Battery analysis method and device, computer equipment, storage medium and program product

Abstract

The invention relates to a battery analysis method and device, computer equipment, a storage medium and a program product. The method comprises the steps of obtaining target battery parameters of a to-be-evaluated battery; according to the target battery parameters and the battery knowledge graph, determining the fault probability of a fault of the to-be-evaluated battery; wherein the battery knowledge graph at least comprises a corresponding relation between each candidate battery parameter and a candidate fault type; each candidate battery parameter at least comprises a candidate battery model, a candidate battery state and candidate battery operation and maintenance data. According to the scheme, when fault analysis is carried out on the to-be-evaluated battery, matching can be directly carried out according to the target battery parameters of the to-be-evaluated battery and the corresponding relations between the candidate battery parameters and the candidate fault types in the battery knowledge graph, and then the fault probability of the fault of the to-be-evaluated battery is determined according to the matching result. And a fault diagnosis instrument is not needed for fault analysis, so that the fault analysis efficiency of the battery is improved.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a battery analysis method, device, computer equipment, storage medium and program product. Background Art

[0002] Batteries are key components in new energy vehicles, responsible for providing electricity and power. If a battery fails, it may cause vehicle performance to decline, or even cause the vehicle to fail to start or stall while driving. More seriously, battery problems may cause safety hazards such as fire or explosion. Through timely battery fault diagnosis, potential safety risks can be discovered and repaired to ensure the safety of drivers and passengers.

[0003] In traditional technology, a diagnostic instrument is usually used to perform fault analysis on the battery in the vehicle, which has the problem of low fault analysis efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide a battery analysis method, device, computer equipment, storage medium and program product to improve the efficiency of battery fault analysis in response to the above technical problems.

[0005] In a first aspect, the present application provides a battery analysis method, the method comprising:

[0006] Obtain target battery parameters of the battery to be evaluated; wherein the target battery parameters include at least a target battery model, a target battery state, and target battery operation and maintenance data;

[0007] According to the target battery parameters and the battery knowledge graph, the failure probability of the battery to be evaluated is determined; wherein the battery knowledge graph at least includes the corresponding relationship between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes a candidate battery model, a candidate battery status and a candidate battery operation and maintenance data.

[0008] In one embodiment, determining the failure probability of the battery to be evaluated according to the target battery parameter and the battery knowledge graph includes:

[0009] Determining parameter similarity between the target battery parameter and each candidate battery parameter in the battery knowledge graph;

[0010] The maximum parameter similarity is used as the failure probability of the battery to be evaluated.

[0011] In one embodiment, the battery knowledge graph is constructed in the following manner:

[0012] Determine the battery keywords corresponding to the battery of each candidate battery model in the battery life cycle; wherein the battery keywords at least include candidate battery parameters and candidate fault types;

[0013] Establishing a logical relationship between each battery keyword; wherein the logical relationship includes at least one of an attribution relationship, a causal relationship, and a parallel relationship;

[0014] The battery knowledge graph is established based on the logical relationship between the battery keywords.

[0015] In one embodiment, the step of establishing a logical relationship between battery keywords includes:

[0016] Using each battery keyword as an index, searching a text database for a relationship description field containing at least two battery keywords;

[0017] According to the relationship description fields found, the logical relationship between the battery keywords is established.

[0018] In one embodiment, the method further comprises:

[0019] Obtain real-time battery operation and maintenance data of batteries of each candidate battery model;

[0020] The logical relationship between each battery keyword is updated according to the real-time battery operation and maintenance data of the batteries of each candidate battery model.

[0021] In one embodiment, the method further comprises:

[0022] Taking the candidate fault type corresponding to the candidate battery parameter that is most similar to the battery parameter of the battery to be evaluated as the target fault type;

[0023] According to the failure probability and target failure type of the battery to be evaluated, the strategy for producing and operating the battery to be evaluated is adjusted.

[0024] In a second aspect, the present application also provides a battery analysis device, the device comprising:

[0025] An acquisition module, used to acquire target battery parameters of the battery to be evaluated; wherein the target battery parameters at least include a target battery model, a target battery state and a target battery operation and maintenance data;

[0026] A determination module is used to determine the failure probability of the battery to be evaluated based on the target battery parameters and the battery knowledge graph; wherein the battery knowledge graph at least includes the corresponding relationship between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes a candidate battery model, a candidate battery status and a candidate battery operation and maintenance data.

[0027] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0028] Obtain target battery parameters of the battery to be evaluated; wherein the target battery parameters include at least a target battery model, a target battery state, and target battery operation and maintenance data;

[0029] According to the target battery parameters and the battery knowledge graph, the failure probability of the battery to be evaluated is determined; wherein the battery knowledge graph at least includes the corresponding relationship between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes a candidate battery model, a candidate battery status and a candidate battery operation and maintenance data.

