New energy power supply test data management method and system
Data analysis rules are constructed through deep learning algorithms, which solves the problems of low efficiency and misjudgment of test data analysis of new energy batteries, realizes auxiliary support for automated analysis and improvement measures, and improves the efficiency of test data management of new energy batteries.
Patent Information
- Application Number
- CN202411366402.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-29
- Publication Date
- 2025-01-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the prior art, the analysis of new energy battery test data is low and dependent on manual labor, which is prone to misjudgment problems and requires professional knowledge.
Deep learning algorithm is used to build initial data analysis rules, identify the relationship between historical new energy power supply test data and manual labels, and form power supply data analysis rules for real-time data analysis, and determine improvement measures through table matching to reduce professional knowledge Require.
It improves the analysis efficiency of new energy power supply test data, reduces misjudgment problems, and assists staff in battery improvements.
Smart Images
Figure CN119249167A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of data processing, and in particular relates to a new energy power supply test data management method and system. Background Art
[0002] At present, new energy can be divided into multiple categories such as solar energy, wind energy, biomass energy, chemical energy, and nuclear energy. At present, the automotive industry has gradually begun to enter the field of new energy, and automobile energy uses new energy batteries. New energy batteries refer to batteries that use renewable energy as the main energy source. New energy batteries can be divided into lithium-ion batteries, batteries (lithium iron phosphate), lithium manganese oxide batteries, etc. New energy batteries have the characteristics of high energy density, low transmission loss, and high safety. They are currently widely used in photovoltaic power generation, new energy vehicles and other industries. In order to ensure the safe and efficient use of new energy batteries, it is necessary to conduct multi-faceted testing of new energy batteries. The testing of new energy includes voltage detection, current detection, short circuit test, explosion-proof safety test, and impact test. In the prior art, after testing new energy batteries, manual analysis methods are often used to analyze the test data to determine the power supply performance characteristics, and the power supply is improved based on the power supply performance characteristics. However, the use of manual analysis methods not only has the problem of low efficiency, but also requires relatively professional knowledge, which leads to the problem of misanalysis. Summary of the invention
[0003] The present invention provides a new energy power supply test data management method and system, which are used to solve the problems existing in the prior art.
[0004] In one aspect, the present invention provides a new energy power supply test data management method, comprising: Acquire historical new energy power supply test data and manual labels; wherein the manual labels are used to characterize the new energy power supply performance indicators input by the staff through human-computer interaction; Using a deep learning algorithm to construct an initial data analysis rule, and using the initial data analysis rule to identify the relationship between the historical new energy power supply test data and the manual label to obtain a power supply data analysis rule; Collect real-time new energy power supply test data, and use power supply data analysis rules to identify the real-time new energy power supply test data to obtain analysis results corresponding to the new energy power supply test data; Based on the analysis results corresponding to the new energy power supply test data, a table lookup matching method is used to determine the new energy power supply improvement measures corresponding to the analysis results; The real-time new energy power supply test data, the analysis results corresponding to the real-time new energy power supply test data, and the new energy power supply improvement measures are associated and stored to complete the management of the new energy power supply test data.
[0005] Furthermore, when obtaining historical new energy power supply test data and manual labels, it also includes: obtaining the new energy power supply improvement measures corresponding to each historical new energy power supply test data, and based on the new energy power supply improvement measures corresponding to all historical new energy power supply test data, determining at least one new energy power supply improvement measure corresponding to each type of manual label, and establishing an association relationship table between manual labels and new energy power supply improvement measures.
[0006] Furthermore, a deep learning algorithm is used to construct initial data analysis rules, including: using a CNN algorithm to construct initial data analysis rules.
