Method and system for detecting residual electric quantity of battery pack

Abstract

The invention provides a battery pack remaining capacity detection method and system, and relates to the technical field of battery pack remaining capacity detection, and the method comprises the steps: dividing battery cells with good consistency and battery cells with poor consistency into different clusters through detecting the real-time operation data of the battery cells; lifting and calculating the weight for the high-consistency cluster, and reducing the corresponding weight for the low-consistency cluster; the clustering calculation is beneficial to reducing the calculation amount, and the output final SOC value is more accurate; in addition, signals can be sent to the BMS for the battery cells divided into the low-consistency clusters, output of the battery cells is reduced through control of the BMS, and the situation that the safety is affected due to the fact that the EV is limited due to power shortage of the battery cells is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of battery pack remaining power detection technology, and more specifically, to a battery pack remaining power detection method and system. Background Art

[0002] Lithium iron phosphate batteries are widely used in electric vehicles due to their low cost and high safety. SOC refers to the remaining power of the battery; for lithium iron phosphate batteries, when the SOC is 100%, all lithium ions have moved from the positive electrode to the negative electrode and are embedded in the carbon of the negative electrode. The discharge process is also the process of lithium ions moving from the negative electrode to the positive electrode. When all the lithium ions in the negative electrode move to the positive electrode, the SOC is 0%.

[0003] During discharge, no matter what the SOC value is, the voltage of the positive electrode of lithium iron phosphate is 3.45V, and the voltage of the negative electrode of lithium iron phosphate is a variable value. When the SOC is equal to 0%, the negative electrode voltage value is about 1.5V, but when the SOC is close to 100%, the voltage value is only about 0.08V. Therefore, the OCV range is 1.95V-3.37V, and its OCV-SOC curve is as follows Figure 4 As shown in the figure, we can see that the SOC curve is too flat when the SOC is between 20% and 80%, and the extreme value is only about 0.1V, which leads to a problem: SOC is easy to be inaccurately measured within this range; Different manufacturers have different methods of measuring SOC. A common solution is to estimate the remaining battery capacity by calculating the integral of current and time. This method is very dependent on the accuracy of the sensor. If it is not fully calibrated for a long time, the error will continue to accumulate and become larger. In addition, low temperature will also cause the battery capacity to decrease, which will also affect the measurement accuracy of this method.

[0004] Poor consistency of lithium iron phosphate refers to the poor consistency of remaining power between different lithium iron phosphate cells. This is because the internal resistance of lithium iron phosphate batteries is high, and the internal resistance of each battery cell is different. Part of the power is consumed by the internal resistance during charging and discharging (equivalent to several bottles of the same size leaking water, but the volume of the leak is different). Over time, the difference in power between batteries will become larger and larger. Another is that divalent iron may be oxidized or reduced to trivalent iron and iron element during the redox reaction, which may also change the internal resistance of the battery. In addition to the problem of inaccurate SOC measurement, overcharging or over-discharging of a single cell will also affect the internal resistance of the battery. In the end, it is possible that the actual SOC of 4 batteries is 80%, 70%, 50%, and 30%. This is a problem of poor consistency of lithium iron phosphate; The battery pack of new energy vehicles is composed of modules composed of individual batteries (cells) connected in series or in parallel, and then multiple modules are combined to form a battery pack. The cycle number of lithium iron phosphate single cells can reach 3000-4000 times, but the life of the entire battery pack is affected by the worst single cell, and the overall cycle may not reach 4000 times or even less than 3000 times. This is the barrel effect of the battery.

[0005] Assume there are 4 cells with SOC of 80%, 80%, 80%, and 30%. Since the difference between the OCV voltages of 30% and 80% is not big, the system may calculate the overall SOC as 75%.

[0006] When 30% of the cells are out of power, the SOC of the four batteries is 50%, 50%, 50%, and 0%. At this time, the battery management system protects the worst battery, which will trigger the battery's over-discharge protection and the system's overall SOC will be displayed as 0%.

[0007] At this time, only 30% of the electricity will be used, and the power display will drop directly from 75% to 0%, which is a power jump. If the power drops directly to 0%, the EV will be restricted, affecting the normal driving of new energy vehicles and easily causing safety accidents.

[0008] Therefore, there is an urgent need for an accurate solution for detecting the remaining battery capacity of a lithium iron phosphate power battery pack. Summary of the invention

[0009] In order to solve the above technical problems, the present invention provides a method and system for detecting the remaining power of a battery pack.

