Method for predicting battery capacity cliff and related device
By comparing the difference between predicted and actual measured values during battery charge and discharge cycles, the problem of predicting the inflection point of battery capacity drop is solved, enabling early prediction of battery capacity and timely detection of rapid reduction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- EVE POWER CO LTD
- Filing Date
- 2023-08-31
- Publication Date
- 2026-07-21
AI Technical Summary
Existing technologies lack a unified method to predict the inflection point of battery capacity drop, making it impossible to predict the rapid decline in battery capacity in advance.
By obtaining the difference between the predicted value and the actual measured value of the battery capacity in multiple prediction cycles of battery charging and discharging, and comparing it with the difference threshold, if the difference exceeds the threshold for a consecutive preset number of times, it is determined that a battery capacity drop inflection point has occurred.
It enables early prediction of the inflection point of battery capacity drop, timely detection of rapid decrease in battery capacity, and reduction of resource waste.
Smart Images
Figure CN117214717B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of battery technology, and in particular to a method and related equipment for predicting the inflection point of battery capacity drop. Background Technology
[0002] Battery cycle life is a crucial indicator for battery performance evaluation. Cycle life performance is typically assessed during battery product development, but the long testing cycles can lead to accelerated capacity degradation—a sudden drop in battery capacity—often referred to as "battery plunge." Currently, there is no universally accepted definition of the "inflection point" in the battery industry. It is generally defined as a period of slow capacity decline for most of the battery's lifespan, followed by a rapid decline. There is no standardized quantitative method for determining the battery aging inflection point. Commonly used methods include the Kneedle method, Bacon-Watts method, tangent method, and bisector method. All of these require testing until a significant acceleration in capacity degradation occurs, nearing the cell's end-of-life (EOL), making it impossible to predict the inflection point of the battery's cycle aging trajectory. Summary of the Invention
[0003] Therefore, it is necessary to provide a method and related equipment for predicting the inflection point of battery capacity drop in order to address the above-mentioned technical problems, which can predict the inflection point of battery capacity drop in advance.
[0004] In a first aspect, this application provides a method for predicting the inflection point of battery capacity drop, the prediction method comprising:
[0005] In the multiple prediction cycles of battery charging and discharging, the predicted value of battery capacity for each prediction cycle is obtained.
[0006] Obtain the actual measured value of the battery capacity for each of the predicted cycles;
[0007] The difference between the predicted value and the actual measured value for each prediction cycle is obtained, and each difference is compared with a difference threshold. If the difference for a consecutive preset number of prediction cycles exceeds the difference threshold, the battery capacity drop inflection point is determined to occur in the first prediction cycle of the consecutive preset number of prediction cycles.
[0008] In one embodiment, the step of obtaining the predicted value of the battery capacity for each prediction cycle further includes:
[0009] Obtain the predicted loss rate of battery capacity for each prediction cycle;
[0010] The predicted value of the battery capacity for each prediction period is obtained based on the predicted loss rate of the battery capacity for each prediction period.
[0011] In one embodiment, the step of obtaining the predicted loss rate of the battery capacity for each prediction cycle further includes:
[0012] Construct a battery capacity prediction loss rate model that satisfies the following formula:
[0013] q n =e An ×n Zn (1),
[0014] The q n Let e be the battery capacity loss rate in the nth prediction cycle, and let A be the natural constant. n Z is a constant coefficient, where n is the number of prediction periods and is an integer greater than 0. n A is the exponential constant of n. n and the Z n It varies depending on the value of n;
[0015] The value of n is taken according to each prediction period, so as to obtain the predicted loss rate of battery capacity for each prediction period through the formula (1).
[0016] In one embodiment, the step of obtaining the predicted value of the battery capacity for each prediction period based on the predicted loss rate of the battery capacity for each prediction period further includes:
[0017] Taking the logarithm of both sides of formula (1), we obtain the following formula:
[0018] lnq n =A n +Z n ×lnn (2),
[0019] Obtain the actual battery capacity loss rate and the corresponding prediction cycle number for n prediction cycles, and substitute the actual loss rate and the corresponding prediction cycle number into the q in formula (2). n And the n, to perform linear fitting on the formula (2) to obtain the A n and the Z n The value;
[0020] According to A n and the Z n The value is used to obtain the predicted value of the battery capacity over n+1 prediction cycles.
