Power battery capacity fading anomaly detection method and system, terminal and medium

Abstract

The invention discloses a power battery capacity attenuation anomaly detection method and system, a terminal and a medium, and relates to the technical field of battery detection.The power battery capacity attenuation anomaly detection method is characterized in that a standard attenuation curve is established to serve as a reference, and anomaly is recognized by combining real-time monitoring data prediction with deviation of a theoretical value; complex model training and frequent off-line detection are not needed, and meanwhile, the dependence on a single data source is reduced; and in consideration of more influence factors of power battery capacity attenuation, the theoretical residual capacity at the third moment is calculated by the sum of the actual residual capacity at the second moment and the standard capacity attenuation variable, so that the adaptability to nonlinear change conditions can be improved. The method has the advantages of light weight, real-time performance and robustness, and is particularly suitable for scenes sensitive to cost and computing resources, such as real-time operation of an embedded system.

Description

Technical Field

[0001] The present invention relates to the technical field of battery detection, and more specifically, to a method, system, terminal and medium for detecting abnormal capacity attenuation of power batteries. Background Art

[0002] The detection of abnormal capacity attenuation of power batteries can achieve precise health management, extend the battery life, ensure system reliability, and support the efficient utilization of the entire life cycle of the battery. With the rapid development of the new energy industry, this technology will become the core support for intelligent battery management, green energy transformation and sustainable resource utilization. It plays a key role especially in the fields of electric vehicles, energy storage systems, drones, etc.

[0003] The existing methods for detecting abnormal capacity attenuation of power batteries mainly include direct measurement method, model-driven method and data-driven method. Among them, the direct measurement method generally includes capacity measurement and EIS (electrochemical impedance spectroscopy), which rely on physical detection and require offline operation; the model-driven method requires dynamic update of model parameters and real-time iterative calculation, and the calculation load is relatively high, such as Kalman filtering; while the data-driven method relies on a large amount of historical data to train the model. Although it can handle non-linear problems, it requires a large amount of data, such as the method based on neural network.

[0004] Therefore, how to research and design a method, system, terminal and medium for detecting abnormal capacity attenuation of power batteries that can overcome the above defects is an urgent problem for us to solve at present. Summary of the Invention

[0005] To solve the deficiencies in the prior art, the purpose of the present invention is to provide a method, system, terminal and medium for detecting abnormal capacity attenuation of power batteries. By establishing a standard attenuation curve as a benchmark and combining the deviation between the prediction and the theoretical value with real-time monitoring data to identify abnormalities, complex model training and frequent offline detection are not required, and at the same time, the dependence on a single data source is reduced; and considering that there are many influencing factors for the capacity attenuation of power batteries, the theoretical remaining capacity at the third moment is calculated by the sum of the actual remaining capacity at the second moment and the standard capacity attenuation variable, which can improve the adaptability to non-linear change situations.

[0006] The above technical object of the present invention is achieved through the following technical solutions:

[0007] In the first aspect, a method for detecting abnormal capacity attenuation of power batteries is provided, including the following steps:

[0008] Simulate and construct a standard change curve of the capacity attenuation of the power battery according to the charge and discharge times of the power battery;

[0009] Extract the standard capacity decay variable from the second moment to the third moment from the standard change curve according to the first charge-discharge times at the second moment and the second charge-discharge times at the third moment;

[0010] Simulate and predict the estimated remaining capacity at the third moment based on the actual remaining capacity monitored at each moment between the first moment and the second moment;

[0011] Calculate the theoretical remaining capacity at the third moment by summing the actual remaining capacity at the second moment and the standard capacity decay variable;

[0012] Compare and analyze the estimated remaining capacity and the theoretical remaining capacity to determine the detection result of the abnormal detection of the power battery capacity decay.

[0013] Further, the standard change curve is constructed using a linear decay model, and the specific expression is:

[0014] Cn = C0(1 - n×α);

[0015] Where, Cn represents the remaining capacity corresponding to the charge-discharge times n of the power battery; C0 represents the initial capacity of the power battery; n represents the charge-discharge times; α represents the decay rate related to temperature.

[0016] Further, the standard change curve is constructed using a power-law decay model, and the specific expression is:

[0017] Cn = C0(1 - k×nβ);

[0018] Where, Cn represents the remaining capacity corresponding to the charge-discharge times n of the power battery; C0 represents the initial capacity of the power battery; n represents the charge-discharge times; α represents the fitting rate related to temperature; k represents the fitting parameter related to the battery material.

