Method and device for detecting short-circuit fault in vehicle lithium battery, medium, terminal and program product

Abstract

The invention provides a vehicle lithium battery internal short circuit fault detection method and device, a medium, a terminal and a program product. The method comprises the steps of obtaining average voltage data and minimum voltage data; extracting the first charging data slot based on an extraction starting condition and an extraction ending condition, and extracting a second charging data slot at an extraction frequency within an extraction period based on the extraction starting condition; respectively calculating a first voltage difference average value and a second voltage difference average value, and then calculating a voltage difference ratio of the two values; and according to the first voltage difference average value, the second voltage difference average value, the voltage difference ratio and the minimum voltage sequence in the second charging data segment, constructing an internal short circuit fault detection model based on a long and short time memory network model, and deploying the internal short circuit fault detection model to output a current internal short circuit fault detection result. According to the invention, the internal short-circuit fault of the lithium battery can be detected under a conventional charging condition, and the accuracy and reliability of internal short-circuit fault detection are improved.

Description

Technical Field

[0001] This application relates to the field of new energy vehicle technology, and in particular to a method, device, medium, terminal and program product for detecting internal short circuit faults in vehicle lithium batteries. Background Technology

[0002] Lithium-ion batteries, due to their high energy density, long cycle life, and environmental friendliness, have been widely used in electric vehicles, energy storage power stations, aerospace, and consumer electronics. However, with the continuous improvement of energy density and the rapid expansion of application scale, safety accidents involving lithium-ion batteries, especially thermal runaway caused by internal short circuits, have become a hindrance to the further development of the industry. An internal short circuit in a lithium-ion battery refers to the phenomenon where direct contact occurs between the positive and negative electrodes inside the battery or between the positive and negative electrodes and the battery casing, causing a short circuit and current to flow. Initially, it may only manifest as weak abnormal electrochemical behavior, but if not detected in time, it will gradually evolve into a violent exothermic reaction, eventually leading to thermal runaway, causing fires or even explosions.

[0003] Currently, the industry lacks mature and standardized technical solutions for proactive early warning of internal short circuits, and most commercial battery management systems (BMS) do not integrate dedicated internal short circuit detection functions. Existing main detection technologies include the following:

[0004] (1) Detection method based on self-discharge rate: This method utilizes the characteristic that internal short circuits form additional self-discharge channels. It identifies faults by monitoring the voltage drop rate (i.e., self-discharge rate) of the battery during long-term static storage. Specifically, the BMS continuously monitors the voltage of individual cells and calculates their voltage drop rate. If the battery has an internal short circuit, its self-discharge rate during long-term static storage will be significantly higher than that of a normal battery, thus detecting whether the battery has an internal short circuit. However, this method requires a long static storage time, making it difficult to adapt to highly random usage scenarios such as new energy vehicles. Furthermore, this method is not sensitive to small internal short circuits, resulting in a large detection error.

[0005] (2) Incremental capacity analysis method: During constant current charging, dQ / dV (incremental capacity) or dV / dQ (differential voltage) is calculated and compared with the baseline curve of its health state to identify the characteristic shift caused by short circuit in the battery. However, this method is computationally complex, requires high-precision voltage and current sampling, and is usually carried out under steady-state conditions such as slow charging below 0.1C, which is seriously inconsistent with the actual operating conditions of electric vehicle fast charging and dynamic load, and is difficult to be effectively applied to new energy vehicles.

[0006] (3) Battery voltage consistency analysis method: By calculating the range or standard deviation of the voltage of all cells in the battery pack in real time, if the voltage of a certain cell starts to "fall behind" (falls faster during discharge and rises more slowly during charging), an early warning is issued. However, this method does not have a clear fault judgment threshold, and it is easy to count failures when multiple batteries are at risk, leading to missed or false alarms.

[0007] Therefore, existing technologies rely on long periods of inactivity, have insufficient sensitivity, limited applicability, and poor prediction accuracy. It is necessary to provide a method, device, medium, terminal, and program product for detecting short circuit faults in vehicle lithium batteries to solve the above-mentioned problems in existing technologies. Summary of the Invention

[0008] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a method, device, medium, terminal and program product for detecting short circuit faults in vehicle lithium batteries, in order to solve the technical problems of the prior art that rely on long-term static placement, insufficient sensitivity, limited applicable scenarios and poor prediction accuracy.

