Charging early warning method based on AI intelligent analysis

Abstract

The invention discloses a charging early warning method based on AI intelligent analysis. The charging early warning method comprises the following steps: acquiring multi-dimensional time sequence data; wherein the multi-dimensional time sequence data comprises at least two of battery voltage, battery current, battery temperature, charging equipment state data and environment temperature; inputting the multi-dimensional time series data into an intelligent analysis model to obtain health state information and risk feature information; according to the health state information and the risk feature information, judging whether an early warning triggering condition is met; and if yes, generating a target early warning instruction. According to the technical scheme of the embodiment of the invention, the accuracy of battery charging early warning can be improved, the false alarm rate is reduced, and early and accurate risk prevention is realized.

Description

Technical Field

[0001] This invention relates to the field of battery safety management technology, and in particular to a charging early warning method based on AI intelligent analysis. Background Technology

[0002] With the widespread adoption of electric vehicles and portable electronic devices, rechargeable batteries such as lithium-ion batteries are increasingly used. However, batteries pose safety risks during charging, including overheating, overcharging, and internal short circuits, which can lead to fires or explosions, seriously threatening life and property. Traditional charging warning methods are mostly based on simple voltage or current threshold judgments, lacking insight into the coupled effects of multiple factors and the gradual degradation of battery performance. These methods suffer from low accuracy and high false alarm rates, failing to achieve early and accurate risk prevention. Summary of the Invention

[0003] This invention provides a charging early warning method based on AI intelligent analysis to achieve early warning of the battery charging process, effectively improving charging safety and battery life.

[0004] According to one aspect of the present invention, a charging early warning method based on AI intelligent analysis is provided, comprising: Acquire multi-dimensional time-series data; wherein, the multi-dimensional time-series data includes at least two of the following: battery voltage, battery current, battery temperature, charging device status data, and ambient temperature; The multi-dimensional time-series data is input into the intelligent analysis model to obtain health status information and risk characteristic information; Based on the health status information and the risk characteristic information, determine whether the early warning triggering conditions are met; If so, a target warning command will be generated.

[0005] Furthermore, the intelligent analysis model includes a recurrent neural network model, a long short-term memory network model, or a temporal convolutional network model.

[0006] Furthermore, the intelligent analysis model is trained through the following steps: Acquire historical multi-dimensional time-series data and historical status information; The target historical multi-dimensional time series data is obtained by preprocessing the historical multi-dimensional time series data. The intelligent analysis model is obtained by training the neural network model using the target's historical multi-dimensional time-series data and the historical state information.

[0007] Furthermore, according to the above, inputting the multi-dimensional time-series data into the intelligent analysis model to obtain health status information and risk characteristic information includes: using the intelligent analysis model to extract features from the multi-dimensional time-series data to obtain target status information and target fault values.

[0008] Furthermore, based on the health status information and the risk characteristic information, it is determined whether the early warning triggering conditions are met, including: If the health status information is lower than a preset health threshold, and / or the risk characteristic information is higher than a preset risk threshold, then the warning triggering condition is met.

[0009] Furthermore, according to the target warning instruction, the instructions include: sending warning information, issuing audible and visual alarms, reducing charging power, and actively cutting off the charging circuit.

[0010] Furthermore, the method also includes: recording the multi-dimensional time-series data, the health status information, and the risk characteristic information into a database for optimizing the intelligent analysis model.

[0011] According to another aspect of the present invention, a charging early warning device based on AI intelligent analysis is provided, comprising: A multi-dimensional time-series data acquisition module is used to acquire multi-dimensional time-series data; wherein, the multi-dimensional time-series data includes at least two of the following: battery voltage, battery current, battery temperature, charging device status data, and ambient temperature; The intelligent analysis model processing module is used to input the multi-dimensional time-series data into the intelligent analysis model to obtain health status information and risk characteristic information. The early warning triggering condition judgment module is used to determine whether the early warning triggering condition is met based on the health status information and the risk characteristic information. The target warning instruction generation module is used to generate a target warning instruction if the condition is met.

[0012] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the charging warning method based on AI intelligent analysis as described in any embodiment of the present invention.

[0013] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions. The computer instructions are configured to cause a processor to execute and implement the AI-based intelligent analysis-based charging warning method described in any embodiment of the present invention.