[0021] In one embodiment, the step of obtaining the actual battery capacity loss rate over n prediction cycles further includes:
[0022] The actual loss rate of the battery capacity satisfies the following formula:
[0023] q i =1-Q i (3),
[0024] Where q i Q represents the actual loss rate of the battery capacity in the i-th prediction period. i The actual measured value of the battery capacity during the i-th prediction cycle;
[0025] The value of i is taken according to each prediction period. When the value of i is equal to n, the actual loss rate of the battery capacity for n prediction periods is obtained by formula (3).
[0026] In one embodiment, the statement based on A... n and the Z n The step of obtaining the predicted value of the battery capacity over n+1 prediction periods further includes:
[0027] Construct a battery capacity prediction model that satisfies the following formula:
[0028] Q n+1 =1-e An ×(n+1) Zn (4),
[0029] Wherein, Q n+1 This is the predicted value of the battery capacity in the (n+1)th prediction cycle.
[0030] In one embodiment, the method for predicting the inflection point of battery capacity drop further includes:
[0031] In two adjacent prediction cycles of battery charging and discharging, a first predicted value of the battery capacity in the previous prediction cycle and a second predicted value of the battery capacity in the next prediction cycle are obtained respectively.
[0032] The first actual measurement value of the battery capacity in the previous prediction cycle and the second actual measurement value of the battery capacity in the next prediction cycle are obtained respectively.
[0033] Obtain a first difference between the first predicted value and the first actual measured value, and obtain a second difference between the second predicted value and the second actual measured value;
[0034] The first difference and the second difference are compared with the difference threshold respectively. If both the first difference and the second difference exceed the difference threshold, it is determined that the battery capacity drop inflection point occurred in the previous prediction cycle.
[0035] Secondly, this application also provides a device for predicting the inflection point of battery capacity drop, the device comprising:
[0036] The first acquisition module is used to acquire the predicted value of the battery capacity for each of the multiple prediction cycles of the battery charging and discharging.
[0037] The second acquisition module is used to acquire the actual measured value of the battery capacity for each prediction cycle.
[0038] The third acquisition module is used to acquire the difference between the predicted value and the actual measured value for each prediction period;
[0039] The comparison module is used to compare each of the differences with a difference threshold;
[0040] The judgment module is used to determine the battery capacity drop inflection point when the comparison module finds that the differences corresponding to the prediction cycles of the consecutive preset number of prediction cycles all exceed the difference threshold.
[0041] Thirdly, this application also provides a device for predicting the inflection point of battery capacity drop. The device includes a memory and a processor. The memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the method described above.
[0042] Fourthly, this application also provides a computer-readable storage medium storing computer-readable instructions that, when executed by a processor, implement the steps of the method described above.
