Method and device for predicting battery health state of energy storage battery pack

Abstract

The invention discloses a battery health state prediction method and device of an energy storage battery pack, electronic equipment and a storage medium. The method comprises the following steps: acquiring real-time operation data of a target energy storage battery pack through a battery management system; determining a first battery health state prediction result of the target energy storage battery pack according to the real-time operation data and a first prediction model deployed locally in the battery management system; uploading the real-time operation data to a cloud end, and determining a second battery health state prediction result of the target energy storage battery pack according to the real-time operation data and a second prediction model deployed in the cloud end; and determining a target battery health state prediction result of the target energy storage battery pack according to the first battery health state prediction result and the second battery health state prediction result. According to the technical scheme of the embodiment of the invention, the prediction accuracy of the battery health state of the target energy storage battery pack can be improved, and then the battery health of the target energy storage battery pack is evaluated and managed in real time.

Description

Technical Field

[0001] This invention relates to the field of battery management technology, and in particular to a method, apparatus, electronic device, and storage medium for predicting the battery health status of an energy storage battery pack. Background Technology

[0002] Predicting the state of health (SOH) of energy storage battery packs is a core technology for ensuring system safety and lifespan. Currently, methods for predicting the SOH of individual energy storage cells (such as lithium-ion cells) have high accuracy. However, due to the inherent inconsistencies within energy storage battery packs, the reliability of predictions based on individual cells is poor when applied to the overall battery pack's SOH, making it difficult to meet engineering requirements. Therefore, a method for predicting the SOH of energy storage battery packs is urgently needed. Summary of the Invention

[0003] This invention provides a method, device, electronic device, and storage medium for predicting the battery health status of an energy storage battery pack, which can improve the accuracy of predicting the battery health status of a target energy storage battery pack, thereby enabling real-time assessment and management of the battery health of the target energy storage battery pack.

[0004] According to one aspect of the present invention, a method for predicting the battery health status of an energy storage battery pack is provided, the method comprising:

[0005] Real-time operating data of the target energy storage battery pack is obtained through the battery management system.

[0006] The first battery health state prediction result of the target energy storage battery pack is determined based on the real-time operating data and the first prediction model deployed locally on the battery management system; wherein, the first prediction model is a semi-empirical model constructed by combining the electrochemical characteristics and cell characteristics of the target energy storage battery pack.

[0007] The real-time operating data is uploaded to the cloud, and the second battery health status prediction result of the target energy storage battery pack is determined based on the real-time operating data and the second prediction model deployed in the cloud; wherein, the second prediction model includes at least two different types of cloud computing models;

[0008] The target battery health status prediction result of the target energy storage battery pack is determined based on the first battery health status prediction result and the second battery health status prediction result.

[0009] According to another aspect of the present invention, a battery health status prediction device for an energy storage battery pack is provided, the device comprising:

[0010] The real-time operation data acquisition module is used to acquire real-time operation data of the target energy storage battery pack through the battery management system;

[0011] The first prediction result acquisition module is used to determine the first battery health state prediction result of the target energy storage battery pack based on the real-time operating data and the first prediction model deployed locally on the battery management system; wherein, the first prediction model is a semi-empirical model constructed by combining the electrochemical characteristics and cell characteristics of the target energy storage battery pack.

[0012] The second prediction result acquisition module is used to upload the real-time operating data to the cloud, and determine the second battery health status prediction result of the target energy storage battery pack based on the real-time operating data and the second prediction model deployed in the cloud; wherein, the second prediction model includes at least two different types of cloud computing models;

[0013] The target prediction result acquisition module is used to determine the target battery health state prediction result of the target energy storage battery pack based on the first battery health state prediction result and the second battery health state prediction result.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the battery health status prediction method for energy storage battery packs according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the battery health status prediction method for an energy storage battery pack according to any embodiment of the present invention.

