Efficient control and intelligent evaluation method and system for detection test of electrochemical energy storage system

Abstract

The invention relates to an electrochemical energy storage system detection test efficient control and intelligent evaluation method and system. The method comprises the following steps: constructing a MySQL database based on an SQLAlchemy module; the method comprises the following steps: scanning a tag of an RFID or a two-dimensional code on equipment of an electrochemical energy storage system through a scanner, identifying basic information of the equipment, calling a corresponding detection item from a MySQL database by using an SQLAlchemy module, and constructing basic detection test content of the equipment; according to the basic detection test content of the equipment of the electrochemical energy storage system, generating an optimal detection test task scheduling scheme by using a genetic algorithm; automatically collecting and recording detection test results of the equipment of the electrochemical energy storage system by adopting automatic test equipment; performing intelligent analysis on a detection test result by using a pre-trained deep neural network; and constructing a performance evaluation index system of the electrochemical energy storage system, and forming a visual analysis report according to a prediction result of the deep neural network.

Description

Technical Field

[0001] The present application relates to the field of automated detection technology, and more specifically, to an efficient control and intelligent evaluation method and system for electrochemical energy storage system detection tests. Background Art

[0002] In recent years, with the continuous advancement of battery technology and the reduction of costs, electrochemical energy storage systems have received widespread attention and application due to their efficient energy storage and release characteristics. However, the safety hazards faced by electrochemical energy storage systems in large-scale applications have gradually become prominent and have become an urgent problem to be solved. Most of the current test and detection systems only focus on independent tests for specific electrochemical energy storage systems, and lack a comprehensive intelligent management and control platform to support comprehensive detection and evaluation of the entire system.

[0003] In existing research, many test systems only focus on building a basic support platform, but lack the ability to integrate and coordinate various key components. This leads to a situation where the test data is scattered and difficult to compare and comprehensively analyze. Therefore, it is urgent to develop an intelligent control platform for electrochemical energy storage system test and detection.

[0004] Prior art, such as the Chinese patent with patent number "CN105785312A", discloses a method and system for automatic detection of smart meter functions. The method includes a test plan generation step, in which the control device generates a test plan according to the test requirements; a test function test step, in which the test device performs tests according to the test plan generated by the control device and performs synchronous tests on items that can be tested simultaneously; a data sorting step, in which the test device feeds back the test results to the control device, and the control device saves the data and generates a test report that is transmitted to the printing device for printing; the system includes a control device for generating test items, issuing human intervention reminders, and performing data processing, a test device for performing test function tests, and a printing device for printing test reports. Compared with the prior art, the present invention has the advantages of high integration, high test speed, and the ability to implement intensive control and centralized management.

[0005] The problem with the above-mentioned prior art is that this method generates a test plan based on specific test requirements. When faced with smart meters of different models, specifications or special requirements, it may lack sufficient flexibility to adjust the test plan and is difficult to adapt to the diverse smart meter detection requirements. Although synchronous testing of items that can be tested simultaneously increases the test speed, there may be interference problems between certain items. If there is mutual influence between the items tested synchronously, inaccurate test results may result. Summary of the invention

[0006] In order to solve the above technical problems, the present invention proposes an efficient control and intelligent evaluation method and system for electrochemical energy storage system detection and testing.

[0007] The technical solution of the present invention is as follows:

[0008] The present invention proposes an efficient control and intelligent evaluation method for electrochemical energy storage system detection test, comprising the following steps:

[0009] Step S1, constructing a MySQL database based on the SQLAlchemy module; the MySQL database is used to store equipment detection test items, detection test methods and detection test cycles of the electrochemical energy storage system; the storage electrochemical energy storage system includes: an energy storage inverter, an energy storage inverter co-control device, an energy storage battery, a battery management system, and an energy management system;

