Fire detection linkage control system and method

Abstract

The embodiment of this specification discloses a fire detection linkage control system and method, which relates to the field of automatic control technology. The system includes a fire detection unit and a charging control unit, wherein the fire detection unit includes a first data acquisition unit, a second data acquisition unit, and a detection evaluation unit; the first data acquisition unit is used to acquire relevant information of a target vehicle entering a target area for charging, and determine a first risk index based on the relevant information; the second data acquisition unit is used to acquire battery status parameters of the target vehicle, and determine a second risk index based on the battery status parameters; the detection evaluation unit is used to acquire real-time charging parameters and real-time power supply parameters during the charging process, and use a fire evaluation model to determine a fire detection evaluation result based on the first risk index, the second risk index, the real-time charging parameters, and the real-time power supply parameters; the charging control unit is used to perform linkage control on the charging equipment based on the fire detection evaluation result.

Description

Technical Field

[0001] The present application relates to the field of automatic control technology, and in particular to a fire detection linkage control system and method. Background Art

[0002] With the popularity of electric vehicles, the number of charging stations and charging equipment is also increasing. However, during the charging process of electric vehicles, fire accidents may occur due to battery failure, charging equipment failure or other reasons. Moreover, the speed of fire development is faster than other electrical fires. Traditional fire detection systems usually have slow response speeds when dealing with fire risk detection during the charging process of electric vehicles, which is difficult to meet actual needs. Therefore, there is an urgent need for a system and method that can monitor the fire risk during the charging process in real time and perform linkage control. Summary of the invention

[0003] One aspect of an embodiment of the present specification provides a fire detection linkage control system, the system comprising a fire detection unit and a charging control unit, the fire detection unit comprising a first data acquisition unit, a second data acquisition unit and a detection evaluation unit;

[0004] The first data acquisition unit is used to acquire relevant information of a target vehicle entering a target area for charging, and determine a first risk index according to the relevant information of the target vehicle, wherein the target area is a charging area corresponding to the charging device;

[0005] The second data acquisition unit is used to acquire a battery status parameter of the target vehicle and determine a second risk index according to the battery status parameter;

[0006] The detection and evaluation unit is used to obtain the real-time charging parameters of the target vehicle during the charging process and the real-time power supply parameters corresponding to the charging device, and use the trained fire assessment model to process based on the first risk index, the second risk index, the real-time charging parameters and the real-time power supply parameters to obtain a fire detection evaluation result;

[0007] The charging control unit is used to perform linkage control on the charging device according to the fire detection evaluation result, and the linkage control includes adjusting the power supply parameters of the charging device or ending the charging task.

[0008] In some embodiments, the relevant information of the target vehicle includes vehicle brand and model information and first battery type information corresponding to the vehicle brand and model information, and the first data acquisition unit is specifically used to:

[0009] Acquire the vehicle brand and model information of the target vehicle through image recognition technology, and match the corresponding original battery type information by querying a database, thereby determining the first battery type information corresponding to the vehicle brand and model information;

[0010] The first risk index is determined according to historical fire information corresponding to the vehicle brand and model information and / or the first battery type information.

[0011] In some embodiments, the obtaining of the vehicle brand and model information of the target vehicle by using image recognition technology includes:

[0012] Extracting visual features from a first target image collected for the target vehicle to obtain first target image features;

[0013] Obtaining N candidate brands and models from a fine-grained classification set based on the first target image feature, wherein the fine-grained classification set includes features corresponding to multiple vehicle brands and models;

[0014] Extracting target feature information of each of the N candidate brand models in a target state based on the feature description data corresponding to each of the N candidate brand models, wherein the target state is an image acquisition state used to distinguish the N candidate brand models;

[0015] Based on the target feature information of each of the N candidate brands and models in the target state, the vehicle brand and model information of the target vehicle is determined from the N candidate brands and models.

[0016] In some embodiments, the battery status parameter includes second battery type information and a battery health index, wherein the second battery type information is battery type information for the current charging task, and the second data acquisition unit is specifically used to:

[0017] Acquiring second battery type information and a battery health index of the target vehicle through a battery management system of the target vehicle;

[0018] Determining whether the second battery type information is consistent with the first battery type information;

[0019] If the second battery type information is consistent with the first battery type information, the second risk index is determined based on the battery health index; if the second battery type information is inconsistent with the first battery type information, the first risk index is corrected based on the second battery type information, and the second risk index is determined based on the corrected first risk index and the battery health index.

[0020] In some embodiments, the detection and evaluation unit is specifically configured to:

[0021] Generate a first feature vector according to a plurality of real-time charging parameters and real-time power supply parameters acquired at a plurality of consecutive data collection moments, wherein the real-time charging parameters include battery voltage, battery current and battery temperature, and the real-time power supply parameters include power supply voltage, power supply current and power supply power;

[0022] Concatenate the first feature vector with the first risk index and the second risk index to obtain a second feature vector;

[0023] The second feature vector is input into the trained fire assessment model for processing to obtain the fire detection assessment result.

[0024] In some embodiments, the system further includes a fire control unit, and the fire detection unit further includes a third data acquisition unit; wherein,

[0025] The third data acquisition unit includes a temperature detector and a smoke detector. The temperature detector is used to detect the ambient temperature of the target area, and sends a first detection signal to the fire control unit when the ambient temperature value is detected to exceed a first preset threshold value; the smoke detector is used to detect the smoke concentration value of the target area, and sends a second detection signal to the fire control unit when the smoke concentration value is detected to exceed a second preset threshold value; the first preset threshold value and the second preset threshold value are both determined based on the first risk index and the second risk index;

[0026] The fire control unit is used to control the fire equipment in the target area according to the first detection signal and the second detection signal.

[0027] In some embodiments, the fire detection unit further includes a fourth data acquisition unit, the fourth data acquisition unit being used to acquire a second target image for the target area, and perform fire detection based on the second target image to obtain a third detection signal;

[0028] The fire control unit is used to control the fire-fighting equipment in the target area according to at least one of the first detection signal, the second detection signal and the third detection signal.

[0029] In some embodiments, the performing fire detection based on the second target image to obtain a third detection signal includes:

[0030] Acquire a second target image captured for the target vehicle;

[0031] Determine a pixel distribution histogram according to the second target image, wherein the pixel distribution histogram is used to represent the probability distribution of grayscale values ​​and corresponding gradients of pixels contained in the second target image;

[0032] Starting from a starting position, searching at each coordinate position of the pixel distribution histogram, and obtaining a segmentation parameter corresponding to a current search position during the search process;

[0033] Determine a candidate segmentation position corresponding to the current search position according to the segmentation parameter;

[0034] Determining a target range according to the candidate segmentation position corresponding to the current search position, and segmenting suspected flame pixels from the second target image according to the target range;

[0035] The suspected flame pixel is subjected to feature extraction, and when the extracted pixel feature of the suspected flame pixel matches the preset flame pixel feature, the third detection signal is generated.

