Battery capacity attenuation assessment method, device, equipment and medium

Abstract

The embodiment of the present invention provides a battery capacity decay assessment method, device, equipment and medium, the method comprising: obtaining battery characteristic data of a target battery, the battery characteristic data being obtained by preprocessing and feature extraction of key usage parameters of the target battery; encrypting the battery characteristic data and storing it in a blockchain, in which a first smart contract is deployed; when the triggering condition of the first smart contract is met, the first smart contract is automatically executed, a preset battery assessment model is called to assess and calculate the battery characteristic data stored in the blockchain, and a battery assessment result is output; the battery assessment model is a machine learning model deployed in the first smart contract; the battery assessment result is used to indicate the capacity decay state of the target battery. The embodiment of the present invention can improve the accuracy of battery capacity decay assessment and realize the secure storage and traceability of battery characteristic data.

Description

Technical Field

[0001] The present invention relates to the field of blockchain technology, and in particular to a battery capacity attenuation assessment method, device, equipment and medium. Background Art

[0002] With the widespread use of electric vehicles and various mobile devices, the evaluation and management of battery performance is particularly important. The attenuation of battery capacity has a direct impact on the performance and service life of the device.

[0003] At present, the evaluation of battery capacity decay mainly relies on traditional battery models and empirical formulas. However, these methods generally have problems such as insufficient accuracy, difficulty in ensuring data security, and difficulty in backtracking. Summary of the invention

[0004] In view of the above problems, an embodiment of the present invention is proposed to provide a battery capacity decay assessment method that overcomes the above problems or at least partially solves the above problems, which can improve the accuracy of battery capacity decay assessment and achieve safe storage and traceability of battery characteristic data.

[0005] Correspondingly, an embodiment of the present invention further provides a battery capacity decay assessment device, an electronic device, and a readable storage medium to ensure the implementation and application of the above method.

[0006] In a first aspect, an embodiment of the present invention discloses a method for evaluating battery capacity attenuation, the method comprising:

[0007] Acquire battery characteristic data of a target battery, wherein the battery characteristic data is obtained by preprocessing and extracting characteristics of key usage parameters of the target battery;

[0008] Encrypting the battery characteristic data and storing it in a blockchain, wherein a first smart contract is deployed in the blockchain;

[0009] When the triggering condition of the first smart contract is met, the first smart contract is automatically executed, a preset battery evaluation model is called to evaluate and calculate the battery characteristic data stored in the blockchain, and a battery evaluation result is output; the battery evaluation model is a machine learning model deployed in the first smart contract; the battery evaluation result is used to indicate the capacity attenuation state of the target battery;

[0010] The triggering condition of the first smart contract includes the arrival of a preset period, or the reception of a target triggering event; wherein the target triggering event includes a transaction application operation of a user device for the first smart contract, or the addition of new battery characteristic data to the blockchain.

[0011] In a second aspect, an embodiment of the present invention discloses a battery capacity decay assessment device, the device comprising:

[0012] A data acquisition module, used to acquire battery characteristic data of a target battery, wherein the battery characteristic data is obtained by preprocessing and extracting characteristics of key usage parameters of the target battery;

[0013] A data storage module, used for encrypting the battery characteristic data and storing it in a blockchain, wherein a first smart contract is deployed in the blockchain;

[0014] An automatic evaluation module is used to automatically execute the first smart contract when the triggering condition of the first smart contract is met, call a preset battery evaluation model to evaluate and calculate the battery characteristic data stored in the blockchain, and output a battery evaluation result; the battery evaluation model is a machine learning model deployed in the first smart contract; the battery evaluation result is used to indicate the capacity decay state of the target battery; the triggering condition of the first smart contract includes the arrival of a preset period, or the reception of a target triggering event; wherein the target triggering event includes a transaction application operation of a user device for the first smart contract, or the addition of new battery characteristic data to the blockchain.

[0015] In a third aspect, an embodiment of the present invention discloses an electronic device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the steps of the battery capacity decay assessment method as described in any of the above.

[0016] In a fourth aspect, an embodiment of the present invention discloses a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the battery capacity decay assessment method as described in any of the above can be implemented.

[0017] In a fifth aspect, an embodiment of the present invention discloses a computer program product, including a computer program, which, when executed by a processor, performs the steps of any of the battery capacity decay assessment methods described above.

[0018] The embodiments of the present invention include the following advantages:

[0019] The battery capacity attenuation evaluation method provided by the embodiment of the present invention utilizes the encryption and distributed storage characteristics of blockchain technology to ensure the security and tamper-proof capability of battery feature data. The introduction of blockchain technology can also enhance the user's trust in the battery evaluation results, which helps to improve user satisfaction and loyalty. Further, the embodiment of the present invention can store the battery feature data and the battery evaluation results in the blockchain, so that the authenticity of the data can be traced and verified. In addition, the embodiment of the present invention can reduce manual operations and improve the efficiency of battery capacity attenuation evaluation through the automated smart contract execution evaluation process. Through the machine learning algorithm, the battery feature data is deeply analyzed, and the attenuation of the battery capacity can be more accurately evaluated. Furthermore, based on the accurate battery attenuation evaluation results, the embodiment of the present invention can formulate more scientific and reasonable battery maintenance suggestions, thereby extending the battery life, reducing unnecessary battery replacement and maintenance, and thus helping users and enterprises reduce operating costs. Finally, the embodiment of the present invention combines edge computing technology with blockchain technology to promote the development of battery management systems to a higher level of intelligence and automation, and provide technical support for future smart grids and smart transportation systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flowchart of a method for evaluating battery capacity attenuation according to an embodiment of the present invention;

[0021] Figure 2 is a structural block diagram of an embodiment of a battery capacity decay assessment device of the present invention;

[0022] Figure 3 is a structural block diagram of an embodiment of a battery capacity decay assessment system of the present invention;

[0023] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] The terms "first", "second", etc. in the specification and claims of the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable when appropriate, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, the term "and / or" in the specification and claims is used to describe the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. In the embodiments of the present invention, the term "multiple" refers to two or more, and other quantifiers are similar.

[0026] Reference Figure 1 , shows a flow chart of a method for evaluating battery capacity attenuation according to an embodiment of the present invention, the method may include the following steps:

[0027] Step 101, obtaining battery characteristic data of a target battery, wherein the battery characteristic data is obtained by preprocessing and extracting characteristics of key usage parameters of the target battery;

[0028] Step 102: encrypt the battery characteristic data and store it in a blockchain, wherein a first smart contract is deployed in the blockchain;

[0029] Step 103: When the triggering condition of the first smart contract is met, the first smart contract is automatically executed, a preset battery evaluation model is called to evaluate and calculate the battery characteristic data stored in the blockchain, and a battery evaluation result is output; the battery evaluation model is a machine learning model deployed in the first smart contract; the battery evaluation result is used to indicate the capacity decay state of the target battery; the triggering condition of the first smart contract includes the arrival of a preset period, or the reception of a target triggering event; wherein the target triggering event includes a transaction application operation by a user device for the first smart contract, or the addition of new battery characteristic data to the blockchain.

[0030] In the embodiment of the present invention, the target battery may be any type of electrochemical energy storage battery. The embodiment of the present invention does not limit the type of the target battery and the type of device to which the target battery is applied. For example, the target battery may be a battery in an electric vehicle, or the target battery may be a battery in a mobile device, and so on.

[0031] Blockchain is a chain data structure that combines blocks in a sequential manner in chronological order, and uses cryptography to ensure that the distributed ledger cannot be tampered with or forged. A blockchain network can include several blockchain nodes. Multiple blockchain nodes can jointly maintain a growing distributed data record. The content and timing of these recorded data can be protected by cryptography technology, making it difficult for any party to tamper with, deny, or forge. Blockchain nodes can be devices with computing capabilities, such as servers, server groups, blockchain chips, etc.

[0032] In the blockchain, data (such as transaction information, transaction execution results, etc.) can be encapsulated in the form of blocks. The header of each block contains the timestamp of the current block, the hash value of the previous block information, and the hash value of the current block information, thereby realizing mutual verification between blocks and forming an unalterable blockchain. Each block can be understood as a data block (a unit for storing data). As a decentralized database, the blockchain is a string of data blocks generated by cryptographic methods. Each data block contains information about a network transaction, which is used to verify the validity of its information and generate the next block. The chain formed by connecting blocks end to end is the blockchain. If the data in the block needs to be modified, the content of all blocks after this block needs to be modified, and the data backed up by all nodes in the blockchain network needs to be modified. Therefore, the blockchain has the characteristics of being difficult to tamper with and delete. After the data has been saved to the blockchain, it is reliable as a method to maintain the integrity of the content.