[0010] Step S2, scanning the RFID or QR code label on the device of the electrochemical energy storage system by a scanner, identifying the basic information of the device, and using the SQLAlchemy module to call the corresponding test items, test methods and test cycles from the MySQL database to construct the basic test content of the device;

[0011] Step S3, using a genetic algorithm to generate an optimal test task scheduling plan based on the basic test content of the equipment of the electrochemical energy storage system; using automated testing equipment to automatically collect and record the test results of the equipment of the electrochemical energy storage system;

[0012] Step S4, using a pre-trained deep neural network to intelligently analyze the test results, the analysis content includes: the service life of the energy storage battery, the identification of equipment failure types, and the optimization and adjustment of key parameters of the electrochemical energy storage system;

[0013] Step S5, constructing a performance evaluation index system for the electrochemical energy storage system, and generating a visual analysis report based on the prediction results of the deep neural network.

[0014] As a preferred implementation, the automated testing equipment automatically completes the corresponding test according to the test content, and has high-speed data transmission and processing capabilities.

[0015] As a preferred implementation, the method of using a genetic algorithm to generate an optimal detection test task scheduling scheme includes the following steps:

[0016] Encoding: Each trial task is represented as an integer, and the entire scheduling scheme is represented as a sequence of integers;

[0017] Initialize the population: randomly generate a certain number of initial scheduling schemes as the initial population of the genetic algorithm;

[0018] Fitness evaluation: For each scheduling scheme, calculate its fitness value; the fitness function is as follows:

[0019]

[0020] Where: T is the total completion time of the scheduling plan; C is the total cost of the scheduling plan;

[0021] Selection: According to the fitness value, select a part of excellent scheduling schemes from the current population as parents to generate the next generation population;

[0022] Crossover and mutation: Perform crossover operations on the selected parent scheduling scheme to generate new child scheduling schemes; perform mutation operations on the newly generated child scheduling schemes to increase the diversity of the population;

[0023] Repeat iteration: add the newly generated child scheduling scheme to the population to form a new generation of population;

[0024] Output result: When the number of iterations is reached or the fitness meets the requirement, the optimal solution of the scheduling plan is output.

[0025] As a preferred implementation, the method of using a pre-trained deep neural network to intelligently analyze the service life test results of the energy storage battery comprises the following steps:

[0026] The battery management system BMS is used to extensively collect data on the entire life cycle of electrochemical energy storage batteries; the data collected on the entire life cycle of electrochemical energy storage batteries is screened and cleaned to remove outliers and noise;

[0027] By using the pre-processed data of the entire life cycle of the electrochemical energy storage battery, the key features that affect the battery life are calculated, and the key features are normalized to form a feature matrix;

[0028] Construct a hybrid neural network consisting of a gated recurrent unit (GRU) and a long short-term memory (LSTM) network, which is used to predict the life of electrochemical energy storage batteries.

[0029] The feature matrix of the entire life cycle of the collected electrochemical energy storage battery is divided into a training set, a validation set and a test set to train and evaluate the life prediction model of the electrochemical energy storage battery; and a trained life prediction model of the electrochemical energy storage battery is obtained;

[0030] Use the trained electrochemical energy storage battery life prediction model to predict the battery life of new battery data.

[0031] As a preferred implementation, a hybrid neural network consisting of a gated recurrent unit GRU and a long short-term memory network LSTM is constructed, wherein the gated recurrent unit GRU is used to quickly capture local features of short-term battery performance changes; the long short-term memory network LSTM is used to analyze trends and cycles of long-term battery performance changes.

[0032] As a preferred embodiment, the performance evaluation index system of the electrochemical energy storage system is constructed, wherein the first-level index includes: performance index, reliability index, safety index and environmental adaptability index, and a number of second-level indexes are set under each first-level index.

[0033] As a preferred implementation, a visual analysis report is formed based on the prediction results of the deep neural network. The analysis report not only includes basic contents such as test items, test results, performance evaluation, etc., but also includes problem analysis and suggestions.

