Database-based comprehensive management method for energy storage device standard detection examples

Abstract

The application relates to a database-based comprehensive management and control method for standard detection examples of energy storage equipment, which comprises the following steps: formulating a detection process according to the type, parameters and working conditions of the energy storage equipment; standardizing the detection process to obtain a standardized detection process; establishing a matching relationship between the standardized detection process and the action instructions of the energy storage equipment detection platform; issuing instructions to the detection platform and collecting and storing detection data through the interface between the comprehensive management and control system and the detection platform; establishing a database to store the detection standards, detection processes and detection data of the energy storage equipment through the database; performing data processing on the detection data to obtain processed detection data, establishing an artificial intelligence model, training the artificial intelligence model with the processed detection data, obtaining a trained artificial intelligence detection model, and evaluating the health condition of the energy storage equipment by using the trained artificial intelligence detection model.

Description

TECHNICAL FIELD

[0001] The application relates to a database-based energy storage device standard detection example comprehensive management method, and relates to the technical field of energy management. BACKGROUND

[0002] Under the background of comprehensively promoting the implementation of the double carbon target, China is actively promoting the increase of the proportion of new energy in the power system. In the face of the instability of photovoltaic, wind power and other new energy power generation, energy storage technology plays a key role in peak shaving, valley filling and ensuring the stability of power grid operation. This trend shows that the widespread application of energy storage technology not only helps to make up for the defects of new energy volatility, but also provides key support for the flexibility and reliability of the power system. In the upgrading and transformation process of the power system, energy storage technology is gradually becoming an important driving force for promoting high penetration of clean energy.

[0003] On the basis of this development trend, the importance of energy storage device detection is more prominent. First, energy storage device detection is the basis for ensuring device performance and safety. For energy storage batteries, battery management systems, energy storage converters, coordination controllers, energy storage energy management systems and other key energy storage devices, their performance is directly related to the storage efficiency and release performance of electric energy. Through comprehensive and accurate detection, potential problems of the device can be found in time to ensure efficient and stable operation of the device in operation. Second, energy storage device detection is a driving force for technological innovation and development. Through systematic and comprehensive detection of energy storage devices, the working mechanism, response characteristics and other key parameters of the devices can be deeply understood. These data and information provide valuable research materials for engineers, which helps to continuously improve and innovate energy storage technology and promote the continuous development of the entire field. In addition, energy storage device detection also has a positive effect on the establishment of standards and specifications. Through the detection of various energy storage devices, a large amount of experimental data and performance indicators can be accumulated to provide scientific basis for the establishment of national standards and industry standards. The establishment of standards helps to promote the healthy and orderly development of the entire energy storage industry and improve the standardization of device manufacturing and use.

[0004] The Beijing University Molecular Engineering Sunan Research Institute has established a power and energy storage battery detection platform that can test energy storage batteries including battery cells, modules and battery packs. Xia Liao et al. of China Electric Power Research Institute provide a test platform for large-scale energy storage converters, which can realize the test detection of energy storage converters. Liu Jian et al. propose a battery management system detection platform that can be used for functional detection of battery management systems under complex working conditions. Xie Jingchi and Chen Jiacheng of Changyuan Deep Blue Automation Co., Ltd. have developed a detection platform for energy storage coordination controllers, which can realize standardized detection of energy storage coordination controllers.

[0005] Although there are currently various detection platforms for key energy storage devices, significant progress has been made in the design and development of device detection. However, compared to the comprehensive management and continuous updating and expansion of standardized detection processes for energy storage devices, research and attention are still insufficient.