[0030] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0031] Obtain target battery parameters of the battery to be evaluated; wherein the target battery parameters include at least a target battery model, a target battery state, and target battery operation and maintenance data;

[0032] According to the target battery parameters and the battery knowledge graph, the failure probability of the battery to be evaluated is determined; wherein the battery knowledge graph at least includes the corresponding relationship between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes a candidate battery model, a candidate battery status and a candidate battery operation and maintenance data.

[0033] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, which implements the following steps when executed by a processor:

[0034] Obtain target battery parameters of the battery to be evaluated; wherein the target battery parameters include at least a target battery model, a target battery state, and target battery operation and maintenance data;

[0035] According to the target battery parameters and the battery knowledge graph, the failure probability of the battery to be evaluated is determined; wherein the battery knowledge graph at least includes the corresponding relationship between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes a candidate battery model, a candidate battery status and a candidate battery operation and maintenance data.

[0036] The above-mentioned battery analysis method, device, computer equipment, storage medium and program product obtain the target battery parameters of the battery to be evaluated; wherein the target battery parameters at least include the target battery model, target battery status and target battery operation and maintenance data; according to the target battery parameters and the battery knowledge graph, the failure probability of the battery to be evaluated is determined; wherein the battery knowledge graph at least includes the correspondence between each candidate battery parameter and the candidate fault type; each candidate battery parameter at least includes the candidate battery model, candidate battery status and candidate battery operation and maintenance data. The above-mentioned scheme establishes a battery knowledge graph by including the correspondence between each candidate battery parameter and the candidate fault type. When performing fault analysis on the battery to be evaluated, the target battery parameters of the battery to be evaluated can be directly matched with the correspondence between each candidate battery parameter and the candidate fault type in the battery knowledge graph, and then the failure probability of the battery to be evaluated is determined according to the matching result. There is no need to use a fault diagnosis instrument to perform fault analysis, which improves the efficiency of fault analysis of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of a battery analysis method according to an embodiment;

[0038] Figure 2 A schematic diagram of a process for determining a failure probability of a battery to be evaluated that fails in one embodiment;

[0039] Figure 3 A schematic diagram of a process for constructing a battery knowledge graph in one embodiment;

[0040] Figure 4 A schematic diagram of a flow chart for establishing a logical relationship between battery keywords in an embodiment;

[0041] Figure 5 A schematic diagram of a flow chart for updating the logical relationship between battery keywords according to an embodiment;

[0042] Figure 6 A schematic diagram of a process for adjusting a strategy for producing and operating a battery to be evaluated according to an embodiment;

[0043] Figure 7 A schematic diagram of an ontology hierarchical structure established by using the protégé tool in one embodiment;

[0044] Figure 8 A schematic diagram showing the relationship between design parameters of a battery according to an embodiment;

[0045] Fig. 9 is a structural block diagram of a battery analysis device in one embodiment;

[0046] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] The battery analysis method provided in the embodiment of the present application can be applied to the application scenario of analyzing the battery, specifically to the application scenario of fault analysis, production and operation and maintenance strategy analysis of the battery. The method can be executed by a server, or by a terminal with a certain computing power. Among them, the server can be implemented as an independent server or a server cluster composed of multiple servers. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.

[0049] In one embodiment, Figure 1 As shown, a battery analysis method is provided, which is described by taking the application of the method to a server as an example, and includes the following steps:

[0050] S101, obtaining target battery parameters of a battery to be evaluated.

[0051] Exemplarily, the battery to be evaluated can be a battery of any model. The target battery parameters of the battery to be evaluated include at least a target battery model, a target battery state, and a target battery operation and maintenance data; wherein the target battery model is the model of the battery to be evaluated, and the target battery model can be a battery type, for example, a lithium battery. The target battery state is the state of the battery to be evaluated, such as data such as the current battery capacity, battery charging rate, and current during battery discharge. The target battery operation and maintenance data is the current or historical operation and maintenance data of the battery to be evaluated, for example, it can be the battery's usage conditions, usage duration, and usage methods in historical usage stages.

[0052] S102, determining the failure probability of the battery to be evaluated according to the target battery parameters and the battery knowledge graph.

[0053] Exemplarily, the battery knowledge graph can be pre-established, for example, the battery knowledge graph can be generated by integrating relevant knowledge in the battery field. Among them, the battery knowledge graph includes at least the correspondence between each candidate battery parameter and the candidate fault type; each candidate battery parameter includes at least a candidate battery model, a candidate battery state and a candidate battery operation and maintenance data. Among them, the candidate battery model is the model of the battery to be evaluated, and the candidate battery model can be a battery type, for example, it can be a lithium battery. The candidate battery state is the state of the battery to be evaluated, for example, data such as battery capacity, battery charging rate, and current during battery discharge. The candidate battery operation and maintenance data is the historical operation and maintenance data of the battery to be evaluated, for example, it can be the use conditions, use time and use methods of the battery in the historical use stage. The candidate fault types can be electrodes, diaphragms, electrolyte defects, battery overcharge, battery overdischarge, battery short circuit, electrolyte density is too high, battery aging, lithium precipitation, solid electrolyte interface layer (Solid Electrolyte Interphase, SEI) growth, electrolyte drying and active particle rupture.

