A battery spray valve risk real-time early warning method and device, electronic equipment and medium

Abstract

A battery spray valve risk real-time early warning method and device, electronic equipment and medium are disclosed. The method comprises obtaining current battery sampling data and historical battery sampling data to construct a sample data set. The battery sampling data comprises battery internal pressure data. The sample data set is used to obtain a battery internal pressure change rate. The battery internal pressure change rate and the current battery internal pressure data are used to determine a battery spray valve early warning countdown. Real-time early warning is performed according to the battery spray valve early warning countdown. The application early warns the battery spray valve risk before the battery thermal runaway occurs, and gives the battery spray valve countdown, which facilitates the power station operation and maintenance personnel to intervene in advance and avoids larger accidents.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of batteries, in particular to a battery spray valve risk real-time early warning method, system, device and medium. BACKGROUND

[0002] The state sets a "double carbon" goal, and the proportion of green power represented by light and wind is rapidly increasing due to the influence of policy and the enhancement of people's environmental protection awareness. Due to the randomness and volatility of light and wind, in order to maintain the safety and stability of the power grid, energy storage systems with peak shaving and frequency modulation capabilities have become a standard for the power grid. Among them, the electrochemical energy storage represented by lithium iron phosphate has the fastest growth because of its characteristics such as fast response, flexible adjustment, no geographical environment constraints, and high energy density. However, the battery in the electrochemical energy storage system is prone to thermal runaway risk due to its own electrochemical characteristics and external influences (overcharge, high and low temperature, short circuit, etc.), which threatens the safe operation of the energy storage system.

[0003] The prior art solutions are mostly focused on early warning, alarm, and in-process and post-process fire fighting solutions for battery thermal runaway; such solutions can effectively prevent and reduce the loss caused by accidents, but if the early warning can be further advanced and the countdown (if no measures are taken) is given; in this way, the power station operation and maintenance personnel can intervene in advance to avoid accidents. At the same time, many existing early warning solutions focus on threshold classification and cannot give specific time estimates, which poses a big problem for energy storage system operation and maintenance personnel: although the early warning level is determined, the remaining time is unknown, which causes great psychological pressure on the operation and maintenance personnel and even poses a threat to personal safety. SUMMARY

[0004] In view of the problems existing in the prior art, the present application provides a battery spray valve risk real-time early warning method, system, device and medium to solve the above problems.

[0005] To achieve the above purpose, the present application provides a battery spray valve risk real-time early warning method, which comprises:

[0006] Obtain current battery sampling data and historical battery sampling data to construct a sample data set; wherein the battery sampling data includes battery internal pressure data;

[0007] Obtain the battery internal pressure change rate using the sample data set;

[0008] Determine the battery spray valve early warning countdown according to the battery internal pressure change rate and the current battery internal pressure data;

[0009] Real-time early warning according to the battery spray valve early warning countdown.

[0010] In an optional embodiment of the present application, the real-time warning according to the battery spray valve early warning countdown specifically includes:

[0011] The current battery internal pressure data and / or the battery spray valve early warning countdown are used to determine a warning level.

[0012] The battery sampling point position relationship distribution map is used to determine a warning cell position.

[0013] Real-time warning is performed according to the warning level and the warning cell position.

[0014] In an optional embodiment of the present application, the current battery sampling data and historical battery sampling data are obtained to construct a sample data set, specifically including:

[0015] The current battery sampling data and historical battery sampling data are obtained.

[0016] Data cleaning is performed on all the obtained battery sampling data to construct the sample data set.

[0017] In an optional embodiment of the present application, the sample data set is used to obtain a battery internal pressure change rate, specifically including:

[0018] The change amount of the current battery internal pressure data relative to the historical battery internal pressure data in a preset time period is calculated.

[0019] In an optional embodiment of the present application, the sample data set is used to obtain a battery internal pressure change rate, specifically including:

[0020] The sample data set is input into a linear model for calculation to obtain the battery internal pressure change rate; wherein the linear model is generated by fitting and training the historical battery internal pressure data.

[0021] In an optional embodiment of the present application, the linear model is a univariate linear model with time as the independent variable and battery internal pressure as the dependent variable, which is constructed by fitting and training the historical battery internal pressure data.