[0009] To achieve the above and other related objectives, the first aspect of this application provides a method for detecting internal short-circuit faults in a vehicle lithium battery, comprising:

[0010] Collect the voltage data of individual cells of the vehicle's lithium battery, and process the individual cell voltage data to obtain average voltage data and minimum voltage data;

[0011] A first charging data segment is extracted based on preset start and end extraction conditions. The first charging data segment records the voltage difference data between the average voltage data and the minimum voltage data. A second charging data segment is extracted based on the preset start extraction conditions within a preset extraction period at a preset extraction frequency. The second charging data segment records the minimum voltage sequence within the extraction period.

[0012] Calculate the first average voltage difference based on the voltage difference data in the first charging data segment, and calculate the second average voltage difference within a preset time range after the end extraction condition; and calculate the voltage difference ratio based on the first average voltage difference and the second average voltage difference.

[0013] The average value of the first voltage difference, the average value of the second voltage difference, the voltage difference ratio, and the minimum voltage sequence in the second charging data segment are preprocessed and input into a long short-time memory network model for training to construct an internal short-circuit fault detection model.

[0014] The internal short-circuit fault detection model is deployed to output the current internal short-circuit fault detection results of the vehicle's lithium battery.

[0015] In some embodiments of the first aspect of this application, the specific training process of the internal short-circuit fault detection model includes: normalizing the first average voltage difference, the second average voltage difference, the voltage difference ratio, and the minimum voltage sequence in the second charging data segment, and converting the normalized minimum voltage sequence into a tensor of a preset shape; inputting the tensor of the preset shape into a first long short-term memory network layer to extract primary temporal features to output a first hidden state sequence for all time steps; inputting the first hidden state sequence output by the first long short-term memory network layer into a second long short-term memory network layer for processing to output a second hidden state sequence for all time steps; inputting the second hidden state sequence output by the second long short-term memory network layer into a third long short-term memory network layer for processing to output a final feature sequence; converting the final feature sequence into a temporal feature vector based on the accessed global pooling layer; concatenating the temporal feature vector with the first average voltage difference, the second average voltage difference, and the voltage difference ratio to obtain a fused feature vector; and outputting the current vehicle lithium battery internal short-circuit fault detection result as normal or faulty based on the fused feature vector.

[0016] In some embodiments of the first aspect of this application, after collecting the individual cell voltage data of the vehicle lithium battery and processing the individual cell voltage data to obtain average voltage data and minimum voltage data, the method further includes: if the initial average voltage data is detected to be higher than a preset threshold, the process exits directly; if the average voltage data is detected to be lower than the preset threshold and the SOC data increases by 20%, the process proceeds to the subsequent extraction of charging data segments.

[0017] In some embodiments of the first aspect of this application, the preset start extraction condition is: within a continuous preset time period, the average voltage data is between 3300 mV and 3400 mV and the voltage difference between the average voltage data and the minimum voltage data is greater than 15 mV.

[0018] In some embodiments of the first aspect of this application, the preset end extraction condition is: within a continuous preset time period, the voltage difference between the average voltage data and the minimum voltage data is less than or equal to 15 millivolts.

[0019] In some embodiments of the first aspect of this application, if the average voltage data is detected to be between 3300 and 3400 millivolts, and the voltage difference between the average voltage data and the minimum voltage data is greater than 15 millivolts and not continuous within a preset time, the lithium battery of the current vehicle is determined to be normal.

[0020] To achieve the above and other related objectives, a second aspect of this application provides a vehicle lithium battery internal short-circuit fault detection device, comprising:

[0021] The acquisition module is used to acquire the voltage data of individual cells of the vehicle's lithium battery, and process the individual cell voltage data to obtain average voltage data and minimum voltage data.

[0022] The charging data segment extraction module is used to extract a first charging data segment based on preset start extraction conditions and end extraction conditions. The first charging data segment records the voltage difference data between the average voltage data and the minimum voltage data. Based on the preset start extraction conditions, the module extracts a second charging data segment within a preset extraction period at a preset extraction frequency. The second charging data segment records the minimum voltage sequence within the extraction period.

[0023] The calculation module is used to calculate a first average voltage difference based on the voltage difference data in the first charging data segment, and to calculate a second average voltage difference within a preset time range after the end extraction condition; and to calculate the voltage difference ratio based on the first average voltage difference and the second average voltage difference.