[0036] In some embodiments, the fire-fighting equipment in the target area includes at least one of an automatic sprinkler and an automatic fire extinguisher, wherein the automatic fire extinguisher is equipped with a fire extinguishing medium, and the fire extinguishing medium includes any one of carbon dioxide, ABC dry powder, BC dry powder, heptafluoropropane, perfluorohexanone, and nitrogen;

[0037] The fire control unit is specifically used to control the fire fighting equipment in the target area to perform fire extinguishing operations when any one or more of the first detection signal, the second detection signal and the third detection signal are received.

[0038] Another aspect of the embodiments of this specification also provides a fire detection linkage control method, the method comprising:

[0039] Obtaining relevant information of a target vehicle entering a target area for charging, and determining a first risk index according to the relevant information of the target vehicle, wherein the target area is a charging area corresponding to the charging device;

[0040] Acquiring a battery status parameter of the target vehicle, and determining a second risk index according to the battery status parameter;

[0041] Acquire the real-time charging parameters of the target vehicle during the charging process and the real-time power supply parameters corresponding to the charging device, and use the trained fire assessment model to process based on the first risk index, the second risk index, the real-time charging parameters and the real-time power supply parameters to obtain a fire detection assessment result;

[0042] The charging device is controlled in linkage according to the fire detection evaluation result, and the linkage control includes adjusting the power supply parameters of the charging device or ending the charging task.

[0043] The fire detection linkage control system and method provided in the embodiments of this specification may bring at least the following beneficial effects:

[0044] (1) By considering both the risk factors of the charging vehicle itself and the potential risk factors reflected by the real-time charging data and power supply data during the charging process, the probability of fire and the potential risk can be better predicted;

[0045] (2) By determining the fire detection assessment results based on the risk factors of the charging vehicle itself and the potential risk factors reflected by the real-time charging data and power supply data during the charging process, and controlling the charging equipment based on the fire detection assessment results, the fire risk of the vehicle during the charging process can be reduced, and the safety of the charging process can be better ensured;

[0046] (3) By controlling the fire-fighting equipment based on the fire detection signal, the fire-fighting operation can be performed in time when a fire is detected, thereby improving the response speed of the fire-fighting operation and reducing the losses caused by the fire.

[0047] Additional features will be described in part in the following description. For those skilled in the art, it will become apparent by reviewing the following and accompanying drawings, or it may be understood by the production or operation of the examples. The features of this specification may be implemented and obtained by practicing or using various aspects of the methods, tools, and combinations described in the following detailed examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0049] Figure 1 is an exemplary module diagram of a fire detection linkage control system according to some embodiments of this specification;

[0050] Figure 2 is an exemplary flow chart of a fire detection linkage control method according to some embodiments of this specification;

[0051] Figure 3 is an exemplary flow chart of vehicle brand and model identification according to some embodiments of this specification;

[0052] Figure 4 is a schematic diagram of fire detection linkage control according to some embodiments of this specification;

[0053] Figure 5 It is a flowchart of exemplary steps of a fire detection method based on image recognition according to some embodiments of this specification. DETAILED DESCRIPTION

[0054] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0055] It should be understood that the "system", "device", "unit" and / or "module" used in this specification is a method for distinguishing different components, elements, parts, parts or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0056] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0057] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0058] At present, most charging stations (or charging equipment) are self-service and unattended. Therefore, in order to protect the property safety of charging users and charging service providers, fire detection systems and automatic fire extinguishing systems are particularly important for charging stations.

[0059] Traditional automatic fire extinguishing systems usually use sensors (generally including smoke detectors and temperature detectors) to detect the monitoring area, and send an abnormality detection signal to the fire control unit after detecting an abnormality. After receiving the abnormality detection signal, the fire control unit can control the fire-fighting equipment (such as automatic sprinkler equipment, automatic fire extinguisher, etc.) to perform fire extinguishing operations according to the abnormality detection signal. However, since electric vehicles include lithium batteries, and fires caused by lithium batteries often develop rapidly, the best time to extinguish the fire may have been missed when the fire is detected by the sensor. Therefore, it is difficult to meet actual needs.

[0060] Based on the above technical problems, this specification provides a fire detection linkage control system and method, which performs fire detection assessment by combining relevant information of the charging vehicle, battery status parameters, real-time charging parameters and real-time power supply parameters, and performs linkage control on the charging equipment based on the fire detection assessment, thereby monitoring the fire risk in the charging process in real time and performing timely control and response, thereby improving the safety of the charging process.

[0061] The fire detection linkage control system and method provided in the embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0062] Figure 1 Schematic diagram of a fire detection linkage control system according to some embodiments of this specification. Figure 1 In some embodiments, the fire detection linkage control system 100 may include a fire detection unit 110 and a charging control unit 120 , wherein the fire detection unit 110 includes a first data acquisition unit 111 , a second data acquisition unit 112 and a detection evaluation unit 113 .

[0063] In an embodiment of the present application, the first data acquisition unit 111 can be used to obtain relevant information of a target vehicle entering a target area for charging, and determine a first risk index based on the relevant information of the target vehicle, wherein the target area is a charging area corresponding to the charging device.

[0064] The second data acquisition unit 112 may be used to acquire a battery status parameter of the target vehicle and determine a second risk index according to the battery status parameter.

[0065] The detection and evaluation unit 113 can be used to obtain the real-time charging parameters of the target vehicle during the charging process and the real-time power supply parameters corresponding to the charging equipment, and use the trained fire assessment model to process based on the first risk index, the second risk index, the real-time charging parameters and the real-time power supply parameters to obtain a fire detection evaluation result.

[0066] The charging control unit 120 may be configured to perform linkage control on the charging device according to the fire detection evaluation result, wherein the linkage control may include adjusting power supply parameters of the charging device or terminating a charging task.