[0022] In an optional embodiment of the present application, the battery sampling data further includes one or more combinations of battery temperature, battery temperature change rate, charge-discharge rate, battery charge-discharge cycle number, voltage, current, and battery working condition.

[0023] In an optional embodiment of the present application, the linear model is a multivariate linear model with the battery sampling data as the independent variable and the battery internal pressure change rate as the dependent variable, which is constructed by fitting and training the historical battery internal pressure data.

[0024] In an optional embodiment of the present application, the inputting the sample data set into the linear model for calculation to obtain the battery internal pressure change rate comprises:

[0025] determining whether the sample data set meets a preset condition, if yes, calculating the battery internal pressure change rate by using the linear model, otherwise, updating and training the linear model by using the sample data set, and obtaining the battery internal pressure change rate.

[0026] In an optional embodiment of the present application, the updating and training the linear model by using the sample data set comprises:

[0027] determining whether the size of the sample data set exceeds a data threshold:

[0028] if yes, deleting part of the historical battery sampling data in the sample data set, and updating and training the linear model by using the sample data set after the deletion processing;

[0029] otherwise, directly updating and training the linear model by using the sample data set.

[0030] In an optional embodiment of the present application, the preset condition is to determine whether the sampling time span of the historical battery sampling data reaches a preset interval time.

[0031] In an optional embodiment of the present application, the preset condition is to determine whether the size of the historical battery sampling data reaches a preset threshold.

[0032] To achieve the above object and other related objects, the present application further discloses a battery spray valve risk real-time early warning device, which comprises:

[0033] a data acquisition module, configured to acquire current battery sampling data and historical battery sampling data to construct a sample data set, wherein the battery sampling data comprises battery internal pressure data;

[0034] a battery internal pressure change rate calculation module, configured to obtain a battery internal pressure change rate by using the sample data set;

[0035] a spray valve countdown determination module, configured to determine a battery spray valve early warning countdown according to the battery internal pressure change rate and the current battery internal pressure data;

[0036] a warning module, configured to perform real-time early warning according to the battery spray valve early warning countdown.

[0037] To achieve the above object and other related objects, the present application further discloses an electronic device, which comprises:

[0038] one or more processors;

[0039] a memory, a processor, and a computer program stored on the memory and executable on the processor, and characterized in that the processor implements the steps of the method as described above when executing the computer program.

[0040] To achieve the above object and other related objects, the present application also discloses an electronic device having a computer program stored thereon, characterized by comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, and characterized in that the processor implements the steps of the method as described above when executing the computer program.

[0041] To achieve the above object and other related objects, the present application also discloses a readable storage medium having a computer program stored thereon, and characterized in that the computer program implements the steps of the method as described above when executed by a processor.

[0042] Advantages:

[0043] The battery spray valve risk real-time early warning method disclosed by the application comprises the following steps: obtaining current battery sampling data and historical battery sampling data to construct a sample data set; wherein the battery sampling data comprises battery internal pressure data; obtaining a battery internal pressure change rate by using the sample data set; determining a battery spray valve early warning countdown according to the battery internal pressure change rate and the current battery internal pressure data; and performing real-time early warning according to the battery spray valve early warning countdown. The application early warns the battery spray valve risk before the battery thermal runaway occurs, and gives the battery spray valve countdown, so as to facilitate the power station operation and maintenance personnel to intervene in advance and avoid larger accidents.

[0044] In addition, the battery spray valve risk real-time early warning method disclosed by the application can also determine the specific position of the battery cell at the fault position, so as to facilitate the power station operation and maintenance personnel to maintain. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0046] Figure 1 A flowchart of a battery spray valve risk real-time early warning method provided in an embodiment of the application.

[0047] Figure 2 A flowchart of calculating a battery internal pressure change rate in a specific embodiment of the application.

[0048] Figure 3For Figure 1 The specific flowchart of step S14 is shown.

[0049] Figure 4 The structural schematic diagram of a battery spray valve risk real-time early warning device provided in an embodiment of the present application is shown.

