Energy Efficiency Testing Method, Device, Equipment and Storage Medium of Battery

Abstract

The present invention relates to the technical field of data processing, and discloses a method, device, equipment and storage medium for testing the energy efficiency of a battery. The method for testing the energy efficiency of the battery includes: receiving a battery energy efficiency test request sent by a terminal device, determining a target battery to be tested according to the battery energy efficiency test request, and performing a battery energy efficiency test on the target battery according to preset current parameters; collecting the current state, voltage state and temperature state of the target battery during the battery energy efficiency test according to the set test time range; respectively analyzing the current state, voltage state and temperature state of the target battery during the battery energy efficiency test based on a preset battery state analysis algorithm to obtain corresponding battery current data, battery voltage data and battery temperature data. The present invention can timely discover and handle battery energy efficiency problems and reduce the energy consumption of equipment by performing abnormal analysis of the energy efficiency loss index through a battery energy efficiency analysis model.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method, device, equipment and storage medium for testing the energy efficiency of a battery. Background Art

[0002] With the wide application of electronic devices, the performance of batteries has gradually become the focus of attention, and the energy efficiency of batteries is an important indicator for measuring battery performance. The energy efficiency test of batteries mainly includes the measurement of the energy input and output of batteries, as well as the calculation of energy efficiency differences.

[0003] Current battery energy efficiency test technologies often only focus on a single parameter, such as the current state or voltage state of the battery, and cannot comprehensively evaluate the energy efficiency of the battery. In addition, the currently common battery energy efficiency analysis models usually simply compare the energy efficiency of the battery in different states, and cannot perform in-depth data association and mining. On the other hand, such models cannot automatically analyze the anomalies of power efficiency, cannot adjust and optimize the working state of the battery in real time, and cannot maximize the energy efficiency of the battery.

[0004] Therefore, there is an urgent need for an automated method that can effectively monitor and evaluate the energy efficiency of batteries to solve the above problems. Summary of the Invention

[0005] The present invention provides a method, device, equipment and storage medium for testing the energy efficiency of a battery, which is used to solve the technical problem of how to effectively monitor and evaluate the energy efficiency of a battery.

[0006] In a first aspect of the present invention, a method for testing the energy efficiency of a battery is provided. The method for testing the energy efficiency of the battery includes:

[0007] Receiving a battery energy efficiency test request sent by a terminal device, determining a target battery to be tested according to the battery energy efficiency test request, and performing a battery energy efficiency test on the target battery according to a preset current parameter;

[0008] Collecting the current state, voltage state and temperature state of the target battery during the battery energy efficiency test according to a set test time range;

[0009] Analyzing the current state, voltage state and temperature state of the target battery during the battery energy efficiency test respectively based on a preset battery state analysis algorithm to obtain corresponding battery current data, battery voltage data and battery temperature data;

[0010] Calculating the energy input of the target battery according to the battery current data and the preset current parameter, and calculating the energy output of the target battery according to a preset energy efficiency calculation formula and the battery voltage data;

[0011] Calculate the energy efficiency difference between the energy input and the energy output; wherein, the energy efficiency difference is the energy efficiency loss index of the target battery in the working state;

[0012] Based on the timestamps within the set test time range, perform data association on the energy efficiency loss index and the battery temperature data to obtain an associated data set; wherein, the association rules for the energy efficiency loss index and the battery temperature data are stored in advance in the database;

[0013] Generate a corresponding target input vector based on the associated data set, input the target input vector into the trained battery energy efficiency analysis model, perform anomaly analysis on the energy efficiency loss index, and obtain the diagnostic result of the target battery energy efficiency.

[0014] Optionally, in the first implementation manner of the first aspect of the present invention, the training process of the battery energy efficiency analysis model includes:

[0015] Obtain battery energy efficiency test data, the battery energy efficiency test data includes corresponding identification information, perform feature analysis on the battery energy efficiency test data to obtain a first feature vector;

[0016] Input the first feature vector into a preset feature analysis model for feature extraction to obtain a second feature vector;

[0017] Input the obtained second feature vector into a preset gated recurrent unit model, and process the second feature vector through the hidden state in the preset gated recurrent unit model to obtain a third feature vector;

[0018] Input the third feature vector into a preset long short-term memory neuron model, and perform historical dependence analysis processing on the third feature vector through the preset long short-term memory neuron model to generate a fourth feature vector;

[0019] Generate a random and non-repeating fifth feature vector that is generated only once within a preset period, and perform feature fusion on the fourth feature vector and the fifth feature vector to obtain a sixth feature vector; wherein, the generation rule of the fifth feature vector and the fusion rule of the fifth feature vector and the fourth feature vector are stored in advance in the database;

[0020] Input the second feature vector, the fourth feature vector, the sixth feature vector, and the corresponding identification information into a classifier for model training, and iteratively optimize the model parameters of the preset feature analysis model, the gated recurrent unit model, and the long short-term memory neuron model during the training process until the loss function of the model reaches the expected convergence degree, and then complete the training of the battery energy efficiency analysis model.