[0043] The above describes a method and related equipment for predicting the inflection point of battery capacity drop. The prediction method includes: acquiring a predicted value of battery capacity for each prediction cycle in multiple prediction cycles of battery charging and discharging; acquiring an actual measured value of battery capacity for each prediction cycle; acquiring the difference between the predicted value and the actual measured value for each prediction cycle; comparing each difference with a difference threshold; and if the difference for a consecutive preset number of prediction cycles exceeds the difference threshold, then the battery capacity drop inflection point is determined to occur in the first prediction cycle of the consecutive preset number of prediction cycles. Therefore, by acquiring the predicted value and actual measured value of battery capacity for multiple prediction cycles, the prediction cycle time point for the battery capacity drop inflection point can be predicted, allowing for early prediction of the battery capacity drop inflection point and timely and effective detection of rapid battery capacity reduction. Attached Figure Description
[0044] Figure 1 This is an exemplary system architecture diagram in which the prediction method for the inflection point of battery capacity drop in this application can be applied;
[0045] Figure 2 This is a flowchart illustrating a method for predicting the inflection point of battery capacity drop provided in an embodiment of this application;
[0046] Figure 3 This is a flowchart illustrating another method for predicting the inflection point of battery capacity drop provided in this application embodiment;
[0047] Figure 4 This is a flowchart illustrating another method for predicting the inflection point of battery capacity drop provided in this application embodiment;
[0048] Figure 5 This is a flowchart illustrating another method for predicting the inflection point of battery capacity drop provided in this application embodiment;
[0049] Figure 6 This is a flowchart illustrating another method for predicting the inflection point of battery capacity drop provided in this application embodiment;
[0050] Figure 7 This is a flowchart illustrating another method for predicting the inflection point of battery capacity drop provided in this application embodiment;
[0051] Figure 8 This is a schematic diagram of the structure of a device for predicting the inflection point of battery capacity drop provided in an embodiment of this application;
[0052] Figure 9 This is a basic structural block diagram of a battery capacity drop inflection point prediction device provided in an embodiment of this application. Detailed Implementation
[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0054] Please see Figure 1 , Figure 1 This is an exemplary system architecture diagram to which this application can be applied. For example... Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.
[0055] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.
[0056] Terminal devices 101, 102, and 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), laptops, and desktop computers, etc.
[0057] Server 105 can be a server that provides various services, such as a backend server that supports the pages displayed on terminal devices 101, 102, and 103.
[0058] It should be noted that the method for predicting the inflection point of battery capacity drop provided in this application is generally executed by a server / terminal device. Accordingly, the device for predicting the inflection point of battery capacity drop is generally located in the server / terminal device.
[0059] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.
[0060] Continue reading Figure 2 , Figure 2 This is a flowchart illustrating a method for predicting the inflection point of battery capacity drop, as provided in an embodiment of this application. Figure 2 As shown, the method for predicting the inflection point of battery capacity drop includes the following steps:
[0061] Step S1: In the multiple prediction cycles of the battery charging and discharging, obtain the predicted value of the battery capacity for each prediction cycle.
[0062] In practical applications, battery charge-discharge cycle testing can be designed with standard capacity calibration steps and a test frequency of M charge-discharge cycles (where M can be 50 ≤ M ≤ 300) to perform one battery capacity calibration. In other words, M charge-discharge cycles constitute one prediction cycle, recording the battery capacity once. This battery capacity includes both the predicted value and the actual measured value.
[0063] In other words, in step S1, each time the battery completes a predicted charge-discharge cycle, a corresponding predicted value of the battery capacity is obtained.
[0064] Step S2: Obtain the actual measured value of the battery capacity for each of the predicted cycles.
[0065] In other words, once the battery completes a predicted charge-discharge cycle, an actual measurement of the corresponding battery capacity is obtained.
[0066] Step S3: Obtain the difference between the predicted value and the actual measured value for each prediction cycle, and compare each difference with a difference threshold. If the difference for a consecutive preset number of prediction cycles exceeds the difference threshold, then determine that the battery capacity drop inflection point occurs in the first prediction cycle of the consecutive preset number of prediction cycles.
[0067] Therefore, by obtaining the predicted values of battery capacity and the actual measured values of battery capacity over multiple prediction cycles, the predicted cycle time point at which the battery capacity drop inflection point will occur can be predicted in advance, and the rapid decrease in battery capacity can be detected in a timely and effective manner.
[0068] In a specific implementation, only two consecutive prediction periods are needed to determine whether a battery capacity drop inflection point has occurred. For details, please refer to [link to relevant documentation]. Figure 3 , Figure 3 This is a flowchart illustrating another method for predicting the inflection point of battery capacity drop provided in this application. Figure 3 As shown, the method for predicting the inflection point of battery capacity drop includes the following steps:
[0069] Step S21: In two adjacent prediction cycles of battery charging and discharging, obtain the first predicted value of the battery capacity in the previous prediction cycle and the second predicted value of the battery capacity in the next prediction cycle.
[0070] Step S22: Obtain the first actual measurement value of the battery capacity in the previous prediction cycle and the second actual measurement value of the battery capacity in the next prediction cycle.