[0014] The technical solution of the present invention has the following beneficial effects: First, multi-dimensional time-series data is acquired, and then input into an intelligent analysis model to obtain health status information and risk characteristic information. Based on the health status information and risk characteristic information, it is determined whether the early warning triggering conditions are met; if so, a target early warning instruction is generated. The technical solution of this invention can improve the accuracy of battery charging early warning, reduce the false alarm rate, and achieve early and accurate risk prevention. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of a charging early warning method based on AI intelligent analysis provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of another charging early warning method based on AI intelligent analysis provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the structure of a charging early warning device based on AI intelligent analysis provided in Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0017] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0018] It should be noted that the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.

[0019] Example 1 Figure 1 This is a flowchart of a charging early warning method based on AI intelligent analysis provided in Embodiment 1 of the present invention. This embodiment of the invention is applicable to situations with high demands for charging safety, device lifespan, and intelligent management. The method can be executed by an AI intelligent analysis-based charging device, which can be implemented in software and / or hardware and is generally integrated into electronic devices. This embodiment of the invention does not limit the specific type of electronic device. Correspondingly, as... Figure 1 As shown, the method includes the following operations: S110. Obtain multi-dimensional time-series data; wherein, the multi-dimensional time-series data includes at least two of the following: battery voltage, battery current, battery temperature, charging device status data, and ambient temperature.

[0020] The multi-dimensional time-series data can represent the battery's current charging state. Battery voltage can be the operating voltage sampled every 100ms using a high-precision voltage divider resistor network. Battery current can be the operating current sampled using a Hall effect current sensor. Battery temperature can be the real-time temperature collected by a temperature measuring device integrated within the battery pack. Charging device status data can include parameters such as the battery's operating frequency, fan speed, and relay status. Ambient temperature can be the external temperature sampled every 500ms by a digital sensor. In essence, the battery's charging state can be determined by data from multiple dimensions.

[0021] For example, acquiring multi-dimensional time-series data can be achieved by measuring the battery's current and voltage using an ammeter or voltmeter, obtaining the battery temperature using a temperature sensor, or obtaining the ambient temperature using an infrared sensor. In this embodiment of the invention, the method of acquiring multi-dimensional time-series data is not limited; any method capable of obtaining data representing the battery's current charging state can be used.

[0022] S120. Input the multi-dimensional time series data into the intelligent analysis model to obtain health status information and risk characteristic information.

[0023] The intelligent analysis model can be any network model capable of capturing time-series features and processing dynamically changing data. Health status information can be data representing the battery's health condition. Risk characteristic information can be data representing the risk level of potential safety hazards in the battery; easily understood, risk characteristic information can be data generated during sudden temperature increases or abnormal voltage fluctuations.

[0024] In this embodiment of the invention, multi-dimensional time-series data can be used as input data for an intelligent analysis model, and the model can be analyzed and processed to obtain the health status characteristics and risk characteristics of the battery during charging. In this embodiment of the invention, the type of intelligent analysis model is not limited.

[0025] S130. Based on the health status information and the risk characteristic information, determine whether the early warning triggering conditions are met.

[0026] Among them, the warning triggering condition can be a judgment condition used to determine whether the battery in the charging process poses a safety hazard.

[0027] For example, a warning could be triggered when the battery health status information during charging is lower than a standard value. Alternatively, a warning could be triggered when the battery risk characteristic information during charging is higher than a standard value. In this embodiment of the invention, the specific method for determining the warning trigger condition is not limited.

[0028] S140. If so, generate a target warning command.

[0029] Among them, the target warning instruction can be a warning instruction used to remind the user that the currently charging battery has a safety hazard.

[0030] In this embodiment of the invention, if the health status information and risk characteristic information obtained through intelligent analysis meet the early warning triggering conditions, a target early warning instruction is generated. This instruction can be sent as text / graphic warning content to users or management / maintenance personnel via APP push notifications, SMS messages, or device screen displays. Alternatively, it can be indicated by a prompt sound from the battery charging device's built-in speaker and / or flashing LED indicators. It can also reduce the battery load by adjusting the charging device's output parameters; adjusting the output parameters can involve reducing the current. Finally, it can physically disconnect the battery from the power source and terminate the charging process by using a relay or circuit breaker that triggers the charging device.

[0031] The technical solution of this invention first acquires multi-dimensional time-series data, including at least two of the following: battery voltage, battery current, battery temperature, charging device status data, and ambient temperature. Then, the multi-dimensional time-series data is input into an intelligent analysis model to obtain health status information and risk characteristic information. Subsequently, based on the health status information and risk characteristic information, it is determined whether the early warning triggering conditions are met; if so, a target early warning command is generated. This invention can improve the accuracy of battery charging early warnings, reduce false alarm rates, and achieve early and accurate risk prevention.