[0021] Optionally, in the second implementation manner of the first aspect of the present invention, after the step of obtaining the diagnostic result of the target battery energy efficiency, it includes:

[0022] Set a string with a specified length as the initial analysis code;

[0023] In a distributed system including many data processing units and processing nodes, set recognizable data processing center labels and node ID labels, and generate a location identification code based on the data processing center labels and node ID labels;

[0024] Obtain the year and month in the timestamp information, and based on the year and month, obtain the corresponding target coding map; wherein, the target coding map is obtained by re - coding the standard coding map based on the year and month;

[0025] Decode the millisecond - level timestamp in each timestamp information based on the target coding map to obtain the time identification code corresponding to each millisecond - level timestamp;

[0026] Initialize an accumulator for generating different node identification codes for each battery health assessment result within a single - millisecond time frame;

[0027] Each time a node identification code is generated, compare whether the current time is the same as the time when the previous node identification code was generated. If they are the same, the accumulator increases by one counting unit. If a new millisecond is entered, reset the accumulator and re - count within the new millisecond time frame to obtain the current count value of the accumulator;

[0028] Combine the initial analysis code, time identification code, location identification code, node identification code, and the current count value of the accumulator according to a predetermined order to generate a unique identification code for the battery health assessment result;

[0029] Encrypt the diagnostic result of the target battery energy efficiency based on the unique identification code of the battery health assessment result.

[0030] Optionally, in the third implementation manner of the first aspect of the present invention, the step of obtaining the year and month in the timestamp information and obtaining the corresponding target coding map based on the year and month includes:

[0031] By setting the mapping relationship between the year and the standard coding map, find the standard coding map corresponding to a specific year in the database; wherein, the standard coding map includes two parts, one part is the serial number digit, and the other part is the character corresponding to the serial number digit;

[0032] Obtain the digital combination corresponding to the year and month in the timestamp information, divide the year number by the month number, and only take the tenths digit of the decimal part of the obtained digital result as the specific serial number digit. Take all the digits corresponding to the specific serial number digit in the serial number digits as the first digit set, and find the coding symbol corresponding to the first digit set as the first symbol. Delete all symbols other than the first symbol from the coding symbol as the second symbol; wherein, the digits corresponding to the year and month in the timestamp information include at least ten digital combinations of the year and month, and the digital combinations are all integers;

[0033] According to the preset arrangement order, reassign the second symbol to the second digit set; wherein, the order of the second symbol conforms to the order in the standard coding diagram;

[0034] After all the second symbols have been reassigned the corresponding second digit sets, assign serial number digits to the first symbol in sequence;

[0035] Integrate the second symbol, the first symbol, and the corresponding serial number digits after the serial number digits have been reassigned to obtain the target coding diagram.

[0036] Optionally, in the fourth implementation manner of the first aspect of the present invention, the position identification code is used to identify the specific node for processing the battery energy efficiency test task. The position identification code is generated by the data processing center annotation and the node ID annotation, providing a unique identifier for each node for processing the battery energy efficiency test task;

[0037] The current count value of the accumulator is used to ensure that each node state analysis result of the battery energy efficiency test task within the same millisecond has a unique identification code; when entering a new millisecond, the accumulator is reset to zero and starts a new round of counting to adapt to the node state analysis results of the battery energy efficiency test tasks generated within the new millisecond.

[0038] The second aspect of the present invention provides a battery energy efficiency test device, and the battery energy efficiency test device includes:

[0039] A test module, configured to receive a battery energy efficiency test request sent by a terminal device, determine a target battery to be tested according to the battery energy efficiency test request, and perform a battery energy efficiency test on the target battery according to preset current parameters;

[0040] A collection module, configured to collect the current state, voltage state, and temperature state of the target battery during the battery energy efficiency test according to the set test time range;

[0041] An analysis module for analyzing the current state, voltage state, and temperature state of a target battery during a battery energy efficiency test based on a preset battery state analysis algorithm to obtain corresponding battery power data, battery voltage data, and battery temperature data;

[0042] A first calculation model for calculating the energy input of the target battery according to the battery current data and preset current parameters, and calculating the energy output of the target battery according to a preset energy efficiency calculation formula and the battery voltage data;

[0043] A second calculation module for calculating the energy efficiency difference between the energy input and the energy output; wherein, the energy efficiency difference is the energy efficiency loss index of the target battery in the working state;

[0044] An association module for associating the energy efficiency loss index and the battery temperature data based on the time stamps within a set test time range to obtain an associated data set; wherein, the association rules for the energy efficiency loss index and the battery temperature data are stored in advance in the database;

[0045] An analysis module for generating a corresponding target input vector based on the associated data set, inputting the target input vector into a trained battery energy efficiency analysis model for abnormal analysis of the energy efficiency loss index, and obtaining a diagnostic result of the target battery energy efficiency.

[0046] A third aspect of the present invention provides a battery energy efficiency test device, including: a memory and at least one processor, wherein instructions are stored in the memory; the at least one processor calls the instructions in the memory to enable the battery energy efficiency test device to execute the above battery energy efficiency test method.

[0047] A fourth aspect of the present invention provides a computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium, and when it runs on a computer, it enables the computer to execute the above battery energy efficiency test method.