[0050] Figure 5 The structural schematic diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application is shown. DETAILED DESCRIPTION

[0051] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0052] It should be noted that the terms "include" and "have" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units need not be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0053] As Figure 1 shown, the present application discloses a battery spray valve risk real-time early warning method, which at least includes:

[0054] Step S11, obtaining current battery sampling data and historical battery sampling data to construct a sample data set; wherein the battery sampling data includes battery internal pressure data;

[0055] First of all, it should be noted that the battery internal pressure refers to the internal pressure of the battery, which is due to the gas generated during the charging and discharging process of the battery, plus its own self-heating, sealing and other factors. Generally, the battery internal pressure will maintain at a normal level when the battery is working normally; but in the case of overcharging or overdischarging, short circuit and other abnormal conditions, the battery temperature will rise and the internal pressure will increase, which may have a destructive effect on the battery, such as liquid leakage, bulging, and even valve spray.

[0056] It should be noted that in the present embodiment, the battery internal pressure data can be obtained by the following methods:

[0057] 1. Directly obtain, install a pressure sensor into the battery to sample the pressure data in real time;

[0058] 2. Indirectly obtain, install a surface tension sensor on the center of the battery surface to measure the surface tension of the battery to obtain the sampling data, and then obtain P by the relationship P 内 =P 张 +0, P0 is a to-be-determined coefficient, which can be determined by experiment test.

[0059] In a specific embodiment, the current battery sampling data and the historical battery sampling data are obtained to construct a sample data set, specifically including:

[0060] Obtaining the current battery sampling data and the historical battery sampling data;

[0061] Data cleaning is performed on all the obtained battery sampling data to construct the sample data set.

[0062] Due to the obtained battery sampling data, there are often some missing values, repeated values, and other data abnormal conditions. If the original sampling data is not processed and the model is directly trained, there will be a large error between the trained model and the actual situation, so some cleaning rules need to be defined according to the specific scene, such as limit value, mutation value, 0 value, difference value, cross-validation, etc.

[0063] Step S12, obtaining the battery internal pressure change rate by using the sample data set;

[0064] Since the internal pressure of the energy storage battery changes approximately linearly with time under abnormal conditions such as overcharge, overdischarge, and short circuit, the k value can be calculated by using the change rate definition under the condition of only considering the pressure factor. Specifically:

[0065] The change amount of the current battery internal pressure data relative to the historical battery internal pressure data in a preset time period is calculated, and then substituted into the formula , the battery internal pressure change rate can be obtained.

[0066] It should be noted that the method of obtaining the battery internal pressure change rate according to the definition above will be affected by local sampling, and thus a large error will exist between the obtained battery internal pressure change rate k and the actual battery internal pressure change rate.

[0067] Therefore, in another specific embodiment of the present application, the battery internal pressure change rate is obtained by using the sample data set, specifically including:

[0068] inputting the sample data set into a linear model for calculation to obtain the battery internal pressure change rate; wherein the linear model is generated according to historical battery internal pressure data.

[0069] It should be noted that, in a specific embodiment, the linear model is a univariate linear model with time as the independent variable and battery internal pressure as the dependent variable, which is constructed by fitting and training the historical battery internal pressure data, and the training construction process of the univariate linear model is as follows:

[0070] Construct a univariate linear model with time as the independent variable and battery internal pressure as the dependent variable.

[0071] Specifically, the univariate linear model is set as: f(t) = k p t + b, wherein the parameters k p of the model are the battery internal pressure change rate k,

[0072] The univariate linear model is trained using historical battery internal pressure data to obtain the battery internal pressure change rate.

[0073] First, the following training samples are constructed:

[0074] [(1, p1), (1 + T, p2), (1 + 2T, p3)... (1 + (n-1)T, pn)], wherein T is the sampling interval, p1, p2, p3... pn are the sampling values at the corresponding time. Preferably, the sampling interval T is 1s.

[0075] Then, the training samples are input into the constructed univariate linear model, and the model will fit the most appropriate k p and b values through mathematical statistical methods.

[0076] After training, the above k p value is taken as the battery internal pressure change rate k.