[0019] The technical solution of this invention involves acquiring real-time operating data of a target energy storage battery pack through a battery management system; determining a first battery health state prediction result for the target energy storage battery pack based on the real-time operating data and a first prediction model deployed locally on the battery management system; wherein the first prediction model is a semi-empirical model constructed by combining the electrochemical characteristics and cell characteristics of the target energy storage battery pack; uploading the real-time operating data to the cloud, and determining a second battery health state prediction result for the target energy storage battery pack based on the real-time operating data and a second prediction model deployed in the cloud; wherein the second prediction model includes at least two different types of cloud computing models; and determining a target battery health state prediction result for the target energy storage battery pack based on the first battery health state prediction result and the second battery health state prediction result. This technical solution of the present invention, by comprehensively considering the first battery health state prediction result obtained from the locally deployed semi-empirical model and the second battery health state prediction result obtained from the cloud-deployed cloud computing model, determines the target health state prediction result, thereby improving the prediction accuracy of the battery health state of the target energy storage battery pack, and thus enabling real-time assessment and management of the battery health of the target energy storage battery pack.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a battery health status prediction method for an energy storage battery pack according to Embodiment 1 of the present invention;

[0023] Figure 2 This is a schematic diagram of the process for determining the prediction result of the target battery health status according to Embodiment 1 of the present invention;

[0024] Figure 3 This is a flowchart of a battery health status prediction method for an energy storage battery pack according to Embodiment 2 of the present invention;

[0025] Figure 4 This is a schematic diagram of the process for determining the prediction result of a first battery health status according to Embodiment 2 of the present invention;

[0026] Figure 5 This is a schematic diagram of the process for determining the prediction result of a second battery health status according to Embodiment 2 of the present invention;

[0027] Figure 6 This is a schematic diagram of the parameter optimization process of a first prediction model and a second prediction model according to Embodiment 2 of the present invention;

[0028] Figure 7 This is a schematic diagram of the structure of a battery health status prediction device for an energy storage battery pack according to Embodiment 3 of the present invention;

[0029] Figure 8 This is a schematic diagram of the structure of an electronic device that implements the battery health status prediction method for energy storage battery packs according to embodiments of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Example 1

[0033] Figure 1 This is a flowchart illustrating a method for predicting the battery health status of an energy storage battery pack, as provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where the battery health status of an energy storage battery pack needs to be predicted. This method can be executed by a battery health status prediction device for the energy storage battery pack. This device can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0034] S110. Obtain real-time operating data of the target energy storage battery pack through the battery management system.

[0035] Among them, the Battery Management System (BMS) is one of the core subsystems of the energy storage system. Its core functions include, but are not limited to, battery status monitoring, safety protection, equalization management, thermal management coordination, data communication and storage.

[0036] In this embodiment of the invention, the real-time operating data of the target energy storage battery pack can be obtained through the battery management system (BMS) of the target energy storage battery pack, including the real-time operating temperature, voltage, current, state of charge (SOC), and depth of discharge (DOD) of the target energy storage battery pack. The data accuracy is at the second level. The battery management system can also summarize, organize, and store the real-time operating data to provide a data foundation for subsequent battery health status prediction.

[0037] S120. Determine the first battery health state prediction result of the target energy storage battery pack based on real-time operating data and the first prediction model deployed locally in the battery management system; wherein, the first prediction model is a semi-empirical model constructed by combining the electrochemical characteristics and cell characteristics of the target energy storage battery pack.