[0048] In the technical solution provided by the present invention, the beneficial effects are as follows: The present invention receives a battery energy efficiency test request sent by a terminal device, determines a target battery to be tested according to the battery energy efficiency test request, and performs a battery energy efficiency test on the target battery according to preset current parameters; according to a set test time range, collects the current state, voltage state, and temperature state of the target battery during the battery energy efficiency test; based on a preset battery state analysis algorithm, analyzes the current state, voltage state, and temperature state of the target battery during the battery energy efficiency test respectively to obtain corresponding battery current data, battery voltage data, and battery temperature data; calculates the energy input of the target battery according to the battery current data and the preset current parameters, and calculates the energy output of the target battery according to a preset energy efficiency calculation formula and the battery voltage data; calculates the energy efficiency difference between the energy input and the energy output; performs data association on the energy efficiency loss index and the battery temperature data based on the time stamps within the set test time range to obtain an associated data set; generates a corresponding target input vector based on the associated data set, inputs the target input vector into a trained battery energy efficiency analysis model to perform abnormal analysis of the energy efficiency loss index, and obtains a diagnostic result of the target battery energy efficiency. By collecting and analyzing the current state, voltage state, and temperature state of the target battery during the energy efficiency test, the present invention can comprehensively understand the working performance and state of the battery, which is beneficial to implementing more accurate battery energy efficiency evaluation. By performing data association analysis on the energy efficiency loss index and the battery temperature data, it can provide in-depth insight and understanding of the battery energy efficiency loss, help optimize the use and management of the battery, and extend the service life of the battery. By performing abnormal analysis of the energy efficiency loss index through a trained battery energy efficiency analysis model, it can timely discover and handle battery energy efficiency problems and reduce the energy consumption of the device. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 FIG. is a schematic diagram of an embodiment of a battery energy efficiency test method in an embodiment of the present invention;

[0050] Figure 2 FIG. is a schematic diagram of an embodiment of a battery energy efficiency test device in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] An embodiment of the present invention provides a method, device, equipment, and storage medium for testing the energy efficiency of a battery. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims, and above-mentioned drawings of the present invention are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or equipment that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to the process, method, product, or equipment.

[0052] For ease of understanding, the specific process of the embodiment of the present invention is described below. Please refer to Figure 1 An embodiment of the energy efficiency testing method for the battery in the embodiment of the present invention includes:

[0053] Step 101: Receive a battery energy efficiency test request sent by a terminal device, determine a target battery to be tested according to the battery energy efficiency test request, and perform a battery energy efficiency test on the target battery according to preset current parameters;

[0054] It can be understood that the execution subject of the present invention can be a battery energy efficiency testing device, or a terminal or a server. Specifically, it is not limited here. The embodiment of the present invention takes the server as the execution subject for illustration.

[0055] Specifically, the implementation steps for receiving a battery energy efficiency test request through a terminal device:

[0056] Design and implement a communication interface between the terminal device and the battery energy efficiency testing system to ensure that the interface can receive and parse requests from the terminal device;

[0057] Create an energy efficiency test request interface on the terminal device to provide users with an interface to input test request parameters on the terminal device;

[0058] The terminal device sends the energy efficiency test request parameters input by the user to the battery energy efficiency testing system through the communication interface.

[0059] The implementation steps for determining the target battery to be tested according to the battery energy efficiency test request:

[0060] After receiving the energy efficiency test request through the communication interface, parse the information included in the request, including battery type, battery parameters, etc.;

[0061] Query and determine the target battery that meets the requirements in the battery energy efficiency test database according to the battery type and parameter information;

[0062] Create a test task in the battery energy efficiency test system and associate the determined target battery with the task.

[0063] Implementation steps for conducting battery energy efficiency tests on the target battery according to the preset current parameters:

[0064] Set the current parameters in the battery energy efficiency test system, including the current magnitude, current duration, etc.;

[0065] Associate the set current parameters with the previously created test task to ensure that the test task can be performed according to the preset current parameters;

[0066] Start the test task in the battery energy efficiency test system, and the system conducts battery energy efficiency tests on the target battery according to the preset current parameters;

[0067] The test system monitors the performance of the target battery during the test in real time and records the test results, including the battery usage time, battery discharge efficiency, etc.

[0068] Step 102: Collect the current state, voltage state, and temperature state of the target battery during the battery energy efficiency test according to the set test time range;

[0069] Specifically, the implementation steps for collecting the current state, voltage state, and temperature state of the target battery according to the set test time range:

[0070] In the battery energy efficiency test system, set the test time range and specify the start time and end time of the test;

[0071] Add current, voltage, and temperature sensors to the test task and connect them to the target battery;

[0072] After the test task starts, the current, voltage, and temperature sensors collect the relevant state data of the battery in real time;

[0073] Save the collected current, voltage, and temperature data to the battery energy efficiency test database;

[0074] After the test task ends, stop data collection.

[0075] Step 103: Analyze the current state, voltage state, and temperature state of the target battery during the battery energy efficiency test respectively based on the preset battery state analysis algorithm to obtain the corresponding battery current data, battery voltage data, and battery temperature data;

[0076] Specifically, the implementation steps for analyzing the current state, voltage state, and temperature state of the target battery based on a preset battery state analysis algorithm are as follows:

[0077] Establish a battery state analysis algorithm module in the battery energy efficiency test system to process current, voltage, and temperature data;

[0078] Set the preset battery state analysis algorithm, including the current state analysis algorithm, voltage state analysis algorithm, and temperature state analysis algorithm;

[0079] Transfer the collected current, voltage, and temperature data to the battery state analysis algorithm module;

[0080] The battery state analysis algorithm module analyzes the input current, voltage, and temperature data according to the preset algorithm and obtains the corresponding battery current data, battery voltage data, and battery temperature data;

[0081] Save the analyzed data to the battery energy efficiency test database.