[0032] Example 2 Figure 2 This is a flowchart of another charging early warning method based on AI intelligent analysis provided in Embodiment 2 of the present invention. This embodiment is a specific embodiment based on the above embodiment. In this embodiment, various specific optional implementation methods are given for determining whether the early warning triggering conditions are met based on health status information and risk characteristic information. Correspondingly, as Figure 2 As shown, the method in this embodiment may include: S210, Obtain multi-dimensional time series data.

[0033] In this embodiment of the invention, while the battery is charging, multiple state indicators of the battery are collected to obtain multi-dimensional time-series data. It is easy to understand that a battery is a multi-parameter coupled system, and its health status is affected by multiple factors; a single data point cannot fully reflect the actual operating state. Therefore, obtaining multi-dimensional time-series data facilitates subsequent cross-validation and addresses the limitations of single-parameter monitoring.

[0034] S220. Input the multi-dimensional time-series data into the intelligent analysis model to obtain health status information and risk characteristic information.

[0035] Optionally, the intelligent analysis model may include a recurrent neural network model, a long short-term memory network model, or a temporal convolutional network model.

[0036] Among these, recurrent neural network models can be deep learning models capable of processing time-series data, accurately predicting future trends in battery state changes based on the changing trends of multi-dimensional time-series data. Long short-term memory network models can be deep learning models capable of efficiently processing time-series data, focusing on meaningful multi-dimensional time-series data while ignoring irrelevant data interference, thus predicting future trends in battery state changes more efficiently and accurately. Temporal convolutional network models can utilize the sliding of convolutional kernels in neural networks to capture the changing trends of multi-dimensional time-series data.

[0037] In this embodiment of the invention, the intelligent analysis model can be a temporal convolutional network model. When analyzing battery temperature data, the intelligent analysis model can capture short-term battery temperature fluctuations and identify battery temperature change trends over several consecutive hours through multi-layer convolution operations.

[0038] The intelligent analysis model is trained through the following steps: Acquire historical multi-dimensional time-series data and historical status information; The target historical multi-dimensional time series data is obtained by preprocessing the historical multi-dimensional time series data. The intelligent analysis model is obtained by training the neural network model using the target's historical multi-dimensional time-series data and the historical state information.

[0039] The historical multi-dimensional time-series data can be standard rechargeable battery status data. For example, historical multi-dimensional time-series data can include battery voltage, battery current, battery temperature, and other battery status data during the battery's healthy state. Historical status information can be a label of the battery's operating status, combining historical fault records and expert judgment. The target historical multi-dimensional time-series data can be status data that accurately displays the battery's charging status, obtained by cleaning the historical multi-dimensional time-series data.

[0040] In an optional embodiment of the present invention, a measuring device can be used to acquire the individual cell voltage (100ms / acquisition per cell), charging / discharging current (1kHz / acquisition), and battery surface temperature of the rechargeable battery. Simultaneously, historical fault records and expert judgment are needed to determine the battery operating state corresponding to the current individual cell voltage, charging / discharging current, and battery surface temperature, and this information is used as historical state information.

[0041] Furthermore, the individual cell voltage, charging / discharging current, and battery surface temperature are cleaned to obtain the target historical multi-dimensional time-series data. For example, obviously abnormal or invalid data and data missing due to sensor malfunctions can be removed from the historical multi-dimensional time-series data to obtain time-series data that can represent the battery charging status.

[0042] Furthermore, the target's historical multi-dimensional time-series data and historical state information are used as input data for the neural network model, and then fed into the neural network model for training to obtain an intelligent analysis model capable of analyzing battery charging warnings.

[0043] The step of inputting the multi-dimensional time-series data into the intelligent analysis model to obtain health status information and risk characteristic information includes: using the intelligent analysis model to extract features from the multi-dimensional time-series data to obtain target status information and target fault values.

[0044] The target status information can be indicator data showing that the rechargeable battery is in a faulty state. The target fault value can be a numerical value used to represent the degree of fault of the rechargeable battery.

[0045] In one embodiment of the present invention, multidimensional time-series data is sent as input data to the intelligent analysis model for feature extraction, thereby obtaining target state information and corresponding target fault values. For example, the target state information could be: a single cell voltage stable between 3.2-3.3V, a maximum voltage difference ≤0.05V, a battery surface temperature maintained at 26-28℃, a temperature difference ≤3℃ from the ambient temperature, and a temperature change rate <0.1℃ / min; in this case, the target fault value could be 0% (no risk). Alternatively, the target state information could be: the battery surface temperature rising from 5℃ to 8℃, a temperature change rate of 0.6℃ / min, an initial charging current of 180A, and a drop to 175A after 5 minutes; in this case, the target fault value could be 10%-30% (low risk). Another example is: during a single cell voltage drop from 3.8V to 3.6V, the voltage difference between the two cells widens to 0.2V (the voltage difference should be ≤0.15V during normal discharge), and the discharge current fluctuates between 15-16A; in this case, the target fault value could be 30%-60% (medium-high risk). Finally, the target state information could be: an abnormal increase in current + a temperature rise of 2℃ / min; in this case, the target fault value could be above 60% (high risk).