[0077] It should be noted that the above linear model is constructed only according to the pressure characteristic parameter to estimate the internal pressure change. However, in actual application, facing complex and diverse use scenarios, the battery internal pressure change rate will also be affected by the battery temperature, temperature change rate, charge-discharge rate, battery charge-discharge cycle number, voltage, current, and battery working condition. If the constructed linear model ignores these influencing factors, there will still be a large error between the calculated battery internal pressure change rate and the actual value, which is extremely unfavorable for the subsequent determination of the spray valve countdown time.

[0078] To improve the estimation accuracy of the battery internal pressure change rate, in another specific embodiment of the present application, the linear model is a multivariate linear model constructed by fitting and training the historical battery internal pressure data, with the battery sampling data as the independent variable and the battery internal pressure change rate as the dependent variable, wherein the construction process of the multivariate linear model is as follows:

[0079] Constructing a multivariate linear model with the historical battery internal pressure data as the independent variable and the battery internal pressure change rate as the dependent variable;

[0080] First of all, it should be noted that the battery data at this time also includes one kind of data or a combination of two or more kinds of data of battery temperature, temperature change rate, charge-discharge rate, battery charge-discharge cycle number, voltage, current, and battery working condition, wherein the battery working condition includes standing, normal charging, normal discharging, overcharging, overdischarging, etc.

[0081] As an example, the multivariate linear model can be constructed as follows:

[0082] f(x) = w1*x1 + w2*x2 + … + w8*x8 + b, wherein x1-x8 respectively represent battery internal pressure, temperature, temperature change rate, charge-discharge rate, battery charge-discharge cycle number, voltage, current, and battery working condition, and f(x) represents the battery internal pressure change rate.

[0083] The multivariate linear model is trained using the historical battery internal pressure data to obtain the battery internal pressure change rate.

[0084] Wherein the battery internal pressure change rate participating in the training can be obtained by the following formula:

[0085] P n is the internal pressure value at the n sampling time, P n-1 is the internal pressure value at the (n-1) sampling time, and T is the sampling interval;

[0086] By collecting the data of battery internal pressure, temperature, temperature change rate, charge-discharge rate, battery charge-discharge cycle number, voltage, current, and battery working condition for a long period of time, a large number of training samples will be formed, which are input into the multivariate linear model for training. Through a large number of mathematical calculations, the multivariate linear model can finally fit the most appropriate w1, w2, … w8 and b values. After the above parameters are determined, when calculating the internal pressure change rate in the subsequent, we only need to measure the data of battery internal pressure, temperature, temperature change rate, charge-discharge rate, battery charge-discharge cycle number, voltage, current, and battery working condition, and the battery internal pressure change rate at this time can be estimated very accurately.

[0087] Please refer to Figure 2In another specific embodiment of the present application, the battery internal pressure change rate is obtained using the sample data set, specifically comprising:

[0088] If the sample data set does not meet the preset condition, the battery internal pressure change rate is calculated using the linear model; if the sample data set meets the preset condition, the linear model is updated using the sample data set, and the battery internal pressure change rate is calculated.

[0089] In a specific embodiment, the preset condition is to determine whether the sampling time span of the historical battery sampling data reaches a preset interval time.

[0090] In another specific embodiment, the preset condition is to determine whether the size of the historical battery sampling data reaches a preset threshold.

[0091] In a specific embodiment of the present application, the linear model is updated using the sample data set, specifically comprising:

[0092] It is determined whether the size of the sample data set exceeds a data threshold:

[0093] If it exceeds, part of the historical battery sampling data in the sample data set is deleted, and the linear model is updated using the sample data set after the deletion processing;

[0094] Otherwise, the original model is directly used for calculation.

[0095] It should be noted that, in a preferred embodiment, the battery sampling data with the earliest time in the sample data set is deleted.

[0096] It should be noted that, by deleting part of the historical battery sampling data in the sample data set, the size of the entire training sample can be maintained at a reasonable size, avoiding the problem of low training efficiency caused by too large amount of data participating in model training, which affects the timeliness of early warning.

[0097] Step S13, determining the battery jet valve early warning countdown according to the battery internal pressure change rate and the current battery internal pressure data;

[0098] From step S12, the battery internal pressure change rate can be determined, according to the formula The battery jet valve countdown can be calculated, wherein P r is the battery jet valve pressure, P t is the current pressure value. It should be noted that the battery jet valve pressure P r is a constant value, which is calibrated by the manufacturer before the battery is shipped. If it is not calibrated, it can also be calibrated through separate testing.

