored for abnormalities. When an abnormality is detected in the charging pile controller, an alarm is issued and maintenance personnel are notified to perform maintenance. Otherwise, the charging pile controller continues to be monitored.

9. The early warning method for a battery vehicle charging system with fire capture, identification and early warning functions according to claim 8, characterized in that: The method further includes: The cloud control platform transmits fire information to the mobile platform and controls various parameters of the charging pile at the same time; After receiving the fire information from the fire capture and identification system, the cloud control platform and mobile platform distribute the fire warning information according to the preset requirements.

10. The early warning method of the battery vehicle charging system with fire capture, identification and early warning function according to claim 8, characterized in that: The method further includes: When fire information is identified, environmental data is collected; Calculate the fire severity value based on the identified fire information and the collected environmental data; Based on the fire severity value, fire severity level and resource requirement data are issued to rescue personnel.

Citation Information

Cited By

  • Fire early warning and alarming device for battery car and working method of fire early warning and alarming device

    CN119580421A