[0038] The first prediction model is a semi-empirical model constructed by combining the electrochemical characteristics of the target energy storage battery pack and the characteristics of the battery cells. It can effectively improve the problems of difficult deployment of localized battery state of health (SOH) models under high complexity and poor prediction accuracy under low complexity. The first prediction model follows the Arrhenius equation and includes a calendar decay model and a cycle decay model. Optionally, the cycle decay model can be expressed as:

[0039]

[0040] Alternatively, the calendar decay model can be expressed as:

[0041]

[0042] Among them, Q loss1 For capacity cyclic decay, A is the pre-exponential factor of cyclic decay, and E is the capacity cyclic decay factor. a As the activation energy, C Rate R is the charge / discharge rate, R is the gas constant, and T is the discharge rate. cycle Let Q be the battery temperature during cycling, Q be the battery capacity (characterized by its state of health), and z be the power-law exponent of capacity decay. loss2 B is the capacity calendar decay, B is the calendar decay pre-exponential factor, and T is the actual temperature. refHere, C is the reference temperature, C is the SOC sensitivity coefficient, SOC is the current state of charge, y is the optimal SOC, d is the time decay coefficient, τ is the resting time, and m is the time power law exponent. It should be noted that when applying the cyclic decay model and calendar decay model in practice, the relevant model parameters need to be adjusted according to the type of battery cell.

[0043] In this embodiment of the invention, the first prediction model is deployed locally in the battery management system (BMS). After obtaining real-time operating data, the capacity decay of the target energy storage battery pack during the cycle period and the storage period can be determined according to the first prediction model, namely the cycle decay model and the calendar decay model, respectively, thereby obtaining the first battery health status prediction result of the target energy storage battery pack.

[0044] S130. Upload real-time operating data to the cloud, and determine the second battery health status prediction result of the target energy storage battery pack based on the real-time operating data and the second prediction model deployed in the cloud; wherein, the second prediction model includes at least two different types of cloud computing models.

[0045] The second prediction model includes at least two different types of cloud computing models, such as machine learning algorithm models and deep learning algorithm models, to address the problem of predicting the battery health status of target energy storage battery packs under different operating conditions and with different battery types. In this embodiment of the invention, the second prediction model can be initially trained based on historical operating data. Specifically, temperature, voltage, current, SOC, DOD, and charge / discharge capacity throughput can be integrated into the energy storage data of the energy storage battery pack. Energy storage data of different types and different usage stages of energy storage battery packs are collected from historical operating data, and the SOH values ​​of different energy storage data are labeled. The SOH values ​​are used as health status labels to construct a training sample set A = {T, U, I, SOC, DOD, Q} for training the second prediction model.

[0046] In this embodiment of the invention, the second prediction model is deployed in the cloud. After obtaining real-time operational data, the real-time operational data can be uploaded to the cloud via 5G or wireless communication. Based on the real-time operational data and the second prediction model, the predicted health status of the second battery of the target energy storage battery pack is determined. Specifically, a suitable type of cloud computing model can be selected from the second prediction models to determine the health status of the second battery of the target energy storage battery pack, depending on the amount of real-time operational data uploaded to the cloud. For example, when the data volume is small, a cloud computing model from a machine learning algorithm model can be selected to determine the health status of the second battery. Simultaneously, the real-time operational data and the corresponding second battery health status are used as sample data to train the deep learning algorithm model. When the data volume increases to a certain extent, a cloud computing model from a deep learning algorithm model can be selected to determine the health status of the second battery.

[0047] S140. Determine the target battery health state prediction result of the target energy storage battery pack based on the first battery health state prediction result and the second battery health state prediction result.

[0048] In this embodiment of the invention, both the locally deployed first prediction model and the cloud-deployed second prediction model have certain limitations. For example, the first prediction model has limited storage and computing power, resulting in poor prediction performance when faced with large amounts of data. The second prediction model has insufficient prediction accuracy when the amount of data is small and is prone to underfitting / overfitting. Therefore, the prediction results of the first battery health status obtained from the first prediction model and the second battery health status obtained from the second prediction model can be comprehensively considered to determine the prediction result of the target battery health status. The parameters of the prediction models can be continuously optimized to improve the prediction accuracy of the battery health status of the target energy storage battery pack, thereby enabling real-time assessment and management of the battery health of the target energy storage battery pack. For example, Figure 2 A schematic diagram of the process for determining the prediction result of a target battery health status is shown.