[0082] Step 104: Calculate the energy input of the target battery based on the battery current data and the preset current parameters, and calculate the energy output of the target battery according to the preset energy efficiency calculation formula and the battery voltage data;

[0083] Specifically, the implementation steps for calculating the energy input of the target battery based on the battery current data and the preset current parameters are as follows:

[0084] Obtain the collected battery current data, including the current value and sampling time;

[0085] In the battery energy efficiency test system, perform integral calculation on the current data according to the time interval set by the preset current parameters to obtain the energy input within the test time range;

[0086] Save the calculated energy input to the battery energy efficiency test database.

[0087] The implementation steps for calculating the energy output of the target battery according to the preset energy efficiency calculation formula and the battery voltage data are as follows:

[0088] Obtain the collected battery voltage data, including the voltage value and sampling time;

[0089] In the battery energy efficiency test system, calculate the energy output according to the preset energy efficiency calculation formula, combined with the battery voltage data and the corresponding timestamp;

[0090] Save the calculated energy output to the battery energy efficiency test database.

[0091] Energy input: It refers to the total amount of energy received by the target battery during the battery energy efficiency test. By integrating the battery current data, the energy input can be obtained.

[0092] Energy output: It refers to the total amount of energy output by the target battery during the battery energy efficiency test. According to the preset energy efficiency calculation formula, combined with the battery voltage data and time stamps, the energy output can be calculated.

[0093] Step 105: Calculate the energy efficiency difference between the energy input and the energy output; wherein, the energy efficiency difference is the energy efficiency loss index of the target battery in the working state.

[0094] Specifically, the implementation steps for calculating the energy efficiency difference between the energy input and the energy output and obtaining the energy efficiency loss index of the target battery are as follows:

[0095] Obtain the calculated energy input and energy output from the battery energy efficiency test database.

[0096] According to the values of the energy input and the energy output, calculate the energy efficiency difference, that is, the ratio between the energy input and the energy output.

[0097] Express the energy efficiency difference as the energy efficiency loss index, which represents the degree of energy efficiency loss of the target battery in the working state.

[0098] Step 106: Based on the time stamps within the set test time range, perform data association on the energy efficiency loss index and the battery temperature data to obtain an associated data set; wherein, the association rule between the energy efficiency loss index and the battery temperature data is stored in the database in advance.

[0099] Specifically, the implementation steps for performing data association on the energy efficiency loss index and the battery temperature data based on the time stamps within the set test time range to obtain an associated data set are as follows:

[0100] Obtain the stored energy efficiency loss index data and battery temperature data from the battery energy efficiency test database.

[0101] According to the time stamps within the set test time range, filter out the energy efficiency loss index data and battery temperature data that meet the conditions.

[0102] Associate the energy efficiency loss index data and the battery temperature data to form an associated data set.

[0103] Step 107: Generate a corresponding target input vector based on the associated data set, input the target input vector into the trained battery energy efficiency analysis model, perform abnormal analysis of the energy efficiency loss index, and obtain the diagnostic result of the target battery energy efficiency.

[0104] Specifically, the implementation steps for generating a corresponding target input vector based on the associated dataset, inputting the target input vector into the trained battery energy efficiency analysis model, and performing anomaly analysis on the energy efficiency loss index to obtain the diagnostic result of the target battery energy efficiency are as follows:

[0105] Generate a corresponding target input vector by using relevant data such as the energy efficiency loss index and battery temperature in the associated dataset;

[0106] Input the generated target input vector into the trained battery energy efficiency analysis model;

[0107] Analyze the target input vector through the battery energy efficiency analysis model to parse the anomaly of the energy efficiency loss index;

[0108] Obtain the diagnostic result of the target battery energy efficiency and determine whether there is an anomaly in the energy efficiency loss.

[0109] Anomaly analysis of the energy efficiency loss index: Analyze and parse the energy efficiency loss index in the target input vector through the battery energy efficiency analysis model to determine whether there is an anomaly. The anomaly analysis can be judged by comparing the energy efficiency loss index of the target battery with a preset threshold or historical data.

[0110] Diagnostic result: The result obtained by analyzing the target battery energy efficiency through the battery energy efficiency analysis model, which is used to indicate whether there is an anomaly in the energy efficiency loss of the target battery. The diagnostic result can be a binary (normal, abnormal) or quantitative (energy efficiency loss percentage) evaluation.

[0111] Another embodiment of the battery energy efficiency test method in the embodiments of the present invention includes: The training process of the battery energy efficiency analysis model includes:

[0112] Obtain battery energy efficiency test data, where the battery energy efficiency test data includes corresponding identification information, perform feature parsing on the battery energy efficiency test data to obtain a first feature vector;

[0113] Input the first feature vector into a preset feature parsing model for feature extraction to obtain a second feature vector;

[0114] Input the obtained second feature vector into a preset gated recurrent unit model, and process the second feature vector through the hidden state in the preset gated recurrent unit model to obtain a third feature vector;

[0115] Input the third feature vector into a preset long short-term memory neuron model, and perform historical dependence analysis processing on the third feature vector through the preset long short-term memory neuron model to generate a fourth feature vector;

[0116] A random and non-repeating fifth feature vector that is generated only once within a preset period, and the fourth feature vector and the fifth feature vector are feature-fused to obtain a sixth feature vector; wherein, the generation rule of the fifth feature vector and the fusion rule of the fifth feature vector and the fourth feature vector are stored in advance in a database.

[0117] The second feature vector, the fourth feature vector, and the sixth feature vector, as well as the corresponding identification information, are input into a classifier for model training, and during the training process, the model parameters of a preset feature parsing model, a gated recurrent unit model, and a long short-term memory neuron model are iteratively optimized until the loss function of the model reaches the expected convergence degree, and then the training of the battery energy efficiency analysis model is completed.

