Internet of things large model-based stationary vehicle emergency monitoring system, method and medium

Abstract

The application provides a stationary vehicle emergency monitoring system, method and medium based on an Internet of Things large model, and relates to the field of vehicle monitoring. The system comprises an emergency supervision management platform configured to execute the method. The method comprises: collecting temperature data of a target vehicle in a preset space according to a preset collection period based on a temperature measurement camera; constructing a temperature distribution cloud map of the target vehicle based on the temperature data; determining temperature information of a battery pack area of the target vehicle based on the temperature distribution cloud map; determining a thermal risk coefficient of the target vehicle based on the temperature information; determining a risk vehicle based on the thermal risk coefficient; determining an early warning frequency based on the thermal risk coefficient of the risk vehicle and the temperature data of the risk vehicle; and controlling a warning light in a monitoring room to flash at the early warning frequency. The method can also be read and run after computer instructions stored in a computer readable storage medium. The application can realize real-time monitoring and effective early warning of vehicle thermal runaway risk.

Description

Technical Field

[0001] This specification relates to the field of vehicle monitoring, and in particular to an emergency monitoring system, method and medium for stationary vehicles based on a large Internet of Things (IoT) model. Background Technology

[0002] With the rapid increase in the number of new energy vehicles, the risk of spontaneous combustion of their high-energy-density batteries due to internal aging, external short circuits, or thermal runaway when they are stationary is becoming increasingly prominent. Existing parking lots generally lack the ability to perceive and warn of the temperature status of vehicle batteries in real time, and cannot effectively and timely intervene before the vehicle thermal runaway, posing a huge fire hazard.

[0003] Therefore, there is an urgent need to provide an emergency monitoring system, method, and medium for stationary vehicles based on a large IoT model. By monitoring the battery temperature of stationary vehicles, this system can achieve real-time monitoring and effective early warning of the risk of thermal runaway, enabling early intervention. Summary of the Invention

[0004] To address the challenge of effectively and promptly intervening before a vehicle experiences thermal runaway, this invention provides a stationary vehicle emergency monitoring system, method, and medium based on a large-scale Internet of Things (IoT) model.

[0005] The invention includes an emergency monitoring system for stationary vehicles based on an Internet of Things (IoT) big data model, comprising an emergency monitoring and management platform; the emergency monitoring and management platform is configured to execute an emergency monitoring method for stationary vehicles based on an IoT big data model.

[0006] The invention includes a method for emergency monitoring of stationary vehicles based on an Internet of Things (IoT) big data model. The method is executed by an emergency monitoring and management platform within an IoT-based emergency monitoring system for stationary vehicles. The method includes: collecting temperature data of a target vehicle within a preset space using a temperature-measuring camera according to a preset collection cycle; constructing a temperature distribution cloud map of the target vehicle based on the temperature data; determining the temperature information of the battery pack area of ​​the target vehicle based on the temperature distribution cloud map; determining the thermal risk coefficient of the target vehicle based on the temperature information; identifying high-risk vehicles based on the thermal risk coefficient; determining a warning frequency based on the thermal risk coefficient and the temperature data of the high-risk vehicles; and controlling a warning light in the monitoring room to flash at the warning frequency.

[0007] The invention includes a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the above-mentioned emergency monitoring method for stationary vehicles based on the Internet of Things (IoT) big data model.

[0008] The beneficial effects of the above invention include, but are not limited to: (1) Real-time full-area monitoring of the target vehicle is carried out by temperature measurement camera, the monitoring area is accurately matched to the location of the battery pack area, and the temperature information of the battery pack area is converted into a gradeable and comparable single-value index by thermal risk coefficient. Once the set risk threshold is exceeded, the warning light can be controlled to flash at the warning frequency to achieve early identification and intervention; (2) By using the temperature data of the first reference vehicle of the target vehicle, the environmental reference temperature can be determined to filter out the interference of external factors such as weather and surface radiation. Then, by comparing the temperature information of the battery pack area with the environmental reference temperature, only the heat abnormality of the battery pack itself is retained, reducing false alarms; The thermal risk coefficient is determined based on the abnormal temperature information of the battery pack area, and multiple precursors such as short circuit and heat diffusion are identified at the same time, making the risk judgment more accurate; (3) By obtaining the owner information of the risk vehicle and other vehicles adjacent to it, the neighborhood warning information is automatically generated and sent to the owner terminal, so that the owners of the risk vehicle and the vehicles adjacent to it can take timely measures to prevent the thermal runaway of the risk vehicle from causing a larger-scale accident. This can more comprehensively prevent the occurrence of large-scale thermal runaway accidents and further improve the safety of the entire preset space. Attached Figure Description

[0009] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0010] Figure 1 This is a platform structure diagram of a stationary vehicle emergency monitoring system based on an Internet of Things (IoT) big data model, as shown in some embodiments of this specification. Figure 2 This is an exemplary flowchart of an emergency monitoring method for stationary vehicles based on a large IoT model, as shown in some embodiments of this specification. Figure 3 This is an exemplary schematic diagram illustrating the determination of thermal risk factors according to some embodiments of this specification; Figure 4 This is an exemplary flowchart illustrating the sending of alerts according to some embodiments of this specification; Figure 5 This is an exemplary flowchart illustrating the collection of temperature data from potentially hazardous vehicles according to some embodiments of this specification. Detailed Implementation

[0011] The accompanying drawings used in the description of the embodiments will be briefly introduced below. The drawings do not represent all embodiments.

