Battery detection method and device, electronic equipment and storage medium

Abstract

The invention discloses a battery detection method and device, electronic equipment and a storage medium, and is applied to the technical field of data processing. The battery detection method comprises the steps of obtaining detection data of a detection feature of a battery in a first time period, obtaining a first weight of the detection feature in a first battery detection model according to the detection feature, and further obtaining a second weight of the detection feature in a second battery detection model according to the detection data of the detection feature in the first time period. And adjusting a first weight corresponding to the detection feature in the first battery detection model to obtain a second battery detection model, and inputting detection data of the detection feature in the first time period into the second battery detection model to obtain a detection result output by the second battery detection model, and the accuracy of determining the health state of the battery is improved.

Description

Technical Field

[0001] This application belongs to the technical field of data processing, and in particular relates to a battery detection method, device, electronic device, and storage medium. Background Art

[0002] Batteries are an important part of communication devices such as base stations and communication buildings, and are key components for ensuring the safe and efficient operation of communication devices. To ensure the normal operation of communication devices and extend the service life of the batteries in communication devices, the health status of the batteries in communication can be detected. Among them, the State of Health (SOH) of a battery refers to a quantitative description of the performance and aging degree of the battery under usage conditions relative to its brand-new state, and this health status can be affected by detection features such as the internal resistance of the battery, the temperature of the battery, and the charge amount of the battery.

[0003] In the related art, the health status of a battery can be determined based on a fixed single detection feature and a fixed detection threshold of this detection feature. For example, when the temperature of the battery is higher than the preset temperature detection threshold, it can indicate that the health status of the battery is poor. Since the foregoing detection method is one-sided and cannot accurately determine the health status of the battery, it affects the normal operation of communication devices. Summary of the Invention

[0004] Embodiments of this application provide a battery detection method, device, electronic device, and storage medium, which can solve the problem of low accuracy in determining the health status of a battery.

[0005] In a first aspect, embodiments of this application provide a battery detection method, and the battery detection method includes:

[0006] Obtain the detection data of the detection features of the battery within a first time period, where the detection features are used to measure the battery performance and / or aging degree of the battery, and the detection features include at least one of the following first detection features: electrical signal, temperature, discharge signal;

[0007] According to the detection features, obtain the first weights of the detection features in a first battery detection model;

[0008] According to the detection data of the detection features within the first time period, adjust the first weights corresponding to the detection features in the first battery detection model to obtain a second battery detection model. The second battery prediction model includes second weights corresponding to the detection features, and the second weights are the second weights after the first weights are adjusted;

[0009] Input the detection data of the detection features within the first time period into the second battery detection model to obtain a detection result output by the second battery detection model, where the detection result is used to reflect the health status of the battery within the first time period.

[0010] In a second aspect, an embodiment of the present application provides a battery detection device, which includes:

[0011] An acquisition module, configured to acquire detection data of a detection feature of a battery within a first time period, where the detection feature is used to measure the battery performance and / or aging degree of the battery, and the detection feature includes at least one of the following first detection features: electrical signal, temperature, discharge signal;

[0012] The acquisition module is further configured to acquire a first weight of the detection feature in a first battery detection model according to the detection feature;

[0013] An adjustment module, configured to adjust a first weight corresponding to the detection feature in the first battery detection model according to the detection data of the detection feature within the first time period, to obtain a second battery detection model, where the second battery prediction model includes a second weight corresponding to the detection feature, and the second weight is the second weight after the first weight is adjusted;

[0014] A determination module, configured to input the detection data of the detection feature within the first time period into the second battery detection model, to obtain a detection result output by the second battery detection model, where the detection result is used to reflect the health status of the battery within the first time period.

[0015] In a third aspect, an embodiment of the present application provides a computer device, which includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the battery detection method according to any item of the first aspect is implemented.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the battery detection method according to any item of the first aspect is implemented.

[0017] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the battery detection method according to any item of the first aspect is implemented.

[0018] The battery detection method of the embodiment of the present application can acquire detection data of a detection feature of a battery within a first time period, and acquire a first weight of the detection feature in a first battery detection model according to the detection feature, and further adjust the first weight corresponding to the detection feature in the first battery detection model according to the detection data of the detection feature within the first time period, to obtain a second battery detection model, and input the detection data of the detection feature within the first time period into the second battery detection model, to obtain a detection result output by the second battery detection model.

[0019] Therefore, in the process of detecting the health state of the battery by the above battery detection method, by analyzing the detection data of the detection feature in the first time period, and then according to the analysis result, dynamically adjusting the first weight corresponding to the detection feature, generating a second weight that is more adapted to the current detection data, so as to improve the accuracy of detecting the health state of the battery based on the detection data. Moreover, the above battery detection method can also analyze the health state of the battery based on multiple detection features, so as to more comprehensively analyze the influence of the detection data corresponding to different detection features on the health state of the battery, and further improve the accuracy of detecting the health state of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0021] Figure 1 It is a flowchart of a battery detection method provided in an embodiment of the present application;

[0022] Figure 2 It is a flowchart of a specific implementation manner of S104 in a battery detection method provided in an embodiment of the present application;

[0023] Figure 3 It is a flowchart of a specific implementation manner of S202 in a battery detection method provided in an embodiment of the present application;

[0024] Figure 4 It is a flowchart of a specific implementation manner of S103 in a battery detection method provided in an embodiment of the present application;

[0025] Figure 5 It is a flowchart of a specific implementation manner of S401 in a battery detection method provided in an embodiment of the present application;

[0026] Figure 6 It is a flowchart of a specific implementation manner of S402 in a battery detection method provided in an embodiment of the present application;

[0027] Figure 7 It is a flowchart of a specific implementation manner of S402 in a battery detection method provided in an embodiment of the present application;

[0028] Figure 8 It is a flowchart of a specific implementation manner of S401 in a battery detection method provided in an embodiment of the present application;

[0029] Figure 9Flowchart of the specific implementation of S402 in a battery detection method provided by an embodiment of the present application;

[0030] Figure 10 Flowchart of the specific implementation after S104 in a battery detection method provided by an embodiment of the present application;

[0031] Figure 11 Schematic structural diagram of a battery detection device provided by an embodiment of the present application;

[0032] Figure 12 Schematic hardware structure diagram of a computer device provided by an embodiment of the present application. Detailed implementation

[0033] The features and exemplary embodiments of various aspects of the present application will be described in detail below. To make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application and not to limit the present application. For those skilled in the art, the present application can be implemented without some of these specific details. The following description of the embodiments is only intended to provide a better understanding of the present application by showing examples of the present application.

[0034] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, the elements defined by the statement "including..." do not exclude the existence of additional identical elements in the process, method, article or device including the elements.

[0035] It should be noted that the acquisition, storage, use, and processing of data in the embodiments of the present application all comply with the relevant regulations of national laws and regulations.

[0036] It should be noted that in the embodiments of the present application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned, and they should be considered exemplary. The purpose is only to illustrate the feasibility in the implementation of the technical solution of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0037] In the related art, the health state of a battery is usually determined based on a fixed single detection feature and a fixed detection threshold for this detection feature. This detection method only considers a certain detection feature in the process of detecting the health state of the battery, which is one-sided, resulting in an inability to accurately determine the health state of the battery and affecting the normal operation of the communication device. Moreover, the fixed detection threshold usually ignores the changes in the communication environment and cannot well adapt to the real-time communication environment, further leading to a low accuracy in determining the health state of the battery.

[0038] To solve the above problems in the related art, the embodiments of the present application provide a battery detection method, device, electronic device, storage medium, and program product. First, the battery detection method provided by the embodiments of the present application will be described in detail below.

[0039] Figure 1 The flowchart of the battery detection method provided by an embodiment of the present application is shown. The execution subject of this battery detection method can be a server. Below, the battery detection method will be described with the server as the execution subject. As Figure 1 shown, the method includes:

[0040] S101, obtain the detection data of the detection feature of the battery within the first time period. The detection feature is used to measure the battery performance and / or aging degree of the battery, and the detection feature includes at least one of the following first detection features: electrical signal, temperature, discharge signal.