[0006] The prior art with publication number CN117706400A, "A multi-condition energy storage battery health evaluation system based on unsupervised domain adaptation", mentions using unsupervised domain adaptation to evaluate the health of energy storage batteries. However, this solution can only evaluate the health of energy storage batteries. Compared to the present invention, the advantages of the present invention are: through database management of detection processes, detection standards and detection data, the automation of detection processes is achieved. Compared to the prior art, the automated process of the present invention not only reduces human intervention, but also improves detection efficiency and accuracy through real-time updating and management of the database; by analyzing and integrating national and industry standards, a detection framework is created and these information is stored in the database. This standardized method ensures the consistency and repeatability of the detection process. Compared to the multi-condition energy storage battery health evaluation system described in the prior art, the present invention provides a more systematic and standardized solution; the matching relationship between the standardized detection process and the action instruction of the energy storage device detection platform is established, which is the key to realizing the automation of the detection process. Compared to the technical solution in the prior art which focuses on battery health state evaluation, this technical feature of the present invention provides an effective means to ensure seamless integration of the detection process and the detection platform; through the interface between the comprehensive management system and the detection platform, the instructions are issued and the detection data is collected and stored, which allows remote control and real-time data collection, improving the response speed of the detection and the efficiency of the data processing; using an artificial intelligence model to train and evaluate the processed detection data, which is significantly different from the unsupervised domain adaptation technology in the prior art. The artificial intelligence model of the present invention can learn and adapt to new data, improving the intelligent level of energy storage device health state evaluation. SUMMARY

[0007] To solve the problems existing in the prior art, the present invention proposes a database-based comprehensive management method for standardized detection examples of energy storage devices.

[0008] The technical solution of the present invention is as follows:

[0009] On the one hand, the present invention provides a database-based comprehensive management method for standardized detection examples of energy storage devices, including the following steps:

[0010] According to the type, parameters and working conditions of the energy storage device, a detection process is formulated; the detection process is standardized to obtain a standardized detection process; an action instruction matching relationship between the standardized detection process and the energy storage device detection platform is established; through the interface between the comprehensive management and control system and the detection platform, instructions are issued to the detection platform and detection data is collected and stored; a database is established to store the detection standards, detection processes and detection data of the energy storage device through the database; the detection data is processed to obtain processed detection data, an artificial intelligence model is established, the processed detection data is trained to the artificial intelligence model to obtain a trained artificial intelligence detection model, and the trained artificial intelligence detection model is used to evaluate the health status of the energy storage device.

[0011] As preferred, the specific steps of the standardized detection process include: analyzing and integrating national standards and industry standards of energy storage devices, creating a detection framework, including defining detection actions, variable parameters and state information, and storing these information in a database; formulating corresponding detection processes according to the detection requirements of different devices, converting the detection processes into standardized processes; establishing a standardized instruction matching table, converting the detection processes into instructions executable by the detection platform, and integrating user interface management tools to enable users to access, manage and update the processes.

[0012] As preferred, the database is tabulated, and the specific steps include:

[0013] A database is established, which includes a device table, a detection platform table, a standard detection process table, and a standardized instruction matching table.

[0014] The device table is used to record the basic information of all energy storage devices, including device type, technical parameters, and manufacturer.

[0015] The detection platform table is used to record the information of all detection platforms, including platform type, supported device type, communication protocol, and detection item.

[0016] The standard detection process table is used to store detailed information of the standard detection process of energy storage devices, including actions, variable parameters, and state information.

[0017] The standardized instruction matching table is used to record the action instruction matching relationship of each energy storage detection device when it is detected on the corresponding detection platform.

[0018] The device table is associated with the standard detection process table to formulate the test detection process corresponding to the energy storage device; the detection platform table is associated with the standard detection process table to view the detection example of each detection platform; the standard detection process table is associated with the standardized instruction matching table to establish a unified standardized example action instruction connecting the standard detection process and each energy storage device detection platform.

[0019] As preferred, the artificial intelligence detection model evaluates the health degree of the multi-working-condition energy storage battery based on the device detection data stored in the data storage device; the evaluation adopts a structural framework of a knowledge query field hybrid network; the knowledge query field hybrid network comprises a scale-aware knowledge query encoder, a bidirectional cross-attention field mixer and a regression head; the scale-aware knowledge query encoder takes the device detection data stored in the database as input, including the voltage, current and capacity of the energy storage battery; generates embedding features related to the health state of a specific field; sets private feature encoders for the source domain and the target domain of different energy storage battery time series data; inputs the source data and the target data corresponding to the source domain and the target domain into the feature encoders, respectively, to generate features of a specific field; the features of the specific field are sent to the bidirectional cross-attention field mixer to reduce the gap between the field features and extract field-invariant features; the field-invariant features generate a prediction result through the regression head to evaluate the health degree of the multi-working-condition energy storage battery;