[0049] The technical solution of this invention involves acquiring real-time operating data of a target energy storage battery pack through a battery management system; determining a first battery health state prediction result for the target energy storage battery pack based on the real-time operating data and a first prediction model deployed locally in the battery management system; wherein the first prediction model is a semi-empirical model constructed by combining the electrochemical characteristics and cell characteristics of the target energy storage battery pack; uploading the real-time operating data to the cloud, and determining a second battery health state prediction result for the target energy storage battery pack based on the real-time operating data and a second prediction model deployed in the cloud; wherein the second prediction model includes at least two different types of cloud computing models; and determining a target battery health state prediction result for the target energy storage battery pack based on the first battery health state prediction result and the second battery health state prediction result. This technical solution of this invention, by comprehensively considering the first battery health state prediction result obtained from the locally deployed semi-empirical model and the second battery health state prediction result obtained from the cloud computing model deployed in the cloud, determines the target health state prediction result, thereby improving the prediction accuracy of the battery health state of the target energy storage battery pack, and thus enabling real-time assessment and management of the battery health of the target energy storage battery pack.

[0050] Example 2

[0051] Figure 3 This is a flowchart of a battery health status prediction method for an energy storage battery pack according to Embodiment 2 of the present invention. The embodiments of the present invention are optimized based on the above embodiments. Solutions not described in detail in the embodiments of the present invention can be found in the above embodiments. Figure 3 As shown, the method includes:

[0052] S210. Obtain real-time operating data of the target energy storage battery pack through the battery management system.

[0053] Optionally, after obtaining the real-time operating data of the target energy storage battery pack through the battery management system, the method further includes: classifying the real-time operating data according to the physical meaning of the parameters in the real-time operating data, and determining the change curve of each type of parameter; determining the correlation change relationship between different types of parameters during the operation of the target energy storage battery pack; wherein the correlation change relationship is used to reflect the trend of a certain type of parameter changing with the change of another type of parameter; and taking data points in the change curve that do not conform to the correlation change relationship as abnormal operating data and removing the abnormal operating data.

[0054] In this embodiment of the invention, after obtaining the real-time operating data of the target energy storage battery pack, the real-time operating data also needs to be preprocessed. Specifically, the real-time operating data can be classified according to the physical meaning of the parameters in the real-time operating data, such as temperature, voltage, current, SOC, DOD, etc., and the change curve of each type of parameter can be determined. It is understood that during the operation of the target energy storage battery pack, the data corresponding to different types of parameters are interrelated. Therefore, the correlation change relationship between different types of parameters can be determined, that is, the trend of different types of parameters changing with the change of a certain type of parameter, such as the temperature of the battery pack increasing when the current increases. By comparing the parameter change curves, data points that do not conform to the correlation change relationship in the change curves can be eliminated as abnormal operating data to ensure the accuracy of the real-time operating data.

[0055] S220. Determine the first battery health state prediction result of the target energy storage battery pack based on real-time operating data and the first prediction model deployed locally on the battery management system.

[0056] Optionally, determining the first battery health state prediction result of the target energy storage battery pack based on the real-time operating data and the first prediction model deployed locally on the battery management system includes: determining the cyclic charge-discharge state operating data in the real-time operating data, calculating the first battery health state decay value based on the cyclic decay model and the cyclic charge-discharge state operating data; determining the storage state operating data in the real-time operating data, calculating the second battery health state decay value based on the calendar decay model and the storage state operating data; taking the sum of the first battery health state decay value and the second battery health state decay value as the total decay value, and taking the battery health state after deducting the total decay value as the first battery health state prediction result.

[0057] In this embodiment of the invention, the operating state of the target energy storage battery pack can be determined based on its real-time operating temperature, voltage, current, SOC, and DOD. The real-time operating data is then divided into cyclic charge / discharge state operating data and storage state operating data. Subsequently, a first battery health state decay value can be calculated based on the cyclic decay model and the cyclic charge / discharge state operating data. A second battery health state decay value can be calculated based on the calendar decay model and the storage state operating data. The first and second battery health state decay values ​​are then summed to obtain a total decay value. Finally, the predicted health state of the first battery is determined based on the total decay value. For example, Figure 4 A schematic diagram of the process for determining the prediction result of the first battery health status is shown.