[0054] It should be noted that since the battery knowledge graph includes the correspondence between each candidate battery parameter and the candidate fault type, the correspondence that matches the target battery parameter of the battery to be evaluated can be screened out in the knowledge graph, and the fault probability of the battery to be evaluated can be determined based on the matching result. For example, if the matching result is a candidate battery parameter that completely matches the target battery parameter in the knowledge graph, it can be considered that the probability of the candidate fault type corresponding to the candidate battery parameter occurring in the battery to be evaluated is 100%. If the matching result is that no candidate battery parameter that completely matches the target battery parameter is found in the knowledge graph, it is considered that the probability of the battery to be evaluated failing is small.

[0055] The above-mentioned battery analysis method obtains the target battery parameters of the battery to be evaluated; wherein the target battery parameters at least include the target battery model, target battery status and target battery operation and maintenance data; according to the target battery parameters and the battery knowledge graph, the failure probability of the battery to be evaluated is determined; wherein the battery knowledge graph at least includes the correspondence between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes the candidate battery model, candidate battery status and candidate battery operation and maintenance data. The above-mentioned scheme establishes a battery knowledge graph by including the correspondence between each candidate battery parameter and the candidate failure type. When performing fault analysis on the battery to be evaluated, the target battery parameters of the battery to be evaluated can be directly matched with the correspondence between each candidate battery parameter and the candidate failure type in the battery knowledge graph, and then the failure probability of the battery to be evaluated is determined according to the matching result. There is no need to use a fault diagnosis instrument to perform fault analysis, which improves the efficiency of fault analysis of the battery.

[0056] In some optional implementations, see Figure 2 , Figure 2 A schematic flow chart of determining the failure probability of a battery to be evaluated is provided, which specifically includes the following steps:

[0057] S201, determining the parameter similarity between the target battery parameters and each candidate battery parameter in the battery knowledge graph.

[0058] Exemplarily, the target battery parameter to be evaluated can be compared with each candidate battery parameter in the battery knowledge graph for similarity. For example, for each candidate battery parameter, the target battery model in the target battery parameter can be compared with the candidate battery type in the candidate battery parameter to obtain a first similarity; the target battery state in the target battery parameter can be compared with the candidate battery state in the candidate battery parameter to obtain a second similarity; the target battery operation and maintenance data in the target battery parameter can be compared with the candidate battery operation and maintenance data in the candidate battery parameter to obtain a third similarity. Then, the weight corresponding to the battery model comparison dimension is multiplied by the first similarity to obtain a first product; the weight corresponding to the battery state comparison dimension is multiplied by the second similarity to obtain a second product; the weight corresponding to the battery operation and maintenance data comparison dimension is multiplied by the third similarity to obtain a third product; and the sum of the first product, the second product, and the third product is taken as the parameter similarity between the target battery parameter and the candidate battery parameter in the battery knowledge graph.

[0059] S202: Taking the maximum parameter similarity as the failure probability of the battery to be evaluated.

[0060] Furthermore, the maximum parameter similarity is used as the failure probability of the battery to be evaluated. It can be understood that the maximum parameter similarity represents that the candidate battery parameters that are most similar to the target battery parameters are found, that is, it can be considered that the battery to be evaluated is most likely to have the candidate failure type corresponding to the candidate battery parameters, and the probability of the candidate failure type occurring is the maximum parameter similarity.

[0061] In the embodiment of the present application, the maximum parameter similarity is used as the failure probability of the battery to be evaluated, so that the determined failure probability has a basis to be found, thereby improving the reliability of the determined failure probability.

[0062] In some optional implementations, see Figure 3 , Figure 3 A schematic diagram of the process of building a battery knowledge graph is provided, which specifically includes the following steps:

[0063] S301, determining battery keywords corresponding to batteries of each candidate battery model in the battery life cycle.

[0064] Exemplarily, the battery life cycle may include the production phase, operation and maintenance phase, and recycling phase. Battery keywords can be understood as all words related to batteries, where battery keywords at least include candidate battery parameters and candidate fault types, and may also include battery attribute data and usage information. For example, it may include battery type, battery technology, battery performance, usage, voltage, capacity, size, weight, material, aging, lithium plating, and SEI growth.

[0065] Optionally, the battery keywords corresponding to the battery life cycle of each candidate battery model can be obtained from the knowledge base corresponding to the battery field. Battery-related knowledge documents can also be collected based on empirical data to automatically extract the battery keywords corresponding to the battery life cycle of each candidate battery model.

[0066] S302: Establishing logical relationships between battery keywords.