[0019] Further, the actual remaining capacity is monitored by using the current integration method for the charging and / or discharging process of the power battery.

[0020] Further, the detection result of the abnormal detection of the power battery capacity decay is specifically:

[0021] If the absolute value of the difference between the estimated remaining capacity and the theoretical remaining capacity is less than the error threshold, the detection result is the normal capacity decay state;

[0022] If the absolute value of the difference between the estimated remaining capacity and the theoretical remaining capacity is greater than the error threshold, and the estimated remaining capacity is greater than the theoretical remaining capacity, the detection result is the capacity temporarily restored state;

[0023] If the absolute value of the difference between the estimated remaining capacity and the theoretical remaining capacity is greater than the error threshold, and the estimated remaining capacity is less than the theoretical remaining capacity, the detection result is the state of abnormal capacity attenuation.

[0024] Further, the method further includes:

[0025] If the detection result is the state of abnormal capacity attenuation, obtain the working condition probability distribution information of multiple capacity attenuation influencing factors of the power battery at the second moment and the third moment;

[0026] Compare the working condition probability distribution information of a single capacity attenuation influencing factor at the second moment and the third moment, and extract the first working condition information with a probability increment change of the corresponding capacity attenuation influencing factor;

[0027] Combine all the first working condition information of all capacity attenuation influencing factors to construct an abnormal working condition of the state of abnormal capacity attenuation.

[0028] Further, the method further includes:

[0029] Adopt a sliding window analysis method to analyze the probability change attributes of the first working condition information at each moment in the corresponding working condition probability distribution information;

[0030] Statistically calculate the proportion of the moments when the probability change attribute of the first working condition information is a probability increment change and the detection result is the state of abnormal capacity attenuation;

[0031] If the proportion of moments is less than the correction threshold, regard the corresponding first working condition information as invalid working condition information that does not belong to the abnormal working condition.

[0032] In a second aspect, a power battery capacity attenuation abnormal detection system is provided. The system is used to implement a power battery capacity attenuation abnormal detection method as described in any one of the first aspects, and includes:

[0033] A curve construction module, configured to simulate and construct a standard change curve of the power battery capacity attenuation according to the charge and discharge times of the power battery;

[0034] A variable extraction module, configured to extract the standard capacity attenuation variable from the second moment to the third moment from the standard change curve according to the first charge and discharge times at the second moment and the second charge and discharge times at the third moment;

[0035] A capacity prediction module, configured to simulate and predict the estimated remaining capacity at the third moment according to the actual remaining capacity monitored at each moment between the first moment and the second moment;

[0036] A theoretical calculation module, configured to calculate the theoretical remaining capacity at the third moment by summing the actual remaining capacity at the second moment and the standard capacity attenuation variable;

[0037] Anomaly detection module, configured to compare and analyze the estimated remaining capacity with the theoretical remaining capacity to determine the detection result of the abnormal detection of the power battery capacity attenuation.

[0038] In a third aspect, a computer terminal is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a method for abnormal detection of power battery capacity attenuation as described in any one of the first aspects is implemented.

[0039] In a fourth aspect, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a method for abnormal detection of power battery capacity attenuation as described in any one of the first aspects can be implemented.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] 1. For a method for abnormal detection of power battery capacity attenuation provided by the present invention, by establishing a standard attenuation curve as a reference, and combining the deviation between the real-time monitoring data prediction and the theoretical value to identify anomalies, complex model training and frequent offline detection are not required, and at the same time, the dependence on a single data source is reduced; and considering that there are many influencing factors for the power battery capacity attenuation, the theoretical remaining capacity at the third moment is calculated by the sum of the actual remaining capacity at the second moment and the standard capacity attenuation variable, which can improve the adaptability to non-linear change situations;

[0042] 2. The present invention has advantages in light weight, real-time performance, and robustness, and is particularly suitable for scenarios sensitive to cost and computing resources, such as real-time operation of embedded systems;

[0043] 3. The present invention conducts a detailed comparative analysis of the estimated remaining capacity and the theoretical remaining capacity, which can not only identify the abnormal attenuation state of the capacity, but also identify the temporarily restored state of the capacity, effectively improving the accuracy of the abnormal detection of the power battery capacity attenuation;

[0044] 4. When the detection result is the abnormal attenuation state of the capacity, the present invention compares the probability distribution information of the single capacity attenuation influencing factor at the second moment and the third moment, and extracts the first working condition information with a probability increment change of the corresponding capacity attenuation influencing factor, which can accurately judge the specific abnormal working condition in the case of multi-factor influencing the power battery capacity attenuation, and can provide detailed reference data for precise health management;