[0033] In order to solve the problems existing in the current battery capacity decay assessment method, the present invention introduces blockchain technology to achieve a more accurate, transparent and traceable battery capacity decay assessment method.

[0034] Specifically, an embodiment of the present invention can obtain battery characteristic data of a target battery, where the battery characteristic data is obtained by extracting characteristics of key usage parameters of the target battery; and encrypt the obtained battery characteristic data and store it in a blockchain.

[0035] The target battery may be a battery in one or more target devices. Each target device has a unique device identifier, and each target battery has a unique battery identifier, and there is a corresponding relationship between the device identifier and the battery identifier. The battery feature data stored in the blockchain may carry the corresponding battery identifier. Furthermore, the battery feature data stored in the blockchain may also carry the device identifier.

[0036] The embodiment of the present invention stores the battery characteristic data of each target battery through blockchain, which can achieve safe management of the battery characteristic data and prevent the data from being tampered with. In addition, the distributed ledger technology of blockchain makes the storage and transmission process of battery characteristic data traceable, enhancing the credibility of the data.

[0037] Furthermore, the step of acquiring battery characteristic data of the target battery may include:

[0038] Step S11: monitor and record key usage parameters of a target battery in the target device in real time through a data collection module deployed in the target device, and send the key usage parameters to an edge computing device connected to the data collection module;

[0039] Step S12: preprocessing and feature extraction of the key usage parameters by the edge computing device to obtain battery feature data of the target battery.

[0040] In the embodiment of the present invention, a data collection module is deployed in the target device where the target battery is located, for real-time monitoring and recording of key usage parameters generated by the target battery during use, and sending the key usage parameters collected in real time to an edge computing device connected to the data collection module. The edge computing device and the data collection module can be connected via a network.

[0041] The key usage parameters of the target battery may include any one or more of the following: the charge and discharge current value, voltage value, temperature value, charge and discharge time, environmental factors (such as high temperature environment or low temperature environment, etc.) of the target battery.

[0042] In a specific implementation, the number of target devices may be greater than or equal to 1, that is, the number of target batteries may be greater than or equal to 1. The number of edge computing devices may be greater than or equal to 1. The distance between the data collection module and the edge computing device to which it is connected may be less than a preset distance range. Exemplarily, within the preset distance range, if a data collection module corresponds to two or more edge computing devices, the edge computing device to which the data collection module uploads battery characteristic data may be specified, or the nearest edge computing device may be selected to upload the real-time collected battery characteristic data.

[0043] Since an edge computing device can correspond to one or more data collection modules, the data collection modules in multiple different target devices respectively collect key usage parameters of the target batteries in their respective target devices in real time, and the types and formats of the collected key usage parameters may be different. Therefore, the edge computing device first preprocesses the received key usage parameters to obtain preprocessed data. The preprocessing includes but is not limited to processing operations such as data cleaning and data formatting to ensure the consistency of the preprocessed data and the quality of the data. Then, the edge computing device performs feature extraction on the preprocessed data and extracts key feature data that can reflect the performance and health status of the battery from the preprocessed data. These key feature data that can reflect the performance and health status of the battery are called battery feature data. Next, the edge computing device encrypts the battery feature data and stores it in the blockchain.

[0044] Feature extraction is an important step in machine learning, which can extract the most useful information from raw data. In an embodiment of the present invention, the feature extraction may include extracting at least one of statistical features, frequency domain features and time domain features from the pre-processed data.

[0045] Among them, statistical features are based on the distribution law of data, and describe the characteristics of data by calculating statistics such as the mean, variance, and median of the data. For one-dimensional data, statistical features can be used to characterize the distribution of data. Frequency domain features extract features by transforming data into the frequency domain. Fourier transform is one of the commonly used frequency domain transformation methods, which can convert signals from the time domain to the frequency domain. In the frequency domain, features can be extracted by calculating the spectrum, power spectrum density, etc. of the signal. Time domain features extract features directly based on the time series of data. It does not require data transformation, and directly uses the time information of the data for analysis and extraction.

[0046] In an embodiment of the present invention, the key usage parameters of the target battery may include real-time operating data and operating status data of the target battery. The data collection module may be composed of a detector in the target battery and a battery management system (BMS) in the target battery. The detector is used to detect the real-time operating data of the target battery, and the real-time operating data includes the voltage value, current value, temperature value, capacitance value, etc. of the target battery when in use. The battery management system is used to obtain the operating status data of the target battery, and the operating status data includes the number of charge and discharge times, discharge power, charge and discharge speed, etc. of the target battery.

[0047] The embodiment of the present invention uses a data collection module to monitor and record the key usage parameters generated by the target battery during use in real time; and deploys an edge computing device near the data source (that is, the data collection module), and uses the edge computing device to perform preliminary processing on the original battery data (key usage parameters of the target battery) collected in real time by the data collection module, which can not only ensure the consistency of the acquired battery characteristic data and guarantee the quality of the data, but also reduce the computing cost of the target device.

[0048] In an optional embodiment of the present invention, the encrypting the battery characteristic data and storing it in the blockchain may include:

[0049] Step S21, encrypting the battery characteristic data of the target battery using a preset encryption algorithm to obtain battery encrypted data;

[0050] Step S22: encapsulate the battery encrypted data to obtain a first blockchain transaction;

[0051] Step S23: Use the private key in the pre-stored preset public-private key pair to sign the first blockchain transaction to obtain signature information;

[0052] Step S24: sending the first blockchain transaction to a blockchain node in the blockchain, wherein the first blockchain transaction carries the signature information; the blockchain node stores the public key in the preset public-private key pair;

[0053] Step S25: The blockchain node uses the public key to verify the signature information in the first blockchain transaction. If the signature information passes the verification, the battery encrypted data is stored in the next block in the blockchain.

[0054] In the embodiment of the present invention, the data collection module in the target device collects the battery characteristic data of the target battery in the target device in real time and sends it to the edge computing device. The edge computing device preprocesses and extracts the received battery characteristic data to obtain the battery characteristic data of the target battery.

[0055] The edge computing device encrypts the battery characteristic data of the target battery using a preset encryption algorithm to obtain battery encrypted data. The preset encryption algorithm may be a symmetric encryption algorithm or an asymmetric encryption algorithm, etc. The present invention does not limit the preset encryption algorithm, which depends on the design and security requirements of the system.

[0056] In an embodiment of the present invention, asymmetric key technology can be used to ensure the security and credibility of battery characteristic data transmitted by the edge computing device to the blockchain. The edge computing device can manage the private key in the preset public-private key pair that has established a binding relationship with the target battery; the private key is the sender's private key; and the blockchain node can store the public key in the preset public-private key pair.

[0057] The edge computing device encapsulates the battery encrypted data to obtain a first blockchain transaction, which may include information such as a hash value and a timestamp of the battery characteristic data.

[0058] The edge computing device signs the first blockchain transaction using a private key in a pre-stored preset public-private key pair to obtain signature information of the first blockchain transaction to ensure the verifiability of the data source.

[0059] The edge computing device sends the first blockchain transaction to at least one blockchain node in the blockchain. The blockchain node stores the public key in the preset public-private key pair. The blockchain node can use the public key to verify the signature information carried by the first blockchain transaction. If the signature information passes the verification, it means that the source of the first blockchain transaction is credible. The blockchain node can add the first blockchain transaction to the blockchain through a consensus mechanism, that is, store the encrypted battery data in the blockchain.

[0060] If the signature information passes the verification, it means that the source of the first blockchain transaction is credible, and the first blockchain transaction can be rejected.

[0061] Specifically, the blockchain node broadcasts the first blockchain transaction to the blockchain network, and the nodes in the blockchain network verify the validity of the first blockchain transaction through a consensus mechanism (such as proof of work PoW, proof of stake PoS, etc.). If the first blockchain transaction is verified to be valid and a consensus is reached, the battery encryption data carried by the first blockchain transaction will be stored in the next block in the blockchain, thereby connecting with the previous block to form an unalterable data chain.