[0067] Furthermore, a logical relationship between each battery keyword can be established. For example, the logical relationship between each battery keyword can be established by professionals in the battery field; or the logical relationship between each battery keyword can be automatically constructed by analyzing battery-related knowledge documents; the logical relationship includes at least one of an attribution relationship, a causal relationship, and a parallel relationship; for example, the logical relationship between the constructed battery keywords can be that lithium battery is a type of battery, and lithium cobalt oxide, lithium manganese oxide, and lithium iron phosphate can all be used as positive electrode materials for lithium batteries; the battery has a linear capacity decrease problem when charged at low temperatures, which means that the battery has a lithium plating failure.

[0068] Among them, the logical relationship can be understood as a triple relationship. For example, the triple relationship can be entity-attribute-value, in which the first element represents the entity, the second element represents an attribute of the entity, and the third element is the value of the attribute. For example, in the battery ontology, it can be expressed that the capacity (attribute) of the battery (entity) is how many Ah (value). The triple relationship can also be entity-relationship-entity, in which the first and third elements both represent entities, and the second element represents the relationship between the two entities. For example, in the battery ontology, it can be expressed that there is a charging relationship between battery A (entity) and charger B (entity).

[0069] S303: Establish a battery knowledge graph based on the logical relationship between the battery keywords.

[0070] Exemplarily, the logical relationships between the battery keywords can be integrated so that the battery keywords have more dimensional relationships, which can basically cover the battery knowledge in the battery field, thereby obtaining a battery knowledge graph.

[0071] For example, the battery knowledge graph can be understood as the battery ontology, which refers to the conceptual framework or model used to describe batteries and their related properties. It covers many aspects such as the basic structure, performance parameters, working principle, and relationship with other entities (such as battery management system, electric vehicles, etc.) of the battery. By building a battery ontology, the systematic, structured and standardized management of battery field knowledge can be achieved. Building a battery knowledge graph can be seen as establishing a battery ontology.

[0072] Optionally, when building the battery body, you can build it in the following steps:

[0073] Step 1: Build knowledge hierarchy based on goals.

[0074] First, the purpose of building the battery ontology needs to be clear, for example, the purpose is to optimize battery generation and operation and maintenance strategies and improve the efficiency of fault analysis of battery data. Based on the goal, determine the battery keywords that need to be covered, such as battery type, battery status, battery parameters, etc. Then organize these battery keywords into a hierarchical structure. For example, "battery" is a top-level concept, under which there can be subcategories such as "lithium-ion battery" and "lead-acid battery".

[0075] Step 2: Determine the approximate main structure.

[0076] First, choose a suitable ontology description language, such as Resource Description Framework (RDF / RDFS) and Web Ontology Language (OWL). These languages ​​provide syntax for defining classes and attributes, establishing relationships, and other functions. And design classes (Class) and subclasses (SubClass) based on the hierarchical relationship. Then determine the relationship between the classes, such as the "has" relationship between "battery" and "design parameters".

[0077] Step 3: Determine the relationship between each node object.

[0078] For example, object attributes are used to connect two instances or classes, such as the relationship between "battery" and "manufacturer" can be represented by the object attribute "made by". It is necessary to clarify whether the logical relationship is directed or undirected, transitive or non-transitive, etc. Or it can be understood as determining whether the logical relationship is a specific attribution relationship, a causal relationship, or a parallel relationship.

[0079] Step 4: Add object attributes and data attributes.

[0080] Object attributes, such as the "made by..." mentioned above, connect two entities (a battery instance and a manufacturer instance). Data attributes are used to describe specific characteristics of an instance, such as "design parameters" or "battery identity ID", which connect instances and specific values. For example, the value of a design parameter is "4000mAh" and the value of a battery ID is "B12345".

[0081] Step 5: Create the ontology.

[0082] You can use ontology editing tools such as Protegé and Ontolingua to formally establish the ontology according to the designed structure, classes and attributes. If you use the ontology language (such as OWL) directly, you need to write the corresponding code file.

[0083] Step 6. Add a battery instance to verify the validity of the ontology.

[0084] According to the defined classes and attributes, a specific battery instance is created and the values ​​of the object attributes and data attributes are assigned to it. The instance is verified to ensure that it conforms to the rules and structure defined in the ontology. For example, an ontology reasoning tool can be used to check whether there are logical contradictions within the ontology. Or query and reasoning can be used to verify whether the instance meets expectations.

[0085] Step 7: Continuously iterate and optimize to eventually form a mature ontology network.

[0086] Then, the ontology structure, attributes, and instances can be adjusted according to the verification results and actual application requirements. Moreover, with the update of domain knowledge and the advancement of technology, the ontology can be continuously optimized to maintain its timeliness and accuracy. Finally, the documentation is improved to provide detailed documentation for the ontology, including the definition and usage guide of classes, attributes, and instances. The ontology is published to a suitable platform and shared with other researchers or developers to promote the exchange and reuse of knowledge.

[0087] In the embodiment of the present application, based on the battery keywords, a logical relationship between the batteries is established, and then a knowledge graph is established, so that the knowledge graph covers almost all relevant knowledge in the battery field, and can provide reference and guidance for battery production, operation and maintenance, and fault analysis.