[0041] Among them, the above battery detection method can detect the health state of the battery in the communication device to ensure the normal operation of the communication device. The communication device can be a base station, a router, a switch, etc. in the communication building. The detection feature refers to a parameter that can measure the battery performance and / or aging degree of the battery of the communication device, and the detection data is the specific value corresponding to the detection feature, or other battery parameters calculated based on the specific value of the detection feature. For example, the detection data can be the specific temperature value corresponding to the temperature. Another example is that the detection data can be the internal resistance data calculated based on the corresponding current data and voltage data in the electrical signal. The first time period can be a certain period in the past.

[0042] Exemplarily, when detecting the health state of the battery of a base station, the server can obtain the temperature data of the battery in the base station on April 15, 2025, as well as the current data and voltage data of the battery in the base station on April 15, 2025, and calculate the internal resistance data of the battery.

[0043] S102, according to the detection feature, obtain the first weight of the detection feature in the first battery detection model.

[0044] S103. Adjust the first weight corresponding to the detection feature in the first battery detection model according to the detection data of the detection feature in the first time period, to obtain a second battery detection model. The second battery prediction model includes a second weight corresponding to the detection feature, and the second weight is the adjusted second weight of the first weight.

[0045] Among them, the first battery detection model can be an LSTM network model, and the first weight refers to the initial weight of the first battery detection model, which can be determined based on expert experience.

[0046] Continuing with the above example, the server can obtain the first weight 0.1 corresponding to the temperature feature in the first battery detection model. According to the temperature data of the base station's battery on April 15, 2025, it is determined that the difference between the maximum temperature and the minimum temperature is 10 degrees, and the first weight 0.1 is adjusted to obtain the second weight 0.4. The server can obtain the first weight 0.1 corresponding to the electrical signal in the first battery detection model, or it can be understood as the first weight 0.1 corresponding to the internal resistance feature. According to the internal resistance data of the base station's battery on April 15, 2025, it is determined that the internal resistance volatility over time is 2%, and the first weight 0.1 is adjusted to obtain the second weight 0.6. The second battery prediction model includes the second weight 0.4 corresponding to the second temperature feature and the second weight 0.6 corresponding to the internal resistance feature.

[0047] S104. Input the detection data of the detection feature in the first time period into the second battery detection model to obtain the detection result output by the second battery detection model, and the detection result is used to reflect the health status of the battery in the first time period.

[0048] Among them, the second battery detection model is a model including the second weight. The second battery detection model is used to output the health status of the battery in the first time period, and this health status can be reflected in the form of a percentage. The higher the corresponding percentage value, the better the health status of the battery.

[0049] Continuing with the above example, input the temperature data of the base station's battery on April 15, 2025 and the internal resistance data on April 15, 2025 into the second battery detection model to obtain the detection result output by the second battery detection model. The health status of the base station's battery in the first time period is 80%. A health status of more than 50% proves that the health status of the battery is good. Therefore, the health status of the base station's battery is good.

[0050] Thus, in the process of detecting the health state of the battery by the above battery detection method, by analyzing the detection data of the detection feature in the first time period, according to the analysis result, the first weight corresponding to the detection feature is dynamically adjusted in a targeted manner, so that the adjusted second weight can better adapt to the current detection data, thereby improving the accuracy of detecting the health state of the battery based on the detection data. Moreover, the above battery detection method can also analyze the health state of the battery based on multiple detection features, so as to more comprehensively analyze the influence of the detection data corresponding to different detection features on the health state of the battery, thereby further improving the accuracy of detecting the health state of the battery.

[0051] The above S101 to S104 are described in detail below, as follows.

[0052] Regarding S101, in the embodiment of the present application, the server can obtain the detection data of the detection feature of the battery in the first time period. Herein, the battery refers to the battery in a communication device, and the communication device can be a base station, a router, a switch, etc. in a communication building. The first time period is usually a historical time period compared to the current time. For example, March 1, 2025.

[0053] The detection feature of the battery refers to a parameter that can measure the battery performance and / or aging degree. The detection feature can include an electrical signal, a temperature, or a discharge signal. The detection feature can be one or more of these three items, and the detection data is the specific value corresponding to the detection feature. For example, the detection data can be the specific temperature value corresponding to the temperature, or the discharge power and discharge times corresponding to the discharge signal. The detection data can also be other battery parameters calculated based on the specific values of the detection feature. For example, the detection data can be the internal resistance data calculated based on the corresponding current data and voltage data in the electrical signal.

[0054] Among them, the electrical signal can be measured by a voltmeter or an ammeter, the temperature can be measured by a temperature sensor, and the discharge signal can be measured by a power measurement instrument. In the actual application process, the health state of the battery can be detected based on different detection features according to actual needs.

[0055] Regarding S102, in the embodiment of the present application, the server can obtain the first weight of the detection feature in the first battery detection model according to the detection feature. Herein, the first battery detection model can be an LSTM network model. The weight of the detection feature can be used to represent the importance degree of the detection feature when analyzing the health state of the battery. The first weight refers to the initial weight of the first battery detection model, which can be determined based on expert experience.

[0056] Regarding S103, in the embodiments of the present application, the server may adjust the first weight corresponding to the detection feature in the first battery detection model according to the detection data of the detection feature in the first time period. That is, the input detection data of the battery detection model is different, and the weight corresponding to the detection feature is also different. The server may perform corresponding adjustment on the first weight corresponding to the detection feature based on the specific detection data to obtain the adjusted second weight, so as to obtain the second battery prediction model.

[0057] In some embodiments of the present application, the task of adjusting the first weight may be assigned to other devices, thereby reducing the computing burden of the server. For example, when the server is a cloud server, the task of adjusting the first weight may be assigned to an edge computing node. Of course, the weight adjustment task may also be executed by the cloud server, and specific limitations are not made herein in this specification.

[0058] Regarding S104, in the embodiments of the present application, the server may input the detection data of the detection feature in the first time period into the second battery detection model to obtain the detection result output by the second battery detection model. The second battery detection model is a model after weight adjustment, and the second battery detection model includes the second weight corresponding to the detection feature.

[0059] Based on this, S104 may include S201 to S203, as Figure 2 shown, Figure 2 which is a flowchart of a specific implementation manner of S104 in a battery detection method provided by an embodiment of the present application.

[0060] The detection feature further includes a second detection feature;

[0061] S201, input the detection data of the detection feature in the first time period into the second battery detection model, and obtain a first detection result according to the detection data of the first detection feature in the first time period and the second weight corresponding to the first detection feature;

[0062] In some embodiments of the present application, in addition to the first detection feature, the detection feature may further include a second detection feature. The server may first determine a detection result based on the detection data of the first detection feature, and then correct the detection result through the detection data of the second detection feature, so as to obtain the detection result of the battery determined based on the detection data of these two detection features.

[0063] Specifically, the server can input the detection data of these two detection features in the first time period into the second battery detection model. Through this second battery detection model, the first detection result can be obtained first according to the detection data of the first detection feature in the first time period and the second weight corresponding to the first detection feature. For example, when determining the first detection result, based on the detection data of each first detection feature in the first time period and the second weight corresponding to each first detection feature, the detection data of each first detection feature in the first time period can be weighted and summed, and the result of the weighted sum is determined as the first detection result. Taking the first detection features including electrical signal, temperature, and discharge signal as an example, the first detection result can be specifically expressed by the following formula (1).