[0062] The embodiment of the present invention encrypts the battery characteristic data of the target battery and stores it on the blockchain, which can ensure the immutability and integrity of the data, and at the same time use the distributed characteristics of the blockchain to achieve secure data storage and prevent any unauthorized data modification. In addition, the embodiment of the present invention combines edge computing technology with blockchain technology to promote the development of battery management systems to a higher level of intelligence and automation.

[0063] Furthermore, the method may also include: encrypting the key usage parameters of the target battery and storing them in the blockchain.

[0064] The embodiment of the present invention can preprocess and extract features of the key usage parameters of the target battery through an edge computing device to obtain battery feature data of the target battery, and store the battery feature data of the target battery in a blockchain, so that the battery feature data stored in the blockchain can be directly used to conveniently evaluate and calculate the target battery.

[0065] In addition, in an embodiment of the present invention, the data collection module in the target device can also establish a network connection with the blockchain node in the blockchain, and directly store the key usage parameters of the target battery collected in real time in the blockchain, so as to save the unprocessed raw battery data in the blockchain, so as to facilitate the subsequent viewing and tracing of the raw battery data.

[0066] In an embodiment of the present invention, a first smart contract is deployed in the blockchain, and a battery evaluation model is deployed in the first smart contract. When the triggering condition of the first smart contract is met, the first smart contract is automatically executed. The first smart contract automatically calls the battery evaluation model to evaluate and calculate the battery characteristic data stored in the blockchain, and outputs the battery evaluation result.

[0067] The battery evaluation model is a pre-trained machine learning model, and the battery evaluation result is used to indicate the capacity attenuation state of the target battery.

[0068] The input of the battery evaluation model is the battery characteristic data of the target battery, and the output of the battery evaluation model is the battery evaluation result of the target battery. The battery characteristic data includes but is not limited to the real-time operation data and / or operation status data of the target battery. The real-time operation data includes but is not limited to any one or more of the following: the voltage value, current value, temperature value, capacitance value, etc. of the target battery when in use. The operation status data includes but is not limited to any one or more of the following: the number of charge and discharge times, discharge power, charge and discharge speed, etc. of the target battery. The battery evaluation result includes but is not limited to the health status value and / or remaining service life value of the target battery.

[0069] The embodiment of the present invention can realize an automated battery capacity decay evaluation process by automatically executing the first smart contract, thereby reducing manual operations and improving the efficiency of battery capacity decay evaluation operations. In addition, the first smart contract obtains the battery evaluation result by calling the battery evaluation model constructed by the machine learning algorithm, which can improve the accuracy of the evaluation result. Furthermore, by using edge computing technology to process and analyze the real-time collected battery data in real time, the real-time and reliability of battery evaluation are enhanced.

[0070] Furthermore, the method may further include: deploying the first smart contract in the blockchain. The deploying the first smart contract in the blockchain may include the following steps:

[0071] Step S31: Writing the source code of the first smart contract based on the programming language supported by the blockchain;

[0072] Step S32: compile the source code of the first smart contract to obtain bytecode recognizable by the blockchain;

[0073] Step S33: generating a second blockchain transaction, wherein the second blockchain transaction includes the bytecode of the first smart contract;

[0074] Step S34: Send the second blockchain transaction to the blockchain node in the blockchain, execute the second blockchain transaction through the blockchain node, and deploy the first smart contract in the blockchain.

[0075] In the embodiment of the present invention, the first smart contract is deployed in the blockchain, and the characteristics of the blockchain technology ensure that the entire process of storage, reading, and execution of the first smart contract is transparent, traceable, and cannot be altered. A smart contract is essentially a piece of code running on a blockchain node to complete a predetermined business logic. This piece of code can be exposed to the outside in the form of multiple functions (or interfaces), and the blockchain account can call different functions as needed. Different functions can be used to implement different functions.

[0076] In some implementations, a user may call a first smart contract deployed in a blockchain by submitting a transaction to a blockchain node. Alternatively, when a trigger condition of the first smart contract is met, the blockchain node may automatically execute the first smart contract and record the execution result and execution status of the first smart contract.

[0077] In an optional embodiment of the present invention, the first smart contract may include a first interface, the input of the first interface is the battery characteristic data of the target battery, and the battery evaluation model is called by calling the first interface.

[0078] The business logic implemented by the first interface is to call the battery evaluation model. When the triggering condition of the first smart contract is met, the blockchain node will automatically call the first interface in the first smart contract, automatically perform battery capacity decay evaluation on the target battery, and obtain the battery evaluation result of the target battery. The input of the first interface may include battery characteristic data of the target battery.

[0079] Furthermore, the first smart contract may also include a second interface, the input of the second interface is the battery evaluation result of the target battery, and the battery maintenance suggestion is generated according to the input battery evaluation result by calling the second interface; wherein the input of the second interface includes the battery evaluation result output in real time by the battery evaluation model, or the input of the second interface includes the battery evaluation result stored in the blockchain.

[0080] The first smart contract may also include a second interface, and the business logic implemented by the second interface is to generate a battery maintenance suggestion based on the battery evaluation result. The input of the second interface may include the battery evaluation result of the target battery.

[0081] Optionally, the input of the second interface may be a battery evaluation result output in real time by the battery evaluation model, or the input of the second interface may be a battery evaluation result stored in the blockchain.

[0082] In a specific implementation, when the first smart contract is triggered to be automatically executed, the first smart contract can automatically obtain the battery characteristic data of the target battery stored in the blockchain, and use the obtained battery characteristic data of the target battery as input to call the first interface, thereby calling the battery evaluation model to perform battery capacity attenuation evaluation on the target battery to obtain the battery evaluation result of the target battery. After obtaining the battery evaluation result of the target battery, the first smart contract can automatically call the second interface to generate battery maintenance suggestions for the battery evaluation result output by the battery evaluation model.

[0083] Furthermore, the first smart contract may also include a third interface, the input of the third interface is the key usage parameters of the target battery, and the battery characteristic data is obtained by calling the third interface to preprocess and extract features for the input key usage parameters.

[0084] The business logic implemented by the third interface is to preprocess and extract features of the input key usage parameters. In a specific implementation, the first interface in the first smart contract can be called based on the battery characteristic data uploaded in real time by the data collection module or the battery characteristic data stored in the blockchain to evaluate the battery capacity attenuation of the target battery. Alternatively, based on the original battery data (key usage parameters of the target battery) uploaded in real time by the data collection module, the third interface in the first smart contract can be called first to obtain the battery characteristic data of the target battery; then, based on the battery characteristic data of the target battery obtained by calling the third interface, the first interface in the first smart contract can be called to evaluate the battery capacity attenuation of the target battery.

[0085] In a specific implementation, deploying the first smart contract in the blockchain may include the following steps: development of a smart contract, compilation of a smart contract, and deployment of a smart contract.

[0086] Among them, the development of smart contracts refers to writing the source code of the first smart contract using a programming language supported by the blockchain platform (such as Ethereum's Solidity, etc.). It contains the business logic implemented by the first smart contract and the external call interface for executing the business logic. For example, the first smart contract includes a first interface, a second interface, and a third interface. By calling the first interface, the business logic of evaluating the battery capacity attenuation of the target battery can be executed. By calling the second interface, the business logic of generating battery maintenance suggestions for the target battery can be executed. By calling the third interface, the business logic of preprocessing and feature extraction of raw battery data can be executed.

[0087] Smart contract compilation refers to compiling the source code of the first smart contract using the Solidity compiler to obtain bytecode that can be understood by the blockchain platform.

[0088] The deployment of a smart contract refers to deploying the compiled bytecode of the first smart contract to the blockchain, that is, registering the first smart contract on the blockchain. The registration process can be completed through a transaction (a second blockchain transaction), which contains the bytecode of the first smart contract. After the first smart contract is successfully registered, the contract identifier (i.e., the smart contract address) provided by the blockchain will be assigned, and the first smart contract will be deployed to each node in the blockchain network. The smart contract address can be used to interact with the first smart contract.

[0089] Furthermore, the embodiment of the present invention sets a trigger condition for the first smart contract, and when the blockchain node deploying the first smart contract determines that the trigger condition is met, the first smart contract is automatically executed. The embodiment of the present invention does not limit the trigger condition of the first smart contract.

[0090] In an embodiment of the present invention, the triggering condition of the first smart contract may include the arrival of a preset period, or the reception of a target triggering event; wherein the target triggering event may include a transaction application operation of a user device for the first smart contract, or the addition of new battery characteristic data to the blockchain.