[0007] Furthermore, the initial data analysis rule is used to identify the relationship between the historical new energy power supply test data and the manual label to obtain a power supply data analysis rule, including: Initializing the rule parameters of the initial data analysis rule, determining the rule parameter code, and obtaining a plurality of different rule parameter codes; For any rule parameter code, a sine function is used to perform a neighborhood search to obtain the rule parameter code after the neighborhood search; For the rule parameter codes after the neighborhood search, each rule parameter code is matched with another other rule parameter code, and a collaborative search is performed on the rule parameter code according to the obtained other rule parameter codes to obtain the rule parameter code after the collaborative search; For the rule parameter coding after the collaborative search, the optimal rule parameter coding is obtained, and all the rule parameter codings are chain-searched around the optimal rule parameter coding to obtain the rule parameter coding after the chain search; For the rule parameter encoding after the chain search, multiple random rule parameter encodings are used to perform mutation search to obtain the rule parameter encoding after the mutation search; Determine whether the current number of learning times is greater than the preset maximum number of learning times. If so, re-obtain the optimal rule parameter code and apply the optimal rule parameter code to the initial data analysis rule to obtain the power data analysis rule. Otherwise, return to the neighborhood search step.
[0008] Furthermore, for any rule parameter code, a sine function is used to perform a neighborhood search, and the rule parameter code after the neighborhood search is obtained as follows:
[0009] in, Indicates t The first i The rule parameter encoding, Indicates the rule parameter encoding after neighborhood search , Indicates the upper limit code corresponding to the rule parameter code. The upper limit code consists of the upper limit of each dimension. Represents random rule parameter encoding, represents the first random number between (0,1), represents the second random number between (0,1), Represents pi.
[0010] Further, for the rule parameter codes after the neighborhood search, each rule parameter code is matched with another other rule parameter code, and a collaborative search is performed on the rule parameter code according to the obtained other rule parameter codes to obtain the rule parameter code after the collaborative search, including: For the rule parameter codes after the neighborhood search, match each rule parameter code with another rule parameter code ; Encode according to other rule parameters obtained The rule parameter encoding for collaborative search is:
[0011] in, Represents the rule parameter encoding after the mth neighborhood search, Represents a random number generated by normal distribution N(0,1), Represents a random number between (0,1), Indicates the preset maximum number of optimizations.
[0012] Furthermore, for the rule parameter coding after the collaborative search, the optimal rule parameter coding is obtained, and all the rule parameter codings are chain-searched around the optimal rule parameter coding to obtain the rule parameter coding after the chain search, including: For the rule parameter codes after the collaborative search, the error function value corresponding to each rule parameter code is obtained, and the rule parameter code with the smallest error function value is determined as the optimal rule parameter code; According to the error function value corresponding to each rule parameter code, the rule parameter codes after collaborative search are arranged in order of error function value from small to large, and all rule parameter codes are chain searched around the optimal rule parameter code as follows:
[0013]
[0014] in, Indicates the nth rule parameter encoding after sorting. Indicates the rule parameter encoding after chain search , represents the optimal rule parameter encoding, represents the third random number between (0,1), represents the control coefficient, Indicates the n-1th rule parameter encoding after sorting. represents the fourth random number between (0,1), Represents pi.
[0015] Furthermore, for the rule parameter encoding after the chain search, multiple random rule parameter encodings are used to perform mutation search, and the rule parameter encoding after the mutation search is obtained as follows:
[0016] in, Indicates h The rule parameter encoding after the chain search corresponds to the mutated search value, represents the first random rule parameter encoding, Indicates the second random rule parameter encoding, Indicates the third random rule parameter encoding, , represents the step size control factor, Indicates the preset step size; Determine the mutation search value Is the error function value less than the rule parameter encoding The error function value of , if so, then use the mutation search value Replace the original rule parameter encoding , get the rule parameter encoding after mutation search, otherwise directly encode the original rule parameter Encoded as rule parameters after mutation search.
[0017] Furthermore, based on the analysis results corresponding to the new energy power supply test data, a table lookup matching method is used to determine the new energy power supply improvement measures corresponding to the analysis results, including: Based on the analysis results corresponding to the new energy power supply test data, a search is performed in the association relationship table between the manual tags and the new energy power supply improvement measures to determine the new energy power supply improvement measures corresponding to the analysis results.