[0064] SOH = σ(W R .R PCA +W T .T FCN +W Cd .C d ) Formula (1)

[0065] In formula (1), SOH is used to represent the first detection result, that is, the health state of the battery determined based on the detection data of the first detection feature in the first time period. W R is used to represent the second weight of the electrical signal, R PCA is used to represent the feature of the internal resistance corresponding to the electrical signal, W T is used to represent the second weight of the temperature, T FCN is used to represent the feature of the temperature, W Cd is used to represent the second weight of the discharge signal, C d is used to represent the feature of the discharge capacity, and σ() is used to represent the activation function. The feature of the internal resistance can be the internal resistance matrix determined by the multi-frequency AC perturbation method. The feature of the temperature can be the feature of the temperature field of the battery, which is a multi-dimensional vector. The feature of the discharge capacity can also be a multi-dimensional vector.

[0066] S202. Determine the equivalent cycle number according to the detection data of the second detection feature in the first time period and the detection data of the discharge signal in the first time period. The equivalent cycle number is the number of times the battery is charged and discharged;

[0067] S203. Correct the first detection result according to the equivalent cycle number to obtain the second detection result, and determine the second detection result as the detection result output by the second battery detection model.

[0068] After determining the first detection result, the server can determine the equivalent cycle count of the battery within the first time period and correct the first detection result based on the equivalent cycle count. Here, the equivalent cycle count can be understood as the number of charge and discharge cycles of the battery, and it is an indicator for measuring the degree of battery aging, which reflects the number of times equivalent to fully charging and discharging the battery's power during charge and discharge within the first time period. Specifically, the server can determine the equivalent cycle count according to the detection data of the second detection feature within the first time period and the detection data of the discharge signal within the first time period. Then, the first detection result can be corrected according to the equivalent cycle count, that is, the influence of the equivalent cycle count is considered when determining the health state of the battery, so as to obtain the second detection result, and the second detection result is determined as the detection result output by the second battery detection model. The second detection result is specifically as shown in formula (2) below.

[0069]

[0070] In formula (2), SOH is used to represent the second detection result, that is, the health state of the battery determined based on the detection data of the first detection feature and the second detection feature within the first time period, W R is used to represent the second weight of the electrical signal, R PCA is used to represent the characteristic of the internal resistance corresponding to the electrical signal, W T is used to represent the second weight of the temperature, T FCN is used to represent the characteristic of the temperature, is used to represent the second weight of the discharge signal, C d is used to represent the characteristic of the discharge capacity, σ() is used to represent the activation function, is used to represent the weight of the equivalent cycle count, which is determined by expert experience, N c is used to represent the equivalent cycle count.

[0071] Of course, before inputting the detection data of the detection feature within the first time period into the second battery detection model, the detection data can be preprocessed, for example, outlier removal processing, missing value filling processing, etc.

[0072] Thus, in the embodiments of the present application, in addition to referring to the detection data of the first detection feature, the detection data of the second detection feature can also be referred to, realizing the analysis of multiple aspects such as internal resistance data, temperature data, discharge data, and equivalent cycle count, so as to determine the final health state of the battery, improving the accuracy of determining the health state of the battery.

[0073] Regarding S202, in the embodiments of the present application, the equivalent cycle count can be determined according to the detection data of the second detection feature within the first time period and the detection data of the discharge signal within the first time period.

[0074] Based on this, S202 may include S301 to S303, specifically as Figure 3 shown, Figure 3 is a flowchart of a specific implementation manner of S202 in a battery detection method provided by an embodiment of the present application.

[0075] The second detection feature includes a charging signal and a battery capacity;

[0076] S301, determine the charging depth of the battery in the first time period according to the charging power corresponding to the charging signal and the battery capacity of the battery;

[0077] S302, determine the discharge depth of the battery in the first time period according to the discharge power corresponding to the discharge signal and the battery capacity of the battery;

[0078] S303, determine the equivalent cycle number according to the charging depth and the discharge depth.

[0079] In an embodiment of the present application, the second detection feature may include a charging signal and a battery capacity. The charging signal can indicate the number of times the battery is charged and the charging power of the battery, and the battery capacity represents the amount of electric charge that the battery can store. The server may first determine the charging depth of the battery in the first time period according to the charging power corresponding to the charging signal and the battery capacity of the battery. The charging depth reflects the degree to which the battery is charged during the charging process. Specifically, the ratio of the charging power of the battery in the first time period to the battery capacity may be determined as the charging depth of the battery in the first time period.

[0080] Then, the server may determine the discharge depth of the battery in the first time period according to the discharge power corresponding to the discharge signal and the battery capacity of the battery. The discharge depth reflects the degree to which the battery discharges during the discharge process. Specifically, the ratio of the discharge power of the battery in the first time period to the battery capacity may be determined as the discharge depth of the battery in the first time period.

[0081] After determining the charging depth of the battery in the first time period and the discharge depth of the battery in the first time period, the equivalent cycle number may be determined according to these two, specifically as the following formula (3).

[0082]

[0083] In formula (3), N is used to represent the equivalent cycle number, DOD is used to represent the discharge depth during the discharge process, SOC end is used to represent the remaining battery capacity at the end of charging, DOD eq is used to represent the equivalent discharge depth, which is a preset reference value.

[0084] In some embodiments of the present application, the equivalent cycle number can also be dynamically corrected to determine the health state of the battery based on the corrected equivalent cycle number, as shown in the following formula (4).

[0085]

[0086] In formula (4), Nc represents the corrected equivalent cycle number, Γ(t k ) is used to represent the time decay factor, λ1D k is used to represent the depth of discharge weight, D k is used to represent the depth of discharge at the k-th cycle, and represents the current intensity weight, I k is used to represent the charge and discharge current at the k-th cycle, and N is the number of discharge cycles.

[0087] Thus, in the embodiments of the present application, the equivalent cycle number can accurately reflect the aging degree of the battery, thereby being able to intuitively reflect the health state of the battery and improving the accuracy of determining the health state of the battery.

[0088] Regarding S103, in the embodiments of the present application, the server can adjust the first weight corresponding to the detection feature in the first battery detection model according to the detection data of the detection feature in the first time period.

[0089] Based on this, S103 may include S401 to S402, specifically as Figure 4 shown Figure 4 is a flowchart of a specific implementation manner of S103 in a battery detection method provided by the embodiments of the present application.

[0090] The detection data includes the detection data of the detection feature at N time points in the first time period;

[0091] S401, determine the difference information corresponding to the detection data at N time points according to the detection data of the detection feature at N time points in the first time period;

[0092] S402, adjust the first weight corresponding to the detection feature in the first battery detection model according to the difference information.

[0093] In an embodiment of the present application, the server may determine the difference information corresponding to the detection data at N time points within the first time period according to the detection features, where N is a positive integer. The difference information may refer to the difference information between the detection data corresponding to the detection features at N time points within the first time period. For example, if the first time period is March 1, 2025, the difference information may be the difference information between the temperature data of the battery every adjacent hour within March 1. Furthermore, the server may adjust the first weight corresponding to the detection feature in the first battery detection model according to the difference information, that is, adjust the initial weight in the first battery detection model, so that the adjusted weight is more adapted to the detection data, thereby improving the accuracy of detecting the health status of the battery.

[0094] Thus, in an embodiment of the present application, the corresponding first weight may be adjusted according to the difference information corresponding to the detection data, so as to obtain the second weight that is more adapted to the current detection data, thereby improving the accuracy of determining the health status of the battery.

[0095] Regarding S401, in an embodiment of the present application, the server may determine the difference information corresponding to the detection data at N time points within the first time period according to the detection features. When the detection feature is an electrical signal, the difference information corresponding to the electrical signal may be determined based on multiple detection data of the electrical signal within the first time period.

[0096] Based on this, S401 may include S501 to S503, specifically as follows Figure 5 , Figure 5 is a flowchart of a specific implementation manner of S401 in a battery detection method provided by an embodiment of the present application.

[0097] The electrical signal includes a voltage signal and a current signal;

[0098] S501, determine the internal resistance value of the battery at each of the N time points according to the voltage value at each of the N time points and the current value at each of the N time points within the first time period;

[0099] S502, determine the fluctuation information of the internal resistance value of the battery at at least two of the N time points according to the internal resistance values of the battery at the N time points;

[0100] S503, determine the fluctuation information as the difference information.