[0118] Specifically, supplementary terms and professional names are as follows:

[0119] Battery energy efficiency test data: A data set used to test the energy efficiency of a battery, which contains various indicators and attributes regarding battery energy efficiency, such as voltage, current, charging efficiency, etc.

[0120] Feature parsing model: A model used to extract useful features from raw battery energy efficiency test data, usually based on feature engineering and statistical analysis methods, such as principal component analysis, wavelet transform, etc.

[0121] Gated recurrent unit model: A recurrent neural network model used to process sequential data, where a gating mechanism determines the hidden state at the current time step and whether to pass the hidden state from the previous time step to the current time step.

[0122] Long short-term memory neuron model: A recurrent neural network model specifically used to process sequential data with long-term dependencies. It controls the transmission and forgetting of information through a gating mechanism to capture long-term dependencies in the sequence.

[0123] In the embodiments of the present invention, the beneficial effects are as follows: In the embodiments of the present invention, through a preset feature parsing model, a gated recurrent unit model, and a long short-term memory neuron model, feature extraction, historical dependency analysis, and fusion are performed on battery energy efficiency test data to achieve a comprehensive analysis and diagnosis of battery energy efficiency. By iteratively optimizing the model parameters, the accuracy and robustness of the model are improved. Classifiers such as support vector machines and random forests are introduced to further enhance the accuracy and reliability of battery energy efficiency analysis.

[0124] Another embodiment of the battery energy efficiency test method in the embodiments of the present invention includes: After the step of obtaining the diagnostic result of the target battery energy efficiency, it includes:

[0125] Set a string with a specified length as the initial analysis code;

[0126] In a distributed system that includes numerous data processing units and processing nodes, set recognizable data processing center labels and node ID labels, and generate a location identification code based on the data processing center labels and node ID labels;

[0127] Obtain the year and month in the timestamp information, and based on the year and month, obtain the corresponding target coding map; wherein, the target coding map is obtained by re-coding the standard coding map based on the year and month;

[0128] Decode the millisecond-level timestamp in each timestamp information based on the target coding map to obtain the time identification code corresponding to each millisecond-level timestamp;

[0129] Initialize an accumulator to generate different node identification codes for each battery health assessment result within a single millisecond time frame;

[0130] Each time a node identification code is generated, compare whether the current time is the same as the time when the previous node identification code was generated. If they are the same, the accumulator increases by one counting unit. If a new millisecond is entered, reset the accumulator and re-count within the new millisecond time frame to obtain the current count value of the accumulator;

[0131] Combine the initial analysis code, time identification code, location identification code, node identification code, and the current count value of the accumulator in a predetermined order to generate a unique identification code for the battery health assessment result;

[0132] Encrypt the diagnostic result of the target battery energy efficiency based on the unique identification code of the battery health assessment result.

[0133] Specifically, in order to obtain the diagnostic result of the target battery energy efficiency, the following is a specific implementation method:

[0134] Set a character string with a specified length as the initial analysis code.

[0135] On each data processing unit and processing node in the distributed system, set recognizable data processing center labels and node ID labels, and generate a location identification code based on them. For example, a unique identifier can be assigned to each unit and node, encoded in binary form, and the encoding result can be used as the location identification code.

[0136] Extract the year and month from the timestamp information, and obtain the corresponding target coding map based on them. The target coding map is obtained by re-coding the standard coding map based on the year and month, and can be converted using coding rules and mapping tables.

[0137] Decode the millisecond-level timestamps in each timestamp information to obtain the time identification codes corresponding to each millisecond-level timestamp. A timestamp parsing algorithm can be used to parse the millisecond-level timestamps and convert them into recognizable time identification codes.

[0138] Initialize an accumulator to generate different node identification codes for the health assessment results of each battery within a single millisecond time frame. The node identification codes can be generated by combining a unique node identifier and a cumulative value.

[0139] Each time a node identification code is generated, compare whether the currently generated time is the same as the time generated last time. If they are the same, increment the accumulator by one counting unit. If a new millisecond time frame is entered, reset the accumulator and start counting again to obtain the current count value of the accumulator.

[0140] According to a predetermined order, combine the initial analysis code, time identification code, location identification code, node identification code, and the current count value of the accumulator to generate a unique identification code for the battery health assessment result. Techniques such as bitwise operations, coding rules, and mapping tables can be used for combination generation.

[0141] Based on the unique identification code of the battery health assessment result, encrypt the diagnostic result of the target battery energy efficiency. Encryption algorithms (such as AES, RSA, etc.) can be used for encryption to ensure the security and confidentiality of the assessment result.

[0142] Another embodiment of the battery energy efficiency test method in the embodiments of the present invention includes: obtaining the year and month in the timestamp information, and based on the year and month, obtaining the corresponding target coding map, including:

[0143] By setting the mapping relationship between the year and the standard coding map, find the standard coding map corresponding to a specific year in the database; wherein, the standard coding map includes two parts, one part is the serial number digit, and the other part is the character corresponding to the serial number digit;

[0144] Obtain the digital combination corresponding to the year and month in the timestamp information, divide the year digit by the month digit, and only take the tenth digit of the decimal part of the obtained digital result as the specific serial number digit. Take all the digits corresponding to the specific serial number digit in the serial number digit as the first digit set, and find the coding symbols corresponding to the first digit set as the first symbol. Delete all symbols other than the first symbol from the coding symbols as the second symbol; wherein, the digits corresponding to the year and month in the timestamp information include at least ten digital combinations corresponding to the year and month, and the digital combinations are all integers;

[0145] Reassign the second symbols to a second set of numbers according to a preset arrangement order; wherein, the order of the second symbols conforms to the order in the standard coding diagram;

[0146] After all the second symbols have been reassigned their corresponding second sets of numbers, sequentially assign serial numbers to the first symbols;

[0147] Integrate the second symbols, the first symbols, and their corresponding serial numbers after the serial numbers have been reassigned to obtain the target coding diagram.