[0045] 5. The present invention uses a sliding window analysis method to analyze the probability change attributes of each moment of the first operating condition information in the corresponding operating condition probability distribution information, and counts the proportion of moments when the probability change attribute of the first operating condition information is a probability increment change and the detection result is a state of abnormal capacity attenuation. For the first operating condition information with a proportion less than the correction threshold, it is regarded as invalid operating condition information that does not belong to the abnormal operating condition. Considering the influence coupling of factors, some unreliable operating conditions are eliminated, improving the accuracy and reliability of abnormal operating condition extraction. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, form a part of this application, and do not limit the embodiments of the present invention. In the drawings:

[0047] Figure 1 is the flowchart in Embodiment 1 of the present invention;

[0048] Figure 2 is the system block diagram in Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and the drawings. The illustrative embodiments and descriptions thereof of the present invention are only used to explain the present invention and do not limit the present invention.

[0050] Embodiment 1: A method for detecting abnormal attenuation of the power battery capacity, as Figure 1 shown, includes the following steps:

[0051] S1: Simulate and construct a standard change curve of the power battery capacity attenuation based on the charge and discharge times of the power battery;

[0052] S2: Extract the standard capacity attenuation variable from the second moment to the third moment from the standard change curve according to the first charge and discharge times at the second moment and the second charge and discharge times at the third moment;

[0053] S3: Simulate and predict the estimated remaining capacity at the third moment based on the actual remaining capacity monitored at each moment between the first moment and the second moment;

[0054] S4: Calculate the theoretical remaining capacity at the third moment by adding the actual remaining capacity at the second moment and the standard capacity attenuation variable;

[0055] S5: Compare and analyze the estimated remaining capacity and the theoretical remaining capacity to determine the detection result of the abnormal attenuation detection of the power battery capacity.

[0056] In step S1, the standard change curve of the power battery capacity attenuation can be constructed based on historical data or experimental statistics using a linear attenuation model, or a power-law attenuation model can be used for construction, or an exponential attenuation model or a piecewise linear model can also be used for construction.

[0057] For example, when the standard change curve is constructed using a linear attenuation model, the specific expression is:

[0058] Cn = C0(1 - n×α);

[0059] Where, Cn represents the remaining capacity corresponding to the charge-discharge cycle number n of the power battery; C0 represents the initial capacity of the power battery; n represents the charge-discharge cycle number; α represents the attenuation rate related to temperature.

[0060] Another example is that when the standard change curve is constructed using a power-law attenuation model, the specific expression is:

[0061] Cn = C0(1 - k×nβ);

[0062] Where, Cn represents the remaining capacity corresponding to the charge-discharge cycle number n of the power battery; C0 represents the initial capacity of the power battery; n represents the charge-discharge cycle number; α represents the fitting rate related to temperature; k represents the fitting parameter related to the battery material.

[0063] In step S2, according to the first charge-discharge cycle number and the second charge-discharge cycle number, the remaining capacities corresponding to the second moment and the third moment can be determined from the standard change curve respectively, and then subtracting the remaining capacity corresponding to the second moment from the remaining capacity corresponding to the third moment, the standard capacity attenuation variable from the second moment to the third moment can be obtained.

[0064] In step S3, the actual remaining capacity can be obtained by monitoring the charging or discharging process of the power battery using the current integration method. In addition, considering that the power battery will not be fully charged or fully discharged during the actual charging and discharging process, in order to ensure the accuracy of the actual remaining capacity, the present invention can mutually verify and correct the actual remaining capacity monitored during the charging process and the actual remaining capacity monitored during the discharging process in one charge-discharge cycle.

[0065] In the present invention, the estimated remaining capacity at the third moment can be predicted using time series prediction or the least squares method.

[0066] In step S4, when there are data fluctuations in the standard change curve, the standard capacity attenuation variable may be positive. In the present invention, its positive value can be replaced with 0 for calculation.

[0067] In step S5, the detection result of the abnormal attenuation of the power battery capacity is specifically as follows: if the absolute value of the difference between the estimated remaining capacity and the theoretical remaining capacity is less than the error threshold, the detection result is the normal attenuation state of the capacity; if the absolute value of the difference between the estimated remaining capacity and the theoretical remaining capacity is greater than the error threshold, and the estimated remaining capacity is greater than the theoretical remaining capacity, the detection result is the temporary recovery state of the capacity; if the absolute value of the difference between the estimated remaining capacity and the theoretical remaining capacity is greater than the error threshold, and the estimated remaining capacity is less than the theoretical remaining capacity, the detection result is the abnormal attenuation state of the capacity.