[0067] It should be noted that in the embodiments of the present application, Figure 1Each unit in the fire detection linkage control system 100 shown can be implemented in software and / or hardware. For example, the first data acquisition unit 111 may include an image acquisition device and a processing device, wherein the image acquisition device can be used to acquire images of a target vehicle entering a target area for charging to obtain a first target image, and then the first target image is processed by the processing device, the vehicle brand and model information of the target vehicle is obtained by image recognition technology, and the corresponding original battery type information is matched by querying a database, so as to determine the first battery type information corresponding to the vehicle brand and model information (the first battery type information can be understood as the original battery type information corresponding to the vehicle brand and model information of the target vehicle), and then the first risk index is determined according to the vehicle brand and model information and / or the historical fire information corresponding to the first battery type information. The second data acquisition unit 112 can be connected to the battery management system (BMS) of the target vehicle through a communication bus (such as a CAN bus), so as to obtain the second battery type information of the target vehicle (the second battery type information is the battery type information for the current charging task) and the battery health index, and then the processing device is used to process based on the second battery type information and the battery health index to obtain the second risk index. Similarly, the detection and evaluation unit 113 can be connected to the battery management system of the target vehicle and the power supply management system of the charging device through a communication bus, and obtain the real-time charging parameters of the target vehicle during the charging process and the real-time power supply parameters corresponding to the charging device, and then the first risk index, the second risk index, the real-time charging parameters and the real-time power supply parameters are processed by the processing device to obtain the fire detection evaluation result. Further, the charging control unit 113 can use the controller to control the charging device in linkage according to the fire detection evaluation result, so as to achieve the safety management of the charging process. For example, when the fire detection evaluation result indicates that there is a fire risk, the charging control unit 120 can immediately cut off the power supply of the charging device, or reduce the charging power to reduce the possibility of fire. In addition, the fire detection linkage control system 100 provided in the embodiment of the present application can also send out an alarm through an alarm device to notify the on-site staff (or the owner) or automatically start the fire protection system to ensure that timely measures are taken to prevent the occurrence or spread of fire, thereby improving the safety level of the charging station and effectively protecting the safety of personnel and property.

[0068] It can be understood that in the embodiment of the present application, the aforementioned fire detection evaluation results can be used to reflect the safety status during the charging process. Moreover, in the embodiment of the present application, the fire detection evaluation results also take into account the risk factors of the charging vehicle itself and the real-time data during the charging process, which can better predict the probability of fire and potential risks, and then the charging equipment can be controlled in a linked manner to better avoid and control the losses caused by charging fires.

[0069] For more details about the above-mentioned units, please refer to other places in this specification (for example Figure 2 to Figure 5 part and its related description), which will not be repeated here.

[0070] It should be understood that Figure 1 The fire detection linkage control system 100 and its units shown can be implemented in various ways. For example, in some embodiments, the system and its units can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented by dedicated logic and / or other corresponding hardware devices; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated hardware.

[0071] It should be noted that the above description of the fire detection linkage control system 100 is provided for illustrative purposes only and is not intended to limit the scope of this specification. It is understandable that, for those skilled in the art, the various units can be arbitrarily combined according to the description of this specification without departing from this principle, or a subsystem can be formed to connect with other modules.

[0072] Figure 2 is an exemplary flow chart of a fire detection linkage control method according to some embodiments of this specification. In some embodiments, the fire detection linkage control method 200 may be executed by processing logic, which may include hardware (e.g., circuits, dedicated logic, programmable logic, microcode, etc.), software (instructions running on a processing device to perform hardware simulation), etc., or any combination thereof. In some embodiments, Figure 2 One or more operations in the flowchart of the fire detection linkage control method 200 shown can be implemented by a processing device and / or a terminal device. For example, the fire detection linkage control method 200 can be stored in a storage device in the form of instructions or a computer program, and called and / or executed by a processing device and / or a terminal device.

[0073] Reference Figure 2 In the embodiment of the present application, the fire detection linkage control method 200 may include:

[0074] Step S210 , obtaining relevant information of a target vehicle entering a target area for charging, and determining a first risk index according to the relevant information of the target vehicle. In some embodiments, step S210 may be performed by the first data acquisition unit 111 .

[0075] Specifically, in the embodiment of the present application, the first data acquisition unit 111 may include an image acquisition device and a processing device, and an exemplary image acquisition device may include a camera, etc. In some embodiments, multiple image acquisition devices may be arranged for the target area to capture images of vehicles entering the target area from different perspectives, and obtain one or more first target images captured for the target vehicles entering the target area. It should be noted that in the embodiment of the present application, the target area can be understood as the charging area corresponding to the charging device, for example, a parking space matched with a charging pile.

[0076] In the embodiment of the present application, the aforementioned processing device may include one or more processors, which may include a central processing unit (CPU), a graphics processing unit (GPU), an application-specific integrated circuit (ASIC) or a field programmable gate array (FPGA), etc. These processors can be used to process the first target image collected for the target vehicle entering the target area, including but not limited to image decoding, enhancement, feature extraction and recognition, data matching and other operations, so as to extract the relevant information of the vehicle from the first target image, such as the vehicle brand model and the first battery type information corresponding to the vehicle brand model information (the first battery type can be understood as the original battery type corresponding to the vehicle brand model, such as lithium-ion battery, ternary polymer lithium battery, nickel-hydrogen battery, air battery, acid battery, sodium-sulfur battery, etc.), and then determine the first risk index according to the historical fire information corresponding to the vehicle brand model information and / or the first battery type information.

[0077] Specifically, in an embodiment of the present application, the processing device of the first data acquisition unit 111 can obtain the vehicle brand and model information of the target vehicle through image recognition technology, and match the corresponding original battery type information by querying the database, thereby determining the first battery type information corresponding to the vehicle brand and model information, and then determine the first risk index based on the historical fire information corresponding to the vehicle brand and model information and / or the first battery type information.

[0078] For example, if the brand model of the target vehicle is identified as an S model car under brand A, and the original battery type corresponding to the brand model is matched to a lithium-ion battery by querying the database, if the database records a case in which a fire occurred in a brand S model car equipped with a lithium-ion battery, then the first data acquisition unit 111 will calculate a higher first risk index based on these historical fire information. On the contrary, if the historical fire information shows that the battery safety of the brand model car is good (i.e., no fire has occurred), a lower first risk index will be calculated. In an embodiment of the present application, the aforementioned database may include a vehicle battery information database and a historical fire information database, wherein the vehicle battery information database can be constructed by a large number of vehicle brands and models and their corresponding battery type information, and the historical fire information database can be constructed by vehicle fire records of the traffic control department or insurance company and corresponding vehicle-related information (such as vehicle brand model and / or corresponding first battery type information).