[0018] On the other hand, the present invention provides a new energy power supply test data management system, including: a historical data acquisition module, a data relationship learning module, a data analysis module, an improvement measure recommendation module and a data storage module; The historical data acquisition module is used to acquire historical new energy power supply test data and manual labels; wherein the manual labels are used to characterize the new energy power supply performance indicators input by the staff through human-computer interaction; The data relationship learning module is used to construct an initial data analysis rule using a deep learning algorithm, and use the initial data analysis rule to identify the relationship between the historical new energy power supply test data and the manual label to obtain a power supply data analysis rule; The data analysis module is used to collect real-time new energy power supply test data, and use power supply data analysis rules to identify the real-time new energy power supply test data to obtain analysis results corresponding to the new energy power supply test data; The improvement measure recommendation module is used to determine the new energy power supply improvement measures corresponding to the analysis results based on the analysis results corresponding to the new energy power supply test data by using a table lookup matching method; The data storage module is used to associate and store the real-time new energy power supply test data, the analysis results corresponding to the real-time new energy power supply test data, and the new energy power supply improvement measures to complete the management of the new energy power supply test data.
[0019] The present invention provides a new energy power supply test data management method and system, which collects historical new energy power supply test data and manual labels, and learns the data relationship between the new energy power supply test data and the manual labels, so as to form a power supply data analysis rule that can analyze the new energy power supply test data, and analyzes the subsequent real-time new energy power supply test data through the power supply data analysis rule, so as to determine the new energy power supply performance index, assist the staff to improve the battery, not only effectively improve the analysis efficiency of the new energy power supply test data, but also reduce the requirements for professional knowledge, and avoid the misjudgment problem caused by manual analysis. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0021] Figure 1 A schematic flow chart of a new energy power supply test data management method provided in an embodiment of the present invention.
[0022] Figure 2 A schematic diagram of the structure of a new energy power supply test data management system provided by an embodiment of the present invention.
[0023] The above drawings have shown clear embodiments of the present invention, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0024] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.
[0025] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.
[0026] like Figure 1 As shown, an embodiment of the present invention provides a new energy power supply test data management method, comprising: S1. Obtain historical new energy power supply test data and manual labels; wherein the manual labels are used to characterize the new energy power supply performance indicators input by the staff through human-computer interaction; The performance indicator of new energy power supply can be a certain type of defect in the new energy power supply, such as performance degradation, short circuit, open circuit and other power supply defects. By learning from the existing historical data, it can replace manual analysis and improve efficiency.
[0027] S2. Using a deep learning algorithm to construct an initial data analysis rule, and using the initial data analysis rule to identify the relationship between the historical new energy power supply test data and the manual label to obtain a power supply data analysis rule; When the power supply test data is small, a deep learning algorithm with vector as input can be used to construct the initial data analysis rules; when the power supply test data is large, a deep learning algorithm with data matrix as input can be used to construct the initial data analysis rules, thereby realizing different data analysis.
[0028] In the process of using the initial data analysis rule to identify the relationship between the historical new energy power supply test data and the manual label, an intelligent optimization algorithm can be used to optimize the rule parameters of the initial data analysis rule to finally obtain the power supply data analysis rule.
[0029] S3, collecting real-time new energy power supply test data, and using power supply data analysis rules to identify the real-time new energy power supply test data, and obtaining analysis results corresponding to the new energy power supply test data; The format of real-time renewable energy power supply test data needs to be the same as that of historical renewable energy power supply test data to ensure that the power supply data analysis rules can accurately identify the data.
[0030] S4. Based on the analysis results corresponding to the new energy power supply test data, a table lookup matching method is used to determine the new energy power supply improvement measures corresponding to the analysis results; Based on historical data, a correlation table between manual labels and new energy power improvement measures can be constructed. After data analysis, the corresponding new energy power improvement measures can be determined based on the correlation table and recommended to the staff to assist the staff in improving work efficiency. It is worth noting that one manual label can correspond to one new energy power improvement measure or multiple new energy power improvement measures.
[0031] S5. Associate and store the real-time new energy power supply test data, the analysis results corresponding to the real-time new energy power supply test data, and the new energy power supply improvement measures to complete the management of the new energy power supply test data.