[0088] Further, see Figure 4 , Figure 4 A flow chart of establishing the logical relationship between battery keywords is provided, which specifically includes the following steps:

[0089] S401, using each battery keyword as an index, searching a text database for a relationship description field containing at least two battery keywords.

[0090] For example, high-quality documents can be first screened out, and the document contents can be converted into text format to obtain a text database. Then, a search tool can be used to query the text database for relationship description fields containing at least two battery keywords, using each battery keyword as an index. For example, the description fields can be "low-temperature charging leads to lithium precipitation" and "The concentration of EC limited the growth rate of SEIs".

[0091] S402: Establishing a logical relationship between battery keywords based on the found relationship description fields.

[0092] Furthermore, the logical relationship between the battery keywords can be established based on the relationship description fields found. For example, the causal relationship between low temperature and lithium precipitation can be established based on the relationship description field "low temperature charging leads to lithium precipitation"; the corresponding relationship between the concentration of EC and the growth rate of SEIs can be established based on the relationship description field "The concentration of EC limited the growth rate of SEIs".

[0093] In an embodiment of the present application, a feasible method for establishing a logical relationship between battery keywords by querying a relationship description field in a text database is provided, so that the established logical relationship between the battery keywords has a basis to follow, thereby improving the reliability of establishing the logical relationship between the battery keywords.

[0094] Furthermore, the embodiment of the present application provides an implementable method for updating the established logical relationship between battery keywords, which can further improve the established logical relationship between battery keywords.

[0095] For example, see Figure 5 , Figure 5 A flowchart for updating the logical relationship between battery keywords is provided, which specifically includes the following steps:

[0096] S501, obtaining real-time battery operation and maintenance data of batteries of each candidate battery model.

[0097] Exemplarily, the real-time battery operation and maintenance data of the batteries of each candidate battery model may be stored, and a uniform resource identifier (URI) may be generated from the storage address, and the real-time battery operation and maintenance data of the batteries of each candidate battery model may be obtained by calling the URI.

[0098] S502: updating the logical relationship between the battery keywords according to the real-time battery operation and maintenance data of the batteries of the candidate battery models.

[0099] Furthermore, by analyzing the real-time battery operation and maintenance data of the batteries of each candidate battery model, the logical relationship between the battery keywords can be obtained, and then the logical relationship between the battery keywords constructed based on the relationship description field queried in the text database can be updated.

[0100] Exemplarily, a URI can be placed in the battery knowledge graph in a linked-data manner, and the URI points to the address where the real-time battery operation and maintenance data is stored. Real-time battery operation and maintenance data (such as temperature, voltage, current time data) is stored in the database and can be accessed. The model of time series data is defined in the battery knowledge graph, including the structure, type, and measurement unit of the data. The URI of the time series data set is placed in the battery knowledge graph as the address of the data set. In this way, real-time battery operation and maintenance data can be accessed when querying and reasoning through the battery knowledge graph, achieving the purpose of updating the logical relationship between each battery keyword.

[0101] In an embodiment of the present application, a feasible method is provided for updating the established logical relationship between each battery keyword based on the real-time battery operation and maintenance data of each candidate battery model, so that the established logical relationship between each battery keyword is more comprehensive, and can provide more authoritative reference and guidance for battery production, operation and maintenance, and fault analysis.

[0102] In some optional implementations, see Figure 6 , Figure 6 A schematic flow chart of adjusting the strategy for producing and maintaining the battery to be evaluated is provided, which specifically includes the following steps:

[0103] S601 , taking a candidate fault type corresponding to a candidate battery parameter that is most similar to a battery parameter of a battery to be evaluated as a target fault type.

[0104] Exemplarily, based on determining the failure probability of the battery to be evaluated, the candidate failure type corresponding to the candidate battery parameters most similar to the battery parameters of the battery to be evaluated can be used as the target failure type, and the target failure type is the type of possible failure of the battery to be evaluated.

[0105] S602: Adjust the production and maintenance strategy of the battery to be evaluated according to the failure probability and target failure type of the battery to be evaluated.

[0106] Furthermore, the production and operation strategies of the battery to be evaluated can be adjusted according to the failure probability and target failure type of the battery to be evaluated. For example, if the battery to be evaluated is prone to aging failure under the target battery parameters, the conditions for using the battery can be adjusted, or the steps and raw materials for producing the battery can be adjusted to avoid similar failures in the same model of battery to be evaluated.

[0107] In the embodiment of the present application, the strategy for producing and operating batteries of the same model as the battery to be evaluated is adjusted according to the target failure type that may occur in the battery to be evaluated, so as to avoid the same failure as the battery to be evaluated, thereby improving the quality and service life of the battery of the same model as the battery to be evaluated.

[0108] Exemplarily, an embodiment of the present application provides an example of establishing a battery knowledge graph, with the purpose of establishing a battery knowledge graph by integrating data on the design and operation and maintenance of a battery production chain and battery instances to infer possible causes of failure of newly input battery instances.