[0079] It is understandable that different battery types and different vehicle brands and models may have different safety levels, and therefore correspond to different risk indexes during the charging process. In some embodiments of the present application, the above-mentioned first risk index can be determined based on one of the vehicle brand model or the battery type. In other embodiments of the present application, the first risk index can also be determined based on both the vehicle brand model and the battery type. As an example only, in some embodiments of the present application, the calculation process of the above-mentioned first risk index can be expressed by the formula as follows:

[0080] F1=norm(α*P1+β*P2)

[0081] Among them, F1 represents the first risk index, P1 represents the ratio of the vehicle brand model information corresponding to the target vehicle in the historical fire information, P2 represents the ratio of the first battery type information corresponding to the target vehicle in the historical fire information, α and ββ are the weight coefficients corresponding to P1 and P2 respectively, and norm represents the normalization operation. In the embodiment of the present application, the aforementioned weight coefficients a and ββ can be determined by statistical analysis and expert evaluation to ensure that the calculation of the risk index is as accurate and fair as possible. As an example only, in some embodiments of the present application, α can be equal to ββ, that is, both are 0.5; in other embodiments, in order to highlight the stronger correlation between battery type and fire, ββ can be made greater than α, for example, α=0.3, ββ=0.7.

[0082] It can be understood that through the above method, a quantitative risk index can be assigned to each target vehicle entering the target area, thereby providing a scientific basis for the safety management of the charging station.

[0083] The following is a brief description of the vehicle brand and model information identification process involved in the embodiment of the present application:

[0084] Figure 3 is an exemplary flow chart of vehicle brand and model identification according to some embodiments of this specification. Figure 3 In some embodiments of the present application, the process of obtaining the vehicle brand and model information of the target vehicle through image recognition technology may include the following steps S310 to S340:

[0085] Step S310: extract visual features from a first target image collected for a target vehicle to obtain features of the first target image.

[0086] In some embodiments of the present application, visual features can be extracted from the first target image using a deep learning algorithm, for example, using a convolutional neural network (CNN) to analyze patterns and structures in the first target image collected for the target vehicle. It can be understood that these algorithms can identify key points and edges in the first target image, thereby extracting features such as the shape, color, texture, pattern (such as brand logo) of the vehicle, and obtaining first target image features for subsequent vehicle brand and model recognition tasks. More details about the use of deep learning algorithms to extract visual features from the first target image can be regarded as prior art and will not be discussed in detail in this specification.

[0087] Step S320: Obtain N candidate brands and models from a fine-grained classification set based on the first target image feature.

[0088] In an embodiment of the present application, the fine-grained classification set can be understood as a database containing a variety of vehicle brands and models, each of which has a detailed visual feature description (e.g., a feature description of two or more dimensions). These feature descriptions may include, but are not limited to, the appearance shape, size, iconic decorative elements, and relative relationships between components of the vehicle. In an embodiment of the present application, the data in the fine-grained classification set is obtained by extracting features from vehicle images with significant brand and model features using a specially trained feature extraction network (e.g., a convolutional neural network CNN). In an embodiment of the present application, the data corresponding to each vehicle brand and model in the fine-grained classification set may include visual feature descriptions under multiple different states (e.g., different viewing angles), wherein the visual feature description under each state can be represented by a multidimensional vector, and one of the dimensions in the multidimensional vector can be used to represent the image acquisition state (i.e., the corresponding acquisition viewing angle).

[0089] For example, in some embodiments, the feature extraction network can be trained through a large number of sample vehicle images with feature labels, so that it can acquire the visual feature extraction capability for vehicle brand and model recognition, and complete the training of the feature extraction network. In this specification, the trained feature extraction network can be referred to as a target feature extraction network, and then the target feature extraction network is used to extract features from a large number of vehicle images with significant brand and model features, thereby obtaining the data in the fine-grained classification set. It should be pointed out that in the embodiment of the present application, the first target image feature in the aforementioned step S310 can also be obtained based on the processing of the target feature extraction network.

[0090] In some embodiments of the present application, the data in the fine-grained classification set can be optimized and updated through a machine learning algorithm. For example, in practical applications, the feature data of the corresponding vehicle brand model in the fine-grained classification set can be updated or supplemented through the vehicle image features collected during the charging process, thereby ensuring the accuracy and reliability of the data.

[0091] In an embodiment of the present application, after obtaining the first target image feature corresponding to the target vehicle through step S310, the first target image feature (the first target image feature may include features extracted from one or more images) may be matched with the data in the fine-grained classification set, and the top M data with the highest similarity are selected, and then N candidate brands and models are obtained based on the M data, where N≤M (because the M data may include feature data corresponding to the same brand model). Exemplarily, in some embodiments of the present application, the similarity between the first target image feature and the feature data in the fine-grained classification set may be calculated by Euclidean distance.

[0092] Step S330: extracting target feature information of each of the N candidate brand models in a target state based on the feature description data corresponding to each of the N candidate brand models.

[0093] After obtaining the aforementioned N candidate brands and models, the target state can be determined according to the image acquisition state (i.e., the corresponding acquisition angle of view) corresponding to the piece of data with the highest similarity to the aforementioned first target image feature (for example, the image acquisition state corresponding to the piece of data with the highest similarity to the aforementioned first target image feature is used as the target state), and then, the target feature information of each of the N candidate brand models in the target state is extracted according to the feature description data corresponding to each of the aforementioned N candidate brand models. Specifically, according to the value of the feature dimension used to represent the image acquisition state in the feature description data corresponding to each of the aforementioned N candidate brand models, the feature data corresponding to each candidate brand model in the target state is selected as the respective target feature information in the target state. It should be noted that, in some cases, the target feature information may not be included in the aforementioned M data.

[0094] Step S340: determining the vehicle brand and model information of the target vehicle from the N candidate brand and model information based on the target feature information of each of the N candidate brand and model information in the target state.

[0095] After obtaining the target feature information of each of the N candidate brand models in the target state through the above steps, the similarity between the target feature information of each of the N candidate brand models in the target state and the first target image feature can be calculated again, and then the target feature information with the highest similarity is selected, and the vehicle brand model information of the target vehicle is determined based on this.

[0096] It should be noted that, in some embodiments of the present application, in order to avoid the interference data (i.e., feature data unrelated to vehicle characteristics, such as feature dimensions used to represent the image acquisition state) in the target feature information of each of the aforementioned N candidate brand models in the target state affecting the result of the similarity calculation, the first target image feature and the target feature information of each of the aforementioned N candidate brand models in the target state may be cleaned before performing the similarity calculation, and only the feature data reflecting the vehicle characteristics is retained.

[0097] In the embodiments of the present application, a variety of data cleaning techniques can be used to improve the accuracy of vehicle brand and model recognition. For example, feature selection techniques can be used to remove feature dimensions that do not contribute significantly to vehicle brand and model recognition, or dimensionality reduction techniques such as principal component analysis (PCA) can be applied to reduce the complexity of the data while retaining key information.