[0099] Step S14, real-time warning according to the battery spray valve early warning countdown, for details, please refer to Figure 3 as shown:

[0100] Step S141, using the current battery pressure data and / or the battery spray valve early warning countdown, to determine the warning level;

[0101] Wherein the classification rules of the warning level can take the following way:

[0102] Way 1:

[0103] : set the number of warning levels to be divided, set the starting pressure of the warning and the pressure increment of each level.

[0104] Now take the division of three levels of warning as an example. Set the starting pressure of the warning as P0, the pressure increment from the first level to the second level as ΔP, the pressure increment from the first level to the second level as ΔP, and the pressure increment from the third level to the battery spray valve pressure P r ΔP r ,0≤ΔP r ≤ΔP, where P0+2ΔP+ΔP r =P r . That is: P0 to P0+ΔP is a first level warning, P0+ΔP to P0+2ΔP is a second level warning, and P0+2ΔP to P r is a third level warning.

[0105] If the current battery pressure value P a collected is greater than or equal to the starting pressure P0 of the warning set and less than the starting pressure of the second level warning (size P0+ΔP), that is, P a ≥P0 and P a <P0+ΔP, then it is in a first level warning at this time;

[0106] If the current battery pressure value collected is greater than or equal to the starting pressure of the second level warning and less than the starting pressure of the third level warning (size P0+2ΔP), that is, P a ≥P0+ΔP and P a <P0+2ΔP, then it is in a second level warning at this time;

[0107] If the current battery pressure value collected is greater than or equal to the starting pressure of the third level warning and less than the battery spray valve pressure P a ≥P0+2ΔP and P a <P r , then it is in a third level warning at this time.

[0108] Way 2:

[0109] : Set the number of warning levels to be divided, the initial warning time, and the time interval before each warning level. Taking a warning divided into three levels as an example, the specific steps are as follows:

[0110] Set the initial warning time as T1, and the interval time between each level as Δt1. T1-Δt1 to T1 can be used as a first-level warning, T1-2Δt1 to T1-Δt1 as a second-level warning, and less than T1-2Δt1 as a third-level warning.

[0111] If the battery valve countdown time is located at Δt between T1-Δt1 and T1, it is in a first-level warning at this time;

[0112] If the battery valve countdown time is located at Δt between T1-2Δt1 and T1-Δt1, it is in a second-level warning at this time;

[0113] If the battery valve countdown time Δt is less than T1-2Δt1, it is in a third-level warning at this time.

[0114] It can be understood that the rules for dividing the warning levels can also be combined with the battery internal pressure value and the battery valve warning countdown time.

[0115] It should be noted that the above rules for dividing the warning levels are only an exemplary description, and it can be understood that in other embodiments, the specific threshold values and the number of divided warning levels can be determined according to specific business scenarios.

[0116] Step S142, determine the position of the battery cell that triggers the warning by using the battery position relationship distribution map.

[0117] For a storage power station, there are usually tens of thousands of batteries, or even hundreds of thousands of batteries. In order to facilitate later maintenance, the on-site staff will save the battery position correspondence relationship in the meta database or in the mapping file, which forms a battery position relationship distribution map.

[0118] In this way, if the sampled battery has a valve warning, the operation and maintenance personnel can determine the position of the battery in which storage unit, Rack, and Pack by combining the battery number that triggers the warning with the position mapping information, thereby helping the operation and maintenance personnel to quickly locate the position of the faulty battery.

[0119] Step S143, perform real-time warning according to the warning level and the position of the battery cell that triggers the warning.

[0120] Perform real-time warning according to the warning level and the position of the battery cell that triggers the warning determined in the foregoing.

[0121] In summary, the present invention discloses a real-time early warning method for battery valve release risk. This method constructs a sample dataset by acquiring current and historical battery sampling data, including battery internal pressure data. Using the sample dataset, the battery internal pressure change rate is obtained. Based on the battery internal pressure change rate and the current battery internal pressure data, a battery valve release warning countdown is determined. Real-time early warning is then provided based on the battery valve release warning countdown. This invention provides early warning of battery valve release risk before thermal runaway occurs and provides a battery valve release countdown, facilitating early intervention by power plant maintenance personnel and preventing larger accidents.