[0109] First, establish a basic knowledge hierarchy relationship and determine the battery keywords that need to be covered. Then, establish a triple relationship based on the battery keywords, process the data of different links such as design and operation and maintenance through the ontology tool to achieve structured links; then establish object attributes based on battery-related knowledge to link different battery keywords. Among them, triple relationships such as "Low-temperature charging ContributeTO lithium deposition", "SEI growth OccurAt negative electrode area", and "Capacity nonlinear attenuation CausedBy lithium deposition".

[0110] For example, see Figure 7 , Figure 7 A schematic diagram of the ontology hierarchy established using the protégé tool is provided. Among them, battery keywords include aging mechanism, basic battery information, usage, negative events, vehicle model, aging area, design parameters, nominal voltage, battery system, manufacturer, battery ID, production location and factory capacity. The battery design parameters are divided into full battery, positive electrode, negative electrode and separator. The positive electrode includes binder, geometric parameters, conductive agent and structural parameters.

[0111] For example, see Figure 8 , Figure 8 A schematic diagram of the relationship between design parameters of a battery is provided. The full battery in the design parameters includes the total volume, total thickness and total mass. The geometric parameters in the positive electrode in the design parameters include the single-sided coating thickness, the current collector thickness, the coating area, the coating width, the coating length and the number of pole pieces; the binder in the positive electrode in the design parameters includes the binder specific gravity and the binder density; the structural parameters in the positive electrode in the design parameters include the tortuosity, porosity, surface capacity and surface loading.

[0112] Exemplarily, a battery example may be added to the battery knowledge graph, and the relationship between the data in the battery example may be constructed based on the battery knowledge graph to verify the battery knowledge graph.

[0113] Exemplarily, when performing fault analysis on a battery to be evaluated, the target battery parameters of the battery to be evaluated can be mapped to the classes and attributes of the battery knowledge graph. The cause of the fault is then determined through the inference engine. For example, the target battery parameters of the battery to be evaluated include a battery ID of 202302140029, and its additional description is "This battery showed linear decrease in capacity and charged at low temperature". Through the query statement, reasoning is performed through the battery knowledge graph to obtain the target fault type and fault probability of the battery to be evaluated that may fail.

[0114] The above embodiments are only used as examples. As the number of instances increases, more batteries can be included in the battery knowledge graph for management. During reasoning, the probability of the aging mechanism can be further output with the help of machine learning methods such as regression analysis. In addition, if the design parameters and manufacturing parameters are input for each battery instance, the correlation between the design parameters, manufacturing parameters and faults can also be analyzed. In addition, the battery knowledge graph in the embodiment of the present application links the data of each model of battery throughout its life cycle, and the battery knowledge graph can be used as a tool to provide a reference for battery generation, operation and maintenance, and fault analysis.

[0115] In an embodiment of the present application, a solution for integrating data from the entire battery chain is provided, which can structure design parameters, manufacturing parameters, and operation and maintenance data in a hierarchical manner and incorporate them all into a battery knowledge graph. Since data from different sources are integrated into a structured framework, cross-data source analysis is facilitated.

[0116] It can also effectively organize and manage battery instances based on a hierarchical structure. Based on a large amount of battery information, it can infer the causes of problems in a batch of batteries. For example, if a batch of batteries overheats under a certain working condition at the same time, then based on the differences between the design parameters and other design parameters, the cause of the failure can be found out based on the battery knowledge graph reasoning.

[0117] In addition, the battery knowledge graph unifies knowledge representation and combines it with the annotation system to facilitate the understanding of various concepts by engineers, professionals, and non-professionals in different fields. Moreover, the battery knowledge graph is computer-readable and combined with the rule engine for deep analysis and reasoning. At the same time, it is easy to apply machine learning methods to accelerate material research and development, iterate battery design, and perform fault inference.

[0118] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0119] Based on the same inventive concept, the embodiment of the present application also provides a battery analysis device for implementing the battery analysis method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more battery analysis device embodiments provided below can refer to the limitations of the battery analysis method above, and will not be repeated here.

[0120] In one embodiment, Fig. 9 As shown, a battery analysis device is provided, comprising:

[0121] An acquisition module 10 is used to acquire target battery parameters of the battery to be evaluated; wherein the target battery parameters at least include a target battery model, a target battery state and a target battery operation and maintenance data;

[0122] The determination module 20 is used to determine the failure probability of the battery to be evaluated based on the target battery parameters and the battery knowledge graph; wherein the battery knowledge graph at least includes the corresponding relationship between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes a candidate battery model, a candidate battery status and a candidate battery operation and maintenance data.