[0024] The model building module is used to preprocess the first average voltage difference, the second average voltage difference, the voltage difference ratio, and the minimum voltage sequence in the second charging data segment and input them into the long short-time memory network model for training, so as to build an internal short-circuit fault detection model.

[0025] The model deployment module is used to deploy the internal short-circuit fault detection model and output the current internal short-circuit fault detection results of the vehicle lithium battery.

[0026] To achieve the above and other related objectives, a third aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method.

[0027] To achieve the above and other related objectives, a fourth aspect of this application provides a computer program product comprising computer program code that, when executed on a computer, causes the computer to implement the method.

[0028] To achieve the above and other related objectives, a fifth aspect of this application provides an electronic terminal, including a memory, a processor, and a computer program stored in the memory; the processor executes the computer program to implement the method.

[0029] As described above, the vehicle lithium battery internal short circuit fault detection method, device, medium, terminal, and program product of this application have the following beneficial effects:

[0030] By collecting and processing the voltage data of individual cells of the vehicle's lithium battery during the charging phase, average voltage data and minimum voltage data are obtained. The average voltage data and minimum voltage data are continuously monitored. When a preset start extraction condition is met, the first charging data segment is extracted, and the second charging data segment is extracted at a preset extraction frequency. The extraction of the first charging data segment ends when a preset end extraction condition is met, and the extraction of the second charging data segment ends when a preset extraction cycle is reached. Then, the first average voltage difference is calculated based on the voltage difference data of the average voltage data and minimum voltage data recorded in the first charging data segment, and the second average voltage difference is calculated within a preset time range after the end extraction condition. The voltage difference ratio is calculated based on the first average voltage difference and the second average voltage difference. The first average voltage difference, the second average voltage difference, the voltage difference ratio, and the minimum voltage sequence recorded in the second charging data segment are preprocessed and input into a long short-term memory network model for training to construct an internal short-circuit fault detection model. This model is used to output the current vehicle lithium battery internal short-circuit fault detection result, thereby realizing the detection of lithium battery internal short-circuit faults under normal charging conditions and improving the accuracy and reliability of internal short-circuit fault detection. Attached Figure Description

[0031] Figure 1 The diagram shown is a flowchart illustrating a method for detecting internal short-circuit faults in a vehicle lithium battery according to an embodiment of this application.

[0032] Figure 2 The diagram shown illustrates the working principle of a vehicle lithium battery internal short-circuit fault detection method according to an embodiment of this application.

[0033] Figure 3 The diagram shows a flowchart illustrating the specific training process of an internal short-circuit fault detection model in one embodiment of this application.

[0034] Figure 4 The diagram shown is a schematic diagram of collecting voltage data of a vehicle lithium battery in one embodiment of this application.

[0035] Figure 5 The diagram shown is a schematic diagram of fault identification based on an internal short-circuit fault detection model in one embodiment of this application.

[0036] Figure 6 The diagram shown is a block diagram of a short-circuit fault detection device for a vehicle lithium battery according to an embodiment of this application.

[0037] Figure 7 The diagram shown is a structural schematic of an electronic terminal according to an embodiment of this application. Detailed Implementation

[0038] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0039] In the embodiments of this application, terms such as "first" and "second" are used to distinguish identical or similar items with essentially the same function and effect. For example, "first XX" and "second XX" are merely used to distinguish different XXs and do not limit their order. Those skilled in the art will understand that terms such as "first" and "second" do not limit the quantity or execution order, and that "first" and "second" do not necessarily imply that they are different.

[0040] It should be noted that, in the embodiments of this application, the words "exemplary" or "for example" indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0041] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0042] Before providing a further detailed description of the present invention, the nouns and terms used in the embodiments of the present invention are explained, and the nouns and terms used in the embodiments of the present invention are subject to the following interpretations:

[0043] <1> Long Short Term Memory (LSTM) network model: It is a special type of recurrent neural network (RNN) designed to solve the gradient vanishing and gradient explosion problems of traditional RNNs when processing long sequence data. It achieves selective memory and forgetting of information by introducing forget gate, input gate, and output gate, as well as cell state, thereby better capturing long-term dependencies in the sequence.

[0044] <2> SOC (State of Charge) data is an important term in battery management, referring to the percentage of the battery's remaining charge relative to its nominal capacity. It reflects the battery's state of charge and is expressed as a percentage between the current available charge and the nominal capacity when the battery is fully charged.