[0012] The terms “system,” “device,” “unit,” and / or “module” as used herein are one method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0013] Unless the context clearly indicates an exception, words such as "a," "an," "a kind," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0014] Figure 1 This is a platform structure diagram of a stationary vehicle emergency monitoring system based on an Internet of Things (IoT) big data model, as shown in some embodiments of this specification.

[0015] In some embodiments, such as Figure 1 As shown, the stationary vehicle emergency monitoring system 100 based on the Internet of Things big data model includes an emergency monitoring user platform 110, an emergency monitoring service platform 120, an emergency monitoring management platform 130, an emergency monitoring sensor network platform 140, and an emergency monitoring perception and control platform 150.

[0016] The emergency supervision user platform 110 refers to a platform used by higher-level regulatory authorities to comprehensively coordinate emergency supervision. In some embodiments, the emergency supervision user platform includes a user terminal, such as a mobile device, a computer, or any combination of other devices with input and / or output functions.

[0017] The Emergency Monitoring Service Platform 120 refers to an interactive service platform that receives and transmits emergency monitoring data.

[0018] In some embodiments, the emergency monitoring service platform interacts upward with the emergency monitoring user platform and downward with the emergency monitoring management platform.

[0019] In some embodiments, the emergency monitoring service platform includes a communication terminal.

[0020] A communication terminal refers to a device or software that enables real-time information exchange. For example, a communication terminal can be a wireless mobile phone, a video monitor, a multimedia computer, etc.

[0021] The emergency monitoring and management platform 130 refers to a comprehensive platform for processing and managing emergency monitoring data of stationary vehicles. In some embodiments, the emergency monitoring and management platform is configured to implement a stationary vehicle emergency monitoring method based on an IoT big data model. For more information on this method, see [link to relevant documentation]. Figures 2-5 Related descriptions.

[0022] In some embodiments, the emergency monitoring and management platform may include processors and / or servers, data centers, etc. The data center is equipped with storage devices.

[0023] The emergency monitoring sensor network platform 140 refers to a platform that transmits sensor data or information related to emergency monitoring, including routers and gateways.

[0024] In some embodiments, the emergency monitoring sensor network platform interacts upward with the emergency monitoring management platform and downward with the emergency monitoring perception and control platform.

[0025] The Emergency Monitoring and Control Platform 150 refers to a platform for collecting emergency monitoring data and implementing commands.

[0026] In some embodiments, the emergency monitoring and control platform may include camera equipment (such as temperature measuring cameras, ordinary visible light cameras, etc.) and early warning devices (such as early warning lights).

[0027] For more information about the above platforms, please refer to [link / reference]. Figures 2-5 And related explanations.

[0028] It should be noted that the above description of the stationary vehicle emergency monitoring system 100 based on the Internet of Things (IoT) big data model is for ease of description only and should not be construed as limiting this specification to the scope of the embodiments described. It is understood that those skilled in the art, after understanding the principles of this system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from these principles. In some embodiments, the various modules may share a single storage module, or each module may have its own separate storage module. Such modifications are all within the scope of protection of this specification.

[0029] Figure 2 This is an exemplary flowchart illustrating an emergency monitoring method for stationary vehicles based on a large-scale Internet of Things (IoT) model, according to some embodiments of this specification. Figure 2 As shown, process 200 includes the following steps. In some embodiments, process 200 may be executed by emergency monitoring and management platform 130.

[0030] Step S210: Based on the temperature measuring camera, collect temperature data of the target vehicle in the preset space according to the preset collection cycle.

[0031] A temperature-measuring camera is a camera device that can measure the surface temperature of an object. For example, an infrared thermal imaging camera.

[0032] The preset acquisition period refers to the time interval between two consecutive temperature data acquisitions, which can be set manually or by system default. For example, 3s, 5s, etc.

[0033] A pre-defined space refers to a space designated for monitoring the risk of vehicle thermal runaway. Examples include underground parking lots.

[0034] The target vehicle refers to a stationary vehicle that has entered and is parked in the preset space.

[0035] In this specification, the application scenario of stationary vehicle emergency monitoring based on the Internet of Things big model is mainly vehicle thermal runaway risk monitoring. Thermal runaway risk refers to the potential danger of fire caused by vehicle battery runaway (such as spontaneous combustion or explosion). That is, the target vehicle is only a new energy vehicle (including pure electric vehicles and hybrid vehicles with battery packs).

[0036] Temperature data refers to temperature-related data of the target vehicle. Temperature data can include temperature values ​​from multiple different locations on the target vehicle, such as the temperature of the chassis and the temperature of the exhaust pipe.

[0037] In some embodiments, at preset acquisition intervals, the temperature-measuring camera scans and measures the surface of the target vehicle once. Each pixel corresponds to a temperature value. The temperatures of multiple locations acquired by the temperature-measuring camera in a single acquisition of the target vehicle can be represented in a preset form (e.g., sequence, matrix, etc.) to construct the temperature data corresponding to that acquisition. That is, the temperature data corresponding to a single acquisition can be represented as a temperature sequence or temperature matrix, etc. The emergency monitoring and management platform can directly acquire the temperature data of the target vehicle measured and uploaded by the temperature-measuring camera.

[0038] Step S220: Based on the temperature data, construct a temperature distribution cloud map of the target vehicle.

[0039] A temperature distribution cloud map is an image that visually displays the temperature distribution on the surface of a target vehicle.

[0040] For example, a temperature distribution cloud map can be a pseudo-color image, using different colors to represent different temperature values. For instance, below 20 ℃ is displayed in blue, 20 ℃-60 ℃ in green, and above 60 ℃ in red.