[0098] In some embodiments of the present application, the license plate number of the target vehicle can also be identified by image recognition technology. It can be understood that the license plate number is associated with the owner and the owner's bad car-using habits (such as placing flammable and explosive items in the car), safety awareness and other risk factors. For example, historical fire information records that a certain license plate number has had a fire, which means that the vehicle has a higher risk index. Based on this, in some embodiments of the present application, the first risk index corresponding to the target vehicle can be determined based on the license plate number, vehicle brand model information and the corresponding first battery type information. The process can be expressed as:

[0099] F1=norm(α*P1+β*P2+γ*P3)

[0100] Among them, P3 is used to indicate the fire occurrence of the license plate number corresponding to the target vehicle. If the fire information related to the license plate is recorded in the historical fire information, P3 = 1, otherwise P3 = 0. γ is the weight coefficient corresponding to P3. In some embodiments, γ can be greater than α and β. As an example only, α and β can be set to 0.3, and γ can be set to 0.4.

[0101] Step S220 , obtaining the battery status parameters of the target vehicle, and determining the second risk index according to the battery status parameters. In some embodiments, step S220 may be performed by the second data acquisition unit 112 .

[0102] In an embodiment of the present application, after the target is connected to the charging device and communication is established, it can be connected to the battery management system (BMS) of the target vehicle through a communication bus (such as a CAN bus) to obtain the battery status parameters of the target vehicle and determine the second risk index based on the battery status parameters.

[0103] In an embodiment of the present application, the battery status parameter may include a second battery type information and a battery health index, wherein the second battery type information may refer to the battery type information targeted by the current charging task (i.e., the battery type information of the current charging object). It is understandable that some vehicles may need to replace the battery, and the replaced battery may not match the aforementioned first battery type information. In this case, it is necessary to re-evaluate its risk index based on the replaced battery. The battery health index refers to the health status of the battery, which reflects key performance indicators such as the remaining capacity of the battery, the number of charge and discharge cycles, and the degree of battery aging. Through these parameters, the risk of use can be reflected to a certain extent. For example, batteries with a lower battery health index often have a higher internal resistance, which may cause the battery to generate excessive heat during charging or discharging, thereby increasing the risk of fire.

[0104] Specifically, in some embodiments of the present application, the second data acquisition unit 112 can be used to determine whether the second battery type information is consistent with the aforementioned first battery type information. If the second battery type information is consistent with the aforementioned first battery type information, the second risk index is directly determined based on the battery health index. At this time, the calculation process of the second risk index can be expressed as follows:

[0105] F2=norm(e 1-h )

[0106] Among them, F2 represents the second risk index, h represents the battery health index (ranging from 0 to 1), and norm represents the normalization operation. It should be noted that in the embodiment of the present application, the second risk index is measured by an exponential operation with the natural constant e as the base and 1-h as the exponent, which can not only reflect the negative correlation between the second risk index and the battery health index, but also reflect the nonlinear relationship between the two (the lower the battery health index, the greater the increase in the risk index).

[0107] On the contrary, if the second battery type information is inconsistent with the aforementioned first battery type information, it means that the target vehicle may have a battery replacement. At this time, it is necessary to re-evaluate the aforementioned first risk index based on the replaced battery. In other words, the aforementioned first risk index is corrected based on the second battery type information, and then the second risk index is determined based on the corrected first risk index and the battery health index.

[0108] In an embodiment of the present application, the process of correcting the aforementioned first risk index based on the second battery type information may include: using the aforementioned formula F1=norm(α*P1+β*P2) or F1=norm(α*P1+β*P2+γ*P3) for calculation, and replacing P2 with the ratio of the second battery type information in the historical fire information.

[0109] Furthermore, the second risk index can be determined according to the corrected first risk index and the battery health index. At this time, the calculation process of the second risk index can be expressed as follows:

[0110]

[0111] in, represents the corrected first risk index, σ is The corresponding weight coefficient is as follows: As an example only, in the embodiment of the present application, σ can be set to 0.1.

[0112] It is understandable that since battery replacement needs to consider some compatibility issues, such as compatibility between battery specifications and other related circuits or hardware, ignoring these issues may increase the probability of battery fire. Therefore, when replacing the battery, it is necessary to ensure that the new battery fully matches the voltage, current, size and other parameters of the device. In addition, the battery's chemical composition and charging characteristics should also be compatible with the device to avoid damage caused by overcharging or over-discharging. However, in the process of replacing the battery, these issues are often not fully guaranteed. Therefore, in the embodiment of the present application, the target vehicle with a replaced battery has a higher second risk index than the vehicle equipped with the original battery.

[0113] Step S230, obtaining the real-time charging parameters of the target vehicle during the charging process and the real-time power supply parameters corresponding to the charging device, and using the trained fire assessment model to process based on the first risk index, the second risk index, the real-time charging parameters and the real-time power supply parameters to obtain a fire detection assessment result. In some embodiments, step S230 can be performed by the detection and assessment unit 113.

[0114] In the embodiment of the present application, the detection and evaluation unit 113 can communicate with the battery management system of the target vehicle and the power supply management system of the charging device through a communication bus to obtain the real-time charging parameters of the target vehicle during the charging process and the real-time power supply parameters corresponding to the charging device. In the embodiment of the present application, the real-time charging parameters include battery voltage, battery current and battery temperature, and the real-time power supply parameters include power supply voltage, power supply current and power supply power.

[0115] Specifically, in some embodiments of the present application, a first feature vector can be generated based on multiple real-time charging parameters and real-time power supply parameters obtained at multiple consecutive data collection moments. For example, characteristic values ​​such as the average voltage value, current change rate, and temperature rise rate of the battery can be calculated based on multiple real-time charging parameters obtained at multiple consecutive data collection moments. These characteristic values ​​can reflect the state changes of the battery during the charging process, which is of great significance for assessing the risk of fire. Similarly, the power supply voltage stability, power supply current fluctuations, and real-time changes in the power supply of the charging device can be calculated based on the real-time power supply parameters of the charging device. The characteristic values ​​of these power supply parameters are also of great significance for assessing the risk of fire during the charging process. For example, if the current change rate of the battery is too high, it indicates that there may be an abnormality in the charging process, and immediate measures need to be taken to prevent potential fires.

[0116] Furthermore, in an embodiment of the present application, a first characteristic vector can be generated based on the average voltage value, current change rate, temperature rise rate of the aforementioned battery, as well as the supply voltage stability of the charging device, the fluctuation of the supply current, and the real-time change of the supply power.

[0117] Furthermore, in an embodiment of the present application, the first feature vector can be concatenated with the aforementioned first risk index and the second risk index to obtain a second feature vector, and then the second feature vector is input into a trained fire assessment model for processing to obtain a fire detection assessment result.