[0045] To facilitate understanding of the embodiments of this application, in conjunction with Figure 1 and Figure 2 Detailed explanation. Figure 1 A flowchart illustrating a method for detecting internal short-circuit faults in a vehicle lithium battery according to an embodiment of the present invention is shown. Figure 2 This illustration shows a schematic diagram illustrating the working principle of a vehicle lithium battery internal short-circuit fault detection method according to an embodiment of the present invention. The vehicle lithium battery internal short-circuit fault detection method in this embodiment includes the following steps:

[0046] Step S11: Collect the voltage data of individual cells of the vehicle's lithium battery, and process the individual cell voltage data to obtain average voltage data and minimum voltage data.

[0047] In some embodiments of this application, after collecting the individual cell voltage data of the vehicle lithium battery and processing the individual cell voltage data to obtain average voltage data and minimum voltage data, the process further includes: if the initial average voltage data is detected to be higher than a preset threshold, the process exits directly; if the average voltage data is detected to be lower than the preset threshold and the SOC data increases by 20%, the process proceeds to the subsequent extraction of charging data segments.

[0048] For example, the preset threshold is 3250 millivolts. At the start of charging, the battery management system monitors average voltage data, minimum voltage data, and SOC data. If the initial average voltage data (V) is detected... avg If the voltage is higher than 3250 millivolts, the process will exit directly without entering the fault determination process; if the initial average voltage data (V) is simultaneously met, the process will exit directly without entering the fault determination process. avg If the voltage is below 3250 mV and the SOC data increases by more than 20%, then the subsequent fault determination process will be initiated. This sets the preconditions for the subsequent fault determination process, saving resources and avoiding unnecessary fault determination resources.

[0049] Step S12: Extract a first charging data segment based on preset start and end extraction conditions. The first charging data segment records the voltage difference data between the average voltage data and the minimum voltage data. Based on the preset start extraction conditions, extract a second charging data segment within a preset extraction period at a preset extraction frequency. The second charging data segment records the minimum voltage sequence within the extraction period.

[0050] In some embodiments of this application, the preset start extraction condition is: within a continuous preset time period, the average voltage data is between 3300 mV and 3400 mV and the voltage difference between the average voltage data and the minimum voltage data is greater than 15 mV.

[0051] In some embodiments of this application, the preset end extraction condition is: within a continuous preset time period, the voltage difference between the average voltage data and the minimum voltage data is less than or equal to 15 millivolts.

[0052] In some embodiments of this application, if the average voltage data is detected to be between 3300 and 3400 millivolts, and the voltage difference between the average voltage data and the minimum voltage data is greater than 15 millivolts and not continuous within a preset time, the lithium battery of the current vehicle is determined to be normal.

[0053] It should be noted that existing methods based on battery voltage consistency analysis cannot detect internal short circuits when the lithium battery is not fully charged or discharged, nor can they guarantee the consistency of the degree of discharge at the end of each charge or discharge cycle. Furthermore, they cannot perform longitudinal comparisons of the voltage difference at the end of each charge or discharge cycle, thus failing to determine the severity of internal short circuits in lithium batteries. The internal short circuit fault detection method for vehicle lithium batteries proposed in this application selects a charging segment between 3300 mV and 3400 mV, which translates to approximately 30% to 50% of the State of Charge (SOC). This is a segment that is relatively easy to obtain in a conventional charging process. Simultaneously, due to the short length of the required charging timing data, it consumes less hardware storage and computing resources, making it suitable for integration into vehicle battery management systems (BMS). Moreover, analysis of historical data and actual battery pack disassembly revealed that the cells screened using this charging segment anomaly have an internal short circuit probability of over 70%, with no missed detections, thus avoiding both false positives and false negatives.

[0054] Specifically, as charging continues, the vehicle's lithium battery voltage gradually increases, and when the average voltage data (V) is monitored... avg If the voltage is not yet between 3300 mV and 3400 mV, the lithium battery is considered normal and does not require further fault diagnosis. When the average voltage data (V) is monitored... avg The voltage is between 3300 mV and 3400 mV and the average voltage data (V) is between 3300 mV and 3400 mV. avg) and minimum voltage data (V min If the voltage difference is greater than 15 millivolts, but does not occur continuously for a preset time (e.g., 10 seconds), the vehicle's lithium battery is considered normal, and no further fault diagnosis process is required. If charging stops during this period, no fault diagnosis is performed. When the average voltage data (V) is monitored... avg The voltage is between 3300 mV and 3400 mV and the average voltage data (V) is between 3300 mV and 3400 mV. avg ) and minimum voltage data (V min If the voltage difference is greater than 15 millivolts and occurs continuously for a preset time, such as 10 seconds, then the extraction of the first charging data segment will begin, and the extraction of the second charging data segment will begin at a preset extraction frequency.