[0091] In one embodiment, the triggering condition of the first smart contract can be set to the arrival of a preset period. For example, the blockchain node can automatically perform the battery capacity decay assessment operation at regular intervals (preset period).

[0092] In one embodiment, the trigger condition of the first smart contract may be set to receive a target trigger event. The target trigger event may include a specific transaction or specific data. The specific transaction may be, for example, a transaction application operation of the user device for the first smart contract. That is, if the preset period is not reached, the first smart contract may be actively requested to be executed by the user device.

[0093] The receiving of specific data refers to the addition of new battery characteristic data in the blockchain. For example, the addition of new battery characteristic data of a target battery in the blockchain, or the addition of new battery characteristic data of an existing target battery in the blockchain. That is, when new battery characteristic data is added to the blockchain, the operation of executing the first smart contract to perform battery capacity decay evaluation can be automatically triggered.

[0094] In one example, the blockchain has stored the battery characteristic data of target battery 1 and the battery characteristic data of target battery 2. When the battery characteristic data of target battery 3 is added to the blockchain, it can be determined that the target trigger event is received. Alternatively, when the new battery characteristic data of target battery 1 is added to the blockchain, it can be determined that the target trigger event is received.

[0095] In an optional embodiment of the present invention, the trigger condition may also include evaluation frequencies corresponding to different target batteries, which are used to constrain the frequency of the first smart contract calling the battery evaluation model for the target battery; the evaluation frequency corresponding to the target battery is determined according to the usage mode of the target battery, the battery type of the target battery and the battery evaluation result of the target battery; the usage mode includes one or more of the following: regular usage mode, high-intensity usage mode and low-temperature environment usage mode.

[0096] In a specific implementation, when the triggering condition of the first smart contract is met, the first smart contract will be automatically executed to evaluate the battery capacity decay of the target battery. When the number of target batteries is large, the evaluation efficiency and the performance of the entire system may be affected. To solve this problem, the embodiment of the present invention sets corresponding evaluation frequencies for different target batteries in the first smart contract to constrain the frequency of the first smart contract calling the battery evaluation model for the target battery.

[0097] The evaluation frequency corresponding to the target battery is determined according to the usage mode of the target battery, the battery type of the target battery and the battery evaluation result of the target battery. The usage mode includes but is not limited to one or more of the following: regular usage mode, high-intensity usage mode and low-temperature environment usage mode.

[0098] For different target batteries, the embodiment of the present invention determines the evaluation frequency corresponding to each target battery based on the usage mode of the target battery, the battery type of the target battery and the battery evaluation result of the target battery, and then the evaluation frequency corresponding to different target models can be set in the first smart contract.

[0099] Furthermore, a machine learning model for predicting the evaluation frequency, such as a frequency prediction model, may be pre-trained. The usage pattern, battery type, and battery evaluation result of the target battery are input into the frequency prediction model to predict the evaluation frequency corresponding to the target battery.

[0100] The embodiment of the present invention does not limit the method for training the frequency prediction model. The frequency prediction model can be obtained by supervised or unsupervised training based on a large amount of training data and a machine learning algorithm based on an existing neural network. The training data may include a large amount of collected usage patterns of different batteries, battery types, and historical battery evaluation results.

[0101] The method may further comprise:

[0102] According to the key usage parameters of the target battery acquired in real time and the battery evaluation result of the target battery stored in the blockchain, the evaluation frequency corresponding to the target battery in the first smart contract is dynamically adjusted.

[0103] Optionally, the embodiment of the present invention can also dynamically adjust the evaluation frequency corresponding to the target battery set in the first smart contract according to the actual situation of the target battery. Specifically, it can be dynamically adjusted according to the key usage parameters of the target battery obtained in real time and the historical battery evaluation results of the target battery stored in the blockchain to continuously optimize the evaluation frequency corresponding to the target battery.

[0104] Exemplarily, if the target battery is detected to be in a stable state based on the key usage parameters of the target battery acquired in real time and the historical battery evaluation results of the target battery stored in the blockchain, the evaluation frequency of the target battery can be reduced; conversely, if the target battery is detected to be in an abnormal state or the battery capacity is on a downward trend, the evaluation frequency of the target battery can be increased.

[0105] Optionally, the embodiment of the present invention can also dynamically adjust the evaluation frequency of the target battery according to the resource consumption of the first smart contract. For example, the resource consumption of the first smart contract and the evaluation frequency of the target battery can be regularly evaluated, and the evaluation frequency of the target battery can be dynamically adjusted according to the resource consumption of the first smart contract, so that the resource consumption and evaluation frequency of the first smart contract can achieve the expected balance effect.

[0106] Optionally, the embodiment of the present invention can also continuously optimize the adjustment algorithm of the evaluation frequency through adaptive learning, and continuously optimize the adjustment algorithm of the evaluation frequency according to the battery evaluation result of the target battery and the performance feedback of the target battery.

[0107] Optionally, the evaluation frequency of the target battery can also be set by user customization, so that the user can set the trigger condition of the first smart contract deployed in the blockchain through the user device, and adjust the evaluation frequency of the target battery according to their specific needs, so that the first smart contract can make a comprehensive decision based on the user settings and the usage pattern of the target battery.

[0108] An embodiment of the present invention deploys a first smart contract on a blockchain platform, and the first smart contract can be used to automatically perform operations related to battery capacity decay assessment.

[0109] Optionally, the operations related to the battery capacity decay assessment may include: automatically calling the battery assessment model to evaluate and calculate the battery characteristic data stored in the blockchain, and outputting the battery assessment result. Optionally, the operations related to the battery capacity decay assessment may also include: generating battery maintenance suggestions based on the battery assessment result.

[0110] The embodiment of the present invention uses an advanced machine learning algorithm to construct a high-efficiency battery evaluation model, which can improve the accuracy of battery capacity decay evaluation. The battery evaluation model is a machine learning model trained based on the collected historical battery data and the machine learning algorithm. The machine learning model can predict the decay state of the battery capacity based on the input battery characteristic data. The historical battery data includes key usage parameters generated by different batteries during use. By preprocessing and extracting features from the historical battery data, training data for training the battery evaluation model can be obtained.

[0111] In an optional embodiment of the present invention, the method may further include:

[0112] Step S41, constructing an initial battery evaluation model;

[0113] Step S42: iteratively training the initial battery evaluation model using a machine learning algorithm based on the collected historical battery data;

[0114] Step S43: When the iteration stop condition is met, a trained battery evaluation model is obtained.

[0115] In order to improve the accuracy of battery capacity decay assessment, the present invention trains a battery assessment model based on the collected historical battery data and a machine learning algorithm. The training data used to train the battery assessment model can come from battery characteristic data of a large number of different target batteries.

[0116] A machine learning model refers to a model that continuously improves its own performance by organizing existing knowledge structures based on empirical data, such as linear regression models, random forest models, and neural network models. The training of a machine learning model requires processing the training data and learning the optimal mathematical representation that satisfies the constraints under certain constraints. The machine learning model in the embodiment of the present invention mainly includes the structure of the model (such as the neural network structure) and the parameters of the model (such as the connection weight parameters between the various layers of the neural network, and the weight parameters of each feature item of the logistic regression).

[0117] A smart contract is a piece of code running on a blockchain node, which is exposed to the outside in the form of a function. Accounts on the blockchain can call different functions according to demand. In this embodiment, the battery evaluation model can be, for example, a function on a blockchain node, that is, a function in a smart contract (the first smart contract). When the triggering condition of the first smart contract is met, the first smart contract will be automatically executed to call the battery evaluation model in the first smart contract.

[0118] The first smart contract is deployed on a blockchain node, and a battery evaluation model is deployed in the first smart contract, and the battery evaluation model can be a pre-trained machine learning model. The battery evaluation model can be implemented by a function call.

[0119] In one example, the battery evaluation model can be obtained by supervised or unsupervised training based on an existing neural network according to a large amount of training data and a machine learning algorithm. It should be noted that the embodiment of the present invention does not limit the model structure and training method of the battery evaluation model. The battery evaluation model can integrate multiple neural networks. The neural network may include but is not limited to a combination, superposition, or nesting of at least one or at least two of the following: CNN (Convolutional Neural Network), LSTM (Long Short-Term Memory) network, RNN (Simple Recurrent Neural Network), attention neural network, etc.