[0032] Optionally, a cloud database may be used to associate and store real-time new energy power supply test data, analysis results corresponding to the real-time new energy power supply test data, and new energy power supply improvement measures to facilitate staff to view the data.
[0033] The present invention provides a new energy power supply test data management method, which collects historical new energy power supply test data and manual labels, and learns the data relationship between the new energy power supply test data and the manual labels, so as to form a power supply data analysis rule that can analyze the new energy power supply test data, and analyzes the subsequent real-time new energy power supply test data through the power supply data analysis rule, so as to determine the new energy power supply performance index, assist the staff to improve the battery, not only effectively improve the analysis efficiency of the new energy power supply test data, but also reduce the requirements for professional knowledge, and avoid the misjudgment problem caused by manual analysis.
[0034] In an embodiment of the present invention, when obtaining historical new energy power supply test data and manual labels, it also includes: obtaining new energy power supply improvement measures corresponding to each historical new energy power supply test data, and determining at least one new energy power supply improvement measure corresponding to each type of manual label based on the new energy power supply improvement measures corresponding to all historical new energy power supply test data, and establishing an association relationship table between manual labels and new energy power supply improvement measures.
[0035] In an embodiment of the present invention, a deep learning algorithm is used to construct the initial data analysis rules, including: using a CNN (Convolutional Neural Networks) algorithm to construct the initial data analysis rules. However, it is worth noting that the use of a CNN algorithm is only a preferred implementation of the embodiment of the present invention, and other deep learning algorithms can also be used to construct the initial data analysis rules.
[0036] In an embodiment of the present invention, the initial data analysis rule is used to identify the relationship between the historical new energy power supply test data and the manual label to obtain the power supply data analysis rule, including: Initializing the rule parameters of the initial data analysis rule, determining the rule parameter code, and obtaining a plurality of different rule parameter codes; For example, suppose that the CNN algorithm is used to construct the initial data analysis rules, and the rule parameters are weight parameters and threshold parameters. These parameters have fixed upper and lower limits, so they can be randomly initialized between the upper and lower limits of the rule parameters to determine a rule parameter encoding.
[0037] Optionally, during the learning process, some rule parameter encodings may be selected for optimization, or all rule parameter encodings may be selected for optimization.
[0038] For any rule parameter code, a sine function is used to perform a neighborhood search to obtain the rule parameter code after the neighborhood search; For the rule parameter codes after the neighborhood search, each rule parameter code is matched with another other rule parameter code, and a collaborative search is performed on the rule parameter code according to the obtained other rule parameter codes to obtain the rule parameter code after the collaborative search; For the rule parameter coding after the collaborative search, the optimal rule parameter coding is obtained, and all the rule parameter codings are chain-searched around the optimal rule parameter coding to obtain the rule parameter coding after the chain search; For the rule parameter encoding after the chain search, multiple random rule parameter encodings are used to perform mutation search to obtain the rule parameter encoding after the mutation search; Determine whether the current number of learning times is greater than the preset maximum number of learning times. If so, re-obtain the optimal rule parameter code and apply the optimal rule parameter code to the initial data analysis rule to obtain the power data analysis rule. Otherwise, return to the neighborhood search step.
[0039] Due to the problems in the prior art, the final power data analysis rule may have a poor effect on the analysis of the parameters and test data. Therefore, an embodiment of the present invention provides an intelligent optimization algorithm to improve the data recognition capability of the power data analysis rule.
[0040] In the embodiment of the present invention, for any rule parameter code, a sine function is used to perform a neighborhood search, and the rule parameter code after the neighborhood search is obtained as follows:
[0041] in, Indicates t The first iThe rule parameter encoding, Indicates the rule parameter encoding after neighborhood search , Indicates the upper limit code corresponding to the rule parameter code. The upper limit code consists of the upper limit of each dimension. Represents random rule parameter encoding, represents the first random number between (0,1), represents the second random number between (0,1), Represents pi.
[0042] The method for performing neighborhood search using a sine function provided in an embodiment of the present invention can effectively implement neighborhood search based on information encoded by other rule parameters, thereby improving the local exploration effect.