[0041] In some embodiments, at each preset collection period, the emergency monitoring and management platform can visualize and render the temperature data corresponding to a single collection to obtain a temperature distribution cloud map corresponding to that collection.

[0042] Step S230: Based on the temperature distribution cloud map, determine the temperature information of the battery pack area of ​​the target vehicle.

[0043] The battery pack area refers to the physical area at the bottom of the target vehicle used to house the battery.

[0044] Temperature information can include temperature distribution and thermal gradient changes. Temperature distribution refers to the spatial distribution of temperature values ​​at various points in the battery pack area, while thermal gradient changes refer to the rate and direction of temperature change in space, i.e., the amount of temperature change per unit distance.

[0045] In some embodiments, the emergency monitoring and management platform can utilize technologies such as spatial registration to overlay the temperature distribution cloud map of the target vehicle with a visible light reference map at the pixel level. This allows the temperature of each area of ​​the vehicle to be visually mapped onto the vehicle's structural outline provided by the visible light reference map. Therefore, the emergency monitoring and management platform can directly capture the battery pack area to obtain its temperature distribution. A visible light reference map refers to an image acquired by a standard visible light camera, used to provide spatial location and outline reference.

[0046] In some embodiments, the emergency monitoring and management platform can obtain the thermal gradient change by performing spatial difference calculations on the temperature distribution data of the battery pack area. For example, the platform can calculate the temperature difference between each pixel and its adjacent pixels along a preset positive direction in the temperature distribution of the battery pack area, divide the temperature difference by the actual physical distance between the two pixels, and obtain the thermal gradient value corresponding to each pixel, thus forming the thermal gradient change of the battery pack area. The temperature difference is the temperature value of the adjacent pixels along the preset positive direction minus the current temperature value of that pixel. The preset positive direction can be manually preset or set by system default.

[0047] Step S240: Determine the thermal risk coefficient of the target vehicle based on temperature information.

[0048] The thermal risk coefficient is a numerical value that quantifies the degree of thermal runaway risk of a target vehicle. The thermal risk coefficient can be represented by a value from 0 to 100, with a higher value indicating a greater risk of battery thermal runaway.

[0049] In some embodiments, the emergency monitoring and management platform can determine the thermal risk coefficient based on temperature information through various methods. For example, the emergency monitoring and management platform can determine the thermal risk coefficient by querying a first preset table based on temperature distribution and changes in thermal gradient.

[0050] The first preset table includes the correspondence between temperature distribution, thermal gradient changes, and thermal risk coefficients. This first preset table can be constructed manually based on experimental data. For example, battery packs of different models and in different health states (e.g., different remaining battery capacity, different remaining battery fluid capacity, etc.) are selected as experimental subjects. In a laboratory environment, various fault scenarios that may lead to thermal runaway (e.g., internal short circuit, overcharge / over-discharge, cooling system failure, etc.) are simulated, and the experimental temperature distribution and thermal gradient changes of the experimental subjects are continuously monitored. Based on experience, the corresponding thermal risk coefficients are labeled, and the first preset table is constructed.

[0051] For example, if the experimental temperature distribution of the test subject is such that more than 90% of the pixels in the battery pack area have a temperature less than or equal to 45°C, and the experimental thermal gradient change is such that more than 90% of the pixels have a temperature difference of less than or equal to 0.5°C with their adjacent pixels along a preset positive direction, then the test subject is in a normal charging and discharging state and is judged as low risk (e.g., the thermal risk coefficient is labeled as 0-30 points); if the experimental temperature distribution of the test subject is such that more than 90% of the pixels in the battery pack area have a temperature greater than 45°C and less than or equal to 65°C, and / or the experimental thermal gradient change is such that more than 90% of the pixels have a temperature difference of less than or equal to 0.5°C with their adjacent pixels along a preset positive direction, then the test subject is in a normal charging and discharging state and is judged as low risk (e.g., the thermal risk coefficient is labeled as 0-30 points); or if the experimental temperature distribution of the test subject is such that more than 90% of the pixels in the battery pack area have a temperature greater than 45°C and less than or equal to 65°C, and / or the experimental thermal gradient change is such that more than 90% of the pixels have a temperature difference of less than or equal to 0.5°C with their adjacent pixels along a preset positive direction, then the test subject is in a normal charging and discharging state and is judged as low risk (e.g., the thermal risk coefficient is labeled as 0-30 points). If the temperature difference between adjacent pixels in the positive direction is greater than 0.5℃ and less than or equal to 2℃, it indicates that the experimental object is in a state of abnormal temperature rise or local hot spots but is controllable, and is judged as medium risk (e.g., thermal risk coefficient is marked as 31-70 points). If the experimental temperature distribution of the experimental object is that more than 90% of the pixels in the battery pack area have a temperature greater than 65℃, and the experimental thermal gradient change is that more than 90% of the pixels have a temperature difference greater than 2℃ with their adjacent pixels along the preset positive direction, it indicates that the experimental object is in a state of thermal runaway, and is judged as high risk (e.g., thermal risk coefficient is marked as 71-100 points).

[0052] In some embodiments, the emergency monitoring and management platform can determine the ambient reference temperature of the target vehicle based on the temperature data of a first reference vehicle, wherein the first reference vehicle is other target vehicles within a first neighborhood of the target vehicle; determine the abnormal temperature information of the battery pack area of ​​the target vehicle based on the ambient reference temperature and the temperature information of the battery pack area; and determine the thermal risk coefficient of the target vehicle based on the abnormal temperature information of the battery pack area.

[0053] For more information on this section, please refer to [link / reference]. Figure 3 Related explanations.