[0122] Furthermore, the real-time early warning method for battery valve risk disclosed in this invention can also determine the specific location of the battery cell where the fault occurs, facilitating maintenance by power plant operation and maintenance personnel.

[0123] like Figure 4 As shown in the figure, this embodiment also discloses a real-time early warning device for battery spray valve risks. Figure 4 A block diagram of a real-time early warning device 400 for battery valve risk, according to an exemplary embodiment of this application, is shown. The real-time early warning device 400 includes a data acquisition module 401, a battery internal pressure change rate calculation module 402, a valve countdown determination module 403, and an early warning module 404. The data acquisition module 401 acquires current battery sampling data and historical battery sampling data to construct a sample dataset; wherein the battery sampling data includes battery internal pressure data; the battery internal pressure change rate calculation module 402 uses the sample dataset to obtain the battery internal pressure change rate; the valve countdown determination module 403 determines the battery valve early warning countdown based on the battery internal pressure change rate and the current battery internal pressure data; and the early warning module 404 provides real-time early warning based on the battery valve early warning countdown.

[0124] It should be noted that the battery valve risk real-time early warning device 400 provided in the above embodiments and the battery valve risk real-time early warning method provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the battery valve risk real-time early warning device 400 provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0125] Figure 5 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 5The computer system 500 of the electronic device shown is merely one example, and should not be taken as limiting the functionality or use of embodiments of the present application.

[0126] As shown in Figure 5 The computer system 500 includes a central processing unit (CPU) 501 that can perform various suitable actions and processes in accordance with a program stored in read-only memory (ROM) 502 or a program loaded from the storage section 508 into random access memory (RAM) 503, such as performing the methods described in the embodiments above. Various programs and data required for the operation of the system are also stored in the RAM 503. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0127] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as necessary. A removable recording medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 510 as necessary, so that a computer program read therefrom is installed into the storage section 508 as necessary.

[0128] In particular, in accordance with embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing a computer program for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 509, and / or installed from the removable recording medium 511. When the computer program is executed by the central processing unit (CPU) 501, various functions defined in the system of the present application are performed.

[0129] In one embodiment, a readable storage medium is also disclosed, which stores a computer program, the computer program is executed by a processor to implement the steps of the method according to any one of the above embodiments.

[0130] In the present application, the computer readable storage medium can be a tangible medium which can contain or store the computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. Alternatively, the computer readable storage medium can be a machine readable signal medium. More specific examples of the machine readable storage medium will include one or more lines of electrical connection, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.

[0131] The above description of the illustrated embodiments of the application (including what is described in the abstract) is not intended to be exhaustive or to limit the application to the precise forms disclosed. While specific embodiments of, and examples for, the application are described herein for illustrative purposes, various equivalent modifications are possible within the spirit and scope of the application, as those skilled in the relevant art will recognize and appreciate. As indicated, these modifications can be made to the above-described embodiments and yet the application will remain within the scope of the application. Accordingly, no limitation is placed on the scope of the application by the details of the description.

[0132] The systems and methods have been described generally herein as facilitating an understanding of the details of the application. Moreover, various specific details have been given in order to provide a thorough understanding. It will be appreciated, however, by those of ordinary skill that the application can be practiced in a variety of ways without one or more of the specific details, or with other structures, systems, components, materials, parts, and / or the like. In other instances, well known structures, materials, and / or operations have not been shown or described in detail in order to avoid obscuring aspects of the application.

[0133] Thus, although the present application has been described herein with respect to particular embodiments thereof, alterations, modifications and variations will occur to others skilled in the art upon the reading and understanding of the foregoing description. It is intended that the application be construed as including all such alterations, modifications and variations as fall within the scope of the appended claims. Accordingly, the application is not intended to be limited to the specific embodiments described in the specification illustrating one or more aspects of the application and as such, other embodiments of the application will be obvious to one skilled in the art from this disclosure. It is therefore intended that the application not be limited, to the extent that modifications and variations do not constitute departures from the spirit and essence of the application.