[0118] In an embodiment of the present application, the fire assessment model may be a neural network model, which may be trained by a large amount of sample data. The neural network model may include an input layer and multiple hidden layers, each of which may include multiple neurons for processing the complex relationship of the input data (i.e., the aforementioned second eigenvector). The model also includes at least one output layer for outputting the fire detection assessment result. The training process of the fire assessment model is briefly introduced below:

[0119] In an embodiment of the present application, a large amount of sample data can be obtained, and the sample data can be obtained by a method similar to the second eigenvector described above. Furthermore, for each piece of sample data, a fire assessment result label can be determined for it according to its corresponding actual situation. In an embodiment of the present application, the label can be a probability value used to indicate the risk level of fire in the charging state corresponding to each sample data. Furthermore, during the training process, the internal parameters can be adjusted by the back propagation algorithm to minimize the difference between the prediction result and the fire assessment result label, until the training is completed when the difference meets the requirements, and the aforementioned trained fire assessment model is obtained. More details about model training can be regarded as prior art and will not be discussed in detail in this specification.

[0120] After obtaining the aforementioned trained fire assessment model, the second feature vector can be input into the trained fire assessment model for processing, so as to obtain a fire detection assessment result based on the first risk index, the second risk index, the real-time charging parameters and the real-time power supply parameters.

[0121] It should be pointed out that in the embodiment of the present application, the fire detection evaluation result not only takes into account the risk factors of the charging vehicle itself, but also takes into account the potential risk factors reflected by the real-time charging data and power supply data during the charging process, which can better predict the probability of fire and potential risks.

[0122] Step S240 , performing linkage control on the charging device according to the fire detection evaluation result. In some embodiments, step S240 may be performed by the charging control unit 120 .

[0123] After obtaining the fire detection evaluation result through the above steps, the charging control unit 120 can perform linkage control on the charging device according to the fire detection evaluation result. In an embodiment of the present application, the linkage control may include adjusting the power supply parameters of the charging device or ending the charging task. For example, when the probability of fire reflected by the fire detection evaluation result is greater than the first risk threshold (e.g., 0.8), the charging control unit 120 can immediately cut off the power supply of the charging device and stop the charging process to prevent further development of the fire. For another example, when the probability of fire reflected by the fire detection evaluation result is greater than the second risk threshold (e.g., 0.5) but less than the first risk threshold, the charging control unit 120 can adjust the charging current and / or voltage of the charging device to reduce the charging rate, thereby reducing the risk of fire. In addition, if the probability of fire reflected by the fire detection evaluation result is lower than the second risk threshold, the charging control unit 120 can continue to monitor the fire detection evaluation result while maintaining the normal operation of the charging device. It should be noted that the above-mentioned first risk threshold and second risk threshold are only for example purposes. In actual applications, they can be adjusted according to actual needs.

[0124] Figure 4 is an exemplary module diagram of a fire detection linkage control system according to other embodiments of this specification. Figure 4In some embodiments of the present application, the fire detection linkage control system 100 may further include a fire control unit 130, and the fire detection unit 110 may further include a third data acquisition unit 114. The third data acquisition unit 114 may include a temperature detector and a smoke detector, and the temperature detector may be used to detect the ambient temperature of the target area (the closer the temperature detector is to the target vehicle, the better the detection effect), and send a first detection signal to the fire control unit 130 when the ambient temperature value or the rate of change of the ambient temperature value exceeds a first preset threshold. Similarly, the smoke detector may be used to detect the smoke concentration value of the target area (the closer to the target vehicle, the better the detection effect), and send a second detection signal to the fire control unit when the smoke concentration value exceeds a second preset threshold. It should be noted that in some embodiments of the present application, the first preset threshold and the second preset threshold may be determined based on the aforementioned first risk index and the second risk index. For example, in some embodiments, the first preset threshold and the second preset threshold may be negatively correlated with the sum of the aforementioned first risk index and the second risk index, that is, the larger the sum of the aforementioned first risk index and the second risk index, the lower the first preset threshold and the second preset threshold may be, thereby adaptively adjusting the sensitivity of the third data acquisition unit 114 according to the first risk index and the second risk index.

[0125] Further, the fire control unit 130 can control the fire fighting equipment in the target area according to the first detection signal and the second detection signal. Specifically, in some embodiments of the present application, the fire control unit 130 can control the fire fighting equipment in the target area to perform a fire fighting operation upon receiving any one of the first detection signal and the second detection signal. In some embodiments, the fire control unit 130 can control the fire fighting equipment in the target area to perform a fire fighting operation upon receiving both the first detection signal and the second detection signal.

[0126] In the embodiment of the present application, the fire fighting equipment in the target area may include at least one of an automatic sprinkler and an automatic fire extinguisher, wherein the automatic fire extinguisher is equipped with a fire extinguishing medium, and the fire extinguishing medium may include any one or more of carbon dioxide, ABC dry powder, BC dry powder, heptafluoropropane, perfluorohexanone, and nitrogen. It should be noted that in the embodiment of the present application, the fire fighting control unit 130 may be electrically connected to a control switch (e.g., an electric valve) of the automatic sprinkler and / or the automatic fire extinguisher, so as to control the fire extinguishing operation thereof.

[0127] Continue to refer to Figure 4In some embodiments of the present application, the fire detection unit 110 may further include a fourth data acquisition unit 115, which may be used to acquire a second target image for the target area, and perform fire detection based on the second target image to obtain a third detection signal; further, the fire control unit 130 may be used to control the fire-fighting equipment in the target area according to at least one of the first detection signal, the second detection signal, and the third detection signal. Specifically, in an embodiment of the present application, the fire control unit 130 may be used to control the fire-fighting equipment in the target area to perform a fire-fighting operation when the first detection signal and the second detection signal are received, or to control the fire-fighting equipment in the target area to perform a fire-fighting operation when the third detection signal is received, or to control the fire-fighting equipment in the target area to perform a fire-fighting operation when the first detection signal, the second detection signal, and the third detection signal are received.

[0128] Figure 5 is an exemplary flow chart of the steps of a fire detection method based on image recognition according to some embodiments of this specification. Figure 5 In the embodiment of the present application, the fourth data acquisition unit 115 performs fire detection based on the second target image, and the process of obtaining the third detection signal may include the following steps:

[0129] Step S410: Acquire a second target image captured for the target vehicle.

[0130] Step S420: determining a pixel distribution histogram according to the second target image, wherein the pixel distribution histogram is used to represent the probability distribution of the grayscale values ​​and corresponding gradients of the pixels contained in the second target image.