[0010] According to one aspect of the present invention, a method for detecting the remaining power of a battery pack is provided, comprising the following specific steps: S1: Real-time collection of physical parameters and historical data of each battery cell in the battery pack; S2: Calculate the voltage standard deviation, internal resistance difference rate and temperature gradient between each battery cell; generate a comprehensive index of inconsistency; S3: Divide the cells into high consistency clusters and low consistency clusters based on the comprehensive inconsistency index; S4: Use fuzzy control algorithm to dynamically adjust the calculation weights of high consistency clusters and low consistency clusters; S5: Establish an SOC calculation model; take the voltage data of the high consistency cluster and the low consistency cluster and the corresponding weight coefficients as input, and output the SOC calculation value.

[0011] Furthermore, the physical parameters of the battery cells are collected including voltage, current and temperature data.

[0012] Furthermore, the historical data of the battery cell collected in step S1 includes the historical cycle times and the reference internal resistance value.

[0013] Furthermore, in step S2, different weight coefficients are set for the three parameters of voltage standard deviation, internal resistance difference rate and temperature gradient; the weight coefficients are calibrated after experimental calculation; The normalized parameters are calculated by normalizing the three parameters and taking the weighted sum.

[0014] Furthermore, in step S3, a judgment standard is set based on actual experiments; those that are higher than the judgment standard are classified as high consistency clusters, otherwise they are classified as low consistency clusters; Among them, the weight of high consistency clusters is increased, and the weight of low consistency clusters is suppressed; Furthermore, for the cells that have been classified into the high consistency cluster or the low consistency cluster, classification conditions are set; they are further divided into multiple independently calculated clusters and processed separately.

[0015] Furthermore, the input variables of the fuzzy control algorithm in step S4 are the inconsistency comprehensive index and the current SOC estimation value; The output variables are the calculated weights of high-consistency clusters and low-consistency clusters.

[0016] Furthermore, step S5 establishes an SOC calculation model based on the Kalman filter; respectively calculates the SOC mean values ​​of the high consistency cluster and the low consistency cluster, performs weighted fusion, and outputs the final SOC calculation value.

[0017] A second aspect of the present invention provides a battery pack remaining power detection system, which uses the above method for detection, including: a data acquisition module, a data processing module, a weight calculation module and a SOC calculation module; The data acquisition module collects the voltage, current, temperature data, historical cycle times, and benchmark internal resistance value of each battery cell in the battery pack in real time through the BMS; The data processing module processes the collected data, calculates the voltage standard deviation, internal resistance difference rate and temperature gradient between each battery cell, generates an inconsistency comprehensive index, and classifies the data that exceeds the judgment standard into a high consistency cluster according to the pre-set judgment standard, otherwise it is classified as a low consistency cluster; The weight calculation module uses fuzzy control algorithm to dynamically adjust the calculation weights of high consistency clusters and low consistency clusters; The SOC calculation module has a built-in SOC calculation model based on the Kalman filter. It performs weighted fusion through the SOC mean of the high-consistency cluster and the low-consistency cluster and the corresponding calculation weights to output the final SOC calculation value.

[0018] A third aspect of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned battery pack remaining power detection method when executing the computer program.

[0019] Compared with the prior art, the battery pack remaining power detection method and system provided by the present invention detects the real-time operating data of the battery cells and divides the battery cells with good consistency and the battery cells with poor consistency into different clusters; increases the calculation weight of the high-consistency cluster and reduces the corresponding weight of the low-consistency cluster; cluster calculation is beneficial to reduce the amount of calculation, and the final SOC value output is more accurate; in addition, for the battery cells divided into the low-consistency cluster, a signal can be sent to the BMS, and the output of the battery cell can be reduced through BMS control to avoid the situation where the battery cell is low in power and the EV is restricted, which affects safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 Flow chart of a method for detecting remaining power of a battery pack according to an embodiment of the present invention.

[0021] Figure 2 FIG. 4 is a block diagram of a battery pack remaining power detection system according to an embodiment of the present invention.

[0022] Figure 3 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present invention is shown.

[0023] Figure 4 This is the OCV-SOC curve of the lithium iron phosphate battery in the prior art. DETAILED DESCRIPTION

[0024] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.