[0020] The regression head is composed of a 2-layer fully connected neural network, and the algorithm flow of the structural framework is as follows:

[0021]

[0022] Wherein, H(·) is the algorithm operation of the bidirectional cross-attention field mixer; R(·) is the algorithm operation of the regression head; G src is the private feature encoder of the source domain; tgt is the private feature encoder of the target domain; x S is the source data; x t is the target data; is the feature of a specific field; Z SS ,Z tS ,Z tt ,Z St are different field-invariant features, respectively; is the field-invariant feature Z SS ,Z tt generated by the regression head;

[0023] The combination of features (Z ss ,Z ts ) and (Z tt ,Z st ) reduces the difference between different field feature spaces, and an average square error loss function is used to minimize the regression error of all labeled samples to mine the supervision information of each field, and the specific formula is as follows:

[0024]

[0025] Wherein, E(·,·) is the mean square error (MSE) loss function; Lsup is the regression error.

[0026] In another aspect, the present application also provides a database-based energy storage device standard detection example comprehensive management system, comprising:

[0027] a standardization module, which formulates a detection process according to the type, parameters and working conditions of the energy storage device, standardizes the detection process to obtain a standardized detection process, establishes an action instruction matching relationship between the standardized detection process and the energy storage device detection platform, issues instructions to the detection platform and collects and stores detection data through an interface between the comprehensive management system and the detection platform, and processes the detection data to obtain processed detection data;

[0028] a database module, which establishes a database to store the detection standards, detection processes and detection data of the energy storage device through the database;

[0029] an evaluation of the health status of the energy storage device module, which establishes an artificial intelligence model, trains the artificial intelligence model with the processed detection data to obtain a trained artificial intelligence detection model, and uses the trained artificial intelligence detection model to evaluate the health status of the energy storage device.

[0030] As a preferred, the specific steps of the standardized detection process include: analyzing and integrating national standards and industry standards of the energy storage device, creating a detection framework, including defining detection actions, variable parameters and state information, and storing these information in a database; formulating corresponding detection processes according to the detection requirements of different devices, converting the detection processes into standardized processes; establishing a standardized instruction matching table, converting the detection processes into instructions executable by the detection platform, and integrating management tools through a user interface to enable users to access, manage and update the processes.

[0031] As a preferred, the database is tabulated, and the specific steps include:

[0032] establishing a database, wherein the database contains a device table, a detection platform table, a standard detection process table and a standardized instruction matching table;

[0033] the device table is used to record the basic information of all energy storage devices, including device type, technical parameters and manufacturer;

[0034] the detection platform table is used to record the information of all detection platforms, including platform type, supported device type, communication protocol and detection items;

[0035] the standard detection process table is used to store detailed information of the standard detection process of the energy storage device, including actions, variable parameters and state information;

[0036] The standardized instruction matching table is used to record the action instruction matching relationship of each energy storage detection device when it is detected on the corresponding detection platform.

[0037] The device table is associated with the standard detection process table, and the test detection process corresponding to the energy storage device is formulated; the detection platform table is associated with the standard detection process table, and the detection example of each detection platform is viewed; the standard detection process table is associated with the standardized instruction matching table, and the unified standardized example action instruction connecting the standard detection process and each energy storage device detection platform is established.

[0038] As preferred, the artificial intelligence detection model evaluates the health degree of the multi-working-condition energy storage battery based on the energy storage device detection data stored in the data; the evaluation adopts the structural framework of the knowledge query field hybrid network; the knowledge query field hybrid network is composed of a scale perception knowledge query encoder, a bidirectional cross attention field mixer and a regression head; the scale perception knowledge query encoder takes the device detection data stored in the database as input, including the voltage, current and capacity of the energy storage battery; generates health state related embedding features in a specific field; sets private feature encoders for the source domain and the target domain of different energy storage battery time series data, inputs the source data and the target data corresponding to the source domain and the target domain into the feature encoders, respectively, to generate features in a specific field; the features in a specific field are sent to the bidirectional cross attention field mixer to reduce the gap between field features and extract field invariant features; the field invariant features generate a prediction result through the regression head to evaluate the health degree of the multi-working-condition energy storage battery;