[0034] On the other hand, the present invention also provides an electrochemical energy storage system detection test efficient control and intelligent evaluation system, comprising:

[0035] A database construction module is used to construct a MySQL database based on the SQLAlchemy module; the MySQL database is used to store equipment detection test items, detection test methods and detection test cycles of the electrochemical energy storage system; the electrochemical energy storage system includes: an energy storage inverter, an energy storage inverter co-control device, an energy storage battery, a battery management system and an energy management system;

[0036] The test content generation module uses a scanner to scan the RFID or QR code tag on the device of the electrochemical energy storage system to identify the basic information of the device, and uses the SQLAlchemy module to call the corresponding test items, test methods and test cycles from the MySQL database to build the basic test content of the device;

[0037] The efficient control module uses genetic algorithms to generate the optimal test task scheduling plan based on the basic test content of the electrochemical energy storage system equipment; and uses automated testing equipment to automatically collect and record the test results of the electrochemical energy storage system equipment;

[0038] Intelligent analysis module, which uses pre-trained deep neural networks to intelligently analyze the test results, including the service life of the equipment's energy storage battery, equipment fault type identification, and optimization and adjustment of key parameters of the electrochemical energy storage system;

[0039] The result output module constructs a performance evaluation index system for the electrochemical energy storage system and generates a visual analysis report based on the prediction results of the deep neural network.

[0040] On the other hand, the present invention further provides an electronic device having a computer program stored thereon, wherein when the computer program is executed by a processor, an efficient control and intelligent evaluation method for an electrochemical energy storage system detection test as described in any embodiment of the present invention is implemented.

[0041] On the other hand, the present invention also 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 implement an efficient management and intelligent evaluation method for electrochemical energy storage system detection test as described in any embodiment of the present invention.

[0042] The present invention has the following beneficial effects:

[0043] 1. Improve test efficiency: Relying on advanced automatic testing technology, the test efficiency of each independent test and detection system is significantly improved through genetic algorithm optimization. Through unified data collection and processing procedures, the test process is standardized and automated, saving time and resources.

[0044] 2. Realize centralized data storage and intelligent analysis: It has the function of centralized storage and accumulation of test data, providing a strong foundation for subsequent data mining and intelligent analysis.

[0045] 3. Promote the organic integration and coordination of key components: We are committed to achieving the organic integration and coordination between the key components of the electrochemical energy storage system, seamlessly connecting the test and detection of each part, and realizing information sharing and communication. Through system-level experiments, we reveal the mutual influence and action mechanism between different components, achieve the comprehensive effect of "1+1>2", and provide all-round support for the research and development and application of electrochemical energy storage systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 The figure is a schematic diagram of the method flow of embodiment 1. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0050] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0051] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0052] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0053] Embodiment 1:

[0054] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following will be combined with the specific embodiments of the present application and refer to the attached Figure 1 , clearly and completely describe the technical solution of the present invention.

[0055] In order to solve the problems of the prior art, the present invention provides an efficient control and intelligent evaluation method for an electrochemical energy storage system detection test, comprising the following steps:

[0056] Step S1, constructing a MySQL database based on the SQLAlchemy module; the MySQL database is used to store equipment detection test items, detection test methods and detection test cycles of the electrochemical energy storage system;

[0057] MySQL is a relational database management system that stores data in different tables, increasing speed and flexibility. The use of the SQLAlchemy module can improve the ease of migration and calling of MySQL databases in the Python development environment.

[0058] The electrochemical energy storage system includes: energy storage inverter, energy storage inverter co-control equipment, energy storage battery, battery management system and energy management system.