[0101] In some embodiments of the present application, the electrical signal may include a voltage signal and a current signal. The server may determine the internal resistance value of the battery at each of the N time points based on the voltage value at each of the N time points and the current value at each of the N time points within the first time period. Specifically, for each time point, the internal resistance value of the battery at that time point may be calculated based on the voltage value of the battery at that time point and the current value at that time point according to Ohm's law. After determining the internal resistance value of the battery at each time point, the fluctuation information of the internal resistance value of the battery at two or more adjacent time points may be determined based on the internal resistance value of the battery at each time point. The fluctuation information can represent the difference between the internal resistance values of the battery at two or more adjacent time points. After determining the fluctuation information, the fluctuation information is determined as the difference information.

[0102] Thus, in the embodiments of the present application, the difference information corresponding to the resistance data at N time points may be determined based on the fluctuation information of the internal resistance values at at least two time points, ensuring the accuracy of determining the difference information.

[0103] Regarding S402, in some embodiments of the present application, the server may adjust the first weight corresponding to the electrical signal in the first battery detection model based on the difference information of the electrical signals of the battery at N time points.

[0104] Based on this, S402 may include S601 to S605, specifically as Figure 6 shown Figure 6 is a flowchart of a specific implementation manner of S402 in a battery detection method provided by an embodiment of the present application.

[0105] S601, determine the extreme values of the internal resistance value of the battery within the first time period based on the fluctuation information of the internal resistance value;

[0106] S602, divide the first time period according to the extreme values to obtain multiple sub-time periods;

[0107] S603, determine the adjustment direction of the weight based on the fluctuation information of the internal resistance value of the battery within each sub-time period;

[0108] S604, determine the adjustment amplitude of the weight according to the difference between the internal resistance value at the start point or the end point of the time period within the sub-time period and the reference internal resistance value;

[0109] S605, adjust the first weight corresponding to the electrical signal in the first battery detection model according to the adjustment direction and the adjustment amplitude.

[0110] In some embodiments of the present application, the server may determine the extreme values of the internal resistance values of the battery during the first time period based on the fluctuation information of the internal resistance values. Among them, the extreme values may include maximum values and / or minimum values. After determining the extreme values, the server may divide the first time period according to the determined extreme values to obtain multiple sub-time periods. For example, the first time period is from 12:00 to 19:00 on March 1, 2025. There is a maximum value and a minimum value for the internal resistance value of the battery during this first time period. The time point corresponding to the maximum value is 15:00 on March 1, 2025, and the time point corresponding to the minimum value is 16:00 on March 1, 2025. Then, March 1, 2025 can be divided into three sub-time periods according to 15:00 on March 1, 2025 and 16:00 on March 1, 2025, which are from 12:00 to 15:00 on March 1, 2025, from 15:01 to 16:00 on March 1, 2025, and from 16:01 to 19:00 on March 1, 2025.

[0111] Then, the server may determine the adjustment direction of the weight according to the fluctuation information of the internal resistance value of the battery in each sub-time period. Specifically, the server may adjust the corresponding weight according to the fluctuation degree of the internal resistance value of the battery in each sub-time period. If the fluctuation degree is greater than the threshold value, the corresponding weight is adjusted downward. On the contrary, the corresponding weight is not adjusted. The fluctuation degree can be reflected by the difference between the maximum value and the minimum value of the internal resistance of the battery in each sub-time period. If the resistance value of the battery is [20 mΩ, 30 mΩ, 45 mΩ] in a certain sub-time period, the fluctuation degree in this sub-time period is 25 mΩ. If the threshold value is 20 mΩ, the corresponding weight can be adjusted downward. On the contrary, the weight is not adjusted.

[0112] After determining the adjustment direction, it is also necessary to determine the adjustment amplitude. Specifically, the server may determine the adjustment amplitude of the weight according to the difference between the internal resistance value at the start point or the end point of the time period in the sub-time period and the reference internal resistance value. Among them, the reference internal resistance value may be preset according to expert experience. The difference between the internal resistance value at the start point or the end point of the time period in the sub-time period and the reference internal resistance value is negatively correlated with the adjustment amplitude. The larger the difference, the smaller the adjustment amplitude. For example, if the difference between the internal resistance value at the start point or the end point of the time period in a certain sub-time period and the reference internal resistance value is 10 mΩ, the first weight corresponding to the electrical signal can be adjusted downward by 10%. If the difference between the internal resistance value at the start point or the end point of the time period in a certain sub-time period and the reference internal resistance value is 20 mΩ, the first weight corresponding to the electrical signal can be adjusted downward by 5%.

[0113] After determining the adjustment direction and adjustment amplitude, the first weight corresponding to the electrical signal in the first battery detection model can be adjusted according to the adjustment direction and adjustment amplitude.

[0114] In another embodiment of the present application, the degree of fluctuation can also be reflected by an internal resistance fluctuation sensitivity factor, and the internal resistance fluctuation sensitivity factor is specifically as follows in formula (5).

[0115]

[0116] In formula (5), δ R is used to represent the internal resistance fluctuation sensitivity factor, α is used to represent the initial weight, ΔR is used to represent the difference between the resistance value within the sub-time period and the reference internal resistance value, and R rated is used to represent the rated internal resistance of the battery.

[0117] In the above formula (5), the initial weight α can be initialized by the entropy weight method, and the entropy value E of the parameter can be calculated based on the detection data of the historical internal resistance j , and then the initial weight is determined. Specifically, the detection data of the historical internal resistance can be normalized first, specifically as follows in formula (6).

[0118]

[0119] In formula (6), E i is used to represent the entropy value of the i-th index, is used to represent the normalization coefficient, P ij is used to represent the standardized probability value converted from the original data, N is used to represent the total number of categories related to the i-th index, and j is used to represent the index variable.

[0120] After determining the entropy value E j , the initial weight α can be determined based on the entropy value E j , specifically as follows in formula (7).

[0121]

[0122] In formula (7), α is used to represent the initial weight, E i is used to represent the entropy value, and j is used to represent the index variable.

[0123] After determining the internal resistance fluctuation sensitivity factor, the adjusted second weight can be directly determined according to the internal resistance fluctuation sensitivity factor, specifically as follows in formula (8).

[0124]

[0125] In formula (8), W i t is used to represent the second weight at the characteristic t moment of the internal resistance, Wi t-1 The first weight of the characteristic for internal resistance at time t-1, δ R Used to represent the internal resistance fluctuation sensitivity factor, η is used to represent a hyperparameter, ΔW i t-1 Used to represent the change amount of the first weight of the characteristic for internal resistance at time t-1.

[0126] After determining the second weight, directly adjust the first weight to the second weight.

[0127] It should be noted that for each divided sub-time period, it is possible to determine how to specifically adjust the corresponding first weight according to different fluctuation information within the sub-time period, thereby realizing the dynamic adjustment of the corresponding first weight.

[0128] Thus, in the embodiments of the present application, it is possible to adjust the corresponding first weight according to the difference information corresponding to the electrical signal data, so as to make the first weight more adaptable to the second weight of the current electrical signal data, thereby improving the accuracy of determining the health state of the battery.

[0129] Regarding S401, in the embodiments of the present application, the server can determine the difference information corresponding to the detection data at N time points within the first time period according to the detection data at N time points of the detection feature. When the detection feature is temperature, it is possible to determine the difference information corresponding to the detection data based on the temperature data of the battery at multiple time points within the first time period.

[0130] Based on this, S401 may include: determining the difference information of the temperature values of the battery at N time points according to the temperature value of the battery at each of the N time points, and the difference information is used to characterize the difference between the maximum value and the minimum value among the temperature values of the battery at N time points.