[0120] The iteration stop condition may include that the model loss is less than a preset threshold, or that the number of iterative training times reaches a preset number. It should be noted that the embodiment of the present invention does not limit the method for calculating the model loss. For example, a general loss function may be used to calculate the model loss. General loss functions include cross entropy loss function, cosine similarity loss function, etc.

[0121] In an optional embodiment of the present invention, the method may further include:

[0122] After the first smart contract is executed, the battery evaluation result and / or the battery maintenance suggestion are stored in the blockchain.

[0123] The battery evaluation result may include a battery health status value and / or a battery remaining service life value. The battery health status (SOH) indicates the current capacity percentage of the target battery relative to its initial capacity. For example, if the initial capacity of the target battery is 100Ah and the current capacity is 85Ah, then the SOH of the target battery is 85%.

[0124] The remaining useful life (RUL) of a battery indicates how long the target battery is expected to be used or how many times it can be charged and discharged before reaching the end of its life.

[0125] Furthermore, the battery evaluation result may also include at least one of battery performance indicators of the target battery, battery usage statistics, battery fault diagnosis, battery maintenance records, and battery usage recommendations.

[0126] Among them, the battery performance indicators include the current voltage value, current value, charge and discharge efficiency, internal resistance value, etc. of the target battery.

[0127] Battery usage statistics, including the number of charge and discharge times of the target battery, the total energy charged and discharged, and the frequency of use.

[0128] Battery fault diagnosis refers to abnormal conditions that may exist in the target battery, such as sudden voltage drops, abnormal temperature increases, etc., which can point out potential faults or problems.

[0129] Battery maintenance records, including maintenance history information of the target battery, replacement parts records, etc.

[0130] Battery usage recommendations refer to providing usage recommendations based on the usage and health status of the target battery to avoid deep discharge, regular charging, etc.

[0131] In an optional embodiment, the embodiment of the present invention records the battery characteristic data and battery evaluation results of all target batteries on the blockchain, which can ensure the transparency and traceability of the battery data, so that users and related parties can trace and verify the authenticity of the data.

[0132] Furthermore, after the execution of the first smart contract is completed, the battery evaluation result can also be sent to a target device (such as a device where the target battery is located) or a designated user device, so that the user can view the battery evaluation result of the target battery.

[0133] Furthermore, the user device may interact with the first smart contract through a blockchain wallet or a dedicated application. For example, the user device may interact with the first smart contract to submit battery characteristic data to the blockchain, or query the battery evaluation result of the target battery stored in the blockchain based on the battery identification request of the target battery.

[0134] Furthermore, the first smart contract may be tested and audited before deployment to avoid loopholes or security issues in the first smart contract. In addition, the first smart contract deployed in the blockchain may be updated regularly to optimize performance or fix existing problems.

[0135] In an optional embodiment of the present invention, the method may further include:

[0136] Step S51: generating a battery maintenance suggestion for the target battery according to the battery evaluation result;

[0137] Step S52: Send the battery maintenance suggestion to a target area, where the target area includes any one or more of the following: the blockchain, a designated storage address, a designated database, and a designated user device.

[0138] The embodiment of the present invention can generate a battery maintenance suggestion for the target battery based on the battery evaluation result of the target battery, so as to formulate a more scientific and reasonable battery maintenance and replacement plan and extend the battery service life.

[0139] In an embodiment of the present invention, the battery maintenance suggestion can be sent to a target area, and the target area includes any one or more of the following: the blockchain, a designated storage address, a designated database, and a designated device. The designated device is, for example, a designated user device, and a user can view information such as a battery status assessment result, a battery maintenance suggestion, and historical battery data of the target battery through the user device.

[0140] The present invention enhances the user's trust in the battery performance evaluation results by introducing blockchain technology, which helps to improve user satisfaction and loyalty. In addition, the battery maintenance suggestions provided according to the embodiments of the present invention can reduce unnecessary battery replacement and maintenance times, help users and enterprises reduce operating costs, and promote the development of battery management systems in the direction of intelligence and automation, providing technical support for future smart grids and intelligent transportation systems.

[0141] In an optional embodiment of the present invention, the battery evaluation result may include a battery health status value and / or a battery remaining service life value; and generating a battery maintenance suggestion for the target battery according to the battery evaluation result may include:

[0142] When the battery health status value is less than a first preset value, generating a first maintenance suggestion; the first maintenance suggestion is used to prompt the target battery to be replaced or repaired;

[0143] When the remaining service life of the battery is less than a second preset value, a second maintenance suggestion is generated; the second maintenance suggestion is used to prompt the target battery to be replaced.

[0144] The embodiment of the present invention can analyze whether the target battery needs maintenance or replacement based on the SOH and RUL predicted by the battery evaluation model.

[0145] For example, when the battery health status (SOH) is less than a first preset value, a first maintenance suggestion for prompting the repair or replacement of the target battery can be generated. The first preset value can be, for example, 80%. Of course, the first preset value can be set according to actual needs.

[0146] For example, when the remaining useful life value (RUL) of the battery is less than a second preset value, a second maintenance suggestion for prompting replacement of the target battery may be generated. The second preset value may be, for example, 2000 charge and discharge cycles. Of course, the second preset value may be set according to actual needs.

[0147] In an optional embodiment of the present invention, the method may further include:

[0148] Step S61, obtaining a battery performance index of the target battery according to the battery characteristic data;

[0149] Step S62: When an abnormal value appears in the battery performance indicator, generate a third maintenance suggestion; the third maintenance suggestion is used to prompt the target battery to be fault diagnosed or repaired.

[0150] Exemplarily, when the battery performance indicator has an abnormal value, a third maintenance suggestion can be generated to prompt the target battery to perform fault diagnosis or repair. When the battery performance indicator has an abnormal value, such as an increase in internal resistance exceeding a preset threshold, a corresponding fault diagnosis report and repair suggestion are generated.

[0151] In an optional embodiment of the present invention, the method may further include:

[0152] A first update maintenance operation is performed on the first smart contract deployed in the blockchain; and a second update maintenance operation is performed on the battery assessment model deployed in the first smart contract.

[0153] The embodiment of the present invention establishes update and maintenance mechanisms for the first smart contract and the battery evaluation model respectively to ensure that the first smart contract and the battery evaluation model can be continuously optimized and upgraded with the passage of time and technological development.

[0154] The first update maintenance operation may include any one or more of the following:

[0155] Code audit operation: Regularly audit the first smart contract code deployed in the blockchain to check and resolve potential security vulnerabilities and code quality issues.

[0156] Upgrade path operation: When designing the first smart contract, an upgrade interface is reserved or a proxy mode is adopted so that it can be upgraded without affecting existing functions.

[0157] Version management operation: implement version control for the first smart contract, save the version change record of the first smart contract in the blockchain, and ensure that each updated version is backward compatible.

[0158] Emergency response plan operation: formulate a rapid response and repair process when the first smart contract encounters a predetermined security issue, and automatically execute the response and repair process when the first smart contract encounters the predetermined security issue.

[0159] The first update maintenance operation may include any one or more of the following:

[0160] Data monitoring operations: Continuously monitor the quality and integrity of the data input into the battery assessment model to ensure the stability and reliability of the data source.

[0161] Performance tracking operation: regularly evaluating the prediction performance of the battery evaluation model, for example, using indicators such as accuracy, recall, F1 score, etc. Among them, F1 score is an indicator used in statistics to measure the accuracy of a binary classification model, which takes into account both the accuracy and recall of the model.

[0162] Model retraining operation: As more battery characteristic data is collected, the battery evaluation model is regularly retrained using the newly added battery characteristic data to continuously improve the accuracy of model predictions and to improve the dynamic update capability of the battery evaluation model.

[0163] Algorithm optimization operations: Use emerging algorithms or improve the performance of the battery assessment model by optimizing existing algorithms.

[0164] In an optional embodiment of the present invention, a strategy prediction model is further deployed in the first smart contract, and the strategy prediction model is a pre-trained machine learning model. The method may further include:

[0165] Step S71: After the first smart contract is executed, the strategy prediction model is automatically called, and the battery evaluation result and the battery characteristic data are input into the strategy prediction model to obtain the charging and discharging strategy of the target battery;

[0166] Step S72: Apply the charge and discharge strategy of the target battery to the battery management system of the target battery.