[0055] As charging continues, the vehicle's lithium battery voltage plateaus, and the individual voltage differences decrease. When the average voltage data (V) is monitored... avg ) and minimum voltage data (V min If the voltage difference is less than or equal to 15 millivolts and occurs continuously for a preset time, such as 10 seconds, then the recording of the voltage difference data between the average voltage data and the minimum voltage data should be stopped, thus ending the extraction of the first charging data segment.

[0056] When the preset extraction period is reached, the recording of the minimum voltage sequence ends; that is, only the minimum voltage sequence within the preset extraction period is recorded as the second charging data segment. For example, the preset extraction frequency is recording one minimum voltage data point every 1 second, and the preset extraction period is 1000 seconds. When the average voltage data (V) is detected... avg The voltage is between 3300 mV and 3400 mV and the average voltage data (V) is between 3300 mV and 3400 mV. avg ) and minimum voltage data (V min If the voltage difference is greater than 15 millivolts and persists for 10 seconds, the battery management system begins storing the minimum voltage data, recording a minimum voltage value every second. Storage ends after 1000 seconds, thus ending the extraction of the second charging data segment. It should be noted that the actual sampling period is in milliseconds, and storage is completed after 1000 seconds of data. Testing shows that this time-series data extraction frequency of every second improves overall fault detection efficiency while reducing computational load. Step S13: Calculate the first average voltage difference based on the voltage difference data in the first charging data segment, and calculate the second average voltage difference within a pre-set time range after the extraction ends; and calculate the voltage difference ratio based on the first average voltage difference and the second average voltage difference.

[0057] Specifically, the first average voltage difference is calculated based on the voltage difference between the average voltage data and the minimum voltage data recorded in the first charging data segment. The specific calculation formula is as follows:

[0058] ;Formula (1)

[0059] Among them, V avg This is the average voltage data; V min This is the minimum voltage data; The total duration of the first charging data segment.

[0060] At the same time, when the average voltage data (V) is monitored avg ) and minimum voltage data (V min If the voltage difference is less than or equal to 15 millivolts and occurs continuously for 10 seconds, the difference between the average voltage data and the minimum voltage data is recorded within a preset time range, such as 60 seconds. The average value of the second voltage difference is then calculated according to formula (1). At this point, it has entered a stable period.

[0061] Based on the calculated average value of the first voltage difference Average value of the second voltage difference The voltage difference ratio was calculated. The specific formula is as follows:

[0062] ;Formula (2)

[0063] Step S14: Preprocess the first average voltage difference, the second average voltage difference, the voltage difference ratio, and the minimum voltage sequence in the second charging data segment, and input them into the long short-time memory network model for training to construct an internal short-circuit fault detection model.

[0064] In some embodiments of this application, such as Figure 3As shown, the specific training process of the internal short-circuit fault detection model includes: normalizing the first average voltage difference, the second average voltage difference, the voltage difference ratio, and the minimum voltage sequence in the second charging data segment, and converting the normalized minimum voltage sequence into a tensor of a preset shape; inputting the tensor of the preset shape into a first long short-term memory network layer to extract primary temporal features, so as to output the first hidden state sequence of all time steps; inputting the first hidden state sequence output by the first long short-term memory network layer into a second long short-term memory network layer for processing, so as to output the second hidden state sequence of all time steps; inputting the second hidden state sequence output by the second long short-term memory network layer into a third long short-term memory network layer for processing, so as to output the final feature sequence; and converting the final feature sequence into a temporal feature vector based on the accessed global pooling layer; concatenating the temporal feature vector with the first average voltage difference, the second average voltage difference, and the voltage difference ratio to obtain a fused feature vector; and outputting the current vehicle lithium battery internal short-circuit fault detection result as normal or faulty based on the fused feature vector.