[0071] Step S23: Obtain the first difference between the first predicted value and the first actual measured value, and obtain the second difference between the second predicted value and the second actual measured value.
[0072] Step S24: Compare the first difference and the second difference with the difference threshold respectively. If both the first difference and the second difference exceed the difference threshold, it is determined that the battery capacity drop inflection point occurred in the previous prediction cycle.
[0073] If the predicted and actual battery capacity values for two consecutive prediction cycles deviate from the predicted value by more than a threshold, the battery is considered to have experienced a significant capacity drop. In this case, the previous prediction cycle is considered the inflection point of the capacity drop. Optionally, the threshold value should be ≥2%. It should be understood that the threshold value can be changed for different batteries in predicting the inflection point of capacity drop.
[0074] It should be understood that in other implementations, three consecutive prediction periods or other numbers of consecutive prediction periods can be obtained to determine whether a battery capacity drop inflection point has occurred. This application does not limit the number of prediction periods. The specific judgment principle is the same as described above and will not be repeated here.
[0075] Optional, please refer to Figure 4 , Figure 4 This is a flowchart illustrating another method for predicting the inflection point of battery capacity drop provided in this application. For example... Figure 4 As shown, obtaining the predicted battery capacity for each prediction cycle in step S1 includes the following sub-steps:
[0076] Step S31: Obtain the predicted loss rate of battery capacity for each prediction cycle.
[0077] Step S32: Obtain the predicted value of the battery capacity for each prediction period based on the predicted loss rate of the battery capacity for each prediction period.
[0078] Specifically, the sum of the predicted loss rate of battery capacity and the predicted value of battery capacity equals 1. Therefore, given the predicted loss rate of battery capacity, after each prediction cycle of battery charging and discharging is completed, a predicted loss rate of battery capacity is obtained. Thus, the predicted value of battery capacity for each prediction cycle can be obtained by using the relationship that the sum of the predicted loss rate and the predicted value of battery capacity equals 1.
[0079] The specific process for obtaining the predicted loss rate of battery capacity is described below: Please refer to [link / reference]. Figure 5 , Figure 5 This is a flowchart illustrating another method for predicting the inflection point of battery capacity drop provided in this application. For example... Figure 5 As shown, step S31 may include the following sub-steps:
[0080] Step S41: Construct a battery capacity prediction loss rate model that satisfies the following formula:
[0081] q n =e An ×n Zn (1),
[0082] Wherein, the q n Let e be the predicted loss rate of battery capacity in the nth prediction cycle, and let A be the natural constant. n For constant coefficients, specifically, A n A constant coefficient related to charge / discharge rate and temperature, where n is the number of prediction cycles, and n is an integer greater than 0, and Z... n Z is the exponential constant of n, specifically, Z n A is an exponential coefficient related to charge / discharge rate and temperature. n and the Z n It varies depending on the value of n.
[0083] Step S42: n takes a value according to each prediction cycle, so as to obtain the predicted loss rate of battery capacity for each prediction cycle through formula (1). That is, when formula (1) is obtained by constructing the battery capacity prediction loss rate model, n takes a value in sequence after each prediction cycle of battery charging and discharging is completed, so that the predicted loss rate of battery capacity for each prediction cycle can be obtained through formula (1).
[0084] Because of A n and Z n The value of A varies depending on the value of n, therefore, when determining the predicted loss rate of battery capacity, it is first necessary to determine A. n and Z n The specific numerical value. In a specific embodiment, please refer to... Figure 6 , Figure 6 This is a flowchart illustrating another method for predicting the inflection point of battery capacity drop provided in this application. For example... Figure 6 As shown, step S31 may further include the following sub-steps:
[0085] Step S51: Take the logarithm of both sides of the formula (1) to obtain the following formula:
[0086] lnq n =A n +Z n ×lnn (2),
[0087] Step S52: Obtain the actual battery capacity loss rate and the corresponding prediction cycle number for n prediction cycles, and substitute the actual loss rate and the corresponding prediction cycle number into the q in formula (2). n And the n, to perform linear fitting on the formula (2) to obtain the A n and the Z n The value of .