[0148] Specifically, when specifically implementing to obtain the year and month in the timestamp information and obtaining the corresponding target coding diagram based on the year and month, the following steps can be taken:

[0149] First, according to the mapping relationship between the set year and the standard coding diagram, find the standard coding diagram corresponding to a specific year in the database. This can be achieved by establishing a database that contains the standard coding diagrams and their mapping relationships with years, and then querying the database according to the input year to obtain the corresponding standard coding diagram.

[0150] In the standard coding diagram, it includes two parts: serial numbers and the characters corresponding to the serial numbers. The serial numbers start from 1 and gradually increase, and the characters can be different symbols or letters.

[0151] Obtain the digital combination corresponding to the year and month in the timestamp information. Assume that the range of year numbers is from 2000 to 2029, and the range of month numbers is from 1 to 12. The year number and month number can be combined into a four-digit number. For example, 202209 represents September 2022.

[0152] Divide the year number by the month number (i.e., integer division) to obtain a result. For example, divide 202209 by 100 to get 2022.

[0153] Only take the tenths digit of the decimal part of the result as the specific serial number. In this example, the result is 0.22, and taking the tenths digit gives 2 as the specific serial number.

[0154] Find all the numbers in the standard coding diagram corresponding to the specific serial number as the first set of numbers. For example, if the specific serial number is 2, the first set of numbers is all the characters in the standard coding diagram corresponding to the number 2.

[0155] Find the coding symbol corresponding to the first set of numbers as the first symbol. This can be achieved by establishing a mapping relationship between the symbols and the sets of numbers.

[0156] Delete all symbols in the coding symbol except the first symbol to obtain the second symbol. This can be achieved by simple string operations.

[0157] Reassign the second symbols to the second set of numbers according to a preset arrangement order. For example, if the first set of numbers is {A, B, C} and the second symbols are {X, Y, Z}, then the second set of numbers obtained by sequential assignment is {X, Y, Z}.

[0158] Sequentially assign serial numbers to the first symbols. Determine the range of the serial numbers according to the number of the first symbols. For example, if there are three first symbols, then assign the serial numbers as {1, 2, 3}.

[0159] Integrate the second symbols with reassigned serial numbers, the first symbols, and the corresponding serial numbers to obtain the target coding diagram. This can be achieved by establishing a mapping table, combining the second symbols, the first symbols, and the serial numbers, and then generating the target coding diagram according to a specific arrangement order.

[0160] In the embodiment of the present invention, the beneficial effects are as follows: By establishing a database and mapping the standard coding diagram with the year, the corresponding standard coding diagram can be flexibly obtained according to the year without hard coding. And process the result calculated by combining the year and the month, and only take the tenth digit of the decimal part as a specific serial number to ensure that a unique serial number can be obtained for each combination of year and month. Obtain the first symbols according to the first set of numbers and the coding symbols, and determine the range of the serial numbers according to the number of the first symbols. Then, reassign the second symbols to the second set of numbers according to a specific arrangement order. Finally, establish a mapping table, combine the second symbols, the first symbols, and the serial numbers, and generate the target coding diagram according to the preset arrangement order. This can ensure that each combination has a unique target coding diagram and conforms to the preset arrangement order.

[0161] Another embodiment of the battery energy efficiency test method in the embodiment of the present invention includes: The position identification code is used to identify the specific node for processing the battery energy efficiency test task. The position identification code is generated by the data processing center annotation and the node ID annotation, providing a unique identifier for each node processing the battery energy efficiency test task;

[0162] The current count value of the accumulator is used to ensure that each node status analysis result of the battery energy efficiency test task within the same millisecond has a unique identification code; when entering a new millisecond, the accumulator is reset to zero and starts a new round of counting to adapt to the node status analysis results of the battery energy efficiency test tasks generated within the new millisecond.

[0163] The battery energy efficiency test method in the embodiment of the present invention has been described above. Next, the battery energy efficiency test device in the embodiment of the present invention will be described. Please refer to Figure 2, an embodiment of the battery energy efficiency testing device in the embodiments of the present invention includes:

[0164] A testing module, configured to receive a battery energy efficiency testing request sent by a terminal device, determine a target battery to be tested according to the battery energy efficiency testing request, and perform battery energy efficiency testing on the target battery according to preset current parameters;

[0165] A collection module, configured to collect the current state, voltage state, and temperature state of the target battery during the battery energy efficiency testing according to a set testing time range;

[0166] An analysis module, configured to analyze the current state, voltage state, and temperature state of the target battery during the battery energy efficiency testing respectively based on a preset battery state analysis algorithm to obtain corresponding battery power data, battery voltage data, and battery temperature data;

[0167] A first calculation model, configured to calculate the energy input amount of the target battery according to the battery current data and preset current parameters, and calculate the energy output amount of the target battery according to a preset energy efficiency calculation formula and the battery voltage data;

[0168] A second calculation module, configured to calculate the energy efficiency difference between the energy input amount and the energy output amount; wherein, the energy efficiency difference is the energy efficiency loss index of the target battery in the working state;

[0169] An association module, configured to perform data association on the energy efficiency loss index and the battery temperature data based on the time stamps within a set testing time range to obtain an associated data set; wherein, the association rules between the energy efficiency loss index and the battery temperature data are stored in advance in the database;

[0170] A parsing module, configured to generate a corresponding target input vector based on the associated data set, input the target input vector into a trained battery energy efficiency analysis model, perform abnormal parsing of the energy efficiency loss index, and obtain a diagnostic result of the target battery energy efficiency.