[0065] In this embodiment, the Long Short-Term Memory (LSTM) network model is a three-layer network architecture: a first LSM layer with 64 neurons, a second LSM layer with 128 neurons, and a third LSM layer with 32 neurons. First, the input first average voltage difference, second average voltage difference, voltage difference ratio, and the minimum voltage sequence of length 1000 in the second charging data segment are normalized to eliminate dimensional differences. The dimensionless minimum voltage sequence is then converted into a tensor of a specific shape. This tensor data is input into the first LSM layer for processing to extract primary temporal features and output the first hidden state sequence for all time steps. The first hidden state sequence is then input into the second LSM layer for processing to extract higher-level temporal features. The system outputs the second hidden state sequence for all time steps; then, it inputs the second hidden state sequence into the third long short-term memory network layer for processing, which helps prevent overfitting, and outputs the final feature sequence; after the third long short-term memory network layer, a full pooling layer is connected to convert the final feature sequence into a temporal feature vector; the temporal feature vector is concatenated with the previously normalized average first voltage difference, average second voltage difference, and voltage difference ratio to obtain the fused feature vector; and the output layer outputs the binary classification of the current vehicle lithium battery short-circuit fault detection result, i.e., normal or fault.

[0066] Step S15: Deploy the internal short-circuit fault detection model to output the current internal short-circuit fault detection results of the vehicle lithium battery.

[0067] Specifically, the constructed internal short-circuit fault detection model is deployed in the battery management system to output the internal short-circuit fault detection results of the vehicle lithium battery based on the current input first voltage difference average value, second voltage difference average value, voltage difference ratio, and minimum voltage sequence in the second charging data segment. No additional hardware support is required, which improves the accuracy and reliability of fault detection.

[0068] Figure 4 A schematic diagram illustrating the collection of vehicle lithium battery voltage data according to an embodiment of this application is shown. Figure 4 As shown, the cell voltage data of the same set of vehicle lithium batteries was collected and processed to obtain... Figure 4 (a) Displays the maximum (max) voltage data, average (mean) voltage data, minimum (min) voltage data, and Figure 4 (b) Display the difference between the maximum and minimum voltage data, and the difference between the average and minimum voltage data, as the data basis for subsequent processes. Figure 4 The data fragments extracted from the area within the black box shown are used as input data for the Long Short-Term Memory Network model, making the input data easy to obtain and ensuring the accuracy of fault prediction.

[0069] Figure 5 This illustration shows a schematic diagram of fault identification based on an internal short-circuit fault detection model according to an embodiment of this application. For example... Figure 5 As shown, the internal short circuit fault detection model of this application was experimentally tested, and the accuracy of the prediction result of the internal short circuit (ISC) of lithium battery reached 92%, which meets the actual internal short circuit fault detection requirements.

[0070] Figure 6 This is a schematic block diagram of a vehicle lithium battery internal short-circuit fault detection device provided in an embodiment of this application. Figure 6 As shown, the vehicle lithium battery internal short circuit fault detection device 600 includes:

[0071] The acquisition module 601 is used to acquire the voltage data of individual cells of the vehicle lithium battery, and process the individual cell voltage data to obtain average voltage data and minimum voltage data.

[0072] The charging data segment extraction module 602 is used to extract a first charging data segment based on preset start extraction conditions and end extraction conditions. The first charging data segment records the voltage difference data between the average voltage data and the minimum voltage data. Based on the preset start extraction conditions, the module extracts a second charging data segment within a preset extraction period at a preset extraction frequency. The second charging data segment records the minimum voltage sequence within the extraction period.

[0073] The calculation module 603 is used to calculate a first average voltage difference based on the voltage difference data in the first charging data segment, and to calculate a second average voltage difference within a preset time range after the end extraction condition; and to calculate a voltage difference ratio based on the first average voltage difference and the second average voltage difference.

[0074] The model building module 604 is used to preprocess the first average voltage difference, the second average voltage difference, the voltage difference ratio, and the minimum voltage sequence in the second charging data segment and input them into the long short-time memory network model for training, so as to build an internal short-circuit fault detection model.

[0075] The model deployment module 605 is used to deploy the internal short-circuit fault detection model and output the current internal short-circuit fault detection results of the vehicle lithium battery.