[0025] As mentioned in the background technology above, the poor consistency of lithium iron phosphate is due to the high internal resistance of lithium iron phosphate batteries. The internal resistance of each battery cell is different. Part of the power is consumed by the internal resistance during charging and discharging. Over time, the power difference between each battery will become larger and larger. Another reason is that divalent iron may be oxidized or reduced to trivalent iron and iron during the redox reaction, which may also change the internal resistance of the battery. In addition to the problem of inaccurate SOC measurement, it is necessary to accurately measure the remaining power of the battery pack to reduce the risk of stalling of new energy electric vehicles.

[0026] Figure 1 FIG. 1 is a flow chart of a method for detecting the remaining power of a battery pack according to an embodiment of the present invention. Figure 1 As shown, a method for detecting the remaining power of a battery pack includes the following specific steps: S1: Real-time collection of physical parameters and historical data of each battery cell in the battery pack; specifically: synchronously measuring the physical parameters and historical data of each battery cell at a sampling rate of 100Hz; Among them, the physical parameters of the collected battery cells include voltage V （i） , Current I (i) And temperature data T (i) ; In step S1, the historical data of the battery cells are collected, including the historical cycle times C (i) And the reference internal resistance R 0(i) ; ( i Take 1, 2, ..., N ), N is the total number of cells; S2: Calculate the voltage standard deviation, internal resistance difference rate and temperature gradient between each battery cell; generate an inconsistency comprehensive index; in step S2, set different weight coefficients for the three parameters of voltage standard deviation, internal resistance difference rate and temperature gradient; the weight coefficient is calibrated after experimental calculation; The normalized parameters are calculated by normalizing the three parameters and taking the weighted sum.

[0027] The specific steps are as follows: The voltage standard deviation is calculated as follows: In the formula, i is the serial number of the battery cell, N is the total number of cells; V （i） is the voltage of the ith cell, Average voltage of the battery cell; is the standard deviation of voltage; The internal resistance difference rate is calculated according to the following formula: In the formula, i is the serial number of the battery cell, N is the total number of cells; The first i Internal resistance of the battery cell; R 0(i) For the i The reference internal resistance of each battery cell; For the i The difference rate of each battery cell, is the average difference rate of battery pack cells.

[0028] The temperature gradient is calculated as follows: In the formula, is the value of the temperature gradient, which is calculated by the difference between the maximum temperature and the minimum temperature of the i-th cell.

[0029] The inconsistency composite index is calculated as follows: α, β, and γ are the weight coefficients of voltage standard deviation, internal resistance difference rate, and temperature gradient, respectively; where, , , They are respectively the maximum values ​​of voltage standard deviation, internal resistance difference rate and temperature gradient in the collected historical data.

[0030] The weight coefficients are calibrated through experiments, where α is 0.5-0.7, β is 0.2-0.3, and γ is 0.1-0.2.

[0031] S3: Divide the cells into high consistency clusters and low consistency clusters based on the inconsistency comprehensive index; in step S3, a judgment standard is set based on actual experiments; cells that exceed the judgment standard are classified as high consistency clusters, otherwise they are classified as low consistency clusters; The judgment criteria are and ; If other conditions are met, they are classified into high consistency clusters, otherwise they are classified into low consistency clusters; among them, the weight of high consistency clusters is increased; the weight of low consistency clusters is suppressed; For the battery cells that have been classified into high consistency clusters or low consistency clusters, set classification conditions; further divide them into multiple independently calculated clusters and process them separately; for the battery cells classified into different consistency clusters, set initial weights according to the number; for the battery cells in the low consistency cluster, further set classification conditions and perform classification processing to reduce the complexity of calculation and improve calculation efficiency.

[0032] S4: Use fuzzy control algorithm to dynamically adjust the calculation weights of high consistency clusters and low consistency clusters; The input variables of the fuzzy control algorithm in step S4 are the inconsistency comprehensive index and the current SOC estimation value; the output variables are the calculation weights of the high consistency cluster and the low consistency cluster; 1: Define input and output variables Input variables: The comprehensive inconsistency index (ICI) ranges from 0 to 1 (0 indicates perfect agreement and 1 indicates severe inconsistency).

[0033] Current SOC estimate: range 0%-100% (sensitive to consistency at low battery).

[0034] Output variables: High consistency cluster weight W H : Range 0.5-1.0 (low consistency cluster weight is ).

[0035] 2: Design membership function ICI fuzzy set partitioning: Low (L): triangle function, vertex at ICI=0.2; Middle (M): triangle function, vertex at ICI=0.5; Height (H): Triangle function, vertex at ICI=0.8.