[0131] In some embodiments of the present application, the server can determine the maximum value and the minimum value among the temperature values of these time points according to the temperature value of the battery at each time point within the first time period, and determine the difference information of the temperature values of the battery at N time points according to the difference between the maximum value and the minimum value. If there are multiple maximum values and multiple minimum values within the first time period, it is possible to first determine the difference between each set of adjacent maximum values and minimum values, and then, average these differences, and determine the difference information of the temperature values of the battery at N time points according to this average value.

[0132] Thus, in the embodiments of the present application, it is possible to determine the difference information corresponding to the temperature data at N time points according to the maximum value and the minimum value among the temperature values at N time points, ensuring the accuracy of determining the difference information.

[0133] Regarding S402, in some embodiments of the present application, the server may adjust the first weight corresponding to temperature in the first battery detection model according to the difference information of the temperature values of the battery at N time points.

[0134] Based on this, S402 may include S701 to S704, specifically as Figure 7 shown Figure 7 is a flowchart of a specific implementation manner of S402 in a battery detection method provided by an embodiment of the present application.

[0135] S701, divide the first time period into multiple sub - time periods according to the maximum and minimum values of the temperature values of the battery at N time points;

[0136] S702, determine the adjustment direction of the weight according to the fluctuation information of the temperature value of the battery in each sub - time period;

[0137] S703, determine the adjustment amplitude of the weight according to the difference between the maximum and minimum values of the temperature values of the battery at N time points;

[0138] S704, adjust the first weight corresponding to the temperature signal in the first battery detection model according to the adjustment direction and the adjustment amplitude.

[0139] In some embodiments of the present application, the server may divide the first time period into multiple sub - time periods according to the maximum and minimum values of the temperature values of the battery in the first time period. The principle of division is the same as or similar to the aforementioned division principle, and will not be repeated here. The server may determine the adjustment direction of the weight according to the fluctuation information of the temperature value of the battery in each sub - time period. Specifically, the fluctuation information may indicate whether the temperature value of the battery rises or falls in each sub - time period. If the temperature value of the battery rises, the corresponding weight is increased; if the temperature value of the battery falls, the corresponding weight is decreased.

[0140] After determining the adjustment direction of the weight, it is also necessary to determine the adjustment amplitude of the weight. Specifically, the server may determine the adjustment amplitude of the weight according to the difference between the maximum and minimum values of the temperature values of the battery at N time points. This difference has a positive correlation with the adjustment amplitude, that is, the larger the difference, the larger the adjustment amplitude.

[0141] After determining the adjustment direction and the adjustment amplitude, the first weight corresponding to the temperature signal in the first battery detection model may be adjusted according to the adjustment direction and the adjustment amplitude.

[0142] In another embodiment of the present application, the fluctuation information may also be specifically reflected by the temperature gradient influence factor. The temperature gradient influence is specifically as the following formula (9).

[0143]

[0144] In formula (9), δ T is used to represent the temperature gradient influence factor, β is used to represent the initial weight, ΔT is used to represent the difference between the maximum value and the minimum value of the temperature values of the battery in the sub-time period, and T rated is used to represent the temperature threshold of the battery. The determination method of the initial weight β is the same as or similar to the above method for determining the initial weight, and will not be repeated here.

[0145] After determining the temperature gradient influence factor, the adjusted second weight can be directly determined according to the temperature gradient influence factor, as shown in the following formula (10).

[0146]

[0147] In formula (10), W i t is used to represent the second weight at the characteristic time t of the temperature, and W i t-1 is the first weight at the characteristic time t - 1 of the temperature, and δ T is used to represent the temperature gradient influence factor, η is used to represent a hyperparameter, and ΔW i t-1 is used to represent the change amount of the first weight at the characteristic time t - 1 of the temperature.

[0148] After determining the second weight, directly adjust the first weight to the second weight.

[0149] It should be noted that for each divided sub-time period, the specific adjustment of the corresponding first weight can be determined according to different fluctuation information within the sub-time period, thereby realizing the dynamic adjustment of the corresponding first weight.

[0150] Thus, in the embodiment of the present application, the corresponding first weight can be adjusted according to the difference information corresponding to the temperature data, so that the first weight is more adapted to the second weight of the current temperature data, thereby improving the accuracy of determining the health state of the battery.

[0151] Regarding S401, in the embodiment of the present application, the server can determine the difference information corresponding to the detection data at N time points in the first time period according to the detection data at N time points of the detection feature. When the detection feature is a discharge signal, the difference information corresponding to the discharge signal can be determined based on the discharge signals at multiple time points of the battery in the first time period.

[0152] Based on this, S401 may include: S801 to S804, specifically as Figure 8 shown Figure 8It is a flowchart of a specific implementation manner of S401 in a battery detection method provided by an embodiment of this application.

[0153] S801. Generate a discharge curve of the battery in the first time period according to the discharge data of the battery at each of the N time points. The discharge curve is used to characterize the mapping relationship between each of the N time points and the remaining battery capacity of the battery.

[0154] S802. Determine the predicted discharge data of the battery in the second time period according to the discharge curve. The second time period is later than the first time period.

[0155] In some embodiments of this application, the server can generate a discharge curve of the battery in the first time period according to the discharge data of the battery at each of the N time points. For example, the discharge curve can be drawn first through professional drawing software. The discharge curve is used to characterize the mapping relationship between each of the N time points and the remaining battery capacity of the battery. The discharge data of the battery can be calculated based on the remaining battery capacity represented in the discharge curve. The discharge data can be the specific discharge power.

[0156] After determining the discharge curve, the predicted discharge data of the battery in the second time period can be determined according to the discharge curve, where the second time period is later than the first time period and does not overlap with the first time period. For example, the first time period is from 15:00 to 16:00 on February 5, 2025, and the second time can be from 17:00 to 18:00 on February 5, 2025.

[0157] Specifically, the server can map the predicted remaining battery capacity of the battery in the second time period according to the mapping relationship between the time points represented by the discharge curve and the remaining battery capacity, and then determine the predicted discharge capacity of the battery in the second time period based on the predicted remaining battery capacity as the predicted discharge data. For example, the remaining battery capacity of the battery in the second time period is 80 Ah, and the remaining battery capacity at the initial time point of the second time period is 100 Ah. Then, the predicted discharge capacity of the battery in the second time period is 20 Ah.

[0158] S803. Determine residual data according to the actual discharge data and the predicted discharge data of the battery in the second time period.

[0159] S804. Determine the residual data as the difference information corresponding to the discharge signals at the N time points.

[0160] Subsequently, the server can determine the residual data based on the actual discharge data and the predicted discharge data of the battery in the second time period. Continuing with the above example, if the actual discharge data of the battery in the second time period is 30 Ah and the predicted discharge data of the battery in the second time period is 20 Ah, then the residual data is 10 Ah. Furthermore, the residual data is determined as the difference information corresponding to the discharge signals at N time points.

[0161] Thus, in the embodiments of the present application, the difference information corresponding to the discharge signals at N time points can be determined based on the actual discharge data and the predicted discharge data of the battery in the second time period, ensuring the accuracy of determining the difference information.

[0162] Regarding S402, in some embodiments of the present application, the server can adjust the first weight corresponding to the discharge signal in the first battery detection model according to the difference information of the discharge signals of the battery at N time points.

[0163] Based on this, S402 can include S901 to S902, specifically as Figure 9 shown Figure 9 is a flowchart of a specific implementation manner of S103 in a battery detection method provided by an embodiment of the present application.

[0164] The residual data includes N pieces of residual data;

[0165] S901, determine the adjustment direction and adjustment amplitude of the weight according to the difference between each residual data in the N pieces of residual data and the first threshold;

[0166] S902, adjust the first weight corresponding to the discharge signal in the first battery detection model according to the adjustment direction and adjustment amplitude.

[0167] In some embodiments of the present application, the server can determine the adjustment direction and adjustment amplitude of the weight according to the difference between each residual data in the N pieces of residual data and the first threshold. Specifically, for each residual data, the difference between the residual data and the first threshold can be determined. If the difference is a positive number, it proves that the residual data is greater than the first threshold, and then the corresponding weight can be increased; otherwise, it can be decreased.