Claims

1. A method for real-time early warning of risks in battery injection valves, characterized in that, The method includes: Acquire current battery sampling data and historical battery sampling data to construct a sample dataset; wherein, the battery sampling data includes battery internal pressure data; Using the aforementioned sample dataset, the rate of change of battery internal pressure was obtained; Based on the battery internal pressure change rate and the current battery internal pressure data, determine the battery spray valve warning countdown; Real-time warnings are issued based on the battery valve warning countdown; The battery sampling data also includes one or more combinations of battery temperature, battery temperature change rate, charge / discharge rate, number of battery charge / discharge cycles, voltage, current, and battery operating conditions; The process of obtaining the battery internal pressure change rate using the sample dataset specifically includes: The sample dataset is input into a linear model for calculation to obtain the battery internal pressure change rate. The linear model is a multiple linear model constructed by fitting and training historical battery internal pressure data, with the battery sample data as the independent variable and the battery internal pressure change rate as the dependent variable.

2. The real-time early warning method for battery injection valve risk according to claim 1, characterized in that, The real-time warning based on the battery injection valve warning countdown specifically includes: The warning level is determined by using the current battery internal pressure data and / or the battery injection valve warning countdown. The location of the cell that triggered the warning was determined by using the distribution map of the battery sampling points. Real-time warnings are issued based on the warning level and the location of the warning cell.

3. The real-time early warning method for battery injection valve risk according to claim 1, characterized in that, The process of acquiring current battery sampling data and historical battery sampling data to construct a sample dataset specifically includes: Obtain the current battery sampling data and the historical battery sampling data; All the acquired battery sampling data are cleaned to construct the sample dataset.

4. The real-time early warning method for battery injection valve risk according to claim 1, characterized in that, The process of obtaining the battery internal pressure change rate using the sample dataset specifically includes: Calculate the change in the current battery internal pressure data relative to the historical battery internal pressure data within a preset time period.

5. The real-time early warning method for battery injection valve risk according to claim 1, characterized in that, The step of inputting the sample dataset into a linear model for calculation to obtain the battery internal pressure change rate includes: Determine whether the sample dataset meets the preset conditions. If not, calculate the battery internal pressure change rate using the linear model. Otherwise, update the training of the linear model using the sample dataset and calculate the battery internal pressure change rate.

6. The real-time early warning method for battery injection valve risk according to claim 5, characterized in that, Updating and training the linear model using the sample dataset includes: Determine whether the size of the sample dataset exceeds the data threshold: If the number of samples exceeds the limit, delete a portion of the historical battery sampling data from the sample dataset and use the deleted sample dataset to update and train the linear model. Otherwise, the linear model is directly updated and trained using the sample dataset.

7. The real-time early warning method for battery injection valve risk according to claim 5, characterized in that, The preset condition is to determine whether the sampling time span of the historical battery sampling data has reached a preset interval.

8. The real-time early warning method for battery injection valve risk according to claim 5, characterized in that, The preset condition is to determine whether the size of the historical battery sampling data reaches a preset threshold.

9. A real-time early warning device for battery spray valve risks, characterized in that, The device includes: A data acquisition module is used to acquire current battery sampling data and historical battery sampling data to construct a sample dataset; wherein, the battery sampling data includes battery internal pressure data; The battery internal pressure change rate calculation module is used to obtain the battery internal pressure change rate using the sample dataset; The valve countdown determination module is used to determine the battery valve warning countdown based on the battery internal pressure change rate and the current battery internal pressure data. The early warning module is used to provide real-time warnings based on the battery injection valve's countdown timer. The battery sampling data also includes one or more combinations of battery temperature, battery temperature change rate, charge / discharge rate, number of battery charge / discharge cycles, voltage, current, and battery operating conditions; The process of obtaining the battery internal pressure change rate using the sample dataset specifically includes: The sample dataset is input into a linear model for calculation to obtain the battery internal pressure change rate. The linear model is a multiple linear model constructed by fitting and training historical battery internal pressure data, with the battery sample data as the independent variable and the battery internal pressure change rate as the dependent variable.

10. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to perform the method as described in any one of claims 1 to 8.

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

Images