[0068] When the detection result is the abnormal attenuation state of the capacity, the present invention also obtains the working condition probability distribution information of multiple capacity attenuation influencing factors of the power battery at the second moment and the third moment; compares the working condition probability distribution information of a single capacity attenuation influencing factor at the second moment and the third moment, and extracts the first working condition information with a probability increment change of the corresponding capacity attenuation influencing factor; combines all the first working condition information of all capacity attenuation influencing factors to construct an abnormal working condition in the abnormal attenuation state of the capacity.

[0069] The present invention conducts a detailed comparative analysis of the estimated remaining capacity and the theoretical remaining capacity, which can not only identify the abnormal attenuation state of the capacity, but also identify the temporary recovery state of the capacity, effectively improving the accuracy of the abnormal attenuation detection of the power battery capacity.

[0070] In addition, when the detection result is the abnormal attenuation state of the capacity, the present invention uses a sliding window analysis method to analyze the probability change attributes of the first working condition information at each moment in the corresponding working condition probability distribution information; counts the proportion of the moments when the probability change attribute of the first working condition information is a probability increment change and the detection result is the abnormal attenuation state of the capacity; if the moment proportion is less than the correction threshold, the corresponding first working condition information is regarded as invalid working condition information that does not belong to the abnormal working condition.

[0071] The present invention can accurately judge the specific abnormal working condition in the case of multi-factor influencing the power battery capacity attenuation, and can provide detailed reference data for accurate health management.

[0072] Embodiment 2: A system for detecting abnormal attenuation of power battery capacity, which is used to implement a method for detecting abnormal attenuation of power battery capacity as described in Embodiment 1, as Figure 2 shown, includes a curve construction module, a variable extraction module, a capacity prediction module, a theoretical calculation module, and an abnormal detection module.

[0073] Among them, a curve construction module is used to simulate and construct a standard change curve of the power battery capacity attenuation according to the charge and discharge times of the power battery; a variable extraction module is used to extract a standard capacity attenuation variable from the second moment to the third moment from the standard change curve according to the first charge and discharge times at the second moment and the second charge and discharge times at the third moment; a capacity prediction module is used to simulate and predict the estimated remaining capacity at the third moment according to the actually monitored remaining capacity at each moment between the first moment and the second moment; a theoretical calculation module is used to calculate the theoretical remaining capacity at the third moment by adding the actually remaining capacity at the second moment and the standard capacity attenuation variable; an anomaly detection module is used to compare and analyze the estimated remaining capacity and the theoretical remaining capacity to determine the detection result of the anomaly detection of the power battery capacity attenuation.

[0074] The present invention also records a computer terminal, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a method for detecting anomalies in the attenuation of the power battery capacity as recorded in Embodiment 1.

[0075] The present invention also records a computer-readable medium, on which a computer program is stored. When the computer program is executed by a processor, it can implement a method for detecting anomalies in the attenuation of the power battery capacity as recorded in Embodiment 1.

[0076] Working principle: The present invention establishes a standard attenuation curve as a benchmark, combines the deviation between the real-time monitored data prediction and the theoretical value to identify anomalies. Compared with methods such as direct measurement method, model-driven method, and incremental capacity analysis, it does not require complex model training and frequent offline detection, and at the same time reduces the dependence on a single data source; and considering that there are many influencing factors for the power battery capacity attenuation, the theoretical remaining capacity at the third moment is calculated by adding the actually remaining capacity at the second moment and the standard capacity attenuation variable, which can improve the adaptability to non-linear change situations; the present invention has advantages in light weight, real-time performance, and robustness, and is especially suitable for scenarios sensitive to cost and computing resources, such as real-time operation of embedded systems; in addition, the present invention conducts a detailed comparison and analysis of the estimated remaining capacity and the theoretical remaining capacity, which can not only identify the abnormal attenuation state of the capacity, but also identify the temporarily restored state of the capacity, effectively improving the accuracy of the anomaly detection of the power battery capacity attenuation.

[0077] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0078] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or one or more of the blocks.

[0079] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or one or more of the blocks.

[0080] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or one or more of the blocks.