[0076] It should be understood that the specific process of each module performing the above-mentioned steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0077] It should also be understood that the module division in the embodiments of this application is illustrative and only represents a logical functional division; in actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0078] Figure 7 This is a schematic block diagram of the electronic terminal provided in an embodiment of this application. Figure 7 As shown, the electronic terminal 700 includes at least one processor 701, a memory 702, at least one network interface 703, and a user interface 705. The various components in the electronic terminal 700 are coupled together via a bus system 704. It is understood that the bus system 704 is used to implement communication between these components. In addition to a data bus, the bus system 704 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 7 The general will label all buses as bus systems.

[0079] The user interface 705 may include a monitor, keyboard, mouse, trackball, clicker, button, touchpad, or touch screen.

[0080] It is understood that memory 702 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM) or programmable read-only memory (PROM), used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable categories of memory.

[0081] In this embodiment of the invention, the memory 702 is used to store various types of data to support the operation of the electronic terminal 700. Examples of this data include: any executable program for operation on the electronic terminal 700, such as operating system 7021 and application program 7022; operating system 7021 includes various system programs, such as framework layer, core library layer, driver layer, etc., for implementing various basic services and handling hardware-based tasks. Application program 7022 may include various applications, such as media player, browser, etc., for implementing various application services. The methods provided in this embodiment of the invention can be included in application program 7022.

[0082] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by processor 701. Processor 701 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 701 or by instructions in software form. The processor 701 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 701 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. General-purpose processor 701 may be a microprocessor or any conventional processor, etc. The steps of the accessory optimization method provided in the embodiments of the present invention can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, which is located in memory. The processor reads the information in the memory and combines it with its hardware to complete the steps of the aforementioned method.

[0083] In an exemplary embodiment, the electronic terminal 700 may be used by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs) to execute the aforementioned method.

[0084] According to the method provided in the embodiments of this application, this application also provides a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute... Figures 1 to 5 The method of any of the embodiments shown.

[0085] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code, which, when executed on a computer, causes the computer to perform... Figures 1 to 5 The method of any of the embodiments shown.

[0086] As used in this specification, the terms "component," "module," "system," etc., are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0087] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0088] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0090] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0091] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0092] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs, DVDs), or semiconductor media (e.g., solid-state disks, SSDs, etc.).

[0093] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0094] In summary, existing technologies suffer from drawbacks such as prolonged static storage, insufficient sensitivity, limited applicability, and poor prediction accuracy. This application provides a method, device, medium, terminal, and program product for detecting short-circuit faults in vehicle lithium batteries. It collects individual cell voltage data of the vehicle's lithium battery during the charging phase and processes it to obtain average and minimum voltage data. The average and minimum voltage data are continuously monitored. When a preset start extraction condition is met, a first charging data segment is extracted, and a second charging data segment is extracted at a preset extraction frequency. Extraction of the first charging data segment ends when a preset end extraction condition is met, and extraction of the second charging data segment ends when a preset extraction cycle is reached. Then, based on the average voltage data recorded in the first charging data segment... The first average voltage difference is calculated from the voltage difference data of the minimum voltage data, and the second average voltage difference is calculated within a pre-set time range after the extraction ends. The voltage difference ratio is then calculated based on the first and second average voltage difference values. The first average voltage difference, the second average voltage difference, the voltage difference ratio, and the minimum voltage sequence recorded in the second charging data segment are preprocessed and input into a Long Short-Term Memory (LSTM) network model for training, thus constructing an internal short-circuit fault detection model. This model outputs the current internal short-circuit fault detection result for the vehicle's lithium battery. In other words, this application utilizes charging data segments to provide early warning of internal short-circuit faults in the vehicle's lithium battery, thereby enabling the detection of internal short-circuit faults under normal charging conditions and improving the accuracy and reliability of internal short-circuit fault detection. Therefore, this application effectively overcomes the various shortcomings of the prior art and has high industrial application value.

[0095] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for detecting internal short-circuit faults in vehicle lithium batteries, characterized in that, include: Collect the voltage data of individual cells of the vehicle's lithium battery, and process the individual cell voltage data to obtain average voltage data and minimum voltage data; The first charging data segment is extracted based on the preset start and end extraction conditions. The first charging data segment records the voltage difference data between the average voltage data and the minimum voltage data. Based on the preset start extraction conditions, a second charging data segment is extracted within a preset extraction period at a preset extraction frequency. The second charging data segment records the minimum voltage sequence within the extraction period. Calculate the first average voltage difference based on the voltage difference data in the first charging data segment, and calculate the second average voltage difference within a preset time range after the end extraction condition; and calculate the voltage difference ratio based on the first average voltage difference and the second average voltage difference. The average value of the first voltage difference, the average value of the second voltage difference, the voltage difference ratio, and the minimum voltage sequence in the second charging data segment are preprocessed and input into a long short-time memory network model for training to construct an internal short-circuit fault detection model. The internal short-circuit fault detection model is deployed to output the current internal short-circuit fault detection results of the vehicle's lithium battery.