[0168] In addition, for each residual data, the adjustment amplitude of the weight can also be determined according to the difference between the residual data and the first threshold, where the difference is positively correlated with the adjustment amplitude, that is, the larger the difference, the larger the adjustment amplitude.

[0169] In another embodiment of the present application, the adjustment amplitude can also be specifically represented by a residual feedback factor, and the residual feedback factor is specifically as the following formula (11).

[0170]

[0171] In formula (11), δ C is used to represent the residual feedback factor, γ is used to represent the initial weight, ∈ is used to represent the residual data, ∈ th is used to represent the residual threshold of the battery. The determination method of the initial weight γ is the same as or similar to the method for determining the initial weight described above, and will not be repeated here.

[0172] After determining the residual feedback factor, the adjusted second weight can be directly determined according to the residual feedback factor, as shown in formula (12) below.

[0173] W i t = W i t-1 .(1 + δ C + η·ΔW i t-1 ) Formula (12)

[0174] In formula (12), W i t is used to represent the second weight at the t-th moment of the characteristics of the discharge signal, W i t-1 is the first weight at the (t - 1)-th moment of the characteristics of the discharge signal, δ C is used to represent the residual feedback factor, η is used to represent a hyperparameter, ΔW i t-1 is used to represent the change amount of the first weight at the (t - 1)-th moment of the characteristics of the discharge signal.

[0175] After determining the second weight, directly adjust the first weight to the second weight.

[0176] Thus, in the embodiment of the present application, the corresponding first weight can be adjusted according to the difference information corresponding to the discharge signal, so that the first weight is more adapted to the second weight of the current discharge signal, thereby improving the accuracy of determining the health state of the battery.

[0177] In the embodiment of the present application, the above battery detection method further includes S1001 to S1003, as Figure 10 shown Figure 10 is a flowchart of a specific implementation manner after S104 of a battery detection method provided by an embodiment of the present application.

[0178] S1001, determine the predicted battery capacity of the battery in the first time period according to the health state of the battery in the first time period and the initial battery capacity of the battery;

[0179] S1002. Determine the deviation between the measured battery capacity and the predicted battery capacity according to the measured battery capacity and the predicted battery capacity of the battery within the first time period;

[0180] S1003. In the case where the deviation is greater than the second threshold, update the first weight and / or the reference internal resistance value according to the deviation.

[0181] In some embodiments of the present application, it further includes a process of updating the first weight and the reference internal resistance value in the first battery detection model, that is, the first battery detection model can be optimized based on the determined health state of the battery. Specifically, the server can first determine the predicted battery capacity of the battery within the first time period according to the health state of the battery and the initial battery capacity of the battery within the first time period. Among them, the health state of the battery can be expressed in percentage. For example, the health state of the battery is 80%. The server can determine the product of the initial battery capacity of the battery and the health state of the battery, and use the obtained result as the predicted battery capacity of the battery within the first time period.

[0182] Then, the server can determine the deviation between the measured battery capacity and the predicted battery capacity according to the measured battery capacity and the predicted battery capacity of the battery within the first time period. In the case where the deviation is greater than the second threshold, the first weight and / or the reference internal resistance value can be updated according to the deviation. Specifically, the gradient descent method can be used to update the first weight and / or the reference internal resistance. By calculating the gradient of the loss function with respect to the first weight and / or the reference internal resistance value, the first weight and / or the reference internal resistance value are updated along the opposite direction of the gradient to gradually reduce the deviation between the measured battery capacity and the predicted battery capacity.

[0183] Updating the first weight, that is, performing parameter correction, can specifically refer to the following formula (13).

[0184] W i t-1 = W i t .(1 + 0.1.sign(C real - SOH)) Formula (13)

[0185] In formula (13), W i t-1 is used to represent the adjusted weight, W i t is used to represent the weight of the i-th parameter at time t, C real is used to represent the actual capacity of the battery, SOH is used to represent the health state of the battery, and sign() is used to represent the sign function.

[0186] Thus, in the embodiments of the present application, the weight parameters in the battery detection model can be optimized based on the determined health state of the battery, enhancing the generalization ability of the battery detection model.

[0187] In some embodiments of the present application, after determining the health state of the battery, the health state of the battery can also be fed back to the visualization interface of the operation and maintenance terminal, so that the operation and maintenance personnel can replace or repair the battery of the communication device based on the fed-back health state of the battery, thereby ensuring the normal operation of the communication device.

[0188] Specifically, when the detected health state of the battery is lower than the third threshold, a yellow warning is triggered, and the repair strategy recommendation function is started. The repair strategy can be determined from the strategy library and displayed in the form of a strategy report on the visualization interface of the operation and maintenance terminal. The strategy library includes the mapping relationship between the health state of each battery and the repair strategy. For example, when the detected health state of the battery is lower than 85%, or the internal resistance change rate of the battery is greater than 0.5 mΩ / min, a yellow warning is triggered, and the recommended repair strategies can be "Please limit the load power of the communication device to below 85%", "Please turn off the charging circuit of the battery and activate the air cooling system."

[0189] In addition, when it is lower than the fourth threshold, a red warning is triggered and the standby battery of the battery is forced to be switched. For example, when the detected health state of the battery is lower than 70% or the maximum temperature of the battery is greater than 50°C, a red warning is triggered and the standby battery of the battery is forced to be switched.

[0190] After receiving the repair strategy or switching instruction, the communication device can execute the corresponding control instruction through the embedded controller to adjust its own charge and discharge power, switch the power path, etc.

[0191] Thus, in the process of detecting the health state of the battery by the above battery detection method, by analyzing the detection data of the detection feature in the first time period, and then according to the analysis result, dynamically adjusting the first weight corresponding to the detection feature targeted to generate a second weight more adapted to the current detection data, thereby improving the accuracy of detecting the health state of the battery based on the detection data. Moreover, the above battery detection method can also analyze the health state of the battery based on multiple detection features, so as to more comprehensively analyze the influence of the detection data corresponding to different detection features on the health state of the battery, thereby further improving the accuracy of detecting the health state of the battery.

[0192] In addition, after determining the health state of the battery, the above battery detection method can send repair strategy information to the operation and maintenance platform in a feedback manner, so as to realize the early warning of the battery performance. Moreover, the above battery detection method is applicable to various mainstream battery types such as lead-acid batteries and lithium batteries, and can meet the needs of detecting the health state of various batteries.

[0193] Figure 11 The following is a schematic structural diagram of a battery detection device provided by an embodiment of the present application.

[0194] As Figure 11 shown, an embodiment of the present application further provides a battery detection device 1100, and the battery detection device 1100 includes:

[0195] An acquisition module 1101, configured to acquire detection data of a detection feature of a battery within a first time period, where the detection feature is used to measure the battery performance and / or aging degree of the battery, and the detection feature includes at least one of the following first detection features: electrical signal, temperature, discharge signal;

[0196] The acquisition module 1101 is further configured to acquire a first weight of the detection feature in a first battery detection model according to the detection feature.

[0197] An adjustment module 1102, configured to adjust a first weight corresponding to the detection feature in the first battery detection model according to the detection data of the detection feature within the first time period, to obtain a second battery detection model, where the second battery prediction model includes a second weight corresponding to the detection feature, and the second weight is the second weight after the first weight is adjusted.

[0198] A determination module 1103, configured to input the detection data of the detection feature within the first time period into the second battery detection model, to obtain a detection result output by the second battery detection model, where the detection result is used to reflect the health state of the battery within the first time period.

[0199] Thus, during the process of detecting the health state of the battery by the above battery detection device, by analyzing the detection data of the detection feature within the first time period, and according to the analysis result, the first weight corresponding to the detection feature is dynamically adjusted in a targeted manner, and a second weight that is more adapted to the current detection data is generated, so as to improve the accuracy of detecting the health state of the battery based on the detection data. Moreover, the above battery detection method can also analyze the health state of the battery based on multiple detection features, so as to more comprehensively analyze the influence of the detection data corresponding to different detection features on the health state of the battery, thereby further improving the accuracy of detecting the health state of the battery.