[0039] The regression head is composed of a 2-layer fully connected neural network, and the algorithm process of the structural framework is as follows:

[0040]

[0041] Among them, H(·) is the bidirectional cross attention field mixer algorithm operation; R(·) is the regression head algorithm operation; G src is the private feature encoder of the source domain; G tgt is the private feature encoder of the target domain; x s is the source data; x t is the target data; is the feature in a specific field; Z ss ,Z ts ,Z tt ,Z st are different field invariant features, respectively; is the field invariant feature Z SS ,Z tt is the prediction result generated by the regression head;

[0042] The combined feature (Zss ts tt st The average square error loss function is used to minimize the regression error of all labeled samples to mine the supervision information of each field, and the specific formula is as follows:

[0043]

[0044] Wherein, E(·,·) is the mean square error (MSE) loss function; L sup is the regression error.

[0045] In another aspect, the application also provides an electronic device having a computer program stored thereon, wherein the computer program is executed by a processor to implement the database-based energy storage device standard detection case comprehensive management and control method according to any one of the embodiments of the application.

[0046] In another aspect, the application also provides a computer readable medium for storing one or more programs, wherein the one or more programs, when executed by one or more processors, cause the one or more processors to implement the database-based energy storage device standard detection case comprehensive management and control method according to any one of the embodiments of the application.

[0047] The application has the following beneficial effects:

[0048] 1. The application can significantly improve the detection efficiency of energy storage devices through the use of databases and fully automated detection processes. Standardized and automated processes reduce the time and errors of human operation, thereby accelerating the overall detection speed and improving accuracy.

[0049] 2. The application helps to reduce the detection cost of energy storage devices. Through comprehensive management and highly customized detection schemes, resource allocation is optimized, unnecessary resource waste is reduced, resource utilization is improved, and cost effectiveness is achieved.

[0050] 3. The comprehensive management of energy storage device detection standards and processes helps to promote the standardization development of the energy storage device industry. Clear standards and processes help to improve product quality, reduce substandard products, and enhance the standardization level of the entire industry.

[0051] 4. The application can continuously update and expand detection standards as the energy storage industry develops, and it will promote the technological upgrading and innovation of the energy storage device industry. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 is a process schematic diagram of the application;

[0053] ​​​Figure 2 A structural framework diagram of a knowledge query field hybrid network of the present application. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0055] It should be understood that the step numbers used herein are only for the convenience of description, and are not limited to the execution sequence of the steps.

[0056] It should be understood that the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and the appended claims of the present application, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0057] The terms "comprise" and "include" indicate the presence of described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0058] The term "and / or" means any combination of one or more of the associated listed terms and all possible combinations thereof, and includes these combinations.

[0059] Embodiment one:

[0060] Referring to Figures 1-2 A database-based energy storage device standard detection example comprehensive management method, comprising the following steps:

[0061] S10, a detection process is formulated according to the type, parameters and working conditions of the energy storage device; the detection process is standardized to obtain a standardized detection process; an action instruction matching relationship between the standardized detection process and the energy storage device detection platform is established; through an interface between the comprehensive management system and the detection platform, instructions are issued to the detection platform and detection data is collected and stored;

[0062] S20, a database is established, and the detection standards, detection processes and detection data of the energy storage device are stored through the database;

[0063] S30, data processing is performed on the detection data to obtain processed detection data, an artificial intelligence model is established, the processed detection data is used to train the artificial intelligence model, a trained artificial intelligence detection model is obtained, and the trained artificial intelligence detection model is used to evaluate the health condition of the energy storage device.

[0064] As a preferred embodiment of the present embodiment, in steps S10-S30, the detection process of each type of equipment is standardized. The core goal of this step is to extract the actions, variable parameters and state information between the detection platform and the energy storage equipment to be detected, so as to ensure that the subsequent standard examples can fully cover the characteristics of various types of equipment, and the extracted information is comprehensive and representative.