[0058] S230. Determine the second battery health status prediction result of the target energy storage battery pack based on real-time operating data and the second prediction model deployed in the cloud.

[0059] Optionally, determining the second battery health status prediction result of the target energy storage battery pack based on the real-time operating data and the second prediction model deployed in the cloud includes: determining the target system information of the target energy storage battery pack based on the environment, parallel operation capacity, and operating conditions of the target energy storage battery pack; calculating the similarity between the target system information and the system information of at least two different types of cloud computing models in the second prediction model; taking the cloud computing model corresponding to the system information whose similarity to the target system information exceeds a first preset threshold as the target cloud computing model, and determining the second battery health status prediction result based on the real-time operating data through the target cloud computing model.

[0060] In this embodiment of the invention, when calling the second prediction model deployed in the cloud, it is necessary to determine the corresponding cloud computing model for the target energy storage battery pack. Specifically, the target system information of the target energy storage battery pack can be determined first based on the environment, parallel operation, and usage conditions of the target energy storage battery pack. The similarity between the target system information and the system information corresponding to each cloud computing model in the second prediction model is then calculated. The cloud computing model corresponding to the system information with a similarity exceeding a first preset threshold is taken as the target cloud computing model. The first preset threshold can be set by technicians according to actual conditions, such as 90%, and this embodiment of the invention does not limit this. It should be noted that when there are multiple system information pieces with similarities exceeding the first preset threshold to the target system information, the cloud computing model corresponding to the system information with the highest similarity is taken as the target cloud computing model. Then, the second battery health status prediction result can be determined based on real-time operating data using the target cloud computing model. Specifically, temperature, voltage, current, SOC, and DOD from the real-time operating data can be used as input, and the output result of the target cloud computing model can be obtained as the second battery health status prediction result. For example, Figure 5 A schematic diagram of the process for determining the prediction result of a second battery health status is shown.

[0061] S240. Calculate the difference between the first battery health state prediction result and the second battery health state prediction result, and take the time point corresponding to the number of times the difference is less than the second preset threshold as the target time point.

[0062] The target time point refers to the time point at which the maturity of the second prediction model reaches the preset requirements.

[0063] In this embodiment of the invention, the model maturity of the second prediction model can be determined by calculating the difference between the first battery health state prediction result and the second battery health state prediction result. To prevent accidental occurrences, in this embodiment of the invention, the time point corresponding to the number of times the difference between the two is less than a second preset threshold exceeds a preset number is taken as the target time point. The second preset threshold and the preset number can be set by technicians according to actual conditions, and this embodiment of the invention does not limit them.

[0064] S250. Based on the target time point, determine the target battery health state prediction result according to the first battery health state prediction result and the second battery health state prediction result.

[0065] In this embodiment of the invention, the target time point can indicate whether the model maturity of the second prediction model meets the requirements. Therefore, the target battery health state prediction result can be determined based on the target time point, according to the first battery health state prediction result and the second battery health state prediction result.

[0066] Optionally, determining the target battery health state prediction result based on the target time point, according to the first battery health state prediction result and the second battery health state prediction result, includes: before the target time point, using the first battery health state prediction result as the target battery health state prediction result, and optimizing the parameters of the second prediction model based on the first battery health state prediction result; after the target time point, using the second battery health state prediction result as the target battery health state prediction result, and optimizing the parameters of the first prediction model based on the second battery health state prediction result.