[0171] The present invention also provides a battery energy efficiency testing device, where the battery energy efficiency testing device includes a memory and a processor, and computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by the processor, the processor executes the steps of the battery energy efficiency testing method in the above embodiments.

[0172] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer, the computer executes the steps of the battery energy efficiency testing method.

[0173] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be repeated here.

[0174] If the integrated unit 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 such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0175] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and the modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A battery energy efficiency testing method, characterized in that: The following steps are involved: Receive a battery energy efficiency test request sent by a terminal device, determine a target battery to be tested according to the battery energy efficiency test request, and perform a battery energy efficiency test on the target battery according to preset current parameters; According to the set test time range, collect the current state, voltage state and temperature state of the target battery during the battery energy efficiency test; Based on the preset battery state analysis algorithm, the current state, voltage state and temperature state of the target battery during the battery energy efficiency test are analyzed respectively to obtain the corresponding battery current data, battery voltage data and battery temperature data; The energy input of the target battery is calculated according to the battery current data and the preset current parameters, and the energy output of the target battery is calculated according to the preset energy efficiency calculation formula and the battery voltage data; specifically including: the implementation steps of calculating the energy input of the target battery according to the battery current data and the preset current parameters: acquiring the collected battery current data, including the current value and the sampling time; in the battery energy efficiency test system, integrating the current data according to the time interval set by the preset current parameter to obtain the energy input within the test time range; saving the calculated energy input into the battery energy efficiency test database; calculating the energy output of the target battery according to the preset energy efficiency calculation formula and the battery voltage data; The implementation steps of calculating the energy output of the target battery by data are as follows: obtaining the collected battery voltage data, including the voltage value and the sampling time; in the battery energy efficiency test system, according to the preset energy efficiency calculation formula, combined with the battery voltage data and the corresponding timestamp, the energy output is calculated; the calculated energy output is saved in the battery energy efficiency test database; energy input: refers to the total amount of energy received by the target battery during the battery energy efficiency test, and the energy input is obtained by integrating the battery current data; energy output: refers to the total amount of energy output by the target battery during the battery energy efficiency test, and the energy output is calculated according to the preset energy efficiency calculation formula, combined with the battery voltage data and the timestamp; Calculating the energy efficiency difference between the energy input and the energy output; wherein the energy efficiency difference is the energy efficiency loss index of the target battery under the working state; The energy efficiency loss index and the battery temperature data are associated with each other based on the timestamps within the set test time range to obtain an associated data set; wherein the association rules between the energy efficiency loss index and the battery temperature data are stored in advance in the database; A corresponding target input vector is generated based on the associated data set, and the target input vector is input into the trained battery energy efficiency analysis model to perform abnormal analysis of the energy efficiency loss index to obtain a diagnosis result of the target battery energy efficiency.

2. The method for testing the energy efficiency of a battery according to claim 1, characterized in that: The training process of the battery energy efficiency analysis model includes: Acquire battery energy efficiency test data, the battery energy efficiency test data including corresponding identification information, perform feature analysis on the battery energy efficiency test data, and obtain a first feature vector; Inputting the first feature vector into a preset feature analysis model to extract features, thereby obtaining a second feature vector; Inputting the obtained second feature vector into a preset gated recurrent unit model, processing the second feature vector through a hidden state in the preset gated recurrent unit model, and obtaining a third feature vector; Inputting the third eigenvector into a preset long short-term memory neuron model, performing a historical dependency analysis process on the third eigenvector through the preset long short-term memory neuron model to generate a fourth eigenvector; A random and non-repeating fifth eigenvector is generated only once within a preset period, and the fourth eigenvector and the fifth eigenvector are subjected to feature fusion to obtain a sixth eigenvector; wherein the generation rule of the fifth eigenvector and the rule for fusion of the fifth eigenvector and the fourth eigenvector are stored in advance in a database; The second eigenvector, the fourth eigenvector and the sixth eigenvector and the corresponding identification information are input into the classifier for model training, and the model parameters of the preset feature parsing model, the gated recurrent unit model and the long short-term memory neuron model are iteratively optimized during the training process until the loss function of the model reaches the expected convergence degree, thereby completing the training of the battery energy efficiency analysis model.