[0043] In the embodiment of the present invention, for the rule parameter codes after the neighborhood search, each rule parameter code is matched with another other rule parameter code, and a collaborative search is performed on the rule parameter code according to the obtained other rule parameter codes to obtain the rule parameter code after the collaborative search, including: For the rule parameter codes after the neighborhood search, match each rule parameter code with another rule parameter code ; Encode according to other rule parameters obtained The rule parameter encoding for collaborative search is:
[0044] in, Represents the rule parameter encoding after the mth neighborhood search, Represents a random number generated by normal distribution N(0,1), Represents a random number between (0,1), Indicates the preset maximum number of optimizations.
[0045] The collaborative search provided by the embodiment of the present invention can effectively realize information fusion, thereby exploring the unfamiliar space between any two rule parameter codes and improving the search efficiency of the algorithm. It is worth noting that the above collaborative search can also be replaced by .
[0046] In the embodiment of the present invention, for the rule parameter coding after the collaborative search, the optimal rule parameter coding is obtained, and all the rule parameter codings are chain-searched around the optimal rule parameter coding to obtain the rule parameter coding after the chain search, including: For the rule parameter codes after the collaborative search, the error function value corresponding to each rule parameter code is obtained, and the rule parameter code with the smallest error function value is determined as the optimal rule parameter code; According to the error function value corresponding to each rule parameter code, the rule parameter codes after collaborative search are arranged in order of error function value from small to large, and all rule parameter codes are chain searched around the optimal rule parameter code as follows:
[0047]
[0048] in, Indicates the nth rule parameter encoding after sorting. Indicates the rule parameter encoding after chain search , represents the optimal rule parameter encoding, represents the third random number between (0,1), represents the control coefficient, Indicates the parameter encoding of the n-1th rule after sorting. represents the fourth random number between (0,1), Represents pi.
[0049] The chain search provided by the embodiment of the present invention can combine all rule parameter codes together to search around the optimal position in a chain, which can effectively improve development efficiency and enhance the ability to explore the optimal area.
[0050] In the embodiment of the present invention, for the rule parameter code after the chain search, multiple random rule parameter codes are used to perform mutation search, and the rule parameter code after the mutation search is obtained as follows:
[0051] in, Indicates h The rule parameter encoding after the chain search corresponds to the mutated search value, represents the first random rule parameter encoding, Indicates the second random rule parameter encoding, Indicates the third random rule parameter encoding, , represents the step size control factor, Indicates the preset step size; Determine the mutation search value Is the error function value less than the rule parameter encoding The error function value of , if so, then use the mutation search value Replace the original rule parameter encoding , get the rule parameter encoding after mutation search, otherwise directly encode the original rule parameter Encoded as rule parameters after mutation search.
[0052] The variation search provided by the embodiment of the present invention can effectively maintain algorithm diversity to prevent the algorithm from entering the local optimum too early, thereby improving the search effect of the algorithm.
[0053] In an embodiment of the present invention, based on the analysis results corresponding to the new energy power supply test data, a table lookup matching method is used to determine the new energy power supply improvement measures corresponding to the analysis results, including: Based on the analysis results corresponding to the new energy power supply test data, a search is performed in the association relationship table between the manual tags and the new energy power supply improvement measures to determine the new energy power supply improvement measures corresponding to the analysis results.
[0054] like Figure 2 As shown, the embodiment of the present invention provides a new energy power supply test data management system, including: a historical data acquisition module 1, a data relationship learning module 2, a data analysis module 3, an improvement measure recommendation module 4 and a data storage module 5; The historical data acquisition module 1 is used to acquire historical new energy power supply test data and manual labels; wherein the manual labels are used to characterize the new energy power supply performance indicators input by the staff through human-computer interaction; The data relationship learning module 2 is used to construct an initial data analysis rule using a deep learning algorithm, and use the initial data analysis rule to identify the relationship between the historical new energy power supply test data and the manual label to obtain a power supply data analysis rule; The data analysis module 3 is used to collect real-time new energy power supply test data, and use power supply data analysis rules to identify the real-time new energy power supply test data to obtain analysis results corresponding to the new energy power supply test data; The improvement measure recommendation module 4 is used to determine the new energy power improvement measures corresponding to the analysis results using a table lookup matching method based on the analysis results corresponding to the new energy power test data; The data storage module 5 is used to associate and store the real-time new energy power supply test data, the analysis results corresponding to the real-time new energy power supply test data, and the new energy power supply improvement measures to complete the management of the new energy power supply test data.