[0036] Fuzzy set division of SOC: Low battery (L): Trapezoidal function, covering 0%-20%; Medium power (M): trapezoidal function, covering 15%-80%; High power (H): Trapezoidal function, covering 70%-100%.

[0037] Output variable fuzzification High consistency cluster weight W H : Low Weight (LW): Triangle function, vertex at 0.5; Medium Weight (MW): triangle function, vertex at 0.7; High Weight (HW): Triangle function, vertices at 1.0.

[0038] 3: Building a fuzzy rule base Based on expert experience and experimental data, the following rules are designed: 4: Use the centroid method to defuzzify and obtain the calculated weight value.

[0039] S5: Establish an SOC calculation model; take the voltage data of the high consistency cluster and the low consistency cluster and the corresponding weight coefficients as input, and output the SOC calculation value.

[0040] Step S5 establishes an SOC calculation model based on the Kalman filter; calculates the SOC mean of the high consistency cluster and the low consistency cluster respectively, performs weighted fusion, and outputs the final SOC calculation value.

[0041] SOC final is the final calculated value; W H is the high consistency cluster weight, SOC H、 SOC L These are the SOC estimates for the high consistency cluster and the low consistency cluster, respectively.

[0042] The following uses a specific case to introduce the solution of this embodiment. Assume that the power battery pack of a new energy vehicle is a lithium iron phosphate battery with 10 cells, numbered 1, 2, 3, 4, 5, 6, 7, 8, 9, and 10 respectively. The physical parameters and historical data of the power battery cells during operation are collected through the BMS system, and the estimated SOC value is 45%; Real-time collection of physical parameters and historical data of each battery cell in the battery pack; specifically: synchronously measure the physical parameters and historical data of each battery cell at a sampling rate of 100Hz; Among them, the physical parameters of the collected battery cells include voltage V （i） , Current I (i) And temperature data T (i) ; In step S1, the historical data of the battery cells are collected, including the historical cycle times C (i) And the reference internal resistance R 0(i) ; ( i Take 1, 2, ..., N ), N is the total number of cells; Calculate the voltage standard deviation, internal resistance difference rate and temperature gradient between each battery cell; generate an inconsistency comprehensive index; in step S2, set different weight coefficients for the three parameters of voltage standard deviation, internal resistance difference rate and temperature gradient; the weight coefficient is calibrated after experimental calculation; The normalized parameters are calculated by normalizing the three parameters and taking the weighted sum.

[0043] The specific steps are as follows: The voltage standard deviation is calculated as follows: In the formula, i is the serial number of the battery cell, N is the total number of cells; V （i） is the voltage of the ith cell, Average voltage of the battery cell; is the standard deviation of voltage; The internal resistance difference rate is calculated according to the following formula: In the formula, i is the serial number of the battery cell, N is the total number of cells; The first i Internal resistance of the battery cell; R 0(i) For the i The reference internal resistance of each battery cell; For the i The difference rate of each battery cell, is the average difference rate of battery pack cells.

[0044] The temperature gradient is calculated as follows: In the formula, is the value of the temperature gradient, which is calculated by the difference between the maximum temperature and the minimum temperature of the i-th cell.

[0045] The inconsistency composite index is calculated as follows: α, β, and γ are the weight coefficients of voltage standard deviation, internal resistance difference rate, and temperature gradient, respectively; where, , , They are respectively the maximum values ​​of voltage standard deviation, internal resistance difference rate and temperature gradient in the collected historical data.

[0046] The weight coefficients are calibrated through experiments, where α is 0.5-0.7, β is 0.2-0.3, and γ is 0.1-0.2.

[0047] Table 1 BMS data collection table at a certain moment According to the above steps, the voltage standard deviation, the internal resistance difference rate and the temperature gradient are calculated respectively; and the inconsistency comprehensive index ICI is further calculated.