[0088] From formula (2), we can see that lnq n If ln is linearly related, then by obtaining the actual loss rate of multiple battery capacities and the corresponding number of prediction cycles, multiple sets of linear relationships can be determined, thereby fitting formula (2) to obtain A when there are n prediction cycles. n and the Z n The value of . Optional, the goodness of fit R 2 ≥0.99. It is worth noting that the actual loss rate of multiple battery capacities is the value obtained from actual measurements over n prediction cycles.
[0089] For details, please refer to [link / reference]. Figure 7 You can obtain it through the following steps:
[0090] Step S52 includes the following sub-steps:
[0091] Step S61: The battery capacity loss rate satisfies the following formula:
[0092] q i =1-Q i (3),
[0093] Where q i Let Q be the actual loss rate of battery capacity in the i-th prediction cycle. i This represents the actual measured value of the battery capacity during the i-th prediction cycle.
[0094] In practical applications, the recoverable capacity retention rate of the battery is measured after each predicted charge-discharge cycle is completed. This is referred to as the actual measured value of the battery capacity, denoted as Q.i The corresponding capacity loss rate is denoted as q. i Thus, we obtain formula (3). It is worth noting that q i The actual rate of battery capacity loss is expressed by q. i Substituting the corresponding prediction period i into formula (2) q n And n, to fit formula (2) to obtain A at the nth prediction period. n and the Z n The value of .
[0095] In a practical application, taking n as the current prediction period, it is necessary to obtain the constant coefficient A and the exponential constant Z of the current prediction period. It is also necessary to obtain the actual capacity loss rate of the battery and the corresponding prediction period number of the current prediction period and other prediction periods before the current prediction period. Then, these values are substituted into q in formula (2). n And n, to fit formula (2) to determine the constant coefficient A and exponential constant Z of the current prediction period.
[0096] Step S62: i takes a value according to each prediction cycle. When the value of i is equal to n, the actual loss rate of battery capacity for n prediction cycles is obtained by formula (3).
[0097] That is, the actual loss rate of battery capacity for n prediction cycles is obtained by formula (3), and then the actual loss rate of battery capacity for n prediction cycles and the corresponding number of prediction cycles are substituted into formula (2) to fit formula (2) and obtain the constant coefficient An and exponential constant Zn of the nth prediction cycle.
[0098] Step S53: According to the A n and the Z n The value is used to obtain the predicted value of the battery capacity over n+1 prediction cycles.
[0099] In other words, the predicted battery capacity for the next prediction cycle is obtained using the constant coefficient A and the exponential constant Z of the battery loss rate from the previous cycle. Specifically, after obtaining the constant coefficient A for the nth prediction cycle... n and exponential constant Z n Then, according to formula (1) q n =e An ×n Zn Obtain the predicted loss rate of battery capacity over n+1 prediction cycles. Then construct a battery capacity prediction model that satisfies the following formula:
[0100] Q n+1 =1-q n =1-e An ×(n+1) Zn(4),
[0101] Wherein, Q n+1 This is the predicted value of the battery capacity in the (n+1)th prediction cycle. That is, the predicted value of the battery capacity is obtained according to formula (4).
[0102] Based on the prediction methods described above, and taking the current prediction period as n as an example, the prediction process for the inflection point of battery capacity drop is as follows:
[0103] First, according to formula (3) q i =1-Q i Obtain the actual battery capacity loss rate q for n prediction cycles. Then, calculate the actual battery capacity loss rate q and the corresponding prediction cycle using formula (2) lnq. n =A n +Z n The constant coefficient A is determined by fitting ×lnn to the prediction period n. n and exponential constant Z n The value of . Further, the determined constant coefficient A. n and exponential constant Z n Substituting the value into formula (1), we obtain the predicted loss rate q of battery capacity over n+1 prediction cycles. n+1 =e An ×(n+1) Zn Further according to formula (4)Q n+1 =1-e An ×(n+1) Zn Obtain the predicted battery capacity over n+1 prediction cycles. Simultaneously, obtain the actual measured battery capacity over n+1 prediction cycles. Calculate the difference between the actual measured battery capacity over n+1 prediction cycles and the predicted battery capacity, and compare this difference with a difference threshold.