[0065] After obtaining the standard detection process, we match it with the actions of each energy storage equipment detection platform to form a standardization instruction matching table of energy storage detection equipment and detection platform, as shown in Table 1. In the process of establishing the matching table, we consider the detection requirements of different types of energy storage equipment, different parameters and different manufacturers to ensure the universality and applicability of the matching table. This helps our example framework to be flexible and adaptable to the detection requirements of various types of equipment. Table 1 clearly shows the standardized instructions for each equipment on the corresponding platform, laying a foundation for subsequent example construction.

[0066] Table 1 Standardization instruction matching table of energy storage detection equipment and detection platform

[0067]

[0068]

[0069] Finally, based on the format of the detection platform standardization instruction, we compile the standard detection process of the energy storage detection equipment to obtain the action instructions conforming to the format of the detection platform. This step matches the standardized detection process with the specific instruction format, providing a clear operation guide for the subsequent detection process, ensuring that it can be correctly executed by the corresponding equipment detection platform.

[0070] Format of detection platform standardization instruction

[0071] Set parameters set time 600 Check parameters checkI Start do

[0072] Through the above processing, we get the standardized energy storage detection equipment standard detection process. This process has a clear structure and unified format, providing consistent standards for subsequent platform experiments and testing. Such standardized processes not only facilitate the application of equipment on different platforms, but also provide a specific implementation basis for example design. The completion of this series of work lays the foundation for the construction of energy storage equipment detection standard examples. Through standardization processing and instruction matching, we realize the interoperability between different equipment and detection platforms, improving the applicability and practicality of examples. This is expected to provide an efficient and standardized method for future energy storage equipment detection work.

[0073] Example pseudocode

[0074] Taking the grid-connected voltage three-phase imbalance test of PCS as an example, the example pseudocode is given, and the test is carried out according to the standard GB / T 34120-2017 as follows:

[0075] The grid-connected three-phase imbalance should be tested according to the following steps:

[0076] a) Set the energy storage converter to work in grid-connected mode discharge state;

[0077] b) Connect the power quality measurement device to the AC side of the energy storage converter;

[0078] c) Start from the minimum power of the energy storage converter running continuously, take 10% of the rated power of the energy storage converter as an interval, measure the current data continuously for 10 minutes in each interval, and calculate the root mean square value every 3s period from the beginning of the interval, a total of 200 3s period root mean square values;

[0079] d) Record the 95% probability maximum value of the negative sequence current imbalance measurement value and the maximum value of all measurement values respectively;

[0080] e) Set the energy storage converter to work in grid-connected mode charging state, repeat steps b)-d).

[0081]

[0082] In the formula: ε k is the kth measured current or voltage imbalance in 3s;

[0083] After compiling, the pseudocode of the energy storage equipment detection platform can be obtained as follows:

[0084]

[0085]

[0086] By integrating the interface between the standard test case comprehensive management system and each energy storage device test platform, we successfully issued instructions to the test platform and realized the smooth progress of energy storage device testing.

[0087] Test case management system construction

[0088] We designed a library table-based standard test case management scheme, the key of which is to combine the database and table management system to achieve efficient management, query and update of standard test cases. The main work of database design is to establish a database to store various information of standard test cases. The database can include the following tables: Devices, Platforms, TestProcesses, CommandMatching.

[0089] The Devices table is used to record the basic information of all energy storage devices, including device type, technical parameters, manufacturer, etc.

[0090] The Platforms table is used to record the information of all test platforms, including platform type, supported device type, communication protocol, test items, etc.

[0091] The TestProcesses table is used to store detailed information of energy storage device standard test processes, including actions, variable parameters, state information, etc.

[0092] The CommandMatching table is used to record the action instruction matching relationship of each energy storage test device when it is tested on the corresponding test platform.

[0093] Based on the establishment of each table, the association between tables also needs to be established. Proper associations are established in the database to facilitate cross-table queries. The Devices table is associated with the TestProcesses table to facilitate the customization of personalized test processes for each device; the Platforms table is associated with the TestProcesses table to view the test case conditions that each test platform can perform; the TestProcesses table is associated with the CommandMatching table to establish a unified standardized test case action instruction connecting the standard test process and each energy storage device test platform.

[0094] At the same time, the test case management system also designs the user interface, which needs to develop a user-friendly interface to allow users to manage standard test cases through a graphical interface or command line interface. This interface can include:

[0095] Device management: add, delete, modify device information.