[0081] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for detecting abnormal capacity attenuation of a power battery, characterized in that: The following steps are involved: According to the number of charge and discharge times of the power battery, a standard change curve of power battery capacity attenuation is simulated and constructed; According to the first charge and discharge number at the second moment and the second charge and discharge number at the third moment, a standard capacity attenuation variable from the second moment to the third moment is extracted from the standard change curve; The estimated remaining capacity at the third moment is obtained by simulating and predicting the actual remaining capacity monitored at each moment between the first moment and the second moment; The theoretical remaining capacity at the third moment is calculated by the sum of the actual remaining capacity at the second moment and the standard capacity decay variable; The estimated remaining capacity is compared with the theoretical remaining capacity to determine the detection results of abnormal power battery capacity attenuation.

2. A method for detecting abnormal capacity attenuation of a power battery according to claim 1, characterized in that: The standard change curve is constructed using a linear attenuation model, and the specific expression is: Cn=C0(1-n×α); Among them, Cn represents the remaining capacity of the power battery corresponding to the number of charge and discharge times n; C0 represents the initial capacity of the power battery; n represents the number of charge and discharge times; α represents the attenuation rate related to temperature.

3. The method for detecting abnormal capacity attenuation of a power battery according to claim 1, characterized in that: The standard change curve is constructed using a power law decay model, and the specific expression is: Cn=C0(1-k×nβ); Among them, Cn represents the remaining capacity of the power battery corresponding to the number of charge and discharge times n; C0 represents the initial capacity of the power battery; n represents the number of charge and discharge times; α represents the fitting rate related to temperature; k represents the fitting parameter related to the battery material.

4. A method for detecting abnormal capacity attenuation of a power battery according to claim 1, characterized in that: The actual remaining capacity is obtained by monitoring the charging and / or discharging process of the power battery using a current integration method.

5. The method for detecting abnormal capacity attenuation of a power battery according to claim 1, characterized in that: The detection result of the abnormal detection of power battery capacity attenuation is specifically as follows: If the absolute value of the difference between the estimated remaining capacity and the theoretical remaining capacity is less than the error threshold, the detection result is a normal capacity decay state; If the absolute value of the difference between the estimated remaining capacity and the theoretical remaining capacity is greater than the error threshold, and the estimated remaining capacity is greater than the theoretical remaining capacity, the detection result is that the capacity is temporarily restored; If the absolute value of the difference between the estimated remaining capacity and the theoretical remaining capacity is greater than the error threshold, and the estimated remaining capacity is less than the theoretical remaining capacity, the detection result is an abnormal capacity attenuation state.

6. A method for detecting abnormal capacity attenuation of a power battery according to any one of claims 1 to 5, characterized in that: The method further includes: If the detection result is an abnormal capacity attenuation state, obtaining operating condition probability distribution information of multiple capacity attenuation influencing factors of the power battery at the second moment and the third moment; Compare the operating condition probability distribution information of the single capacity decay influence factor at the second moment and the third moment, and extract the first operating condition information with the probability increment change of the corresponding capacity decay influence factor; All first operating condition information of all capacity decay influencing factors are combined to construct an abnormal operating condition of abnormal capacity decay state.

7. A method for detecting abnormal capacity attenuation of a power battery according to claim 6, characterized in that: The method further includes: A sliding window analysis method is used to analyze the probability change attribute of the first operating condition information at each moment in the corresponding operating condition probability distribution information; Counting the time proportion of the probability change attribute of the first operating condition information being a probability increment change and the detection result being an abnormal capacity attenuation state; If the time proportion is less than the correction threshold, the corresponding first operating condition information is regarded as invalid operating condition information that does not belong to an abnormal operating condition.

8. A power battery capacity attenuation abnormality detection system, characterized in that: The system is used to implement a method for detecting abnormal capacity attenuation of a power battery as claimed in any one of claims 1 to 7, comprising: A curve construction module is used to simulate and construct a standard change curve of power battery capacity attenuation according to the number of charge and discharge times of the power battery; A variable extraction module, used to extract a standard capacity attenuation variable from the second moment to the third moment from the standard change curve according to the first charge and discharge number at the second moment and the second charge and discharge number at the third moment; A capacity prediction module, used to simulate and predict the actual remaining capacity monitored at each moment between the first moment and the second moment to obtain the estimated remaining capacity at the third moment; A theoretical calculation module, used to calculate the theoretical remaining capacity at a third moment by the sum of the actual remaining capacity at the second moment and the standard capacity decay variable; The anomaly detection module is used to compare and analyze the estimated remaining capacity with the theoretical remaining capacity to determine the detection result of the power battery capacity attenuation anomaly detection.

9. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for detecting abnormal capacity attenuation of a power battery as described in any one of claims 1 to 7 is implemented.

10. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement a method for detecting abnormal capacity attenuation of a power battery as described in any one of claims 1 to 7.

Images