[0054] Step S250: Based on the thermal risk coefficient, identify the risky vehicles.

[0055] A high-risk vehicle is a target vehicle that is deemed to have a risk of thermal runaway.

[0056] In some embodiments, the emergency monitoring and management platform can identify target vehicles with a thermal risk coefficient greater than a first risk threshold as high-risk vehicles. The first risk threshold can be set manually based on historical experience.

[0057] Step S260: Determine the warning frequency based on the thermal risk coefficient and temperature data of the risky vehicle.

[0058] Warning frequency refers to the frequency at which warnings are issued regarding the risk of vehicle thermal runaway. In some embodiments, the warning frequency can be the number of times a warning light in a monitoring room flashes per unit time. A monitoring room refers to a pre-designated space where management personnel are located.

[0059] In some embodiments, the emergency monitoring and management platform can determine the warning frequency based on the thermal risk coefficient and temperature data of the risky vehicle through a second preset table.

[0060] The second preset table includes the thermal risk coefficient of high-risk vehicles, the correlation between the temperature data of high-risk vehicles and the warning frequency. The higher the thermal risk coefficient of a high-risk vehicle, the higher its temperature, and the faster the warning frequency. The second preset table can be manually constructed based on historical data.

[0061] Step S270: Control the warning lights in the monitoring room to flash at the warning frequency.

[0062] In some embodiments, the emergency monitoring and management platform can generate and issue control commands, including warning frequencies, to control the warning lights in the monitoring room to flash at the warning frequencies.

[0063] In some embodiments of this specification, a temperature-measuring camera is used to perform real-time full-area monitoring of the target vehicle, accurately mapping the monitoring area to the location of the battery pack area, and using a thermal risk coefficient to convert the temperature information of the battery pack area into a graded and comparable single-value index. Once the set risk threshold is exceeded, the warning light can be controlled to flash at a warning frequency to achieve early identification and intervention.

[0064] Figure 3 This is an exemplary schematic diagram illustrating the determination of thermal risk factors according to some embodiments of this specification.

[0065] In some embodiments, such as Figure 3 As shown, the emergency monitoring and management platform can determine the ambient reference temperature 320 of the target vehicle based on the temperature data 310 of the first reference vehicle of the target vehicle, where the first reference vehicle is other target vehicles within the first neighborhood of the target vehicle; based on the ambient reference temperature 320 of the target vehicle and the temperature information 330 of the battery pack area, it can determine the abnormal temperature information 340 of the battery pack area of ​​the target vehicle; based on the abnormal temperature information 340 of the battery pack area, it can determine the thermal risk coefficient 350 of the target vehicle.

[0066] More information regarding the target vehicle, temperature data, battery pack area, temperature information, and thermal risk factor can be found at [link to relevant documentation]. Figure 2 And related explanations.

[0067] The first reference vehicle refers to a neighboring vehicle that provides an ambient temperature reference for the target vehicle. In some embodiments, the first reference vehicle of the target vehicle can be other target vehicles within a first neighborhood of the target vehicle, wherein the first neighborhood can be manually preset or set by system default, such as a circular area within a first preset radius (e.g., 5 meters) centered on the target vehicle.

[0068] Ambient reference temperature refers to a reference temperature value that uses the temperature of surrounding vehicles as a reference standard.

[0069] In some embodiments, the emergency monitoring and management platform can calculate the average temperature of multiple pixels within the battery pack area of ​​the first reference vehicle based on the temperature information of the battery pack area of ​​the first reference vehicle, and use this average temperature as the average temperature of the battery pack area of ​​the first reference vehicle; then, it can perform a weighted summation of the average temperatures of the battery pack areas of all the first reference vehicles for the target vehicle, and determine the result of the weighted summation as the environmental reference temperature of the target vehicle. The weight corresponding to the first reference vehicle is negatively correlated with the distance between the first reference vehicle and the target vehicle.

[0070] Abnormal temperature information refers to abnormal information in the temperature information of the battery pack area. In some embodiments, abnormal temperature information may include abnormal hot spots and abnormal thermal gradient areas.

[0071] An abnormal hot spot refers to an isolated point in the battery pack area where the temperature is significantly higher than the surrounding area.

[0072] An abnormal thermal gradient region refers to a collection of pixels within the battery pack area whose thermal gradient values ​​are abnormal.

[0073] In some embodiments, the emergency monitoring and management platform can determine abnormal temperature information through various methods based on environmental reference temperature and temperature information.

[0074] For example, the emergency monitoring and management platform can identify abnormal hotspots based on temperature information, specifically pixels in the battery pack area whose absolute value of the temperature difference from the ambient reference temperature exceeds a temperature difference threshold; and regions formed by pixels whose thermal gradient values ​​exceed a gradient threshold are identified as abnormal thermal gradient regions. The temperature difference threshold and gradient threshold can be set manually based on historical experience, and the regions formed by pixels can be represented by connected components formed by the spatial adjacency relationships of the pixels.

[0075] In some embodiments, abnormal temperature information may also include the spread path of abnormal hotspots, and the emergency monitoring and management platform may also determine the spread path of abnormal hotspots based on multiple abnormal hotspot centers corresponding to multiple time points.

[0076] The diffusion path refers to the spatial displacement trajectory that can characterize the changes of anomalous hotspots over time.