[0200] In some embodiments of the present application, the detection feature further includes a second detection feature;

[0201] The determination module 1103 is further configured to input the detection data of the detection feature in the first time period into the second battery detection model, and obtain a first detection result according to the detection data of the first detection feature in the first time period and the second weight corresponding to the first detection feature;

[0202] The determination module 1103 is further configured to determine an equivalent cycle number according to the detection data of the second detection feature in the first time period and the detection data of the discharge signal in the first time period, where the equivalent cycle number is the number of times the battery is charged and discharged;

[0203] The battery detection device 1100 further includes a correction module, configured to correct the first detection result according to the equivalent cycle number to obtain a second detection result, and determine the second detection result as the detection result output by the second battery detection model.

[0204] In some embodiments of the present application, the second detection feature includes a charging signal and a battery capacity;

[0205] The determination module 1103 is further configured to determine the charging depth of the battery in the first time period according to the charging power corresponding to the charging signal and the battery capacity of the battery;

[0206] The determination module 1103 is further configured to determine the discharge depth of the battery in the first time period according to the discharge power corresponding to the discharge signal and the battery capacity of the battery;

[0207] The determination module 1103 is further configured to determine the equivalent cycle number according to the charging depth and the discharge depth.

[0208] In some embodiments of the present application, the detection data includes the detection data of the detection feature at N time points in the first time period;

[0209] The determination module 1103 is further configured to determine the difference information corresponding to the detection data at N time points according to the detection data of the detection feature at N time points in the first time period;

[0210] The adjustment module 1102 is further configured to adjust the first weight corresponding to the detection feature in the first battery detection model according to the difference information.

[0211] In some embodiments of the present application, the electrical signal includes a voltage signal and a current signal;

[0212] The determination module 1103 is further configured to determine the internal resistance value of the battery at each of the N time points according to the voltage value at each of the N time points and the current value at each of the N time points in the first time period;

[0213] The determination module 1103 is further configured to determine the fluctuation information of the internal resistance values of the battery at at least two of the N time points according to the internal resistance values of the battery at the N time points;

[0214] The determination module 1103 is further configured to determine the fluctuation information as difference information.

[0215] In some embodiments of the present application, the determination module 1103 is further configured to determine the extreme values of the internal resistance value of the battery within the first time period according to the fluctuation information of the internal resistance value;

[0216] The battery detection device 1100 further includes a division module, configured to divide the first time period according to the extreme values to obtain a plurality of sub-time periods;

[0217] The determination module 1103 is further configured to determine the adjustment direction of the weight according to the fluctuation information of the internal resistance value of the battery within each sub-time period;

[0218] The determination module 1103 is further configured to determine the adjustment amplitude of the weight according to the difference between the internal resistance value at the start point or the end point of the time period within the sub-time period and the reference internal resistance value;

[0219] The adjustment module 1102 is further configured to adjust the first weight corresponding to the electrical signal in the first battery detection model according to the adjustment direction and the adjustment amplitude.

[0220] In some embodiments of the present application, the determination module 1103 is further configured to determine the difference information of the temperature values of the battery at each of the N time points according to the temperature value of the battery at each of the N time points, and the difference information is used to characterize the difference between the maximum value and the minimum value of the temperature values of the battery at the N time points.

[0221] In some embodiments of the present application, the division module is further configured to divide the first time period according to the maximum value and the minimum value of the temperature values of the battery at the N time points to obtain a plurality of sub-time periods;

[0222] The determination module 1103 is further configured to determine the adjustment direction of the weight according to the fluctuation information of the temperature value of the battery within each sub-time period;

[0223] The determination module 1103 is further configured to determine the adjustment amplitude of the weight according to the difference between the maximum value and the minimum value of the temperature values of the battery at the N time points;

[0224] The adjustment module 1102 is further configured to adjust the first weight corresponding to the temperature signal in the first battery detection model according to the adjustment direction and the adjustment amplitude.

[0225] In some embodiments of the present application, the battery detection device 1100 further includes a generation module, configured to generate a discharge curve of the battery in a first time period according to the discharge data of the battery at each of the N time points, where the discharge curve is used to characterize the mapping relationship between each of the N time points and the remaining battery capacity of the battery;

[0226] The determination module 1103 is further configured to determine predicted discharge data of the battery in a second time period according to the discharge curve, where the second time period is later than the first time period;

[0227] The determination module 1103 is further configured to determine residual data according to the actual discharge data and the predicted discharge data of the battery in the second time period;

[0228] The determination module 1103 is further configured to determine the residual data as the difference information corresponding to the discharge signals at the N time points.

[0229] In some embodiments of the present application, the residual data includes N pieces of residual data;

[0230] The determination module 1103 is further configured to determine the adjustment direction and the adjustment amplitude of the weight according to the difference between each piece of residual data in the N pieces of residual data and a first threshold;

[0231] The adjustment module 1102 is further configured to adjust the first weight corresponding to the discharge signal in the first battery detection model according to the adjustment direction and the adjustment amplitude.

[0232] In some embodiments of the present application, the determination module 1103 is further configured to determine the predicted battery capacity of the battery in the first time period according to the health state of the battery in the first time period and the initial battery capacity of the battery;

[0233] The determination module 1103 is further configured to determine the deviation between the measured battery capacity and the predicted battery capacity according to the measured battery capacity and the predicted battery capacity of the battery in the first time period;

[0234] The battery detection device 1100 further includes an update module, configured to update the first weight and / or the reference internal resistance value according to the deviation when the deviation is greater than a second threshold.

[0235] Figure 12 FIG. shows a schematic hardware structure diagram of a computer device provided in some embodiments of the present application.

[0236] The computer device 1200 may include a processor 1201 and a memory 1202 storing computer program instructions.

[0237] Specifically, the above-mentioned processor 1201 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured as one or more integrated circuits for implementing the embodiments of the present application.

[0238] The memory 1202 may include a mass storage for data or instructions. By way of example and not limitation, the memory 1202 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In a suitable case, the memory 1202 may include a removable or non-removable (or fixed) medium. In a suitable case, the memory 1202 may be internal or external to the integrated gateway disaster recovery device. In a specific embodiment, the memory 1202 is a non-volatile solid-state memory.

[0239] In a specific embodiment, the memory 1202 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, generally, the memory 1202 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the battery detection method according to the first aspect of the present application.

[0240] The processor 1201 reads and executes the computer program instructions stored in the memory 1202 to implement any one of the battery detection methods in the above embodiments.

[0241] In one example, the computer device may further include a communication interface 1203 and a bus 1210. Among them, as Figure 12 shown, the processor 1201, the memory 1202, and the communication interface 1203 are connected through the bus 1210 and complete communication with each other.

[0242] The communication interface 1203 is mainly used to implement communication between various modules, devices, units, and / or devices in the embodiments of the present application.

[0243] The bus 1210 includes hardware, software, or both, and couples components of a computer device to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable bus or a combination of two or more of these. Where appropriate, the bus 1210 may include one or more buses. Although embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0244] The computer device can execute the battery detection method in the embodiments of the present application, thereby implementing the combination with Figures 1 to 11 the battery detection method and device described.

[0245] In addition, in combination with the battery detection method in the above embodiments, embodiments of the present application can be implemented by providing a computer-readable storage medium. Computer program instructions are stored on the computer-readable storage medium; when the computer program instructions are executed by a processor, any one of the battery detection methods in the above embodiments is implemented. Examples of computer-readable storage media include non-transitory computer-readable storage media, such as a portable disk, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM or Flash Memory), a Portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, and the like.