[0104] In the same way, the actual measured value of battery capacity and the predicted value of battery capacity are obtained for n+2 prediction cycles, the difference is calculated, and the difference is compared with the difference threshold.
[0105] If the difference at the n+1 prediction cycle and the difference at the n+2 prediction cycle both exceed the difference threshold, then it is determined that the battery capacity drop inflection point occurs at the nth prediction cycle.
[0106] Therefore, this application can predict the inflection point of battery capacity drop in advance and can detect the rapid decrease in battery capacity in a timely and effective manner.
[0107] Further reference Figure 8 As a response to the above Figure 2-7 The implementation of the method shown in this application provides an embodiment of a device for predicting the inflection point of battery capacity drop, which is similar to... Figure 2-7 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.
[0108] like Figure 8 As shown, the battery capacity drop inflection point prediction device 80 described in this embodiment includes a first acquisition module 81, a second acquisition module 82, a third acquisition module 83, a comparison module 84, and a judgment module 85. Wherein:
[0109] The first acquisition module 81 is used to acquire the predicted value of the battery capacity for each of the multiple prediction cycles of the battery charging and discharging.
[0110] The second acquisition module 82 is used to acquire the actual measured value of the battery capacity for each of the prediction cycles.
[0111] The third acquisition module 83 is used to acquire the difference between the predicted value and the actual measured value for each prediction period.
[0112] The comparison module 84 is used to compare each of the differences with a difference threshold.
[0113] The judgment module 85 is used to determine the battery capacity drop inflection point when the comparison module finds that the difference between the prediction cycles corresponding to a consecutive preset number of prediction cycles all exceed the difference threshold.
[0114] Optionally, the first acquisition module 81 is further configured to acquire the predicted loss rate of the battery capacity for each prediction cycle, and then acquire the predicted value of the battery capacity for each prediction cycle based on the predicted loss rate of the battery capacity for each prediction cycle.
[0115] Optionally, the first acquisition module 81 is further used to construct a battery capacity prediction loss rate model, and satisfies the following formula:
[0116] q n =e An ×n Zn (1),
[0117] Wherein, the q n Let e be the predicted loss rate of the battery capacity in the nth prediction period, and let A be the natural constant. n Z is a constant coefficient, where n is the number of prediction periods and is an integer greater than 0. n A is the exponential constant of n. n and the Z n It varies depending on the value of n.
[0118] Furthermore, n takes a value according to each prediction period to obtain the predicted loss rate of battery capacity for each prediction period through the formula (1).
[0119] Optionally, the first acquisition module 81 is further configured to take the logarithm of both sides of the formula (1) to obtain the following formula: lnq n =A n +Z n ×lnn (2),
[0120] Obtain the actual battery capacity loss rate and the corresponding prediction cycle number for n prediction cycles, and substitute the actual loss rate and the corresponding prediction cycle number into the q in formula (2). n And the n, to perform linear fitting on the formula (2) to obtain the A n and the Z n The value;
[0121] Further based on the aforementioned A n and the Z n The value is used to obtain the predicted value of the battery capacity over n+1 prediction cycles.
[0122] Optionally, the actual capacity loss rate of the battery satisfies the following formula:
[0123] q i =1-Q i (3),
[0124] Where q i Q represents the actual loss rate of the battery capacity in the i-th prediction period. i The actual measured value of the battery capacity during the i-th prediction cycle;
[0125] The value of i is taken according to each prediction period. When the value of i is equal to n, the actual loss rate of the battery capacity for n prediction periods is obtained by formula (3).
[0126] Optionally, the first acquisition module 81 is further used to construct a battery capacity prediction model, satisfying the following formula:
[0127] Q n+1 =1-e An ×(n+1) Zn (4),
[0128] Wherein, Q n+1 This is the predicted value of the battery capacity in the (n+1)th prediction cycle.