[0077] In some embodiments, the diffusion path can be represented by a sequence of spatiotemporal coordinates of multiple anomalous hotspots corresponding to multiple time points, arranged chronologically, with earlier spatiotemporal coordinates appearing first. Each spatiotemporal coordinate point consists of the spatial coordinates of the anomalous hotspot center and the corresponding time. For example, the diffusion path is: [(X1, Y1, T1), (X2, Y2, T2), ..., (Xn, Yn, Tn)], where (Xn, Yn, Tn) is the nth spatiotemporal coordinate point, indicating that the spatial coordinates of the anomalous hotspot center at time Tn are (Xn, Yn), and time T(n-1) precedes time Tn. The spatial coordinates can be represented by pixel coordinates.

[0078] In some embodiments, multiple time points may include multiple historical time points and / or one or more future time points.

[0079] A historical point in time refers to a point in time before the current point in time.

[0080] A future point in time refers to a point in time after the current point in time.

[0081] In some embodiments, multiple time points can be selected at even intervals, for example, selecting a historical time point every 5 seconds or setting a future time point.

[0082] In some embodiments, multiple time points can also be determined based on temperature information of the battery pack region. For example, for each historical moment, the average temperature of multiple pixels in the battery pack region is calculated based on the temperature distribution of the battery pack region, and this average temperature is taken as the average temperature of the battery pack region; historical moments in which the average temperature changes abruptly (e.g., the change in average temperature exceeds a preset change threshold) are taken as historical time points.

[0083] An abnormal hotspot center refers to the central representative point of all abnormal hotspots within the battery pack area at the same time.

[0084] In some embodiments, the emergency monitoring and management platform can identify the center of anomalies in various ways. For example, the platform can identify the anomaly with the highest temperature among all anomalies within the battery pack area at the same historical time point as the center of the anomaly.

[0085] In some embodiments, multiple time points may include multiple historical time points and one or more future time points; the emergency monitoring and management platform may also determine one or more abnormal hotspot centers corresponding to one or more future time points based on multiple abnormal hotspot centers corresponding to multiple historical time points through a prediction model, wherein the prediction model is a machine learning model.

[0086] A predictive model is a model used to predict anomalous hotspot centers at future points in time.

[0087] In some embodiments, the prediction model is a machine learning model, such as a Long Short-Term Memory (LSTM) network model.

[0088] In some embodiments, the input to the prediction model includes multiple anomalous hotspot centers corresponding to multiple historical time points, and the output includes one or more anomalous hotspot centers corresponding to one or more future time points. Both the input and output data of the prediction model can be the spatiotemporal coordinates of the anomalous hotspot centers.

[0089] In some embodiments, the emergency monitoring and management platform can train a prediction model based on multiple training samples with training labels.

[0090] Training samples can be obtained based on historical data, and training labels can be manually labeled based on historical data. A single training session may use a set of training samples that includes multiple historical anomalous hotspot centers corresponding to multiple first-sample historical time points. The training labels for this set of training samples are one or more historical anomalous hotspot centers corresponding to one or more second-sample historical time points. The first-sample historical time points are prior to the second-sample historical time points.

[0091] The data used to train the prediction model can all be historical spatiotemporal coordinates corresponding to historical anomaly hotspot centers. In some embodiments, the emergency monitoring and management platform can input training samples into the initial prediction model, construct a loss function based on the training labels and the output of the initial prediction model, iteratively update the parameters of the initial prediction model based on the loss function, and end the iteration when the iteration termination condition is met, thus obtaining the trained prediction model. The iterative update method includes, but is not limited to, gradient descent, and the iteration termination condition can be the convergence of the loss function or the reaching of a threshold number of iterations.

[0092] In some embodiments of this specification, the location of one or more anomalous hotspot centers at future time points can be determined more accurately and quickly by using a predictive model. This facilitates the accurate and rapid determination of anomalous hotspot centers in the battery pack region at multiple future time points, thereby improving the speed and accuracy of diffusion path determination.

[0093] In some embodiments, the emergency monitoring and management platform can determine the diffusion path of abnormal hotspots based on multiple abnormal hotspot centers corresponding to multiple time points. For example, the platform can arrange multiple spatiotemporal coordinates of the abnormal hotspots corresponding to the aforementioned multiple time points into a sequence, which serves as the diffusion path of the abnormal hotspot centers. Alternatively, the platform can use a path fitting algorithm (such as least squares) to smoothly connect the abnormal hotspot centers corresponding to the aforementioned multiple time points, using this connection as the diffusion path of the abnormal hotspot centers. The multiple time points may include multiple historical time points and one or more future time points, or may only include multiple future time points.

[0094] In some embodiments of this specification, by using the abnormal hotspot centers at multiple time points (including historical time points and one or more future time points), the diffusion path of abnormal hotspots in the battery pack area can be predicted, thereby predicting the direction of risk development. More targeted intervention measures can be taken, and dynamic early warning of thermal risks of stationary vehicles can be provided, optimizing the use of early warning resources.

[0095] In some embodiments, the emergency monitoring and management platform can count the number of abnormal hotspots and calculate the area ratio of abnormal thermal gradient regions to the battery pack area; perform a dimensionless weighted summation of the two, and normalize the weighted summation result to map it to the numerical range corresponding to the thermal risk coefficient. The weights can be preset manually based on experience. Normalization methods include, but are not limited to, the min-max normalization method.

[0096] In some embodiments of this specification, the ambient reference temperature can be determined by using the temperature data of the first reference vehicle of the target vehicle, after filtering out interference from external factors such as weather and ground radiation. Then, by comparing the temperature information of the battery pack area with the ambient reference temperature, only the heating abnormality of the battery pack itself is retained, reducing false alarms. The thermal risk coefficient is determined based on the abnormal temperature information of the battery pack area, and multiple precursors such as short circuit and heat diffusion are identified, making the risk assessment more accurate.