[0131] In an embodiment of the present application, the second target image can be obtained by an image acquisition device that is the same as or different from the first target image. Similar to the first target image, in an embodiment of the present application, the second target image can also include multiple images acquired from multiple different viewing angles. After obtaining the second target image, a pixel distribution histogram can be determined based on the second target image, and the pixel distribution histogram can be used to represent the probability distribution of the grayscale values ​​and corresponding gradients of the pixels contained in the second target image. Specifically, the construction of the pixel distribution histogram can be completed by counting the number of pixels at each grayscale level in the second target image. The number of pixels at each grayscale level combined with the gradient value of the level can form a two-dimensional distribution map, which can reveal the distribution of different brightness areas in the image, thereby providing important visual feature information for fire detection. By analyzing the pixel distribution histogram, abnormal brightness patterns in the image can be identified, which may indicate the presence of a fire. For example, if an abnormal high brightness peak appears in the histogram, this may mean the presence of a flame.

[0132] Step S430 , starting from the starting position, searching at each coordinate position in the pixel distribution histogram, and obtaining the segmentation parameter corresponding to the current search position during the search process.

[0133] Step S440: determining a candidate segmentation position corresponding to the current search position according to the segmentation parameters.

[0134] After obtaining the aforementioned pixel distribution histogram, a search can be performed at each coordinate position of the pixel distribution histogram starting from the starting position, and the segmentation parameters corresponding to the current search position are obtained during the search process, and then the candidate segmentation position corresponding to the current search position is determined according to the segmentation parameters. The starting position can be understood as a preset reference point, such as the upper left corner or center point of the image. The selection of the starting position can depend on the design and optimization requirements of the fire detection algorithm. After determining the starting position, the coordinate positions of the pixel distribution histogram can be traversed according to a certain strategy through a search algorithm to find possible segmentation points, which can be regarded as the boundary between the potential fire area and the background area.

[0135] During the search process, the segmentation parameters corresponding to the current search position can be obtained. Specifically, in an embodiment of the present application, the segmentation parameters may include but are not limited to thresholds, gradient directions, edge strengths, etc., which are helpful in distinguishing different areas in the image. For example, by setting a threshold, the pixels can be divided into foreground and background; the gradient direction can indicate the direction of brightness changes in the image, which helps to identify the shape and direction of the flame; the edge strength can be used to detect the severity of the brightness changes in the image, thereby assisting in determining whether there are edge features of the fire. In an embodiment of the present application, the segmentation parameters can be obtained by analyzing the brightness distribution of the image and then combining image processing techniques, such as histogram equalization or filtering, to enhance the contrast of potential fire areas in the image. In some embodiments of the present application, machine learning methods, such as support vector machines (SVM) or neural networks, can be used to train and optimize the segmentation parameters to improve the accuracy of segmentation.

[0136] After the segmentation parameters are obtained, the candidate segmentation position corresponding to the current search position can be determined according to the segmentation parameters. In an embodiment of the present application, the candidate segmentation position can be understood as a preliminary determination of a segmentation reference point, which can be used to determine possible fire areas in the image. In this embodiment, the candidate segmentation position can be determined by a variety of methods, such as threshold-based segmentation, gradient-based segmentation, or edge detection-based segmentation. These methods can be used alone or in combination to improve the accuracy and reliability of fire detection. For example, threshold-based segmentation can divide an image into foreground and background, while gradient-based segmentation can identify areas in the image where brightness changes dramatically, which may be flames. Edge detection can be used to identify edge features of brightness changes in an image, further assisting in the identification of fire areas.

[0137] Step S450, determining a target range according to the candidate segmentation position corresponding to the current search position, and segmenting suspected flame pixels from the second target image according to the target range.

[0138] After the candidate segmentation positions corresponding to the current search position are determined through the above steps, the target range can be determined based on the candidate segmentation positions. For example, all candidate segmentation positions can be closed to obtain a connected domain, and then the target range can be determined based on the connected domain. After the target range is determined, the suspected flame pixels can be segmented from the second target image based on the target range.

[0139] Step S460: extracting features from the suspected flame pixels, and generating a third detection signal when the extracted pixel features of the suspected flame pixels match the preset flame pixel features.

[0140] In the embodiment of the present application, feature extraction can be performed for the aforementioned suspected flame pixel. For example, a color analysis method can be used to determine whether it is a color distribution unique to flames by analyzing the RGB value of the pixel. In addition, texture analysis technology can be used to identify texture features of the suspected flame pixels within the target range, such as irregular edges and dynamic change patterns unique to flames. When the extracted pixel features of the suspected flame pixels match the preset flame pixel features, a third detection signal can be generated and fed back to the fire control unit 130.

[0141] More details about using image recognition technology for fire detection can be regarded as prior art and will not be discussed in detail in this specification.

[0142] It is understandable that there may be a certain delay in the change of ambient temperature and smoke concentration caused by the fire. Therefore, when the temperature detector and the smoke detector detect the occurrence of the fire, the best time for firefighting is usually over. In the embodiment of the present application, by using image recognition technology to detect fire, compared with using temperature detectors and smoke detectors to detect fire, the fire in the charging process of the car can be detected more timely, so that the fire control unit 130 can control the fire fighting equipment in the target area to perform the fire fighting operation more timely, and improve the response speed of the fire fighting operation to a certain extent.

[0143] In some embodiments of the present application, the fire fighting equipment may include a fire fighting door, which can be closed under the control of the fire fighting control unit 130, so that the target area where the fire occurs constitutes an enclosed space, thereby preventing other areas from being affected by the fire and causing more losses.

[0144] In summary, the beneficial effects that may be brought about by the embodiments of the present specification include but are not limited to: (1) In the fire detection linkage control system and method provided in some embodiments of the present specification, by simultaneously considering the risk factors of the charging vehicle itself and the potential risk factors reflected by the real-time charging data and power supply data during the charging process, the probability of fire and the potential risk can be better predicted; (2) In the fire detection linkage control system and method provided in some embodiments of the present specification, by determining the fire detection evaluation result according to the risk factors of the charging vehicle itself and the potential risk factors reflected by the real-time charging data and power supply data during the charging process, and controlling the charging equipment based on the fire detection evaluation result, the fire risk of the vehicle during the charging process can be reduced, and the safety of the charging process can be better guaranteed; (3) In the fire detection linkage control system and method provided in some embodiments of the present specification, by controlling the fire fighting equipment based on the fire detection signal, the fire extinguishing operation can be performed in time when a fire is detected, and the response speed of the fire extinguishing operation can be improved, thereby reducing the losses caused by the fire.

[0145] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or may be any other beneficial effects that may be obtained.