[0059] Step S2: Scan the RFID or QR code tag on the device of the electrochemical energy storage system with a scanner to identify the basic information of the device, and use the SQLAlchemy module to call the corresponding test items, test methods and test cycles from the MySQL database to build the basic test content of the device;

[0060] Taking the PCS energy storage converter as an example, the RFID or QR code tag on the PCS is scanned by a scanner to obtain that the device to be tested is a PCS device, and the corresponding test items are called from the MySQL database as shown in the following table:

[0061]

[0062]

[0063] Step S3, using a genetic algorithm to generate an optimal test task scheduling plan based on the basic test content of the equipment of the electrochemical energy storage system; using automated testing equipment to automatically collect and record the test results of the equipment of the electrochemical energy storage system;

[0064] The automated test equipment automatically completes the corresponding test according to the test content, and has high-speed data transmission and processing capabilities. In this embodiment, for a combined test with multiple unit items, its overall logic can be expressed by the threshold conditional statements of each unit, such as:

[0065]

[0066] Among them, x represents the size of a physical quantity in a test item. If the physical quantity is less than or equal to a threshold value M, the test mark value f(x) is 1, indicating that the test has passed. If the physical quantity is greater than or equal to a threshold value M, it means that the test has not passed. If the physical quantity is less than a limit value u or greater than a limit value U, there may be an error in the test and it needs to be retested.

[0067] Depending on the type of test unit, there may be different test flag values ​​f i (x), there will also be different test physical quantities x, and the segmentation form may also change. For example, u and m can be defined as -INF at the same time, indicating that there is no lower limit, and U and M can be defined as I NF, indicating that there is no upper limit.

[0068] Generate the optimal test task scheduling scheme using genetic algorithm, including the following steps:

[0069] Encoding: Each trial task is represented as an integer, and the entire scheduling scheme is represented as a sequence of integers;

[0070] Initialize the population: randomly generate a certain number of initial scheduling schemes as the initial population of the genetic algorithm;

[0071] Fitness evaluation: For each scheduling scheme, calculate its fitness value; the fitness function is as follows:

[0072]

[0073] Where: T is the total completion time of the scheduling plan; C is the total cost of the scheduling plan;

[0074] Selection: According to the fitness value, select a part of excellent scheduling schemes from the current population as parents to generate the next generation population;

[0075] Crossover and mutation: Perform crossover operations on the selected parent scheduling scheme to generate new child scheduling schemes; perform mutation operations on the newly generated child scheduling schemes to increase the diversity of the population;

[0076] Repeat iteration: add the newly generated child scheduling scheme to the population to form a new generation of population;

[0077] Output result: When the number of iterations is reached or the fitness meets the requirement, the optimal solution of the scheduling plan is output.

[0078] The test results generated in this embodiment are recorded in the following table:

[0079]

[0080] Step S4, using a pre-trained deep neural network to intelligently analyze the test results, the analysis content includes: the service life of the energy storage battery, the identification of equipment failure types, and the optimization and adjustment of key parameters of the electrochemical energy storage system;

[0081] Use the pre-trained deep neural network to intelligently analyze the service life test results of the energy storage battery, including the following steps:

[0082] The battery management system BMS collects extensive data on the entire life cycle of electrochemical energy storage batteries, including: number of charge and discharge cycles, voltage data, current data, temperature data and timestamp; the data collected on the entire life cycle of electrochemical energy storage batteries are screened and cleaned to remove outliers and noise; the data are screened and cleaned to remove outliers and noise using the 3σ Laida criterion.

[0083] By using the pre-processed data of the entire life cycle of the electrochemical energy storage battery, the key features that affect the battery life are calculated, including: average charge and discharge voltage, voltage change rate, temperature change characteristics, charge and discharge rate, and cycle life; the key features are normalized to form a feature matrix;

[0084] The specific formula for normalization is as follows:

[0085]

[0086] Where: a is the original eigenvalue, a max 、a min are the maximum and minimum values ​​of the eigenvalue respectively.

[0087] The feature matrix expression is:

[0088]

[0089] Where: X i is the characteristic matrix of the i-th energy storage battery, are the normalized average charge and discharge voltage, voltage change rate, temperature change characteristics, charge and discharge rate, and cycle life of the i-th energy storage battery; i = 1, 2, 3, …, n, where n is the total number of energy storage battery samples.