[0097] Figure 4 This is an exemplary flowchart illustrating the sending of alerts according to some embodiments of this specification. Figure 4 As shown, process 400 includes the following steps. In some embodiments, process 400 may be executed by emergency monitoring and management platform 130.

[0098] Step S410: Obtain the vehicle identity information of the risk vehicle and the second reference vehicle of the risk vehicle.

[0099] For more information on high-risk vehicles, please refer to [link / reference]. Figure 2 Related descriptions.

[0100] The second reference vehicle refers to a vehicle that may be affected by the thermal runaway risk of the at-risk vehicle. In some embodiments, the second reference vehicle of the at-risk vehicle may be other target vehicles within a second neighborhood of the at-risk vehicle.

[0101] The second neighborhood range refers to the area affected by the thermal runaway risk of the at-risk vehicle. In some embodiments, the second neighborhood range can be manually preset or set by system default, such as a circular area within a second preset radius centered on the at-risk vehicle. The first preset radius and the second preset radius can be the same or different.

[0102] In some embodiments, the second neighborhood range is related to the thermal risk coefficient of the at-risk vehicle. The larger the thermal risk coefficient of the at-risk vehicle, the higher the risk of thermal runaway, and thus the larger the second neighborhood range can be.

[0103] In some embodiments of this specification, the second neighborhood range is dynamically determined based on the thermal risk coefficient of the at-risk vehicle. This allows the warning range to adaptively adjust according to the actual risk level; that is, the higher the risk level (e.g., the higher the thermal risk coefficient), the larger the warning range. This ensures sufficient safety redundancy in high-risk situations, while avoiding unnecessary disturbance to residents in low-risk situations, thereby achieving intelligent and optimized allocation of warning resources.

[0104] Vehicle identification information refers to identification information that can characterize a vehicle, such as license plate number and vehicle location. The vehicle's location can be represented by the parking area or charging station area where the vehicle is located.

[0105] In some embodiments, the emergency monitoring and management platform can obtain vehicle identification information through relevant devices. For example, it can obtain license plate numbers and vehicle locations through video surveillance equipment such as surveillance cameras.

[0106] Step S420: Based on the vehicle identity information, determine the owner information of the risk vehicle and the second reference vehicle.

[0107] Vehicle owner information can include the owner's identity information and contact details, and is mainly used to contact the owner.

[0108] In some embodiments, the emergency monitoring and management platform can obtain vehicle owner information by querying a database based on vehicle identity information. The database stores vehicle identity information and corresponding owner information. For example, the database could be the database of a charging pile management system in an underground parking lot.

[0109] Step S430: Generate neighborhood warning information and send the neighborhood warning information to the owner terminals of the risk vehicle and the second reference vehicle based on the vehicle owner information.

[0110] Neighborhood warning information refers to information that warns of the risk of thermal runaway from vehicles at risk, used to alert the at-risk vehicle and its secondary reference vehicles. For example, a neighborhood warning message might read, "Vehicle with license plate number 'XXX' is at risk of thermal runaway. The owner of this vehicle is requested to stop charging immediately. This vehicle is located in charging station area 1 in the west section of the parking lot. Please move any vehicles nearby as soon as possible." Neighborhood warning information can take various forms, including but not limited to warning text messages and warning voice calls.

[0111] In some embodiments, the emergency monitoring and management platform can automatically generate neighborhood early warning information based on a preset information generation template.

[0112] In some embodiments, the emergency monitoring and management platform can send the generated neighborhood warning information to the owner terminals of the at-risk vehicle and the second reference vehicle based on the vehicle owner information. The owner terminals may include, but are not limited to, the vehicle owner's mobile phone, computer, etc.

[0113] In some embodiments of this specification, by obtaining the owner information of the risky vehicle and other vehicles nearby, neighborhood warning information is automatically generated and sent to the owner's terminal, enabling the owners of the risky vehicle and other vehicles nearby to take timely measures to prevent the risky vehicle's thermal runaway from causing a larger-scale accident. This can more comprehensively prevent the occurrence of large-scale thermal runaway accidents and further improve the safety of the entire preset space.

[0114] Figure 5 This is an exemplary flowchart illustrating the collection of temperature data from potentially hazardous vehicles, according to some embodiments of this specification. Figure 5 As shown, process 500 includes the following steps. In some embodiments, process 500 may be executed by emergency monitoring and management platform 130.

[0115] Step S510: Based on the location information of the potentially risky vehicle, determine the target temperature measurement camera.

[0116] A potential risk vehicle is a vehicle that may become a risk vehicle in the future and requires close monitoring. In some embodiments, a potential risk vehicle can be a target vehicle with a thermal risk coefficient greater than a second risk threshold but not greater than a first risk threshold.

[0117] For an explanation of the first risk threshold, please refer to [link / reference needed]. Figure 2 Related descriptions.

[0118] The second risk threshold is a threshold related to the thermal risk coefficient used to identify potentially risky vehicles. The second risk threshold is lower than the first risk threshold. In some embodiments, the second risk threshold may be preset manually based on experience or set by system default.

[0119] In some embodiments, the second risk threshold may be related to the ambient reference temperature, battery type, and state of charge of the potentially risky vehicle.

[0120] Battery types may include rechargeable batteries, fuel cells, etc. In some embodiments, the emergency monitoring and management platform can identify the vehicle brand and model through vehicle images captured by a camera, and determine the battery type based on the vehicle brand and model through online queries.

[0121] Charging status includes not charging (e.g., not connected to a charging station) and charging (e.g., connected to a charging station and charging or fully charged). In some embodiments, the emergency monitoring and management platform can directly obtain the charging status of potentially at-risk vehicles through communication interfaces (e.g., CAN bus, Ethernet, etc.) based on the charging station management system or vehicle bus system.