[0246] In addition, in combination with the battery detection method in the above embodiments, embodiments of the present application can be implemented by providing a computer program product. The program product is stored in a storage medium, and specifically may include a computer program or instructions. When the computer program or instructions are executed by a processor, any one of the battery detection methods in the above embodiments is implemented. The program product is executed by at least one processor to implement each process of the data processing method embodiment as described above, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0247] It should be clear that the present application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present application.

[0248] The functional blocks shown in the above structural block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, and so on. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted via a data signal carried in a carrier wave over a transmission medium or a communication link. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical discs, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, and so on.

[0249] It should also be noted that the exemplary embodiments mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0250] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block in the flowcharts and / or block diagrams, and the combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing devices to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing devices enable the implementation of the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It can also be understood that each block in the block diagrams and / or flowcharts, and the combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware that performs the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0251] As described above, this is only the specific implementation manner of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. It should be understood that the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present application.

Claims

1. A battery detection method, characterized in that, Including: Obtaining detection data of a battery's detection features within a first time period, where the detection features are used to measure the battery performance and / or aging degree of the battery, and the detection features include at least one of the following first detection features: electrical signal, temperature, discharge signal; Obtaining a first weight of the detection features in a first battery detection model according to the detection features; Adjusting the first weight corresponding to the detection features in the first battery detection model according to the detection data of the detection features within the first time period to obtain a second battery detection model. The second battery prediction model includes a second weight corresponding to the detection features, and the second weight is the second weight after adjustment of the first weight; Inputting the detection data of the detection features within the first time period into the second battery detection model to obtain a detection result output by the second battery detection model, where the detection result is used to reflect the health state of the battery within the first time period.

2. The method according to claim 1, characterized in that The detection features further include second detection features; The step of inputting the detection data of the detection features within the first time period into the second battery detection model to obtain a detection result output by the second battery detection model includes: Inputting the detection data of the detection features within the first time period into the second battery detection model, and obtaining a first detection result according to the detection data of the first detection features within the first time period and the second weight corresponding to the first detection features; Determining an equivalent cycle number according to the detection data of the second detection features within the first time period and the detection data of the discharge signal within the first time period, where the equivalent cycle number is the number of charge and discharge cycles of the battery; Correcting the first detection result according to the equivalent cycle number to obtain a second detection result, and determining the second detection result as the detection result output by the second battery detection model.

3. The method according to claim 2, characterized in that, The second detection features include a charging signal and a battery capacity; The step of determining an equivalent cycle number according to the detection data of the second detection features within the first time period and the detection data of the discharge signal within the first time period includes: Determining a charging depth of the battery within the first time period according to a charging power corresponding to the charging signal and the battery capacity of the battery; Determining a discharge depth of the battery within the first time period according to a discharge power corresponding to the discharge signal and the battery capacity of the battery; Determining an equivalent cycle number according to the charging depth and the discharge depth.

4. The method according to claim 1, wherein The detection data includes detection data of the detection features at N time points within the first time period; The step of adjusting the first weight corresponding to the detection features in the first battery detection model according to the detection data of the detection features within the first time period includes: Determining difference information corresponding to the detection data of the N time points according to the detection data of the detection features at the N time points within the first time period; Adjusting the first weight corresponding to the detection features in the first battery detection model according to the difference information.

5. The method according to claim 4, wherein The electrical signal includes a voltage signal and a current signal; Determining the difference information corresponding to the detection data at N time points within the first time period according to the detection features includes: Determining the internal resistance value of the battery at each of the N time points according to the voltage value at each time point among the N time points and the current value at each time point within the first time period of the N time points; Determining the fluctuation information of the internal resistance value of the battery at at least two of the N time points according to the internal resistance values of the battery at the N time points; Determining the fluctuation information as the difference information.

6. The method according to claim 5, wherein Adjusting the first weight corresponding to the detection feature in the first battery detection model according to the difference information includes: Determining the extreme value of the internal resistance value of the battery within the first time period according to the fluctuation information of the internal resistance value; Dividing the first time period according to the extreme value to obtain a plurality of sub-time periods; Determining the adjustment direction of the weight according to the fluctuation information of the internal resistance value of the battery within each sub-time period; Determining the adjustment amplitude of the weight according to the difference between the internal resistance value at the start point or the end point of the time period within the sub-time period and the reference internal resistance value; Adjusting the first weight corresponding to the electrical signal in the first battery detection model according to the adjustment direction and the adjustment amplitude.

7. The method according to claim 4, characterized in that, Determining the difference information corresponding to the detection data at N time points within the first time period according to the detection features includes: Determining the difference information of the temperature values of the battery at the N time points according to the temperature value of the battery at each of the N time points, where the difference information is used to characterize the difference between the maximum value and the minimum value of the temperature values of the battery at the N time points.

8. The method according to claim 7, wherein Adjusting the first weight corresponding to the detection feature in the first battery detection model according to the difference information includes: Dividing the first time period according to the maximum value and the minimum value of the temperature values of the battery at the N time points to obtain a plurality of sub-time periods; Determining the adjustment direction of the weight according to the fluctuation information of the temperature value of the battery within each sub-time period; Determining the adjustment amplitude of the weight according to the difference between the maximum value and the minimum value of the temperature values of the battery at the N time points; Adjusting the first weight corresponding to the temperature signal in the first battery detection model according to the adjustment direction and the adjustment amplitude.

9. The method according to claim 4, characterized in that, Determining the difference information corresponding to the detection data at N time points within the first time period according to the detection features includes: Generating a discharge curve of the battery within the first time period according to the discharge data of the battery at each of the N time points, where the discharge curve is used to characterize the mapping relationship between each of the N time points and the remaining battery capacity of the battery; Determining the predicted discharge data of the battery within a second time period, where the second time period is later than the first time period, according to the discharge curve; Determining residual data according to the actual discharge data and the predicted discharge data of the battery within the second time period; Determine the residual data as the difference information corresponding to the discharge signals at the N time points.

10. The method according to claim 9, wherein The residual data includes N pieces of residual data; The adjusting the first weight corresponding to the detection feature in the first battery detection model according to the difference information includes: Determine the adjustment direction and the adjustment amplitude of the weight according to the difference between each piece of residual data in the N pieces of residual data and a first threshold; Adjust the first weight corresponding to the discharge signal in the first battery detection model according to the adjustment direction and the adjustment amplitude.

11. The method according to claim 1, characterized in that, The method further includes: Determine the predicted battery capacity of the battery during the first time period according to the health state of the battery during the first time period and the initial battery capacity of the battery; Determine the deviation between the measured battery capacity and the predicted battery capacity according to the measured battery capacity and the predicted battery capacity of the battery during the first time period; When the deviation is greater than a second threshold, update the first weight and / or the reference internal resistance value according to the deviation.

12. A battery detection device, characterized in that, The apparatus includes: An acquisition module, configured to acquire detection data of a detection feature of a battery during a first time period, where the detection feature is used to measure the battery performance and / or aging degree of the battery, and the detection feature includes at least one of the following first detection features: electrical signal, temperature, discharge signal; The acquisition module is further configured to acquire a first weight of the detection feature in a first battery detection model according to the detection feature; An adjustment module, configured to adjust a first weight corresponding to the detection feature in the first battery detection model according to the detection data of the detection feature during the first time period, to obtain a second battery detection model, where the second battery prediction model includes a second weight corresponding to the detection feature, and the second weight is the second weight after the first weight is adjusted; A determination module, configured to input the detection data of the detection feature during the first time period into the second battery detection model, to obtain a detection result output by the second battery detection model, where the detection result is used to reflect the health state of the battery during the first time period.

13. A computer device, characterized in that, The computer device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the battery detection method according to any one of claims 1-11 is implemented.

14. A computer-readable storage medium, characterized in that, Computer program instructions are stored on a computer-readable storage medium, and when the computer program instructions are executed by a processor, the battery detection method according to any one of claims 1-11 is implemented.

15. A computer program product, characterized in that, When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute the battery detection method according to any one of claims 1-11.

Images