[0167] When the triggering condition of the first smart contract is met, the first smart contract is automatically executed. The first smart contract automatically calls the battery evaluation model to evaluate and calculate the battery characteristic data of the target battery stored in the blockchain, and outputs the battery evaluation result of the target battery. The battery evaluation result of the target battery reflects the current state of the target battery, including the health state value, the remaining service life value, etc.

[0168] After the first smart contract is executed, the first smart contract automatically calls the strategy prediction model deployed in the first smart contract. The strategy prediction model uses the battery evaluation results and battery feature data to predict the usage strategy of the target battery.

[0169] Furthermore, the first smart contract may also include a fourth interface, the input of the fourth interface is the battery evaluation result and battery characteristic data of the target battery, and the strategy prediction model can be called by calling the fourth interface. The input of the strategy prediction model is the battery evaluation result and battery characteristic data of the target battery. The strategy prediction model analyzes the input data and generates a charge and discharge strategy for the target battery. The charge and discharge strategy may include the optimal charge and discharge time, rate, battery usage mode, etc.

[0170] After the first smart contract deployed on the blockchain node automatically calls the strategy prediction model to obtain the charging and discharging strategy of the target battery, the blockchain node can push the charging and discharging strategy of the target battery to the target device where the target battery is located, so that the charging and discharging strategy of the target battery is applied to the battery management system of the target battery, thereby guiding the actual charging and discharging process of the target battery to optimize the performance of the target battery and extend the battery life.

[0171] Furthermore, after using the charging and discharging strategy, the data collection module deployed in the target device monitors and records the key usage parameters of the target battery in the target device in real time, uploads them to the edge computing device for processing, and then uploads them to the blockchain, and then inputs them into the battery evaluation model again to perform battery capacity attenuation evaluation, forming a closed-loop system that can continuously optimize the charging and discharging strategy of the target battery.

[0172] In an optional embodiment of the present invention, the battery evaluation model can be obtained by performing transfer learning on a pre-trained model based on training data of sodium-ion batteries; the pre-trained model is obtained by pre-training using training data of lithium-ion batteries.

[0173] In practical applications, due to the lack of usage data for sodium-ion batteries, it is difficult to train a battery evaluation model for sodium-ion batteries, and it is also difficult to ensure the accuracy of the model's predictions.

[0174] To solve this problem, the present invention collects a large amount of historical battery data of lithium-ion batteries to train a battery evaluation model for lithium-ion batteries, which is called a pre-trained model. The pre-trained model can accurately evaluate the health status and remaining service life of lithium-ion batteries. The embodiment of the present invention uses transfer learning technology to migrate the pre-trained model for lithium-ion batteries to sodium-ion batteries, so that the battery evaluation model for sodium-ion batteries obtained by transfer learning can accurately evaluate the health status and remaining service life of sodium-ion batteries.

[0175] Based on transfer learning technology, transfer learning is performed on the pre-trained model, which only requires a small amount of sodium-ion battery training data, and can solve the problem of difficulty in collecting usage data of sodium-ion batteries.

[0176] Based on transfer learning, the pre-trained model is fine-tuned using the training data of sodium-ion batteries, which includes adjusting the parameters of the pre-trained model and optimizing the model to adapt to the specific chemical and physical properties of sodium-ion batteries.

[0177] Next, the migrated model is trained and the validation set is used to evaluate the performance of the migrated model to ensure that the migrated model can accurately assess the health status and remaining service life of the sodium-ion battery.

[0178] In a specific implementation, the target battery may be a lithium-ion battery, and the battery evaluation model deployed in the first smart contract may be a machine learning model trained based on a large amount of historical battery data of lithium-ion batteries.

[0179] The target battery may also be a sodium-ion battery, and the battery evaluation model deployed in the first smart contract may be a battery evaluation model for sodium-ion batteries obtained by transfer learning based on a pre-trained model for lithium-ion batteries.

[0180] Furthermore, a battery evaluation model for lithium-ion batteries and a battery evaluation model for sodium-ion batteries may be deployed in the first smart contract. When the first smart contract automatically calls the battery evaluation model, the corresponding battery evaluation model may be selected according to the battery type of the target battery (such as lithium-ion battery or sodium-ion battery) to perform battery capacity attenuation evaluation processing, and the obtained battery evaluation results may be stored in the blockchain.

[0181] Furthermore, the embodiment of the present invention regularly uses the actual operating data of the sodium-ion battery to optimize and update the battery evaluation model for the sodium-ion battery to maintain the accuracy and adaptability of the model.

[0182] In summary, the battery capacity attenuation evaluation method provided by the embodiment of the present invention utilizes the encryption and distributed storage characteristics of blockchain technology to ensure the security and tamper-proof capability of battery feature data. The introduction of blockchain technology can also enhance the user's trust in the battery evaluation results, which helps to improve user satisfaction and loyalty. Furthermore, the embodiment of the present invention can store the battery feature data and the battery evaluation results in the blockchain, so that the authenticity of the data can be traced and verified. In addition, the embodiment of the present invention can reduce manual operations and improve the efficiency of battery capacity attenuation evaluation through the automated smart contract execution evaluation process. Through the machine learning algorithm, the battery feature data is deeply analyzed, and the attenuation of the battery capacity can be more accurately evaluated. Furthermore, based on the accurate battery attenuation evaluation results, the embodiment of the present invention can formulate more scientific and reasonable battery maintenance suggestions, thereby extending the battery life, reducing unnecessary battery replacement and maintenance, and thus helping users and enterprises reduce operating costs. Finally, the embodiment of the present invention combines edge computing technology with blockchain technology to promote the development of battery management systems to a higher level of intelligence and automation, and provide technical support for future smart grids and smart transportation systems.

[0183] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0184] Reference Figure 2 , shows a structural block diagram of an embodiment of a battery capacity decay assessment device of the present invention, the device may include:

[0185] The data acquisition module 201 is used to acquire battery characteristic data of a target battery, wherein the battery characteristic data is obtained by preprocessing and extracting characteristics of key usage parameters of the target battery;

[0186] A data storage module 202, used to encrypt the battery characteristic data and store it in a blockchain, wherein a first smart contract is deployed in the blockchain;

[0187] The automatic evaluation module 203 is used to automatically execute the first smart contract when the triggering condition of the first smart contract is met, call a preset battery evaluation model to evaluate and calculate the battery characteristic data stored in the blockchain, and output a battery evaluation result; the battery evaluation model is a machine learning model deployed in the first smart contract; the battery evaluation result is used to indicate the capacity decay state of the target battery; the triggering condition of the first smart contract includes the arrival of a preset period, or the reception of a target triggering event; wherein the target triggering event includes a transaction application operation of a user device for the first smart contract, or the addition of new battery characteristic data to the blockchain.

[0188] Optionally, the data acquisition module includes:

[0189] A real-time acquisition submodule, used to monitor and record key usage parameters of a target battery in the target device in real time through a data collection module deployed in the target device, and send the key parameters to an edge computing device connected to the data collection module;

[0190] The data processing submodule is used to preprocess and extract features of the key usage parameters through the edge computing device to obtain battery feature data of the target battery.

[0191] Optionally, the triggering condition of the first smart contract further includes evaluation frequencies corresponding to different target batteries, which is used to constrain the frequency of the first smart contract calling the battery evaluation model for the target battery; the evaluation frequency corresponding to the target battery is determined according to the usage mode of the target battery, the battery type of the target battery and the battery evaluation result of the target battery; the usage mode includes one or more of the following: conventional usage mode, high-intensity usage mode and low-temperature environment usage mode;

[0192] The device also includes:

[0193] A frequency adjustment module is used to dynamically adjust the evaluation frequency corresponding to the target battery in the first smart contract according to the key usage parameters of the target battery acquired in real time and the battery evaluation result of the target battery stored in the blockchain.

[0194] Optionally, the data storage module includes:

[0195] An encryption submodule, used to encrypt the battery characteristic data of the target battery using a preset encryption algorithm to obtain battery encrypted data;

[0196] A packaging submodule, used to package the battery encrypted data to obtain a first blockchain transaction;

[0197] A signing submodule, used to sign the first blockchain transaction using a private key in a pre-stored preset public-private key pair to obtain signature information;

[0198] A transaction sending submodule, configured to send the first blockchain transaction to a blockchain node in the blockchain, wherein the first blockchain transaction carries the signature information; the blockchain node stores a public key in the preset public-private key pair;

[0199] The verification submodule is used for the blockchain node to use the public key to verify the signature information in the first blockchain transaction. If the signature information passes the verification, the battery encrypted data is stored in the next block in the blockchain.