[0067] In this embodiment of the invention, before the target time point, there is limited real-time operational data, resulting in poor prediction accuracy of the second prediction model. In this case, the first battery health state prediction result obtained through a locally deployed first prediction model can be used as the target battery health state prediction result. The parameters of the second prediction model are then optimized based on the first battery health state prediction result to reduce its prediction error. After the target time point, the second prediction model reaches the required maturity, and with the accumulation of real-time operational data, the first prediction model performs poorly when faced with large amounts of data. In this case, the second battery health state prediction result obtained through the second prediction model can be used as the target battery health state prediction result. The parameters of the first prediction model are then optimized based on the second battery health state prediction result to reduce its prediction error.

[0068] Optionally, determining the target battery health status prediction result based on the target time point, according to the first battery health status prediction result and the second battery health status prediction result, further includes: periodically detecting the battery health status of the target energy storage battery pack to determine the actual battery health status detection result; and optimizing the parameters of the first prediction model and the second prediction model based on the actual battery health status detection result.

[0069] In this embodiment of the invention, in addition to optimizing the parameters of the prediction model based on the prediction results, the battery health status of the target energy storage battery pack can also be periodically detected to determine the actual battery health status detection results, and the parameters of the first and second prediction models can be optimized based on the actual battery health status detection results. For example, Figure 6 A schematic diagram of the parameter optimization process for a first prediction model and a second prediction model is shown.

[0070] The technical solution of this invention involves acquiring real-time operating data of a target energy storage battery pack through a battery management system; determining a first battery health state prediction result for the target energy storage battery pack based on the real-time operating data and a first prediction model deployed locally in the battery management system; determining a second battery health state prediction result for the target energy storage battery pack based on the real-time operating data and a second prediction model deployed in the cloud; calculating the difference between the first and second battery health state prediction results, and using the time point corresponding to the number of times the difference is less than a second preset threshold as a preset number as the target time point; and determining the target battery health state prediction result based on the target time point and the first and second battery health state prediction results. This technical solution, by comprehensively considering the first battery health state prediction result obtained from a locally deployed semi-empirical model and the second battery health state prediction result obtained from a cloud computing model deployed in the cloud, can improve the accuracy of predicting the battery health state of the target energy storage battery pack, thereby enabling real-time assessment and management of the battery health of the target energy storage battery pack.

[0071] Example 3

[0072] Figure 7 This is a schematic diagram of a battery health status prediction device for an energy storage battery pack provided in Embodiment 3 of the present invention. Figure 7 As shown, the device includes:

[0073] The real-time operation data acquisition module 310 is used to acquire the real-time operation data of the target energy storage battery pack through the battery management system.

[0074] The first prediction result acquisition module 320 is used to determine the first battery health state prediction result of the target energy storage battery pack based on the real-time operating data and the first prediction model deployed locally on the battery management system; wherein, the first prediction model is a semi-empirical model constructed by combining the electrochemical characteristics and cell characteristics of the target energy storage battery pack.

[0075] The second prediction result acquisition module 330 is used to upload the real-time operating data to the cloud and determine the second battery health status prediction result of the target energy storage battery pack based on the real-time operating data and the second prediction model deployed in the cloud; wherein, the second prediction model includes at least two different types of cloud computing models;

[0076] The target prediction result acquisition module 340 is used to determine the target battery health state prediction result of the target energy storage battery pack based on the first battery health state prediction result and the second battery health state prediction result.

[0077] Optionally, the device further includes:

[0078] The parameter change curve determination module is used to classify the real-time running data according to the physical meaning of the parameters in the real-time running data, and determine the change curve of each type of parameter;

[0079] The correlation change relationship determination module is used to determine the correlation change relationship between different types of parameters during the operation of the target energy storage battery pack; wherein, the correlation change relationship is used to reflect the trend of a certain type of parameter changing with the change of another type of parameter;

[0080] The abnormal operation data removal module is used to identify data points in the change curve that do not conform to the correlation change relationship as abnormal operation data and remove the abnormal operation data.