[0055] A new energy power supply test data management system provided in an embodiment of the present invention can execute the above method and technical solution, and its principles and beneficial effects are similar, which will not be repeated here.
[0056] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0057] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0058] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0059] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0060] A person of ordinary skill in the art can understand that all or part of the steps in realizing the above-mentioned facts and methods can be completed by instructing the relevant hardware through a program, and the program involved or the program described can be stored in a computer-readable storage medium. When the program is executed, it includes the following steps: At this time, the corresponding method steps are derived, and the storage medium can be ROM / RAM, a disk, an optical disk, etc.
[0061] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A new energy power supply test data management method, characterized in that: include: Acquire historical new energy power supply test data and manual labels; wherein the manual labels are used to characterize the new energy power supply performance indicators input by the staff through human-computer interaction; Using a deep learning algorithm to construct an initial data analysis rule, and using the initial data analysis rule to identify the relationship between the historical new energy power supply test data and the manual label to obtain a power supply data analysis rule; Collect real-time new energy power supply test data, and use power supply data analysis rules to identify the real-time new energy power supply test data to obtain analysis results corresponding to the new energy power supply test data; Based on the analysis results corresponding to the new energy power supply test data, a table lookup matching method is used to determine the new energy power supply improvement measures corresponding to the analysis results; The real-time new energy power supply test data, the analysis results corresponding to the real-time new energy power supply test data, and the new energy power supply improvement measures are associated and stored to complete the management of the new energy power supply test data.
2. The new energy power supply test data management method according to claim 1, characterized in that: When obtaining historical new energy power supply test data and manual labels, it also includes: obtaining the new energy power supply improvement measures corresponding to each historical new energy power supply test data, and based on the new energy power supply improvement measures corresponding to all historical new energy power supply test data, determining at least one new energy power supply improvement measure corresponding to each type of manual label, and establishing an association relationship table between manual labels and new energy power supply improvement measures.
3. The new energy power supply test data management method according to claim 1, characterized in that: A deep learning algorithm is used to construct initial data analysis rules, including: using a CNN algorithm to construct initial data analysis rules.
4. The new energy power supply test data management method according to claim 1, characterized in that: The relationship between the historical new energy power supply test data and the manual labels is identified by using the initial data analysis rule to obtain the power supply data analysis rule, including: Initializing the rule parameters of the initial data analysis rule, determining the rule parameter code, and obtaining a plurality of different rule parameter codes; For any rule parameter code, a sine function is used to perform a neighborhood search to obtain the rule parameter code after the neighborhood search; For the rule parameter codes after the neighborhood search, each rule parameter code is matched with another other rule parameter code, and a collaborative search is performed on the rule parameter code according to the other rule parameter codes obtained to obtain the rule parameter code after the collaborative search; For the rule parameter coding after the collaborative search, the optimal rule parameter coding is obtained, and all the rule parameter codings are chain-searched around the optimal rule parameter coding to obtain the rule parameter coding after the chain search; For the rule parameter encoding after the chain search, multiple random rule parameter encodings are used to perform mutation search to obtain the rule parameter encoding after the mutation search; Determine whether the current number of learning times is greater than the preset maximum number of learning times. If so, re-obtain the optimal rule parameter code and apply the optimal rule parameter code to the initial data analysis rule to obtain the power data analysis rule. Otherwise, return to the neighborhood search step.
5. The new energy power supply test data management method according to claim 4, characterized in that: For any rule parameter encoding, a sine function is used to perform a neighborhood search, and the rule parameter encoding after the neighborhood search is obtained as follows: in, Indicates t The first i The rule parameter encoding, Indicates the rule parameter encoding after neighborhood search , Indicates the upper limit code corresponding to the rule parameter code. The upper limit code consists of the upper limit of each dimension. Represents random rule parameter encoding, represents the first random number between (0,1), represents the second random number between (0,1), Represents pi.