[0096] Platform management: add, delete, modify test platform information.

[0097] Case management: manage standard detection procedures, including adding, deleting, modifying procedure case information.

[0098] Instruction matching: view and edit the matching of standard detection procedures and platform case execution instructions on various platforms.

[0099] Permission control: set permissions for different users to ensure that only authorized users can modify and delete.

[0100] This library table management scheme can effectively integrate the information of standard detection cases, improve management efficiency, and ensure the consistency and accuracy of the information. Through the friendly interface and convenient query features, users can easily manage and maintain standard detection cases and query detection results.

[0101] Construction of detection analysis system based on artificial intelligence

[0102] The present application also uses an unsupervised domain adaptation algorithm to extract device detection data obtained from the detection cases stored in the database, and to evaluate the health of the multi-condition energy storage battery. The detection analysis system based on artificial intelligence relies on the comprehensive management and control system of the standard detection cases of the energy storage device to detect a large number of, multiple types and multiple conditions of energy storage battery detection data results, which has an advantage in training an unsupervised domain adaptation algorithm model.

[0103] The multi-condition energy storage battery health evaluation method adopts the structure framework of a knowledge query field hybrid network. The network consists of three parts: a scale perception knowledge query encoder, a bidirectional cross-attention field mixer and a regression head. The scale perception knowledge query encoder takes the device detection data stored in the database as input (including energy storage battery voltage, current, capacity, etc.), which is used to generate health state related embedding features in a specific field. Since each field provides energy storage battery time series data from different feature spaces and different aging patterns, the present application inputs the source data and target data corresponding to the source domain and target domain into the feature encoder to generate features in a specific field; the specific field features are sent to the bidirectional cross-attention field mixer to reduce the gap between the field features and extract field-invariant features; the field-invariant features are passed through the regression head to generate a prediction result, which evaluates the health of the multi-condition energy storage battery.

[0104] The regression head consists of a 2-layer fully connected neural network, and the algorithm flow of the structure framework is as follows:

[0105]

[0106] where H(·) is the bidirectional cross-attention domain mixer algorithm operation; R(·) is the regression head algorithm operation; G src is the private feature encoder of the source domain; Gtgt is a private feature encoder for the target domain; x s is source data; x t is target data; is a domain-specific feature; Z ss ,Z ts ,Z tt ,Z st are different domain-invariant features, respectively; is a domain-invariant feature Z ss ,Z tt is a prediction result generated by the regression head;

[0107] The combination features (Z ss ,Z ts ) and (Z tt ,Z st ) are used to reduce the differences between different domain feature spaces, and an average square error loss function is used to minimize the regression error of all labeled samples to mine the supervision information of each domain. The specific formula is as follows:

[0108]

[0109] Where E(·,·) is the mean square error (MSE) loss function; L sup is the regression error.

[0110] Embodiment two:

[0111] The standardization module formulates a detection process according to the type, parameters and working conditions of the energy storage device, standardizes the detection process to obtain a standardized detection process, establishes a matching relationship between the standardized detection process and the action instructions of the energy storage device detection platform, issues instructions to the detection platform through the interface between the comprehensive management system and the detection platform, collects and stores detection data, processes the detection data to obtain processed detection data, and realizes the function of step S10 in the above embodiment one, and details are not repeated.

[0112] The database module establishes a database, and stores the detection standards, detection processes and detection data of the energy storage device through the database. The module is used to realize the function of step S20 in the above embodiment one, and details are not repeated.

[0113] The evaluation of the health status of the energy storage device module establishes an artificial intelligence model, trains the artificial intelligence model with the processed detection data, obtains a trained artificial intelligence detection model, and evaluates the health status of the energy storage device using the trained artificial intelligence detection model. The module is used to realize the function of step S30 in the above embodiment one, and details are not repeated.

[0114] Embodiment three:

[0115] The embodiment provides an electronic device, which stores a computer program, and the computer program is executed by a processor to realize a database-based energy storage device standard detection example comprehensive management method according to any one of the embodiments of the application.

[0116] Embodiment four:

[0117] The embodiment provides a computer readable medium for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors realize a database-based energy storage device standard detection example comprehensive management method according to any one of the embodiments of the application.