[0129] Optionally, in two adjacent prediction cycles of battery charging and discharging, the first acquisition module 81 acquires a first predicted value of the battery capacity in the previous prediction cycle and a second predicted value of the battery capacity in the next prediction cycle, respectively.
[0130] The second acquisition module 82 acquires the first actual measurement value of the battery capacity in the previous prediction cycle and the second actual measurement value of the battery capacity in the next prediction cycle, respectively.
[0131] The third acquisition module 83 acquires the first difference between the first predicted value and the first actual measured value, and acquires the second difference between the second predicted value and the second actual measured value;
[0132] The price comparison module 84 compares the first difference and the second difference with the difference threshold respectively. If the price comparison module 84 finds that both the first difference and the second difference exceed the difference threshold, the judgment module 85 determines that the battery capacity drop inflection point was generated in the previous prediction cycle.
[0133] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 9 , Figure 9 This is a basic structural block diagram of the computer device in this embodiment.
[0134] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are interconnected via a system bus. It should be noted that only the computer device 6 with components 61-63 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.
[0135] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.
[0136] The memory 61 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 61 may be an internal storage unit of the computer device 6, such as the hard disk or memory of the computer device 6. In other embodiments, the memory 61 may also be an external storage device of the computer device 6, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 6. Of course, the memory 61 may also include both the internal storage unit and its external storage device of the computer device 6. In this embodiment, the memory 61 is typically used to store the operating system and various application software installed on the computer device 6, such as computer-readable instructions for predicting the inflection point of battery capacity drops. In addition, the memory 61 can also be used to temporarily store various types of data that have been output or will be output.
[0137] In some embodiments, the processor 62 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 62 is typically used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to execute computer-readable instructions stored in the memory 61 or to process data, such as computer-readable instructions for executing the method for predicting the inflection point of battery capacity drops.
[0138] The network interface 63 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 6 and other electronic devices.
[0139] Therefore, this application can predict the prediction period for the battery capacity drop inflection point by obtaining the predicted value of the battery capacity and the actual measured value of the battery capacity for multiple prediction cycles. This allows for the prediction of the battery capacity drop inflection point in advance and timely and effective detection of rapid decrease in battery capacity.
[0140] This application also provides another embodiment, namely, a computer program product storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the method for predicting the inflection point of battery capacity drop as described above.
[0141] This application provides a method and related equipment for predicting the inflection point of battery capacity drop. The prediction method includes: acquiring a predicted value of battery capacity for each prediction cycle in multiple prediction cycles of battery charging and discharging; acquiring an actual measured value of battery capacity for each prediction cycle; acquiring the difference between the predicted value and the actual measured value for each prediction cycle; comparing each difference with a difference threshold; and determining that the battery capacity drop inflection point occurs in the first prediction cycle of the consecutive preset number of prediction cycles if the difference exceeds the difference threshold. Therefore, by acquiring the predicted value and actual measured value of battery capacity for multiple prediction cycles, the prediction cycle time point for the battery capacity drop inflection point can be predicted, allowing for early prediction of the battery capacity drop inflection point and timely and effective detection of rapid battery capacity reduction. It has good application scenarios. Furthermore, the method is simple, can be written into a test program, and can automatically identify batteries about to experience a drop in capacity, reducing resource waste.
[0142] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0143] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0144] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for predicting the inflection point of battery capacity drop, characterized in that, The prediction method includes: In multiple prediction cycles of battery charging and discharging, the predicted value of battery capacity for each prediction cycle is obtained. Obtain the actual measured value of the battery capacity for each of the predicted cycles; The difference between the predicted value and the actual measured value for each prediction cycle is obtained, and each difference is compared with a difference threshold. If the difference for a consecutive preset number of prediction cycles exceeds the difference threshold, the battery capacity drop inflection point is determined to occur in the first prediction cycle of the consecutive preset number of prediction cycles.
2. The method for predicting the inflection point of battery capacity drop according to claim 1, characterized in that, The step of obtaining the predicted value of the battery capacity for each prediction cycle further includes: Obtain the predicted loss rate of battery capacity for each prediction cycle; The predicted value of the battery capacity for each prediction period is obtained based on the predicted loss rate of the battery capacity for each prediction period.