[0123] The above-mentioned battery analysis device obtains the target battery parameters of the battery to be evaluated; wherein the target battery parameters at least include the target battery model, target battery status and target battery operation and maintenance data; according to the target battery parameters and the battery knowledge graph, the failure probability of the battery to be evaluated is determined; wherein the battery knowledge graph at least includes the correspondence between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes the candidate battery model, candidate battery status and candidate battery operation and maintenance data. The above-mentioned scheme establishes a battery knowledge graph by including the correspondence between each candidate battery parameter and the candidate failure type. When performing fault analysis on the battery to be evaluated, the target battery parameters of the battery to be evaluated can be directly matched with the correspondence between each candidate battery parameter and the candidate failure type in the battery knowledge graph, and then the failure probability of the battery to be evaluated is determined according to the matching result. There is no need to use a fault diagnosis instrument to perform fault analysis, which improves the efficiency of fault analysis of the battery.

[0124] In one embodiment, the determination module 20 specifically includes:

[0125] A first determination unit, used to determine parameter similarity between the target battery parameter and each candidate battery parameter in the battery knowledge graph;

[0126] The second determining unit is used to use the maximum parameter similarity as the failure probability of the battery to be evaluated.

[0127] In one embodiment, the device further comprises a building block, specifically configured to:

[0128] Determine the battery keywords corresponding to each candidate battery model in the battery life cycle; wherein the battery keywords at least include candidate battery parameters and candidate fault types; establish logical relationships between the battery keywords; wherein the logical relationships include at least one of attribution relationships, causal relationships, and parallel relationships; based on the logical relationships between the battery keywords, establish a battery knowledge graph.

[0129] In one embodiment, the building block is specifically used to:

[0130] Using each battery keyword as an index, a text database is searched for a relationship description field containing at least two battery keywords; and a logical relationship between each battery keyword is established based on the found relationship description field.

[0131] In one embodiment, the device further includes an updating module, specifically configured to:

[0132] Real-time battery operation and maintenance data of batteries of each candidate battery model is obtained; and logical relationships between battery keywords are updated according to the real-time battery operation and maintenance data of batteries of each candidate battery model.

[0133] In one embodiment, the device further includes an adjustment module, specifically configured to:

[0134] The candidate fault type corresponding to the candidate battery parameters that are most similar to the battery parameters of the battery to be evaluated is used as the target fault type; according to the failure probability of the battery to be evaluated and the target fault type, the production and operation and maintenance strategy of the battery to be evaluated is adjusted.

[0135] Each module in the above battery analysis device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0136] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.10 As shown. The computer device includes a processor, a memory and a network interface connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store battery knowledge graph data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a battery analysis method is implemented.

[0137] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0138] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0139] Obtain target battery parameters of the battery to be evaluated; wherein the target battery parameters include at least a target battery model, a target battery state, and target battery operation and maintenance data;

[0140] According to the target battery parameters and the battery knowledge graph, the failure probability of the battery to be evaluated is determined; wherein the battery knowledge graph at least includes the corresponding relationship between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes a candidate battery model, a candidate battery status and a candidate battery operation and maintenance data.

[0141] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0142] Determine the parameter similarity between the target battery parameters and the candidate battery parameters in the battery knowledge graph; take the maximum parameter similarity as the failure probability of the battery to be evaluated.

[0143] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0144] Determine the battery keywords corresponding to each candidate battery model in the battery life cycle; wherein the battery keywords at least include candidate battery parameters and candidate fault types; establish logical relationships between the battery keywords; wherein the logical relationships include at least one of attribution relationships, causal relationships, and parallel relationships; based on the logical relationships between the battery keywords, establish a battery knowledge graph.

[0145] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0146] Using each battery keyword as an index, a text database is searched for a relationship description field containing at least two battery keywords; and a logical relationship between each battery keyword is established based on the found relationship description field.

[0147] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0148] Real-time battery operation and maintenance data of batteries of each candidate battery model is obtained; and logical relationships between battery keywords are updated according to the real-time battery operation and maintenance data of batteries of each candidate battery model.

[0149] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0150] The candidate fault type corresponding to the candidate battery parameters that are most similar to the battery parameters of the battery to be evaluated is used as the target fault type; according to the failure probability of the battery to be evaluated and the target fault type, the production and operation and maintenance strategy of the battery to be evaluated is adjusted.

[0151] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0152] Obtain target battery parameters of the battery to be evaluated; wherein the target battery parameters include at least a target battery model, a target battery state, and target battery operation and maintenance data;

[0153] According to the target battery parameters and the battery knowledge graph, the failure probability of the battery to be evaluated is determined; wherein the battery knowledge graph at least includes the corresponding relationship between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes a candidate battery model, a candidate battery status and a candidate battery operation and maintenance data.

[0154] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0155] Determine the parameter similarity between the target battery parameters and the candidate battery parameters in the battery knowledge graph; take the maximum parameter similarity as the failure probability of the battery to be evaluated.

[0156] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0157] Determine the battery keywords corresponding to each candidate battery model in the battery life cycle; wherein the battery keywords at least include candidate battery parameters and candidate fault types; establish logical relationships between the battery keywords; wherein the logical relationships include at least one of attribution relationships, causal relationships, and parallel relationships; based on the logical relationships between the battery keywords, establish a battery knowledge graph.