[0081] Optionally, the first prediction model includes a calendar decay model and a cyclic decay model; the first prediction result acquisition module 320 includes:

[0082] The first attenuation value determination unit is used to determine the cyclic charge-discharge state operation data in the real-time operation data, and calculate the first battery health state attenuation value according to the cyclic attenuation model and the cyclic charge-discharge state operation data.

[0083] The second attenuation value determination unit is used to determine the stored state operation data in the real-time operation data, and calculate the second battery health state attenuation value according to the calendar attenuation model and the stored state operation data.

[0084] The first prediction result acquisition unit is used to take the sum of the first battery health state decay value and the second battery health state decay value as the total decay value, and take the battery health state after deducting the total decay value as the first battery health state prediction result.

[0085] Optionally, the second prediction result acquisition module 330 includes:

[0086] The target system information determination unit is used to determine the target system information of the target energy storage battery pack based on the environment, parallel operation capacity and operating conditions of the target energy storage battery pack.

[0087] The system information similarity calculation unit is used to calculate the similarity between the target system information and the system information of at least two different types of cloud computing models in the second prediction model;

[0088] The second prediction result acquisition unit is used to take the cloud computing model corresponding to the system information whose similarity to the target system information exceeds a first preset threshold as the target cloud computing model, and determine the second battery health status prediction result based on the real-time operating data through the target cloud computing model.

[0089] Optionally, the target prediction result acquisition module 340 includes:

[0090] The target time point determination unit is used to calculate the difference between the first battery health state prediction result and the second battery health state prediction result, and to take the time point when the number of times the difference is less than the second preset threshold exceeds a preset number as the target time point.

[0091] The target prediction result determination unit is used to determine the target battery health state prediction result based on the target time point, according to the first battery health state prediction result and the second battery health state prediction result.

[0092] Optionally, the target prediction result determination unit is specifically used for:

[0093] Before the target time point, the first battery health state prediction result is used as the target battery health state prediction result, and the parameters of the second prediction model are optimized based on the first battery health state prediction result.

[0094] After the target time point, the second battery health state prediction result is used as the target battery health state prediction result, and the parameters of the first prediction model are optimized based on the second battery health state prediction result.

[0095] Optionally, the target prediction result determination unit is further specifically used for:

[0096] The battery health status of the target energy storage battery pack is periodically tested to determine the actual battery health status test results;

[0097] The parameters of the first prediction model and the second prediction model are optimized based on the actual battery health status detection results.

[0098] The battery health status prediction device for energy storage battery packs provided in this embodiment of the invention can execute the battery health status prediction method for energy storage battery packs provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0099] Example 4

[0100] Figure 8 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0101] like Figure 8 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0102] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0103] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as battery health state prediction methods for energy storage battery packs.

[0104] In some embodiments, the battery health state prediction method for the energy storage battery pack can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the battery health state prediction method for the energy storage battery pack described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the battery health state prediction method for the energy storage battery pack by any other suitable means (e.g., by means of firmware).

[0105] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0106] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0107] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0108] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0109] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0110] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0111] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0112] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting the battery health status of an energy storage battery pack, characterized in that, The method includes: Real-time operating data of the target energy storage battery pack is obtained through the battery management system. The first battery health state prediction result of the target energy storage battery pack is determined based on the real-time operating data and the first prediction model deployed locally on the battery management system; wherein, the first prediction model is a semi-empirical model constructed by combining the electrochemical characteristics and cell characteristics of the target energy storage battery pack. The real-time operating data is uploaded to the cloud, and the second battery health status prediction result of the target energy storage battery pack is determined based on the real-time operating data and the second prediction model deployed in the cloud; wherein, the second prediction model includes at least two different types of cloud computing models; The target battery health status prediction result of the target energy storage battery pack is determined based on the first battery health status prediction result and the second battery health status prediction result.