3. The method for predicting the inflection point of battery capacity drop according to claim 2, characterized in that, The step of obtaining the predicted loss rate of battery capacity for each prediction cycle further includes: Construct a battery capacity prediction loss rate model that satisfies the following formula: q n =e An ×n Zn (1), Wherein, the q n Let e be the predicted loss rate of the battery capacity in the nth prediction period, and let A be the natural constant. n Z is a constant coefficient, where n is the number of prediction periods and is an integer greater than 0. n A is the exponential constant of n. n and the Z n It varies depending on the value of n; The value of n is taken according to each prediction period, so as to obtain the predicted loss rate of battery capacity for each prediction period through the formula (1).
4. The method for predicting the inflection point of battery capacity drop according to claim 3, characterized in that, The step of obtaining the predicted value of the battery capacity for each prediction period based on the predicted loss rate of the battery capacity for each prediction period further includes: Taking the logarithm of both sides of formula (1), we obtain the following formula: lnq n =A n +Z n ×lnn (2), Obtain the actual battery capacity loss rate and the corresponding prediction cycle number for n prediction cycles, and substitute the actual loss rate and the corresponding prediction cycle number into the q in formula (2). n And the n, to perform linear fitting on the formula (2) to obtain the A n and the Z n The value; According to A n and the Z n The value is used to obtain the predicted value of the battery capacity over n+1 prediction cycles.
5. The method for predicting the inflection point of battery capacity drop according to claim 4, characterized in that, The step of obtaining the actual battery capacity loss rate over n prediction cycles further includes: The actual loss rate of the battery capacity satisfies the following formula: q i =1-Q i (3), Where q i Q is the actual loss rate of the battery capacity in the i-th prediction period. i The actual measured value of the battery capacity during the i-th prediction cycle; The value of i is taken according to each prediction period. When the value of i is equal to n, the actual loss rate of the battery capacity for n prediction periods is obtained by formula (3).
6. The method for predicting the inflection point of battery capacity drop according to claim 4, characterized in that, According to A n and the Z n The step of obtaining the predicted value of the battery capacity over n+1 prediction periods further includes: Construct a battery capacity prediction model that satisfies the following formula: Q n+1 =1-e An ×(n+1) Zn (4), Wherein, Q n+1 This is the predicted value of the battery capacity in the (n+1)th prediction cycle.
7. The method for predicting the inflection point of battery capacity drop according to any one of claims 1-6, characterized in that, The method for predicting the inflection point of battery capacity drop also includes: In two adjacent prediction cycles of battery charging and discharging, a first predicted value of the battery capacity in the previous prediction cycle and a second predicted value of the battery capacity in the next prediction cycle are obtained respectively. The first actual measurement value of the battery capacity in the previous prediction cycle and the second actual measurement value of the battery capacity in the next prediction cycle are obtained respectively. Obtain a first difference between the first predicted value and the first actual measured value, and obtain a second difference between the second predicted value and the second actual measured value; The first difference and the second difference are compared with the difference threshold respectively. If both the first difference and the second difference exceed the difference threshold, it is determined that the battery capacity drop inflection point occurred in the previous prediction cycle.
8. A device for predicting the inflection point of battery capacity drop, characterized in that, The prediction device includes: The first acquisition module is used to acquire the predicted value of the battery capacity for each of the multiple prediction cycles of battery charging and discharging. The second acquisition module is used to acquire the actual measured value of the battery capacity for each prediction cycle. The third acquisition module is used to acquire the difference between the predicted value and the actual measured value for each prediction period; The comparison module is used to compare each of the differences with a difference threshold; The judgment module is used to determine the battery capacity drop inflection point when the comparison module finds that the differences corresponding to the prediction cycles of the consecutive preset number of prediction cycles all exceed the difference threshold.
9. A device for predicting the inflection point of battery capacity drop, characterized in that, The prediction device includes a memory and a processor, the memory storing computer-readable instructions, and the processor executing the computer-readable instructions to implement the steps of the method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 7.