[0046] S230. If the health status information is lower than a preset health threshold, and / or the risk characteristic information is higher than a preset risk threshold, then the warning triggering condition is met.

[0047] The preset health threshold can be a value used to determine whether the battery's current health level is within a safe range. The preset risk threshold can be a value used to determine whether the battery's current health level falls within a range that poses a safety hazard.

[0048] In this embodiment of the invention, when the health status information is lower than a preset health threshold and the risk characteristic information is higher than a preset risk threshold, it can be determined that the current battery working state meets the warning triggering conditions.

[0049] S240. If so, generate a target warning instruction; wherein, according to the target warning instruction, the steps include: sending warning information, issuing an audible and visual alarm, reducing charging power, and actively cutting off the charging circuit.

[0050] In this embodiment of the invention, sending warning information can be done by sending text / graphic warning content to users or management / maintenance personnel via APP push, SMS, device screen display, etc., when the current battery operating state is low-risk. Alternatively, when the current battery operating state is medium-risk, the battery charging device can emit a warning sound via its built-in speaker, and / or flash an LED indicator. Furthermore, when the current battery operating state is medium-high-risk, the battery load can be reduced by adjusting the output parameters of the charging device; adjusting the output parameters can involve reducing the current. Finally, when the current battery operating state is high-risk, the connection between the battery and the power source can be physically disconnected by triggering a relay or circuit breaker on the charging device, thus terminating the charging process.

[0051] S250. After generating the target warning instruction, the method further includes: recording the multi-dimensional time-series data, the health status information, and the risk characteristic information into a database for optimizing the intelligent analysis model.

[0052] The database is a data warehouse used to store battery operating status data. It's easy to understand that the database, by comprehensively recording relevant data, provides a traceability basis for subsequent battery fault diagnosis and optimization.

[0053] Specifically, the health status information and risk characteristic information obtained through the intelligent analysis model can be stored in the database together with multi-dimensional time series data, which facilitates the optimization of the intelligent analysis model and further improves the efficiency and accuracy of charging warnings.

[0054] The technical solution of this invention first acquires multi-dimensional time-series data, including at least two of the following: battery voltage, battery current, battery temperature, charging device status data, and ambient temperature. This multi-dimensional time-series data is then used as input data for an intelligent analysis model to train the model, yielding health status information and risk characteristic information. If the health status information is below a preset health threshold, and / or the risk characteristic information is above a preset risk threshold, then the warning trigger condition is met. If so, a target warning instruction is generated, which may include: sending a warning message, issuing an audible and visual alarm, reducing charging power, or actively disconnecting the charging circuit. Finally, the multi-dimensional time-series data, health status information, and risk characteristic information are recorded in a database for further optimization of the intelligent analysis model. This invention enables precise matching of response intensity with health risk levels, avoiding both over-response affecting usability and under-response overlooking risks.

[0055] Example 3 Figure 3 This is a schematic diagram of a charging early warning device based on AI intelligent analysis provided in Embodiment 3 of the present invention, as shown below. Figure 3As shown, the device includes: a multi-dimensional time-series data acquisition module 310, an intelligent analysis model analysis and processing module 320, a warning trigger condition judgment module 330, and a target warning instruction generation module 340, wherein: The multi-dimensional time-series data acquisition module 310 is used to: acquire multi-dimensional time-series data; wherein the multi-dimensional time-series data includes at least two of the following: battery voltage, battery current, battery temperature, charging device status data, and ambient temperature.

[0056] The intelligent analysis model analysis and processing module 320 is used to: input the multi-dimensional time series data into the intelligent analysis model to obtain health status information and risk characteristic information.

[0057] The early warning triggering condition judgment module 330 is used to: determine whether the early warning triggering condition is met based on the health status information and the risk characteristic information.

[0058] The target warning instruction generation module 340 is used to generate a target warning instruction if the condition is met.