2. The method for detecting internal short-circuit faults in vehicle lithium batteries according to claim 1, characterized in that, The specific training process of the internal short-circuit fault detection model includes: The average value of the first voltage difference, the average value of the second voltage difference, the voltage difference ratio, and the minimum voltage sequence in the second charging data segment are normalized, and the normalized minimum voltage sequence is converted into a tensor of a preset shape. A tensor of a preset shape is input into the first long short-term memory network layer to extract primary temporal features, so as to output the first hidden state sequence of all time steps; The first hidden state sequence output by the first long short-term memory network layer is input into the second long short-term memory network layer for processing, so as to output the second hidden state sequence of all time steps; The second hidden state sequence output by the second long short-term memory network layer is input into the third long short-term memory network layer for processing to output the final feature sequence; and the final feature sequence is converted into a temporal feature vector based on the accessed global pooling layer. The time-series feature vector is concatenated with the first average voltage difference, the second average voltage difference, and the voltage difference ratio to obtain the fused feature vector. Based on the fused feature vector, the current vehicle lithium battery internal short circuit fault detection result is output as normal or faulty.

3. The method for detecting internal short-circuit faults in vehicle lithium batteries according to claim 1, characterized in that, After collecting the individual cell voltage data of the vehicle's lithium battery and processing the data to obtain average voltage data and minimum voltage data, the method further includes: If the initial average voltage data is detected to be higher than the preset threshold, the process will exit directly; if the average voltage data is detected to be lower than the preset threshold and the SOC data increases by 20%, the process will proceed to the subsequent process of extracting charging data segments.

4. The method for detecting internal short circuit faults in vehicle lithium batteries according to claim 1, characterized in that, The preset start extraction condition is: within a continuous preset time period, the average voltage data is between 3300 mV and 3400 mV and the voltage difference between the average voltage data and the minimum voltage data is greater than 15 mV.

5. The method for detecting internal short-circuit faults in vehicle lithium batteries according to claim 4, characterized in that, The preset end extraction condition is: within a continuous preset time period, the voltage difference between the average voltage data and the minimum voltage data is less than or equal to 15 millivolts.

6. The method for detecting internal short-circuit faults in vehicle lithium batteries according to claim 4, characterized in that, If the average voltage data is monitored to be between 3300 and 3400 millivolts, and the voltage difference between the average voltage data and the minimum voltage data is greater than 15 millivolts and not continuous within the preset time, then the current vehicle lithium battery is determined to be normal.

7. A short-circuit fault detection device for a vehicle lithium battery, characterized in that, include: The acquisition module is used to acquire the voltage data of individual cells of the vehicle's lithium battery, and process the individual cell voltage data to obtain average voltage data and minimum voltage data. The charging data segment extraction module is used to extract a first charging data segment based on preset start extraction conditions and end extraction conditions. The first charging data segment records the voltage difference data between the average voltage data and the minimum voltage data. Based on the preset start extraction conditions, a second charging data segment is extracted within a preset extraction period at a preset extraction frequency. The second charging data segment records the minimum voltage sequence within the extraction period. The calculation module is used to calculate a first average voltage difference based on the voltage difference data in the first charging data segment, and to calculate a second average voltage difference within a preset time range after the end extraction condition; and to calculate the voltage difference ratio based on the first average voltage difference and the second average voltage difference. The model building module is used to preprocess the first average voltage difference, the second average voltage difference, the voltage difference ratio, and the minimum voltage sequence in the second charging data segment and input them into the long short-time memory network model for training, so as to build an internal short-circuit fault detection model. The model deployment module is used to deploy the internal short-circuit fault detection model and output the current internal short-circuit fault detection results of the vehicle lithium battery.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.

9. A computer program product, characterized in that, The computer program product includes computer program code that, when run on a computer, causes the computer to implement the method as described in any one of claims 1 to 6.

10. An electronic terminal, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the method as described in any one of claims 1 to 6.

Images