[0122] In some embodiments, the emergency monitoring and management platform can determine the initial second risk threshold corresponding to a potentially risky vehicle by querying a third preset table based on the battery type of the potentially risky vehicle; determine the charging state factor based on the charging state of the potentially risky vehicle, including a preset value (e.g., 0.8) less than 1 if the potentially risky vehicle is not charging, and a charging state factor of 1 if the potentially risky vehicle is charging; determine the environmental reference factor based on the environmental reference temperature of the potentially risky vehicle, including an environmental reference factor that is positively correlated with the environmental reference temperature and is represented by a value not exceeding 1; and determine the second risk threshold by multiplying the initial second risk threshold, the charging state factor, and the environmental reference factor.

[0123] The initial second risk threshold refers to the original second risk threshold determined solely based on the vehicle's battery type. The state-of-charge factor reflects the degree to which the vehicle's state of charge affects the second risk threshold. The environmental baseline factor reflects the degree to which the environmental baseline temperature affects the second risk threshold. The third preset table includes multiple battery types and corresponding initial second risk thresholds, which can be pre-constructed manually. For example, the initial second risk threshold for a vehicle with a rechargeable battery is lower than the initial second risk threshold for a vehicle with a fuel cell battery.

[0124] For more information on ambient reference temperature, please see [link to relevant information]. Figure 2 Related descriptions.

[0125] In some embodiments of this specification, when determining the second risk threshold, the ambient reference temperature, battery type, and charging status of the potential risk vehicle are taken into account, so that the monitoring intensity of the potential risk vehicle is more in line with its actual risk tolerance (for example, a lower risk threshold is used for battery types with poor thermal stability), which further improves the accuracy of personalized monitoring and reduces the misjudgment and omission of potential risk vehicles.

[0126] Location information can be represented by the parking area or charging station area where the vehicle is located, or by location coordinates. In some embodiments, the location information of potentially risky vehicles can be obtained based on image information acquired by camera equipment, through image recognition technology (such as road vehicle target detection based on deep learning).

[0127] A target temperature measurement camera is a camera that can clearly capture the temperature of the battery pack area of ​​a potentially hazardous vehicle.

[0128] In some embodiments, the emergency monitoring and management platform can determine the target temperature measuring camera by performing spatial calculations based on the shooting range of the temperature measuring cameras, according to the location information of potentially risky vehicles and the distribution information of multiple temperature measuring cameras in a preset space.

[0129] In some embodiments, the emergency monitoring and management platform can obtain the deployment location and viewing angle of each temperature-measuring camera within a preset space based on the distribution map and factory parameters of the temperature-measuring cameras. Then, using spatial computing technology, it can select one or more temperature-measuring cameras whose viewing angle can completely cover the battery pack area of ​​a potentially risky vehicle as target temperature-measuring cameras. The distribution map and factory parameters of the temperature-measuring cameras are uploaded manually in advance. Spatial computing methods include, but are not limited to, optical positioning algorithms, markerless point recognition calculations, and optical and markerless fusion technologies.

[0130] Step S520: Based on the thermal risk coefficient of the potentially risky vehicle, determine the corresponding data collection period for the potentially risky vehicle.

[0131] The corresponding acquisition period refers to the time interval between two consecutive temperature data acquisitions for a potentially risky vehicle. In some embodiments, the corresponding acquisition period for a potentially risky vehicle may be less than [a certain value]. Figure 2 The preset data collection cycle described in the document applies to all target vehicles.

[0132] In some embodiments, the corresponding data collection period for a potentially risky vehicle may be related to the thermal risk coefficient of the potentially risky vehicle; the higher the thermal risk coefficient, the shorter the corresponding data collection period.

[0133] Step S530: Control the target temperature measurement camera to collect and upload temperature data of potentially risky vehicles according to the corresponding collection cycle.

[0134] In some embodiments, the emergency monitoring and management platform can control the target temperature measurement camera to collect temperature data of potentially hazardous vehicles at regular intervals and upload the temperature data to the platform. When multiple target temperature measurement cameras are present, the platform can select the camera closest to the potentially hazardous vehicle to collect temperature data, or it can fuse the temperature data collected from multiple cameras to obtain the final temperature data. Data fusion methods may include, but are not limited to, averaging.

[0135] The method for collecting temperature data from potentially risky vehicles is similar to the method for collecting temperature data from target vehicles, as described in the aforementioned step S210.

[0136] In some embodiments of this specification, by collecting temperature data of potentially risky vehicles based on their location information and corresponding collection cycles, it is possible to achieve graded monitoring of vehicles with different risk levels. That is, the collection frequency of temperature data for target vehicles with potential risks is increased for focused monitoring, while low-risk vehicles (i.e., non-potential risk vehicles) are monitored routinely. This can improve the accuracy of monitoring potentially risky vehicles, achieve efficient utilization of monitoring resources, and enable refined monitoring of potentially risky vehicles.

[0137] Some embodiments of this specification also provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the static vehicle emergency monitoring method based on the Internet of Things large model as described in any of the above embodiments.

[0138] The basic concepts have been described above. It is clear that the detailed disclosure above is merely illustrative and does not constitute a limitation of the present invention. Although not explicitly stated herein, various modifications, improvements, and corrections may be made to the present invention by those skilled in the art. Such modifications, improvements, and corrections are suggested in this invention and therefore remain within the spirit and scope of the exemplary embodiments of the present invention.