6. The new energy power supply test data management method according to claim 5, characterized in that: For the rule parameter codes after the neighborhood search, each rule parameter code is matched with another other rule parameter code, and a collaborative search is performed on the rule parameter code according to the obtained other rule parameter codes to obtain the rule parameter code after the collaborative search, including: For the rule parameter codes after the neighborhood search, match each rule parameter code with another rule parameter code ; Encode according to other rule parameters obtained The rule parameter encoding for collaborative search is: in, Represents the rule parameter encoding after the mth neighborhood search, Represents a random number generated by normal distribution N(0,1), Represents a random number between (0,1), Indicates the preset maximum number of optimizations.
7. The new energy power supply test data management method according to claim 6, characterized in that: For the rule parameter encoding after the collaborative search, the optimal rule parameter encoding is obtained, and all rule parameter encodings are chain-searched around the optimal rule parameter encoding to obtain the rule parameter encoding after the chain search, including: For the rule parameter codes after the collaborative search, the error function value corresponding to each rule parameter code is obtained, and the rule parameter code with the smallest error function value is determined as the optimal rule parameter code; According to the error function value corresponding to each rule parameter code, the rule parameter codes after collaborative search are arranged in order of error function value from small to large, and all rule parameter codes are chain searched around the optimal rule parameter code as follows: in, Indicates the nth rule parameter encoding after sorting. Indicates the rule parameter encoding after chain search , represents the optimal rule parameter encoding, represents the third random number between (0,1), represents the control coefficient, Indicates the n-1th rule parameter encoding after sorting. represents the fourth random number between (0,1), Represents pi.
8. The new energy power supply test data management method according to claim 7, characterized in that: For the rule parameter encoding after chain search, multiple random rule parameter encodings are used for mutation search, and the rule parameter encoding after mutation search is obtained as follows: in, Indicates h The rule parameter encoding after the chain search corresponds to the mutated search value, represents the first random rule parameter encoding, Indicates the second random rule parameter encoding, Indicates the third random rule parameter encoding, , represents the step size control factor, Indicates the preset step size; Determine the mutation search value Is the error function value less than the rule parameter encoding The error function value of , if so, then use the mutation search value Replace the original rule parameter encoding , get the rule parameter encoding after mutation search, otherwise directly encode the original rule parameter Encoded as rule parameters after mutation search.
9. The new energy power supply test data management method according to claim 2, characterized in that: Based on the analysis results corresponding to the new energy power supply test data, the table lookup matching method is used to determine the new energy power supply improvement measures corresponding to the analysis results, including: Based on the analysis results corresponding to the new energy power supply test data, a search is performed in the association relationship table between the manual tags and the new energy power supply improvement measures to determine the new energy power supply improvement measures corresponding to the analysis results.
10. A new energy power supply test data management system, characterized in that: include: Historical data acquisition module, data relationship learning module, data analysis module, improvement measure recommendation module and data storage module; The historical data acquisition module is used to acquire historical new energy power supply test data and manual labels; wherein the manual labels are used to characterize the new energy power supply performance indicators input by the staff through human-computer interaction; The data relationship learning module is used to construct an initial data analysis rule using a deep learning algorithm, and use the initial data analysis rule to identify the relationship between the historical new energy power supply test data and the manual label to obtain a power supply data analysis rule; The data analysis module is used to collect real-time new energy power supply test data, and use power supply data analysis rules to identify the real-time new energy power supply test data to obtain analysis results corresponding to the new energy power supply test data; The improvement measure recommendation module is used to determine the new energy power supply improvement measures corresponding to the analysis results based on the analysis results corresponding to the new energy power supply test data by using a table lookup matching method; The data storage module is used to associate and store the real-time new energy power supply test data, the analysis results corresponding to the real-time new energy power supply test data, and the new energy power supply improvement measures to complete the management of the new energy power supply test data.