[0090] Construct a hybrid neural network consisting of a gated recurrent unit (GRU) and a long short-term memory (LSTM) network, which is used to predict the life of electrochemical energy storage batteries.

[0091] The feature matrix of the entire life cycle of the collected electrochemical energy storage battery is divided into a training set, a validation set and a test set to train and evaluate the life prediction model of the electrochemical energy storage battery; and a trained life prediction model of the electrochemical energy storage battery is obtained;

[0092] In this embodiment, the loss function of the life prediction model of the electrochemical energy storage battery can be calculated by the following formula:

[0093]

[0094] In the formula, y i is the actual life of the i-th energy storage battery sample, Predict the life of the i-th energy storage battery sample.

[0095] In this embodiment, the trained model is evaluated using a test set, and the evaluation index is calculated using the root mean square error method. The specific formula is as follows:

[0096]

[0097] Use the trained electrochemical energy storage battery life prediction model to predict the battery life of new battery data.

[0098] In this embodiment, the gated recurrent unit GRU is used to quickly capture the local characteristics of short-term battery performance changes; the long short-term memory network LSTM is used to analyze the trend and cycle of long-term battery performance changes.

[0099] Among them, the long short-term memory network LSTM can learn the change patterns of voltage, current, temperature and other data under multiple different cycle times, as well as the cumulative impact of operating temperature on battery performance based on the data collected over the entire life cycle of electrochemical energy storage batteries. For example, over time, the charging and discharging efficiency of the battery may gradually decrease, and LSTM can remember this long-term change pattern and predict the degree of aging in the future.

[0100] The gated recurrent unit (GRU) can extract and analyze the characteristics of voltage, current, and operating temperature in a single charge and discharge cycle. If the battery has a sudden failure in a short period of time during the charge and discharge test, such as a short circuit or open circuit, the GRU can quickly extract these local abnormal characteristics. By analyzing sudden changes in data such as voltage, current, and temperature, the GRU can detect these failures in a timely manner. The GRU can analyze the impact of feature changes on the battery during a single charge and discharge cycle.

[0101] By combining these two neural networks, the impact of short-term features extracted by GRU on battery life is correlated with the long-term trend predicted by LSTM, which conforms to the actual working conditions and working characteristics of energy storage batteries and improves the accuracy of battery life prediction.

[0102] By referring to the automated inspection standards for PCS, batteries, BMS, and co-control equipment, as well as the test contents, intelligent analysis of the service life of energy storage batteries, identification of equipment fault types, and optimization and adjustment of key parameters of electrochemical energy storage systems can be realized. Equipment fault type identification can be determined through threshold conditional statements; intelligent analysis of optimization and adjustment of key parameters of electrochemical energy storage systems can use neural networks to analyze and optimize the test data during the electrochemical energy storage system inspection test.

[0103] The main reference standards for automated testing of PCS, batteries, BMS, and co-control equipment are shown in the table below.

[0104] Serial number Module Name Main reference standards 1 PCS Detection GB / T 34120-2023, GB / T 34133-2017 2 PCS Co-control Detection NB / T XXXX-YYYY 3 Energy storage battery testing GB / T 36276-2023 4 BMS Testing GB / T 34131-2023 5 EMS Testing GB / T 42726-2023

[0105] Step S5, constructing a performance evaluation index system for the electrochemical energy storage system, and generating a visual analysis report based on the prediction results of the deep neural network.

[0106] The performance evaluation index system of the constructed electrochemical energy storage system is as follows:

[0107]

[0108] Visual analysis report, which includes not only basic contents such as test items, test results, performance evaluation, but also problem analysis and suggestions.