[0139] This invention uses specific terms to describe embodiments of the invention. For example, "some embodiments" refers to a particular feature, structure, or characteristic associated with at least one embodiment of the invention. Furthermore, certain features, structures, or characteristics in one or more embodiments of the invention can be appropriately combined.

[0140] Finally, it should be understood that the embodiments described in this invention are merely illustrative of the principles of the invention. Other modifications may also fall within the scope of this invention. Therefore, alternative configurations of the embodiments of this invention are considered as examples and not limitations, and are regarded as consistent with the teachings of this invention. Accordingly, the embodiments of this invention are not limited to those explicitly described and illustrated herein.

Claims

1. A stationary vehicle emergency monitoring system based on an Internet of Things (IoT) big data model, characterized in that, Including an emergency monitoring and management platform; The emergency monitoring and management platform is configured as follows: Based on the temperature measurement camera, the temperature data of the target vehicle in the preset space is collected according to the preset collection cycle; Based on the temperature data, a temperature distribution cloud map of the target vehicle is constructed; Based on the temperature distribution cloud map, the temperature information of the battery pack area of ​​the target vehicle is determined; Based on the temperature information, the thermal risk coefficient of the target vehicle is determined; Based on the aforementioned thermal risk coefficient, vehicles at risk are identified; The warning frequency is determined based on the thermal risk coefficient and temperature data of the risky vehicle. The warning lights in the control room flash at the warning frequency.

2. The system as described in claim 1, characterized in that, The emergency monitoring and management platform is further configured as follows: Based on the temperature data of the first reference vehicle of the target vehicle, the ambient reference temperature of the target vehicle is determined, wherein the first reference vehicle is other target vehicles within a first neighborhood of the target vehicle. Based on the ambient reference temperature and the temperature information of the battery pack area, abnormal temperature information of the battery pack area of ​​the target vehicle is determined; Based on the abnormal temperature information of the battery pack area, the thermal risk coefficient of the target vehicle is determined.

3. The system as described in claim 2, characterized in that, The emergency monitoring and management platform is further configured as follows: Obtain the vehicle identity information of the risk vehicle and the second reference vehicle of the risk vehicle, wherein the second reference vehicle is another target vehicle within the second neighborhood range of the risk vehicle; Based on the vehicle identity information, determine the owner information of the risk vehicle and the second reference vehicle; A neighborhood warning message is generated, and based on the vehicle owner information, the neighborhood warning message is sent to the vehicle owner terminals of the risk vehicle and the second reference vehicle.

4. The system as described in claim 1, characterized in that, The emergency monitoring and management platform is further configured as follows: Based on the location information of potentially risky vehicles, a target temperature measurement camera is determined. The potentially risky vehicle is the target vehicle whose thermal risk coefficient is greater than the second risk threshold and not greater than the first risk threshold. Based on the thermal risk coefficient of the potential risk vehicle, the corresponding data collection period for the potential risk vehicle is determined; The target temperature measurement camera is controlled to collect and upload the temperature data of the potentially risky vehicle according to the corresponding collection cycle.

5. A method for emergency monitoring of stationary vehicles based on a large-scale Internet of Things (IoT) model, characterized in that, The method is executed by the emergency monitoring and management platform in the stationary vehicle emergency monitoring system based on an IoT big data model, and the method includes: Based on the temperature measurement camera, the temperature data of the target vehicle in the preset space is collected according to the preset collection cycle; Based on the temperature data, a temperature distribution cloud map of the target vehicle is constructed; Based on the temperature distribution cloud map, the temperature information of the battery pack area of ​​the target vehicle is determined; Based on the temperature information, the thermal risk coefficient of the target vehicle is determined; Based on the aforementioned thermal risk coefficient, vehicles at risk are identified; The warning frequency is determined based on the thermal risk coefficient and temperature data of the risky vehicle. The warning lights in the control room flash at the warning frequency.

6. The method as described in claim 5, characterized in that, Determining the thermal risk coefficient of the target vehicle based on the temperature information includes: Based on the temperature data of the first reference vehicle of the target vehicle, the ambient reference temperature of the target vehicle is determined, wherein the first reference vehicle is other target vehicles within a first neighborhood of the target vehicle. Based on the ambient reference temperature and the temperature information of the battery pack area, abnormal temperature information of the battery pack area of ​​the target vehicle is determined; Based on the abnormal temperature information of the battery pack area, the thermal risk coefficient of the target vehicle is determined.

7. The method as described in claim 6, characterized in that, The method further includes: Obtain the vehicle identity information of the risk vehicle and the second reference vehicle of the risk vehicle, wherein the second reference vehicle is another target vehicle within the second neighborhood range of the risk vehicle; Based on the vehicle identity information, determine the owner information of the risk vehicle and the second reference vehicle; A neighborhood warning message is generated, and based on the vehicle owner information, the neighborhood warning message is sent to the vehicle owner terminals of the risk vehicle and the second reference vehicle.

8. The method as described in claim 5, characterized in that, The method further includes: Based on the location information of potentially risky vehicles, a target temperature measurement camera is determined. The potentially risky vehicle is the target vehicle whose thermal risk coefficient is greater than the second risk threshold and not greater than the first risk threshold. Based on the thermal risk coefficient of the potential risk vehicle, the corresponding data collection period for the potential risk vehicle is determined; The target temperature measurement camera is controlled to collect and upload the temperature data of the potentially risky vehicle according to the corresponding collection cycle.

9. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When the computer reads the computer instructions from the storage medium, the computer executes the stationary vehicle emergency monitoring method based on the Internet of Things large model as described in claim 5.

Images