2. The method according to claim 1, characterized in that, After obtaining the real-time operating data of the target energy storage battery pack through the battery management system, the method further includes: The real-time running data is classified according to the physical meaning of the parameters in the real-time running data, and the change curve of each type of parameter is determined. Determine the correlation and change relationships between different types of parameters during the operation of the target energy storage battery pack; wherein, the correlation and change relationships are used to reflect the trend of one type of parameter changing with the change of another type of parameter; Data points in the change curve that do not conform to the correlation relationship are considered abnormal operating data and are removed.

3. The method according to claim 1, characterized in that, The first prediction model includes a calendar decay model and a cyclic decay model; The step of determining the first battery health status prediction result of the target energy storage battery pack based on the real-time operating data and the first prediction model deployed locally on the battery management system includes: Determine the cyclic charge-discharge state operation data in the real-time operation data, and calculate the first battery health state degradation value based on the cyclic degradation model and the cyclic charge-discharge state operation data; Determine the stored state operation data in the real-time operation data, and calculate the second battery health state decay value based on the calendar decay model and the stored state operation data; The sum of the first battery health state decay value and the second battery health state decay value is taken as the total decay value, and the battery health state after deducting the total decay value is taken as the first battery health state prediction result.

4. The method according to claim 1, characterized in that, The step of determining the second battery health status prediction result of the target energy storage battery pack based on the real-time operating data and the second prediction model deployed in the cloud includes: The target system information of the target energy storage battery pack is determined based on the environment, parallel capacity, and operating conditions of the target energy storage battery pack. Calculate the similarity between the target system information and the system information of at least two different types of cloud computing models in the second prediction model; The cloud computing model corresponding to the system information whose similarity to the target system information exceeds a first preset threshold is taken as the target cloud computing model, and the second battery health status prediction result is determined by the target cloud computing model based on the real-time operating data.

5. The method according to claim 1, characterized in that, Determining the target battery health status prediction result of the target energy storage battery pack based on the first battery health status prediction result and the second battery health status prediction result includes: Calculate the difference between the first battery health status prediction result and the second battery health status prediction result, and take the time point when the number of times the difference is less than the second preset threshold exceeds the preset number as the target time point; Based on the target time point, the target battery health state prediction result is determined according to the first battery health state prediction result and the second battery health state prediction result.

6. The method according to claim 5, characterized in that, The step of determining the target battery health status prediction result based on the target time point, according to the first battery health status prediction result and the second battery health status prediction result, includes: Before the target time point, the first battery health state prediction result is used as the target battery health state prediction result, and the parameters of the second prediction model are optimized based on the first battery health state prediction result. After the target time point, the second battery health state prediction result is used as the target battery health state prediction result, and the parameters of the first prediction model are optimized based on the second battery health state prediction result.

7. The method according to claim 5, characterized in that, The step of determining the target battery health state prediction result based on the target time point, according to the first battery health state prediction result and the second battery health state prediction result, further includes: The battery health status of the target energy storage battery pack is periodically tested to determine the actual battery health status test results; The parameters of the first prediction model and the second prediction model are optimized based on the actual battery health status detection results.

8. A battery health status prediction device for an energy storage battery pack, characterized in that, The device includes: The real-time operation data acquisition module is used to acquire real-time operation data of the target energy storage battery pack through the battery management system; The first prediction result acquisition module is used to determine the first battery health state prediction result of the target energy storage battery pack based on the real-time operating data and the first prediction model deployed locally on the battery management system; wherein, the first prediction model is a semi-empirical model constructed by combining the electrochemical characteristics and cell characteristics of the target energy storage battery pack. The second prediction result acquisition module is used to upload the real-time operating data to the cloud, and determine the second battery health status prediction result of the target energy storage battery pack based on the real-time operating data and the second prediction model deployed in the cloud; wherein, the second prediction model includes at least two different types of cloud computing models; The target prediction result acquisition module is used to determine the target battery health state prediction result of the target energy storage battery pack based on the first battery health state prediction result and the second battery health state prediction result.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the battery health status prediction method for the energy storage battery pack according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the battery health status prediction method for the energy storage battery pack as described in any one of claims 1-7.

Images