[0109] Embodiment 2:

[0110] This embodiment provides an electrochemical energy storage system detection test efficient management and intelligent evaluation system, including:

[0111] A database construction module is used to construct a MySQL database based on the SQLAlchemy module; the MySQL database is used to store equipment detection test items, detection test methods and detection test cycles of the electrochemical energy storage system; the electrochemical energy storage system includes: an energy storage inverter, an energy storage inverter co-control device, an energy storage battery, a battery management system and an energy management system;

[0112] The test content generation module uses a scanner to scan the RFID or QR code tag on the device of the electrochemical energy storage system to identify the basic information of the device, and uses the SQLAlchemy module to call the corresponding test items, test methods and test cycles from the MySQL database to build the basic test content of the device;

[0113] The efficient control module uses genetic algorithms to generate the optimal test task scheduling plan based on the basic test content of the electrochemical energy storage system equipment; and uses automated testing equipment to automatically collect and record the test results of the electrochemical energy storage system equipment;

[0114] Intelligent analysis module, which uses pre-trained deep neural networks to intelligently analyze the test results, including the service life of the equipment's energy storage battery, equipment fault type identification, and optimization and adjustment of key parameters of the electrochemical energy storage system;

[0115] Embodiment three:

[0116] This embodiment provides an electronic device having a computer program stored thereon, and when the computer program is executed by a processor, an efficient control and intelligent evaluation method for an electrochemical energy storage system detection test as described in any embodiment of the present invention is implemented.

[0117] Embodiment 4:

[0118] This 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 implement an efficient management and control and intelligent evaluation method for electrochemical energy storage system detection test as described in any embodiment of the present invention.

[0119] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0120] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0122] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0123] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An efficient control and intelligent evaluation method for electrochemical energy storage system detection test, characterized in that: The following steps are involved: Step S1, building a MySQL database based on the SQLAlchemy module; The MySQL database is used to store equipment test items, test methods and test cycles of the electrochemical energy storage system; the electrochemical energy storage system includes: an energy storage inverter, an energy storage inverter co-control device, an energy storage battery, a battery management system and an energy management system; Step S2, scanning the RFID or QR code label on the device of the electrochemical energy storage system by a scanner, identifying the basic information of the device, and using the SQLAlchemy module to call the corresponding test items, test methods and test cycles from the MySQL database to construct the basic test content of the device; Step S3, using a genetic algorithm to generate an optimal test task scheduling plan based on the basic test content of the equipment of the electrochemical energy storage system; using automated testing equipment to automatically collect and record the test results of the equipment of the electrochemical energy storage system; Step S4, using a pre-trained deep neural network to intelligently analyze the test results, the analysis content includes: the service life of the energy storage battery, the identification of equipment failure types, and the optimization and adjustment of key parameters of the electrochemical energy storage system; Step S5, constructing a performance evaluation index system for the electrochemical energy storage system, and generating a visual analysis report based on the prediction results of the deep neural network.

2. According to claim 1, an efficient control and intelligent evaluation method for electrochemical energy storage system detection test is characterized by: The automated testing equipment automatically completes corresponding testing tests according to the testing test contents, and has high-speed data transmission and processing capabilities.

3. According to claim 1, a highly efficient control and intelligent evaluation method for electrochemical energy storage system detection test is characterized in that: The method of using a genetic algorithm to generate an optimal detection test task scheduling scheme includes the following steps: Encoding: Each trial task is represented as an integer, and the entire scheduling scheme is represented as a sequence of integers; Initialize the population: randomly generate a certain number of initial scheduling schemes as the initial population of the genetic algorithm; Fitness evaluation: For each scheduling scheme, calculate its fitness value; the fitness function is as follows: Where: T is the total completion time of the scheduling plan; C is the total cost of the scheduling plan; Selection: According to the fitness value, select a part of excellent scheduling schemes from the current population as parents to generate the next generation population; Crossover and mutation: Perform crossover operations on the selected parent scheduling scheme to generate new child scheduling schemes; perform mutation operations on the newly generated child scheduling schemes to increase the diversity of the population; Repeat iteration: add the newly generated child scheduling scheme to the population to form a new generation of population; Output result: When the number of iterations is reached or the fitness meets the requirement, the optimal solution of the scheduling plan is output.