[0146] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0147] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0148] In addition, it will be understood by those skilled in the art that various aspects of this specification may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of this specification may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of this specification may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0149] A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0150] The computer program code required for the operation of each part of this specification can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program code can be run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or processing device. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0151] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing processing device or mobile device.

[0152] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0153] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0154] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0155] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A fire detection linkage control system, characterized in that: It includes a fire detection unit and a charging control unit, wherein the fire detection unit includes a first data acquisition unit, a second data acquisition unit and a detection evaluation unit; The first data acquisition unit is used to acquire relevant information of a target vehicle entering a target area for charging, and determine a first risk index according to the relevant information of the target vehicle, wherein the target area is a charging area corresponding to the charging device; The second data acquisition unit is used to acquire a battery status parameter of the target vehicle and determine a second risk index according to the battery status parameter; The detection and evaluation unit is used to obtain the real-time charging parameters of the target vehicle during the charging process and the real-time power supply parameters corresponding to the charging device, and use the trained fire assessment model to process based on the first risk index, the second risk index, the real-time charging parameters and the real-time power supply parameters to obtain a fire detection evaluation result; The charging control unit is used to perform linkage control on the charging device according to the fire detection evaluation result, and the linkage control includes adjusting the power supply parameters of the charging device or ending the charging task.

2. The system according to claim 1, characterized in that The relevant information of the target vehicle includes vehicle brand and model information and first battery type information corresponding to the vehicle brand and model information, and the first data acquisition unit is specifically used for: Acquire the vehicle brand and model information of the target vehicle through image recognition technology, and match the corresponding original battery type information by querying a database, thereby determining the first battery type information corresponding to the vehicle brand and model information; The first risk index is determined according to historical fire information corresponding to the vehicle brand and model information and / or the first battery type information.

3. The system according to claim 2, characterized in that The obtaining of the vehicle brand and model information of the target vehicle by using image recognition technology includes: Extracting visual features from a first target image collected for the target vehicle to obtain first target image features; Obtaining N candidate brands and models from a fine-grained classification set based on the first target image feature, wherein the fine-grained classification set includes features corresponding to multiple vehicle brands and models; Extracting target feature information of each of the N candidate brand models in a target state based on the feature description data corresponding to each of the N candidate brand models, wherein the target state is an image acquisition state used to distinguish the N candidate brand models; Based on the target feature information of each of the N candidate brands and models in the target state, the vehicle brand and model information of the target vehicle is determined from the N candidate brands and models.

4. The system according to claim 2, characterized in that The battery status parameter includes second battery type information and a battery health index, wherein the second battery type information is battery type information for the current charging task, and the second data acquisition unit is specifically used for: Acquiring second battery type information and a battery health index of the target vehicle through a battery management system of the target vehicle; Determining whether the second battery type information is consistent with the first battery type information; If the second battery type information is consistent with the first battery type information, the second risk index is determined based on the battery health index; if the second battery type information is inconsistent with the first battery type information, the first risk index is corrected based on the second battery type information, and the second risk index is determined based on the corrected first risk index and the battery health index.

5. The system according to claim 1, wherein: The detection and evaluation unit is specifically used for: Generate a first feature vector according to a plurality of real-time charging parameters and real-time power supply parameters acquired at a plurality of consecutive data collection moments, wherein the real-time charging parameters include battery voltage, battery current and battery temperature, and the real-time power supply parameters include power supply voltage, power supply current and power supply power; Concatenate the first feature vector with the first risk index and the second risk index to obtain a second feature vector; The second feature vector is input into the trained fire assessment model for processing to obtain the fire detection assessment result.

6. The system according to any one of claims 1 to 5, characterized in that: The system further comprises a fire control unit, and the fire detection unit further comprises a third data acquisition unit; wherein, The third data acquisition unit includes a temperature detector and a smoke detector. The temperature detector is used to detect the ambient temperature of the target area, and sends a first detection signal to the fire control unit when the ambient temperature value is detected to exceed a first preset threshold value; the smoke detector is used to detect the smoke concentration value of the target area, and sends a second detection signal to the fire control unit when the smoke concentration value is detected to exceed a second preset threshold value; the first preset threshold value and the second preset threshold value are both determined based on the first risk index and the second risk index; The fire control unit is used to control the fire equipment in the target area according to the first detection signal and the second detection signal.

7. The system according to claim 6, characterized in that The fire detection unit further includes a fourth data acquisition unit, the fourth data acquisition unit being used to acquire a second target image for the target area, and perform fire detection based on the second target image to obtain a third detection signal; The fire control unit is used to control the fire-fighting equipment in the target area according to at least one of the first detection signal, the second detection signal and the third detection signal.

8. The system according to claim 7, characterized in that The performing fire detection based on the second target image to obtain a third detection signal includes: Acquire a second target image captured for the target vehicle; Determine a pixel distribution histogram according to the second target image, wherein the pixel distribution histogram is used to represent the probability distribution of grayscale values ​​and corresponding gradients of pixels contained in the second target image; Starting from a starting position, searching at each coordinate position of the pixel distribution histogram, and obtaining a segmentation parameter corresponding to a current search position during the search process; Determine a candidate segmentation position corresponding to the current search position according to the segmentation parameter; Determining a target range according to the candidate segmentation position corresponding to the current search position, and segmenting suspected flame pixels from the second target image according to the target range; The suspected flame pixel is subjected to feature extraction, and when the extracted pixel feature of the suspected flame pixel matches the preset flame pixel feature, the third detection signal is generated.

9. The system according to claim 7, characterized in that The fire-fighting equipment in the target area includes at least one of an automatic sprinkler and an automatic fire extinguisher, wherein the automatic fire extinguisher is equipped with a fire-extinguishing medium, and the fire-extinguishing medium includes any one of carbon dioxide, ABC dry powder, BC dry powder, heptafluoropropane, perfluorohexanone, and nitrogen; The fire control unit is specifically used to control the fire fighting equipment in the target area to perform fire extinguishing operations when any one or more of the first detection signal, the second detection signal and the third detection signal are received.

10. A fire detection linkage control method, characterized in that: include: Obtaining relevant information of a target vehicle entering a target area for charging, and determining a first risk index according to the relevant information of the target vehicle, wherein the target area is a charging area corresponding to the charging device; Acquiring a battery status parameter of the target vehicle, and determining a second risk index according to the battery status parameter; Acquire the real-time charging parameters of the target vehicle during the charging process and the real-time power supply parameters corresponding to the charging device, and use the trained fire assessment model to process based on the first risk index, the second risk index, the real-time charging parameters and the real-time power supply parameters to obtain a fire detection assessment result; The charging device is controlled in linkage according to the fire detection evaluation result, and the linkage control includes adjusting the power supply parameters of the charging device or ending the charging task.

Images