[0048] The calculation results are as follows: =3.222V, =0.085V, =20.6%, ΔT=9℃; ICI=0.751 S3: Divide the cells into high consistency clusters and low consistency clusters based on the inconsistency comprehensive index; in step S3, a judgment standard is set based on actual experiments; cells that exceed the judgment standard are classified as high consistency clusters, otherwise they are classified as low consistency clusters; The judgment criteria are and ; If other conditions are met, they are classified into high consistency clusters, otherwise they are classified into low consistency clusters; among them, the weight of high consistency clusters is increased; the weight of low consistency clusters is suppressed; According to the preset judgment criteria, cells 1, 2, 3, 5, 6, 7, 9, and 10 are classified into the high consistency cluster, and cells 4 and 8 are classified into the low consistency cluster; For the battery cells that have been classified into the high consistency cluster or the low consistency cluster, the classification conditions are set; they are further divided into multiple independently calculated clusters and processed separately; for the battery cells classified into different consistency clusters, the initial weights are set according to the number. Taking this embodiment as an example, there are 10 groups of battery cell data in this embodiment, of which 8 groups are classified into the high consistency cluster and 2 groups are classified into the low consistency cluster; therefore, the initial weight for the high consistency cluster can be set to 0.8, and the initial weight for the low consistency cluster can be set to 0.2. In this embodiment, since the number of battery cells is too small, the use of this method will affect the accuracy of the final weight, so this rule is not used; for the battery cells in the low consistency cluster, the classification conditions can be further set and the classification processing can be carried out to reduce the complexity of the calculation and improve the calculation efficiency; since there are only two battery cells in the low consistency cluster in this experiment, they are not further divided.

[0049] S4: Use fuzzy control algorithm to dynamically adjust the calculation weights of high consistency clusters and low consistency clusters; The input variables of the fuzzy control algorithm in step S4 are the inconsistency comprehensive index and the current SOC estimation value; the output variables are the calculation weights of the high consistency cluster and the low consistency cluster; Input fuzzification ICI=0.751: Membership calculation: ICI=H (high): membership degree = 0.8 (because 0.751 is close to the 0.8 vertex); ICI=M (medium): membership degree = 0.2.

[0050] SOC=45%: Membership calculation: SOC=M (medium charge): membership degree=1.0.

[0051] Fuzzy rule matching Matching rule 8: If ICI=H and SOC=M, the output weight adjustment coefficient is 0.5; Matching rule 6: If ICI=M and SOC=H, but SOC is actually M, this rule is not activated 4: Use the centroid method to defuzzify and obtain the calculated weight value.

[0052] Only rule 8 is activated, with output weight W H =0.5.

[0053] S5: Establish an SOC calculation model; take the voltage data of the high consistency cluster and the low consistency cluster and the corresponding weight coefficients as input, and output the SOC calculation value.

[0054] Step S5 establishes an SOC calculation model based on the Kalman filter; calculates the SOC mean of the high consistency cluster and the low consistency cluster respectively, performs weighted fusion, and outputs the final SOC calculation value.

[0055] SOC final is the final calculated value; W H is the high consistency cluster weight, SOC H、 SOC L These are the SOC estimates for the high consistency cluster and the low consistency cluster, respectively.

[0056] Estimate the remaining battery capacity by calculating the integral of current and time SOC H is 44%, SOC L 35%; The final SOC value calculated through weighted fusion is 39.5%.

[0057] This embodiment detects the real-time operating data of the battery cells and divides the battery cells with good consistency and the battery cells with poor consistency into different clusters; increases the calculation weight of the high-consistency cluster and reduces the corresponding weight of the low-consistency cluster; cluster calculation is beneficial to reducing the amount of calculation, and the final SOC value output is more accurate; in addition, for the battery cells divided into the low-consistency cluster, a signal can be sent to the BMS, and the output of the battery cell can be reduced through BMS control to avoid the situation where the battery cell is low in power and the EV is restricted, which affects safety.

[0058] Example 2 A second aspect of the present invention provides a battery pack remaining power detection system, which uses the above method for detection, including: a data acquisition module, a data processing module, a weight calculation module and a SOC calculation model; The data acquisition module collects the voltage, current, temperature data, historical cycle times, and benchmark internal resistance value of each battery cell in the battery pack in real time through the BMS; The data processing module processes the collected data, calculates the voltage standard deviation, internal resistance difference rate and temperature gradient between each battery cell, generates an inconsistency comprehensive index, and classifies the data that exceeds the judgment standard into a high consistency cluster according to the pre-set judgment standard, otherwise it is classified as a low consistency cluster; The weight calculation module uses fuzzy control algorithm to dynamically adjust the calculation weights of high consistency clusters and low consistency clusters; The SOC calculation module has a built-in SOC calculation model based on the Kalman filter. It performs weighted fusion through the SOC mean of the high-consistency cluster and the low-consistency cluster and the corresponding calculation weights to output the final SOC calculation value.

[0059] Example 3 Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present invention is shown.

[0060] It should be noted that the computer system of the electronic device in this embodiment is only an example and should not bring any limitation to the functions and scope of use of the embodiment of the present invention.