4. According to claim 1, a highly efficient control and intelligent evaluation method for electrochemical energy storage system detection test is characterized in that: The method of using a pre-trained deep neural network to intelligently analyze the service life test results of the energy storage battery comprises the following steps: The battery management system BMS is used to extensively collect data on the entire life cycle of electrochemical energy storage batteries; the data collected on the entire life cycle of electrochemical energy storage batteries is screened and cleaned to remove outliers and noise; By using the pre-processed data of the entire life cycle of the electrochemical energy storage battery, the key features that affect the battery life are calculated, and the key features are normalized to form a feature matrix; Construct a hybrid neural network consisting of a gated recurrent unit (GRU) and a long short-term memory (LSTM) network, which is used to predict the life of electrochemical energy storage batteries. The characteristic matrix of the entire life cycle of the collected electrochemical energy storage battery is divided into a training set, a validation set and a test set to train and evaluate the life prediction model of the electrochemical energy storage battery; and a trained life prediction model of the electrochemical energy storage battery is obtained; Use the trained electrochemical energy storage battery life prediction model to predict the battery life of new battery data.

5. According to claim 4, a highly efficient control and intelligent evaluation method for electrochemical energy storage system detection test is characterized in that: The hybrid neural network is constructed by a gated recurrent unit GRU and a long short-term memory network LSTM, wherein the gated recurrent unit GRU is used to quickly capture the local characteristics of short-term battery performance changes; the long short-term memory network LSTM is used to analyze the trend and cycle of long-term battery performance changes.

6. The method for efficient control and intelligent evaluation of electrochemical energy storage system detection test according to claim 1, characterized in that: The performance evaluation index system of the electrochemical energy storage system is constructed, wherein the first-level index includes: performance index, reliability index, safety index and environmental adaptability index, and a number of second-level indexes are set under each first-level index.

7. The electrochemical energy storage system detection test efficient management and intelligent evaluation system according to claim 1, characterized in that: The above-mentioned visual analysis report is formed based on the prediction results of the deep neural network. The analysis report not only includes basic contents such as test items, test results, performance evaluation, etc., but also includes problem analysis and suggestions.

8. An efficient control and intelligent evaluation system for electrochemical energy storage system detection test, characterized in that: include: Database construction module, building MySQL database based on SQLAlchemy module; The MySQL database is used to store equipment detection test items, detection test methods and detection test cycles of the electrochemical energy storage system; The electrochemical energy storage system includes: an energy storage converter, an energy storage converter co-control device, an energy storage battery, a battery management system, and an energy management system; The test content generation module uses a scanner to scan the RFID or QR code tag on the device of the electrochemical energy storage system to identify the basic information of the device, and uses the SQLAlchemy module to call the corresponding test items, test methods and test cycles from the MySQL database to build the basic test content of the device; The efficient control module uses genetic algorithms to generate the optimal test task scheduling plan based on the basic test content of the electrochemical energy storage system equipment; and uses automated testing equipment to automatically collect and record the test results of the electrochemical energy storage system equipment; Intelligent analysis module, which uses pre-trained deep neural networks to intelligently analyze the test results, including the service life of the equipment's energy storage battery, equipment fault type identification, and optimization and adjustment of key parameters of the electrochemical energy storage system; The result output module constructs a performance evaluation index system for the electrochemical energy storage system and generates a visual analysis report based on the prediction results of the deep neural network.

9. An electronic 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, an efficient control and intelligent evaluation method for electrochemical energy storage system detection test is implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, an efficient control and intelligent evaluation method for electrochemical energy storage system detection test is implemented as described in any one of claims 1 to 7.

Images