[0118] In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent the cases of A alone, A and B together, and B alone. Wherein A and B can be singular or plural. The character " / " generally represents that the associated objects before and after it are in an "or" relationship. "At least one of the following" and the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b, and c can be single or multiple.

[0119] Those skilled in the art can realize that the units and algorithm steps described in the embodiments disclosed in the present application can be realized by electronic hardware, computer software and combination of electronic hardware and computer software. Whether the functions are realized by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-mentioned system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0121] In several embodiments provided in the present application, any function, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0122] The above description is only some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A database-based integrated management and control method for standard testing examples of energy storage equipment, characterized in that, Includes the following steps: Develop testing procedures based on the type, parameters, and operating conditions of energy storage equipment; standardize the testing procedures to obtain standardized testing procedures; establish a matching relationship between the standardized testing procedures and the energy storage equipment testing platform; issue instructions to the testing platform and collect and store testing data through the interface between the integrated management and control system and the testing platform; establish a database to store the testing standards, testing procedures, and testing data of energy storage equipment. The detection data is processed to obtain processed detection data. An artificial intelligence model is built, and the processed detection data is used to train the artificial intelligence model to obtain a trained artificial intelligence detection model. The trained artificial intelligence detection model is then used to assess the health status of the energy storage equipment. The AI ​​detection model assesses the health of multi-condition energy storage batteries based on stored energy storage device detection data. The assessment employs a knowledge query domain hybrid network framework, consisting of a scale-aware knowledge query encoder, a bidirectional cross-attention domain mixer, and a regression head. The scale-aware knowledge query encoder takes device detection data stored in the database as input, including energy storage battery voltage, current, and capacity, and generates corresponding domain-related embedded features. Private feature encoders are set for the source and target domains of different energy storage battery time-series data. The source and target data corresponding to the source and target domains are input into the feature encoders to generate corresponding domain features. These domain features are fed into the bidirectional cross-attention domain mixer to reduce domain feature gaps and extract domain-invariant features. The domain-invariant features generate prediction results through the regression head to assess the health of multi-condition energy storage batteries. The regression head consists of a 2-layer fully connected neural network, and the specific algorithm flow of the structural framework is as follows: in, This refers to the operation of the bidirectional cross-attention domain mixer algorithm; This is for the regression head algorithm operation; This is a private feature encoder for the source domain; A private feature encoder for the target domain; Source data; For target data; Features of the corresponding field; These are characteristics that remain unchanged across different domains; , Domain-invariant features , Predictions generated by the regression head; Utilizing combined features and To reduce the differences in feature spaces across different domains, the mean squared error loss function is used to minimize the regression error of all labeled samples and mine the supervision information for each domain. The specific formula is as follows: in, The mean squared error loss function; This represents the regression error.

2. The comprehensive management and control method for standard testing examples of energy storage equipment based on a database, as described in claim 1, is characterized in that: The specific steps of the standardized testing process include: analyzing and integrating national and industry standards for energy storage equipment, creating a testing framework, including defining testing actions, variable parameters, and status information, and storing this information in a database; developing corresponding testing processes based on the testing requirements of different equipment, and transforming the testing processes into standardized processes; establishing a standardized instruction matching table, converting the testing processes into instructions executable by the testing platform, and integrating management tools through a user interface to allow users to access, manage, and update the processes.

3. The comprehensive management and control method for standard testing examples of energy storage equipment based on a database, as described in claim 1, is characterized in that... The database is converted into tables, and the specific steps include: Establish a database, which includes a device table, a testing platform table, a standard testing process table, and a standardized instruction matching table; The equipment list is used to record information about all energy storage devices, including equipment type, technical parameters, and manufacturer; The testing platform table is used to record information about all testing platforms, including platform type, supported device types, communication protocols, and testing items. The standard testing process table is used to store detailed information about the standard testing process for energy storage devices, including actions, variable parameters, and status information. The standardized instruction matching table is used to record the action instruction matching relationship of each type of energy storage testing device when it is tested on the corresponding testing platform. Link the equipment list with the standard testing procedure list to formulate the corresponding testing procedures for energy storage equipment; link the testing platform list with the standard testing procedure list to view the testing case status of each testing platform; link the standard testing procedure list with the standardized instruction matching table to establish unified standardized case action instructions that connect the standard testing procedure with each energy storage equipment testing platform.