[0059] The technical solution of this invention first acquires multi-dimensional time-series data, then inputs the multi-dimensional time-series data into an intelligent analysis model to obtain health status information and risk characteristic information. Subsequently, based on the health status information and risk characteristic information, it is determined whether the early warning triggering conditions are met; if so, a target early warning instruction is generated. This invention can improve the accuracy of battery charging early warnings, reduce false alarm rates, and achieve early and accurate risk prevention.

[0060] Optionally, the intelligent analysis model may include a recurrent neural network model, a long short-term memory network model, or a temporal convolutional network model.

[0061] Optionally, the intelligent analysis model analysis and processing module 320 is specifically used for: acquiring historical multi-dimensional time-series data and historical state information; preprocessing the historical multi-dimensional time-series data to obtain target historical multi-dimensional time-series data; and training a neural network model using the target historical multi-dimensional time-series data and the historical state information to obtain the intelligent analysis model.

[0062] Optionally, the intelligent analysis model analysis and processing module 320 is further specifically used to: extract features from the multidimensional time series data using the intelligent analysis model to obtain target state information and target fault values.

[0063] Optionally, the warning triggering condition judgment module 330 is specifically used to: if the health status information is lower than a preset health threshold, and / or the risk characteristic information is higher than a preset risk threshold, then the warning triggering condition is met.

[0064] Optionally, the target warning instruction generation module 340 is specifically used for: sending warning information, issuing audible and visual alarms, reducing charging power, and actively cutting off the charging circuit.

[0065] Optionally, the charging warning device based on AI intelligent analysis also includes a storage module, specifically used to record the multi-dimensional time-series data, the health status information, and the risk characteristic information into a database for optimizing the intelligent analysis model.

[0066] The aforementioned AI-based intelligent analysis-based charging early warning device can execute the AI-based intelligent analysis-based charging early warning method provided in any embodiment of the present invention, and possesses the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the event handling method provided in any embodiment of the present invention.

[0067] Example 4 Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0068] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0069] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0070] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a charging warning method based on AI intelligent analysis.

[0071] In some embodiments, the event handling method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the event handling method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured by any other suitable means (e.g., by means of firmware) to perform a charging warning method based on AI intelligent analysis.

[0072] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0073] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0074] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0075] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0076] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0077] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

Claims

1. A charging early warning method based on AI intelligent analysis, characterized in that, include: Acquire multi-dimensional time-series data; wherein, the multi-dimensional time-series data includes at least two of the following: battery voltage, battery current, battery temperature, charging device status data, and ambient temperature; The multi-dimensional time-series data is input into the intelligent analysis model to obtain health status information and risk characteristic information; Based on the health status information and the risk characteristic information, determine whether the early warning triggering conditions are met; If so, a target warning command will be generated.

2. The method according to claim 1, characterized in that, The intelligent analysis model includes a recurrent neural network model, a long short-term memory network model, or a temporal convolutional network model.

3. The method according to claim 2, characterized in that, The intelligent analysis model is trained using the following steps: Acquire historical multi-dimensional time-series data and historical status information; The target historical multi-dimensional time series data is obtained by preprocessing the historical multi-dimensional time series data. The intelligent analysis model is obtained by training the neural network model using the target's historical multi-dimensional time-series data and the historical state information.

4. The method according to claim 1, characterized in that, The process of inputting the multi-dimensional time-series data into an intelligent analysis model to obtain health status information and risk characteristic information includes: using the intelligent analysis model to extract features from the multi-dimensional time-series data to obtain target status information and target fault values.

5. The method according to claim 1, characterized in that, Based on the health status information and the risk characteristic information, determine whether the early warning triggering conditions are met, including: If the health status information is lower than a preset health threshold, and / or the risk characteristic information is higher than a preset risk threshold, then the warning triggering condition is met.

6. The method according to claim 1, characterized in that, According to the target warning instructions, the instructions include: sending warning information, issuing audible and visual alarms, reducing charging power, and actively cutting off the charging circuit.

7. The method according to claim 1, characterized in that, The method further includes: recording the multi-dimensional time-series data, the health status information, and the risk characteristic information into a database for optimizing the intelligent analysis model.

8. A charging early warning device based on AI intelligent analysis, characterized in that, include: A multi-dimensional time-series data acquisition module is used to acquire multi-dimensional time-series data; wherein, the multi-dimensional time-series data includes at least two of the following: battery voltage, battery current, battery temperature, charging device status data, and ambient temperature; The intelligent analysis model processing module is used to input the multi-dimensional time-series data into the intelligent analysis model to obtain health status information and risk characteristic information. The early warning triggering condition judgment module is used to determine whether the early warning triggering condition is met based on the health status information and the risk characteristic information. The target warning instruction generation module is used to generate a target warning instruction if the condition is met.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images