[0061] In the present embodiment, the computer system includes a central processing unit 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory 402 or the program loaded into the random access memory 403 from the storage part 408, such as performing the tailless screw sleeve deformation detection system and method based on multi-spectral imaging described in the above-mentioned embodiment. In the random access memory 403, various programs and data required for system operation are also stored. The central processing unit 401, the read-only memory 402 and the random access memory 403 are connected to each other by a bus 404. The input / output interface 405 is also connected to the bus 404.

[0062] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0063] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit 401, various functions defined in the system of the present invention are executed.

[0064] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0065] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Among them, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0066] The units involved in the embodiments of the present invention may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, limit the units themselves.

[0067] According to one aspect of the present invention, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0068] As another aspect, the present invention further provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the tailless screw sleeve deformation detection system and method based on multispectral imaging described in the above embodiment.

[0069] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0070] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation of the present invention.

[0071] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the embodiments disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary technical means in the art that are not disclosed in the present invention.

[0072] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for detecting the remaining power of a battery pack, characterized in that: The specific steps include: S1: Real-time collection of physical parameters and historical data of each battery cell in the battery pack; S2: Calculate the voltage standard deviation, internal resistance difference rate and temperature gradient between each battery cell; generate a comprehensive index of inconsistency; S3: Divide the cells into high consistency clusters and low consistency clusters based on the comprehensive inconsistency index; S4: Use fuzzy control algorithm to dynamically adjust the calculation weights of high consistency clusters and low consistency clusters; S5: Establish an SOC calculation model; take the voltage data of the high consistency cluster and the low consistency cluster and the corresponding weight coefficients as input, and output the SOC calculation value.

2. The method for detecting the remaining power of a battery pack according to claim 1, characterized in that: In step S1, physical parameters of the battery cell including voltage, current and temperature data are collected.

3. The method for detecting the remaining power of a battery pack according to claim 1 or 2, characterized in that: The historical data of the battery cells collected in step S1 include the historical cycle times and the reference internal resistance value.

4. The method for detecting the remaining power of a battery pack according to claim 1, characterized in that: In step S2, different weight coefficients are set for the three parameters of voltage standard deviation, internal resistance difference rate and temperature gradient; The weight coefficient is calibrated after experimental calculation; The normalized parameters are calculated by normalizing the three parameters and taking the weighted sum.

5. The method for detecting the remaining power of a battery pack according to claim 1, characterized in that: In step S3, a judgment standard is set based on actual experiments; those that are higher than the judgment standard are classified as high consistency clusters, otherwise they are classified as low consistency clusters; Among them, the weight of high consistency clusters is increased, and the weight of low consistency clusters is suppressed.

6. The method for detecting the remaining power of a battery pack according to claim 5, characterized in that: For cells that have been classified into high consistency clusters or low consistency clusters, set classification conditions; further divide them into multiple independently calculated clusters and process them separately.

7. The method for detecting the remaining power of a battery pack according to claim 1, characterized in that: The input variables of the fuzzy control algorithm in step S4 are the inconsistency comprehensive index and the current SOC estimation value; The output variables are the calculated weights of high-consistency clusters and low-consistency clusters.

8. The method for detecting the remaining power of a battery pack according to claim 1, characterized in that: Step S5 establishes an SOC calculation model based on the Kalman filter; calculates the SOC mean of the high consistency cluster and the low consistency cluster respectively, performs weighted fusion, and outputs the final SOC calculation value.

9. A battery pack remaining power detection system, using the method described in any one of claims 1 to 8 for detection, characterized in that: include: Data acquisition module, data processing module, weight calculation module and SOC calculation module; The data acquisition module collects the voltage, current, temperature data, historical cycle times, and benchmark internal resistance value of each battery cell in the battery pack in real time through the BMS; The data processing module processes the collected data, calculates the voltage standard deviation, internal resistance difference rate and temperature gradient between each battery cell, generates an inconsistency comprehensive index, and classifies the data that exceeds the judgment standard into a high consistency cluster according to the pre-set judgment standard, otherwise it is classified as a low consistency cluster; The weight calculation module uses fuzzy control algorithm to dynamically adjust the calculation weights of high consistency clusters and low consistency clusters; The SOC calculation module has a built-in SOC calculation model based on the Kalman filter. It performs weighted fusion through the SOC mean of the high-consistency cluster and the low-consistency cluster and the corresponding calculation weights to output the final SOC calculation value.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the battery pack remaining power detection method described in any one of claims 1-8 are implemented.

Images