4. A database-based integrated management and control system for standard testing examples of energy storage equipment, characterized in that, include: Standardized modules are used to develop testing procedures based on the type, parameters, and operating conditions of energy storage devices. The testing process is standardized to obtain a standardized testing process; Establish a matching relationship between the standardized testing process and the energy storage equipment testing platform; issue instructions to the testing platform and collect and store testing data through the interface between the integrated management and control system and the testing platform; process the testing data to obtain the processed testing data; The database module establishes a database to store the testing standards, testing procedures, and testing data for energy storage devices. The module for assessing the health status of energy storage equipment establishes an artificial intelligence model, trains the processed detection data to obtain a trained artificial intelligence detection model, and uses the trained artificial intelligence detection model to assess the health status of energy storage equipment. The AI ​​detection model assesses the health of multi-condition energy storage batteries based on stored energy storage device detection data. The assessment employs a knowledge query domain hybrid network framework, consisting of a scale-aware knowledge query encoder, a bidirectional cross-attention domain mixer, and a regression head. The scale-aware knowledge query encoder takes device detection data stored in the database as input, including energy storage battery voltage, current, and capacity, and generates corresponding domain-related embedded features. Private feature encoders are set for the source and target domains of different energy storage battery time-series data. The source and target data corresponding to the source and target domains are input into the feature encoders to generate corresponding domain features. These domain features are fed into the bidirectional cross-attention domain mixer to reduce domain feature gaps and extract domain-invariant features. The domain-invariant features generate prediction results through the regression head to assess the health of multi-condition energy storage batteries. The regression head consists of a 2-layer fully connected neural network, and the specific algorithm flow of the structural framework is as follows: in, This refers to the operation of the bidirectional cross-attention domain mixer algorithm; This is for the regression head algorithm operation; This is a private feature encoder for the source domain; A private feature encoder for the target domain; Source data; For target data; Features of the corresponding field; These are characteristics that remain unchanged across different domains; , Domain-invariant features , Predictions generated by the regression head; Utilizing combined features and To reduce the differences in feature spaces across different domains, the mean squared error loss function is used to minimize the regression error of all labeled samples and mine the supervision information for each domain. The specific formula is as follows: in, The mean squared error loss function; This represents the regression error.

5. The database-based integrated management and control system for standard testing examples of energy storage equipment according to claim 4, characterized in that: The specific steps of the standardized testing process include: analyzing and integrating national and industry standards for energy storage equipment, creating a testing framework, including defining testing actions, variable parameters, and status information, and storing this information in a database; developing corresponding testing processes based on the testing requirements of different equipment, and transforming the testing processes into standardized processes; establishing a standardized instruction matching table, converting the testing processes into instructions executable by the testing platform, and integrating management tools through a user interface to allow users to access, manage, and update the processes.

6. The database-based integrated management and control system for standard testing examples of energy storage equipment according to claim 4, characterized in that, The database is converted into tables, and the specific steps include: Establish a database, which includes a device table, a testing platform table, a standard testing process table, and a standardized instruction matching table; The equipment list is used to record basic information about all energy storage devices, including equipment type, technical parameters, and manufacturer; The testing platform table is used to record information about all testing platforms, including platform type, supported device types, communication protocols, and testing items. The standard testing process table is used to store detailed information about the standard testing process for energy storage devices, including actions, variable parameters, and status information. The standardized instruction matching table is used to record the action instruction matching relationship of each type of energy storage testing device when it is tested on the corresponding testing platform. Link the equipment list with the standard testing procedure list to formulate the corresponding testing procedures for energy storage equipment; link the testing platform list with the standard testing procedure list to view the testing case status of each testing platform; link the standard testing procedure list with the standardized instruction matching table to establish unified standardized case action instructions that connect the standard testing procedure with each energy storage equipment testing platform.

7. A physical device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements a database-based comprehensive management and control method for standard testing examples of energy storage devices as described in any one of claims 1 to 3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements a database-based comprehensive management and control method for standard testing of energy storage devices as described in any one of claims 1 to 3.

Images