[0200] Optionally, the device further comprises:

[0201] A suggestion generating module, used for generating a battery maintenance suggestion for the target battery according to the battery evaluation result;

[0202] A suggestion sending module is used to send the battery maintenance suggestion to a target area, and the target area includes any one or more of the following: the blockchain, a specified storage address, a specified database, and a specified user device.

[0203] Optionally, the battery evaluation result includes a battery health status value and / or a battery remaining service life value;

[0204] The suggestion generation module is specifically used for:

[0205] When the battery health status value is less than a first preset value, a first maintenance suggestion is generated; the first maintenance suggestion is used to prompt the target battery to be replaced or repaired; when the battery remaining service life value is less than a second preset value, a second maintenance suggestion is generated; the second maintenance suggestion is used to prompt the target battery to be replaced.

[0206] Optionally, the device further comprises:

[0207] A performance indicator acquisition module, used to acquire the battery performance indicator of the target battery according to the battery characteristic data;

[0208] The suggestion generating module is further used to generate a third maintenance suggestion when an abnormal value appears in the battery performance indicator; the third maintenance suggestion is used to prompt the target battery to be fault diagnosed or repaired.

[0209] Optionally, the device further includes: a model training module; the model training module is specifically used to:

[0210] An initial battery evaluation model is constructed; based on the collected historical battery data, the initial battery evaluation model is iteratively trained using a machine learning algorithm; when an iteration stop condition is met, a trained battery evaluation model is obtained.

[0211] Optionally, the device further comprises:

[0212] A contract writing module, used to write the source code of the first smart contract based on the programming language supported by the blockchain;

[0213] A contract compilation module, used to compile the source code of the first smart contract to obtain bytecode recognizable by the blockchain;

[0214] A contract deployment module is used to generate a second blockchain transaction, wherein the second blockchain transaction includes the bytecode of the first smart contract; send the second blockchain transaction to a blockchain node in the blockchain, execute the second blockchain transaction through the blockchain node, and deploy the first smart contract in the blockchain.

[0215] Optionally, the first smart contract includes a first interface, the input of the first interface is battery characteristic data of the target battery, and the battery evaluation model is called by calling the first interface.

[0216] Optionally, the first smart contract includes a second interface, the input of the second interface is a battery evaluation result of the target battery, and a battery maintenance recommendation is generated for the input battery evaluation result by calling the second interface; wherein the input of the second interface includes the battery evaluation result output in real time by the battery evaluation model, or the input of the second interface includes the battery evaluation result stored in the blockchain.

[0217] Optionally, the first smart contract includes a third interface, and the input of the third interface is the key usage parameters of the target battery. The battery characteristic data is obtained by calling the third interface to preprocess and extract features of the input key usage parameters.

[0218] Optionally, a strategy prediction model is also deployed in the first smart contract, and the device further includes:

[0219] A strategy prediction module, configured to automatically call the strategy prediction model after the execution of the first smart contract is completed, input the battery evaluation result and the battery characteristic data into the strategy prediction model, and obtain the charging and discharging strategy of the target battery;

[0220] A strategy application module is used to apply the charge and discharge strategy of the target battery to the battery management system of the target battery.

[0221] Optionally, the battery evaluation model is obtained by transfer learning a pre-trained model based on training data of sodium-ion batteries; the pre-trained model is obtained by pre-training using training data of lithium-ion batteries.

[0222] The battery capacity attenuation evaluation device provided by the embodiment of the present invention utilizes the encryption and distributed storage characteristics of blockchain technology to ensure the security and tamper-proof capability of battery characteristic data. The introduction of blockchain technology can also enhance the user's trust in the battery evaluation results, which helps to improve user satisfaction and loyalty. Furthermore, the embodiment of the present invention can store the battery characteristic data and the battery evaluation results in the blockchain, so that the authenticity of the data can be traced and verified. In addition, the embodiment of the present invention can reduce manual operations and improve the efficiency of battery capacity attenuation evaluation through the automated smart contract execution evaluation process. Through the machine learning algorithm, the battery characteristic data is deeply analyzed, and the attenuation of the battery capacity can be more accurately evaluated. Furthermore, based on the accurate battery attenuation evaluation results, the embodiment of the present invention can formulate more scientific and reasonable battery maintenance suggestions, thereby extending the battery life, reducing unnecessary battery replacement and maintenance, and thus helping users and enterprises reduce operating costs. Finally, the embodiment of the present invention combines edge computing technology with blockchain technology to promote the development of battery management systems to a higher level of intelligence and automation, and provide technical support for future smart grids and smart transportation systems.

[0223] Reference Figure 3 , showing a structural block diagram of an embodiment of a battery capacity decay assessment system of the present invention, the system may include: a target device 301, an edge computing device 302 and a blockchain 303.

[0224] The number of target devices may be greater than or equal to 1, that is, the number of target batteries may be greater than or equal to 1. The number of edge computing devices may be greater than or equal to 1. A data collection module is deployed in the target device, which is used to monitor and record the key usage parameters of the target battery in the target device in real time, and send them to the edge computing device connected to the data collection module. The distance between the data collection module and the edge computing device to which it is connected may be less than a preset distance range. Exemplarily, within the preset distance range, if a data collection module corresponds to two or more edge computing devices, the edge computing device to which the data collection module uploads the battery characteristic data may be specified, or the edge computing device closest to the data collection module may be selected to upload the battery characteristic data collected in real time.

[0225] The edge computing device is used to preprocess and extract features of the received key usage parameters to obtain battery feature data of the target battery, and encrypt the battery feature data and store it in the blockchain. The blockchain includes multiple blockchain nodes, and a first smart contract is deployed in the blockchain, and a preset battery evaluation model is deployed in the first smart contract. When the triggering condition of the first smart contract is met, the blockchain node where the first smart contract is deployed automatically executes the first smart contract, and the first smart contract automatically calls the battery evaluation model to evaluate and calculate the battery feature data stored in the blockchain, and outputs a battery evaluation result; the battery evaluation model is a machine learning model deployed in the first smart contract; the battery evaluation result is used to indicate the capacity attenuation state of the target battery.

[0226] After the execution of the first smart contract is completed, the obtained battery evaluation result can be stored in the blockchain. Furthermore, the first smart contract can also automatically generate battery maintenance suggestions based on the battery evaluation result output by the machine learning model, and store the battery maintenance suggestions in the blockchain. Furthermore, the battery evaluation result and / or the battery maintenance suggestions can also be sent to the target user device for the user to view.

[0227] The operations of each module in the battery capacity decay assessment system have been described in detail in the above embodiments and will not be repeated here.

[0228] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0229] Reference Figure 4 , is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4As shown, the electronic device includes: a processor, a memory, a communication interface and a communication bus, and the processor, the memory and the communication interface communicate with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the steps of the battery capacity decay evaluation method of the aforementioned embodiment.

[0230] An embodiment of the present invention provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by a program or processor of a terminal, the terminal is enabled to execute the steps of the battery capacity decay assessment method of the aforementioned embodiment.