[0158] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0159] Using each battery keyword as an index, a text database is searched for a relationship description field containing at least two battery keywords; and a logical relationship between each battery keyword is established based on the found relationship description field.

[0160] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0161] Real-time battery operation and maintenance data of batteries of each candidate battery model is obtained; and logical relationships between battery keywords are updated according to the real-time battery operation and maintenance data of batteries of each candidate battery model.

[0162] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0163] The candidate fault type corresponding to the candidate battery parameters that are most similar to the battery parameters of the battery to be evaluated is used as the target fault type; according to the failure probability of the battery to be evaluated and the target fault type, the production and operation and maintenance strategy of the battery to be evaluated is adjusted.

[0164] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0165] Obtain target battery parameters of the battery to be evaluated; wherein the target battery parameters include at least a target battery model, a target battery state, and target battery operation and maintenance data;

[0166] According to the target battery parameters and the battery knowledge graph, the failure probability of the battery to be evaluated is determined; wherein the battery knowledge graph at least includes the corresponding relationship between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes a candidate battery model, a candidate battery status and a candidate battery operation and maintenance data.

[0167] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0168] Determine the parameter similarity between the target battery parameters and the candidate battery parameters in the battery knowledge graph; take the maximum parameter similarity as the failure probability of the battery to be evaluated.

[0169] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0170] Determine the battery keywords corresponding to each candidate battery model in the battery life cycle; wherein the battery keywords at least include candidate battery parameters and candidate fault types; establish logical relationships between the battery keywords; wherein the logical relationships include at least one of attribution relationships, causal relationships, and parallel relationships; based on the logical relationships between the battery keywords, establish a battery knowledge graph.

[0171] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0172] Using each battery keyword as an index, a text database is searched for a relationship description field containing at least two battery keywords; and a logical relationship between each battery keyword is established based on the found relationship description field.

[0173] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0174] Real-time battery operation and maintenance data of batteries of each candidate battery model is obtained; and logical relationships between battery keywords are updated according to the real-time battery operation and maintenance data of batteries of each candidate battery model.

[0175] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0176] The candidate fault type corresponding to the candidate battery parameters that are most similar to the battery parameters of the battery to be evaluated is used as the target fault type; according to the failure probability of the battery to be evaluated and the target fault type, the production and operation and maintenance strategy of the battery to be evaluated is adjusted.

[0177] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0178] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0179] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0180] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A battery analysis method, characterized in that: The method comprises: Obtain target battery parameters of the battery to be evaluated; wherein the target battery parameters include at least a target battery model, a target battery state, and target battery operation and maintenance data; According to the target battery parameters and the battery knowledge graph, the failure probability of the battery to be evaluated is determined; wherein the battery knowledge graph at least includes the corresponding relationship between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes a candidate battery model, a candidate battery status and a candidate battery operation and maintenance data.

2. The method according to claim 1, characterized in that The determining, according to the target battery parameters and the battery knowledge graph, the failure probability of the battery to be evaluated, includes: Determining parameter similarity between the target battery parameter and each candidate battery parameter in the battery knowledge graph; The maximum parameter similarity is used as the failure probability of the battery to be evaluated.

3. The method according to claim 1, characterized in that The battery knowledge graph is constructed in the following way: Determine the battery keywords corresponding to the battery of each candidate battery model in the battery life cycle; wherein the battery keywords at least include candidate battery parameters and candidate fault types; Establishing a logical relationship between each battery keyword; wherein the logical relationship includes at least one of an attribution relationship, a causal relationship, and a parallel relationship; The battery knowledge graph is established based on the logical relationship between the battery keywords.

4. The method according to claim 3, characterized in that The step of establishing the logical relationship between the battery keywords includes: Using each battery keyword as an index, searching a text database for a relationship description field containing at least two battery keywords; According to the relationship description fields found, the logical relationship between the battery keywords is established.

5. The method according to claim 3, characterized in that: The method further comprises: Obtain real-time battery operation and maintenance data of batteries of each candidate battery model; The logical relationship between each battery keyword is updated according to the real-time battery operation and maintenance data of the batteries of each candidate battery model.

6. The method according to claim 2, characterized in that The method further comprises: Taking the candidate fault type corresponding to the candidate battery parameter that is most similar to the battery parameter of the battery to be evaluated as the target fault type; According to the failure probability and target failure type of the battery to be evaluated, the strategy for producing and operating the battery to be evaluated is adjusted.

7. A battery analysis device, characterized in that: The device comprises: An acquisition module, used to acquire target battery parameters of the battery to be evaluated; wherein the target battery parameters at least include a target battery model, a target battery state and a target battery operation and maintenance data; A determination module is used to determine the failure probability of the battery to be evaluated based on the target battery parameters and the battery knowledge graph; wherein the battery knowledge graph at least includes the corresponding relationship between each candidate battery parameter and the candidate failure type; each candidate battery parameter at least includes a candidate battery model, a candidate battery status and a candidate battery operation and maintenance data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images