3. The method for testing the energy efficiency of a battery according to claim 1, characterized in that: After the step of obtaining the diagnostic result of the target battery energy efficiency, the method further comprises: Set a string with a specified length as the initial analysis code; In a distributed system including a plurality of data processing units and processing nodes, an identifiable data processing center label and a node ID label are set, and a location identification code is generated based on the data processing center label and the node ID label; Obtain the year and month in the timestamp information, and obtain a corresponding target code map based on the year and month; wherein the target code map is obtained by re-encoding the standard code map based on the year and month; Decoding the millisecond timestamp in each timestamp information based on the target coding diagram to obtain a time identification code corresponding to each millisecond timestamp; Initialize an accumulator to generate a different node identification code for each battery health status assessment result within a single millisecond time frame; Each time a node identification code is generated, the current time is compared with the time when the node identification code was generated last time to see if they are the same. If they are the same, the accumulator increases by one counting unit. If a new millisecond is entered, the accumulator is reset and counted again in the new millisecond time frame to obtain the current counting value of the accumulator. Combining the initial analysis code, the time identification code, the location identification code, the node identification code, and the current count value of the accumulator according to a predetermined order to generate a unique identification code for the battery health assessment result; Based on the unique identification code of the battery health assessment result, the diagnosis result of the target battery energy efficiency is encrypted.

4. The method for testing the energy efficiency of a battery according to claim 3, characterized in that: The step of obtaining the year and month in the timestamp information and obtaining a corresponding target code map based on the year and month includes: By setting the mapping relationship between the year and the standard coding diagram, the standard coding diagram corresponding to the specific year is found in the database; wherein the standard coding diagram includes two parts, one part is the serial number, and the other part is the character corresponding to the serial number; Obtain a digital combination corresponding to the year and month in the timestamp information, divide the year digit by the month digit, take only the tenth digit of the decimal place in the obtained digital result as a specific serial number, take all the digits in the serial number corresponding to the specific serial number as a first digital set, find out a coding symbol corresponding to the first digital set as a first symbol, delete all symbols except the first symbol from the coding symbol as a second symbol; wherein the digits corresponding to the year and month in the timestamp information include at least ten digital combinations corresponding to the year and month, and all digital combinations are integers; reallocating the second symbols to a second set of digits according to a preset arrangement order; wherein the order of the second symbols matches the order in the standard coding diagram; After all second symbols are reassigned corresponding second digital sets, the first symbols are assigned serial numbers in sequence; The second symbol to which the serial numbers have been reallocated, the first symbol and the corresponding serial numbers are integrated to obtain the target coding diagram.

5. The method for testing the energy efficiency of a battery according to claim 3, characterized in that: The location identification code is used to identify the specific node that processes the battery energy efficiency test task. The location identification code is generated by the data processing center labeling and the node ID labeling, and provides a unique identification for each node that processes the battery energy efficiency test task; The current count value of the accumulator is used to ensure that each node status analysis result of processing the battery energy efficiency test task within the same millisecond has a unique identification code; when entering a new millisecond, the accumulator is reset to zero and a new round of counting begins to adapt to the node status analysis results of the battery energy efficiency test task generated within the new millisecond.

6. A battery energy efficiency testing device, characterized in that: The battery energy efficiency testing device comprises: A test module, used to receive a battery energy efficiency test request sent by a terminal device, determine a target battery to be tested according to the battery energy efficiency test request, and perform a battery energy efficiency test on the target battery according to preset current parameters; A collection module is used to collect the current state, voltage state and temperature state of the target battery during the battery energy efficiency test according to the set test time range; An analysis module, used to analyze the current state, voltage state and temperature state of the target battery during the battery energy efficiency test based on a preset battery state analysis algorithm, and obtain corresponding battery current data, battery voltage data and battery temperature data; The first calculation model is used to calculate the energy input of the target battery according to the battery current data and the preset current parameters, and calculate the energy output of the target battery according to the preset energy efficiency calculation formula and the battery voltage data; specifically includes: the implementation steps of calculating the energy input of the target battery according to the battery current data and the preset current parameters: acquiring the collected battery current data, including the current value and the sampling time; in the battery energy efficiency test system, integrating the current data according to the time interval set by the preset current parameter to obtain the energy input within the test time range; saving the calculated energy input into the battery energy efficiency test database; calculating the energy output of the target battery according to the preset energy efficiency calculation formula and The implementation steps of calculating the energy output of the target battery from the battery voltage data are as follows: obtaining the collected battery voltage data, including the voltage value and the sampling time; in the battery energy efficiency test system, calculating the energy output according to the preset energy efficiency calculation formula, combined with the battery voltage data and the corresponding timestamp; saving the calculated energy output to the battery energy efficiency test database; energy input: refers to the total amount of energy received by the target battery during the battery energy efficiency test, and the energy input is obtained by integrating the battery current data; energy output: refers to the total amount of energy output by the target battery during the battery energy efficiency test, and the energy output is calculated according to the preset energy efficiency calculation formula, combined with the battery voltage data and the timestamp; A second calculation module is used to calculate the energy efficiency difference between the energy input and the energy output; wherein the energy efficiency difference is the energy efficiency loss index of the target battery in the working state; An association module is used to associate the energy efficiency loss index and the battery temperature data based on the timestamp within the set test time range to obtain an associated data set; wherein the association rules between the energy efficiency loss index and the battery temperature data are stored in advance in the database; The analysis module is used to generate a corresponding target input vector based on the associated data set, input the target input vector into the trained battery energy efficiency analysis model, perform abnormal analysis of the energy efficiency loss index, and obtain a diagnosis result of the target battery energy efficiency.

7. A battery energy efficiency test device, characterized in that: The battery energy efficiency test device comprises: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the battery energy efficiency testing device to execute the battery energy efficiency testing method according to any one of claims 1 to 5.

8. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by a processor, the energy efficiency testing method for a battery according to any one of claims 1 to 5 is implemented.

Images