[0231] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0232] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0233] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0234] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal device to operate in a predictable manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0235] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0236] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0237] Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A battery capacity attenuation evaluation method, characterized in that: The method comprises: Acquire battery characteristic data of a target battery, wherein the battery characteristic data is obtained by preprocessing and extracting characteristics of key usage parameters of the target battery; Encrypting the battery characteristic data and storing it in a blockchain, wherein a first smart contract is deployed in the blockchain; When the triggering condition of the first smart contract is met, the first smart contract is automatically executed, and a preset battery evaluation model is called to evaluate and calculate the battery characteristic data stored in the blockchain, and a battery evaluation result is output; the battery evaluation model is a machine learning model deployed in the first smart contract; the battery evaluation result is used to indicate the capacity decay state of the target battery; wherein, a battery evaluation model for lithium-ion batteries and a battery evaluation model for sodium-ion batteries are deployed in the first smart contract; when the first smart contract automatically calls the battery evaluation model, the corresponding battery evaluation model is selected according to the battery type of the target battery to perform battery capacity decay evaluation processing; the battery evaluation model for sodium-ion batteries is obtained by transfer learning based on the pre-trained model for lithium-ion batteries that has been trained; on the basis of transfer learning, the pre-trained model is fine-tuned using the training data of sodium-ion batteries, including adjusting the parameters of the pre-trained model and optimizing the model to adapt to the specific chemical and physical properties of sodium-ion batteries; and the battery evaluation model for the sodium-ion battery is regularly optimized and updated using the actual operation data of the sodium-ion battery; The triggering condition of the first smart contract includes the arrival of a preset period, or the reception of a target triggering event; wherein the target triggering event includes a transaction application operation of a user device for the first smart contract, or the addition of battery characteristic data in the blockchain; the added battery characteristic data includes: battery characteristic data of a new target battery added in the blockchain, or new battery characteristic data of an existing target battery added in the blockchain; The trigger condition also includes an evaluation frequency corresponding to different target batteries, which is used to constrain the frequency at which the first smart contract calls the battery evaluation model for the target battery; the evaluation frequency corresponding to the target battery is determined according to the usage mode of the target battery, the battery type of the target battery, and the battery evaluation result of the target battery; the usage mode includes one or more of the following: a regular usage mode, a high-intensity usage mode, and a low-temperature environment usage mode; The method further comprises: For different target batteries, based on the usage mode of the target battery, the battery type of the target battery and the battery evaluation result of the target battery, determining the evaluation frequency corresponding to each target battery; The evaluation frequency corresponding to the target battery in the first smart contract is dynamically adjusted according to the key usage parameters of the target battery acquired in real time, the battery evaluation result of the target battery stored in the blockchain, the performance feedback of the target battery, and the resource consumption of the first smart contract.

2. The method according to claim 1, characterized in that The step of obtaining battery characteristic data of a target battery includes: The key usage parameters of the target battery in the target device are monitored and recorded in real time by a data collection module deployed in the target device, and sent to an edge computing device connected to the data collection module; The key usage parameters are preprocessed and feature extracted by the edge computing device to obtain battery feature data of the target battery.

3. The method according to claim 1, characterized in that The step of encrypting the battery characteristic data and storing it in a blockchain includes: Encrypt the battery characteristic data of the target battery using a preset encryption algorithm to obtain battery encrypted data; Encapsulating the battery encrypted data to obtain a first blockchain transaction; Using a private key in a pre-stored preset public-private key pair to sign the first blockchain transaction to obtain signature information; Sending the first blockchain transaction to a blockchain node in the blockchain, where the first blockchain transaction carries the signature information; the blockchain node stores a public key in the preset public-private key pair; The blockchain node uses the public key to verify the signature information in the first blockchain transaction. If the signature information passes the verification, the battery encrypted data is stored in the next block in the blockchain.

4. The method according to claim 1, characterized in that: The method further comprises: Generating a battery maintenance suggestion for the target battery according to the battery evaluation result; The battery maintenance suggestion is sent to a target area, where the target area includes any one or more of the following: the blockchain, a specified storage address, a specified database, and a specified user device.

5. The method according to claim 4, characterized in that The battery evaluation result includes a battery health status value and / or a battery remaining service life value; Generating a battery maintenance suggestion for the target battery according to the battery evaluation result includes: When the battery health status value is less than a first preset value, generating a first maintenance suggestion; the first maintenance suggestion is used to prompt the target battery to be replaced or repaired; When the remaining service life of the battery is less than a second preset value, a second maintenance suggestion is generated; the second maintenance suggestion is used to prompt the target battery to be replaced.

6. The method according to claim 1, characterized in that The method further comprises: Acquiring a battery performance indicator of the target battery according to the battery characteristic data; When an abnormal value appears in the battery performance indicator, a third maintenance suggestion is generated; the third maintenance suggestion is used to prompt the target battery to be diagnosed or repaired.

7. The method according to claim 1, characterized in that The method further comprises: Build an initial battery assessment model; Iteratively training the initial battery assessment model using a machine learning algorithm based on the collected historical battery data; When the iteration stop condition is met, a trained battery evaluation model is obtained.

8. The method according to claim 1, characterized in that The method further comprises: Writing the source code of the first smart contract based on the programming language supported by the blockchain; Compile the source code of the first smart contract to obtain bytecode recognizable by the blockchain; Generate a second blockchain transaction, wherein the second blockchain transaction includes the bytecode of the first smart contract; The second blockchain transaction is sent to a blockchain node in the blockchain, the second blockchain transaction is executed through the blockchain node, and the first smart contract is deployed in the blockchain.

9. The method according to claim 1, characterized in that: The first smart contract includes a first interface, the input of the first interface is the battery characteristic data of the target battery, and the battery evaluation model is called by calling the first interface.

10. The method according to claim 1, characterized in that The first smart contract includes a second interface, the input of the second interface is a battery evaluation result of the target battery, and a battery maintenance suggestion is generated for the input battery evaluation result by calling the second interface; wherein the input of the second interface includes the battery evaluation result output in real time by the battery evaluation model, or the input of the second interface includes the battery evaluation result stored in the blockchain.

11. The method according to claim 1, characterized in that: The first smart contract includes a third interface, the input of the third interface is the key usage parameters of the target battery, and the battery characteristic data is obtained by calling the third interface to preprocess and extract features of the input key usage parameters.

12. The method according to claim 1, characterized in that A strategy prediction model is also deployed in the first smart contract, and the method further includes: After the first smart contract is executed, the strategy prediction model is automatically called, and the battery evaluation result and the battery characteristic data are input into the strategy prediction model to obtain the charging and discharging strategy of the target battery; The charge and discharge strategy of the target battery is applied to the battery management system of the target battery.

13. A battery capacity attenuation assessment device, characterized in that: The device comprises: A data acquisition module, used to acquire battery characteristic data of a target battery, wherein the battery characteristic data is obtained by preprocessing and extracting characteristics of key usage parameters of the target battery; A data storage module, used for encrypting the battery characteristic data and storing it in a blockchain, wherein a first smart contract is deployed in the blockchain; An automatic evaluation module, used to automatically execute the first smart contract when the triggering condition of the first smart contract is met, call a preset battery evaluation model to evaluate and calculate the battery characteristic data stored in the blockchain, and output a battery evaluation result; the battery evaluation model is a machine learning model deployed in the first smart contract; the battery evaluation result is used to indicate the capacity decay state of the target battery; wherein, a battery evaluation model for lithium-ion batteries and a battery evaluation model for sodium-ion batteries are deployed in the first smart contract; when the first smart contract automatically calls the battery evaluation model, the corresponding battery evaluation model is selected according to the battery type of the target battery to perform battery capacity decay evaluation processing; the battery evaluation model for sodium-ion batteries is obtained by transfer learning based on a pre-trained model for lithium-ion batteries that has been trained; on the basis of transfer learning, the pre-trained model is fine-tuned using the training data of sodium-ion batteries, including adjusting the parameters of the pre-trained model and optimizing the model to adapt to the specific chemical and physical properties of sodium-ion batteries; and the battery evaluation model for the sodium-ion battery is regularly optimized and updated using the actual operation data of the sodium-ion battery; The triggering condition of the first smart contract includes the arrival of a preset period, or the reception of a target triggering event; wherein the target triggering event includes a transaction application operation of a user device for the first smart contract, or the addition of battery characteristic data in the blockchain; the added battery characteristic data includes: battery characteristic data of a new target battery added in the blockchain, or new battery characteristic data of an existing target battery added in the blockchain; The trigger condition also includes an evaluation frequency corresponding to different target batteries, which is used to constrain the frequency at which the first smart contract calls the battery evaluation model for the target battery; the evaluation frequency corresponding to the target battery is determined according to the usage mode of the target battery, the battery type of the target battery, and the battery evaluation result of the target battery; the usage mode includes one or more of the following: a regular usage mode, a high-intensity usage mode, and a low-temperature environment usage mode; The device also includes: A frequency determination module, for determining, for different target batteries, an evaluation frequency corresponding to each target battery based on a usage mode of the target battery, a battery type of the target battery, and a battery evaluation result of the target battery; A frequency adjustment module is used to dynamically adjust the evaluation frequency corresponding to the target battery in the first smart contract according to the key usage parameters of the target battery acquired in real time, the battery evaluation result of the target battery stored in the blockchain, the performance feedback of the target battery, and the resource consumption of the first smart contract.

14. An electronic device, characterized in that: include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the steps of the battery capacity decay assessment method as described in any one of claims 1 to 12.

15. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the battery capacity decay assessment method as described in any one of claims 1 to 12 are implemented.

Images