CN117192373A - Power battery fault analysis method, device, computer equipment and storage medium - Google Patents
Power battery fault analysis method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117192373A CN117192373A CN202310994993.8A CN202310994993A CN117192373A CN 117192373 A CN117192373 A CN 117192373A CN 202310994993 A CN202310994993 A CN 202310994993A CN 117192373 A CN117192373 A CN 117192373A
- Authority
- CN
- China
- Prior art keywords
- fault
- power battery
- alarm
- determining
- item
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 61
- 230000002776 aggregation Effects 0.000 claims abstract description 55
- 238000004220 aggregation Methods 0.000 claims abstract description 55
- 230000002159 abnormal effect Effects 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 27
- 230000003993 interaction Effects 0.000 claims description 86
- 230000002452 interceptive effect Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 13
- 230000007246 mechanism Effects 0.000 claims description 12
- 238000012423 maintenance Methods 0.000 claims description 10
- 230000004931 aggregating effect Effects 0.000 claims description 8
- 238000010586 diagram Methods 0.000 description 16
- 208000032953 Device battery issue Diseases 0.000 description 14
- 239000011159 matrix material Substances 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000010845 search algorithm Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Landscapes
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The application relates to a power battery fault analysis method, a power battery fault analysis device, computer equipment and a storage medium. The method comprises the following steps: acquiring power battery fault alarm data based on a power battery fault alarm database, determining a power battery fault knowledge graph based on a power battery fault knowledge base, determining a fault knowledge aggregation abnormal pattern based on the power battery fault knowledge graph, determining a fault alarm abnormal pattern based on the power battery fault alarm data, determining a power battery fault abnormal pattern based on the fault knowledge aggregation abnormal pattern and the fault alarm abnormal pattern, determining a power battery fault evolution path and a fault item importance degree based on the power battery fault abnormal pattern, and determining a fault item analysis report based on the power battery fault evolution path and the fault item importance degree. The association relation of the power battery faults can be accurately and effectively analyzed, and meanwhile, the reliability of the power battery fault analysis is improved.
Description
Technical Field
The present application relates to the field of fault analysis technologies, and in particular, to a method and apparatus for analyzing a power battery fault, a computer device, and a storage medium.
Background
Along with the increasing market application of electric vehicles, the power battery is used as a power source of the whole vehicle, provides a power source for the electric vehicle, and is very important for maintenance of the power battery. The routine maintenance of the power battery generally comprises fault analysis and fault overhaul, and in the conventional technology, the fault analysis of the power battery generally only analyzes single faults, and cannot find the association relation and potential risk factors between the faults. Meanwhile, the power battery fault analysis mainly relies on manual experience analysis, maintenance personnel need to master comprehensive and systematic professional knowledge and business experience, and the technical problems of high manual analysis difficulty, unstable reliability and the like of the power battery caused by insufficient knowledge and experience reserves exist.
Therefore, there is a need in the related art for a way to analyze the power battery fault correlation while improving the reliability of power battery fault analysis.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a power battery failure analysis method, apparatus, computer device, and computer-readable storage medium that are capable of analyzing a power battery failure association relationship while improving reliability of power battery failure analysis.
In a first aspect, the present application provides a method for power cell failure analysis. The method comprises the following steps:
acquiring power battery fault alarm data based on a power battery fault alarm database;
determining a power battery fault knowledge graph based on a power battery fault knowledge base, and determining a fault knowledge aggregation heterogram based on the power battery fault knowledge graph, wherein the fault knowledge aggregation heterogram comprises entity nodes and topological relations among the nodes, the entity nodes are fault items, and the attribute of the entity nodes comprises a fault item theoretical feature;
determining a fault alarm heterogram based on the power battery fault alarm data, wherein the fault alarm heterogram comprises entity nodes and topological relations among the nodes, the entity nodes are fault items, the attribute of the entity nodes comprises power battery state characteristics, and the topological relations comprise fault item interaction alarm characteristics;
determining a power battery fault heterogram based on the fault knowledge aggregation heterogram and the fault alarm heterogram, wherein the power battery fault heterogram comprises entity nodes and topological relations among the nodes, the entity nodes are fault items, the attribute of the entity nodes comprises a fault item theoretical characteristic and a power battery state characteristic, and the topological relations comprise fault item interaction alarm characteristics;
Determining a power battery fault evolution path and a fault item importance based on the power battery fault heterogram;
and determining a fault item analysis report based on the power battery fault evolution path and the importance of the fault item.
Optionally, in one embodiment of the present application, the determining the fault knowledge aggregate heterogeneous map based on the power battery fault knowledge map includes:
determining source node characteristics, edge characteristics and target node characteristics based on a power battery fault knowledge graph;
determining a fault knowledge aggregation heterogram based on the source node characteristics, the edge characteristics and the target node characteristics, wherein the target node comprises a fault item, the source node comprises at least two of a fault phenomenon, a fault reason, a fault mechanism, a fault result and a maintenance scheme, and the edge characteristics comprise at least two of a phenomenon, a reason, a mechanism, a result and a scheme.
Optionally, in one embodiment of the present application, the determining the fault knowledge aggregate heterogeneous graph based on the source node feature, the edge feature and the target node feature includes:
aggregating the source node characteristics and the edge characteristics to obtain theoretical characteristics of fault items;
updating target node characteristics based on the theoretical characteristics of the fault items, and determining a battery fault knowledge aggregation iso-graph based on the target node characteristics.
Optionally, in an embodiment of the present application, the power battery fault alarm data includes cloud fault alarm data and vehicle end fault alarm data, and determining the fault alarm heterogeneous map based on the power battery fault alarm data includes:
determining cloud interaction alarm characteristics and vehicle-end interaction alarm characteristics based on cloud fault alarm data and vehicle-end fault alarm data;
and determining the total alarm characteristic based on the cloud interactive alarm characteristic and the vehicle-end interactive alarm characteristic.
Optionally, in an embodiment of the present application, the power battery fault alarm data includes cloud power battery index data and vehicle-end power battery index data, and determining the fault alarm abnormal pattern based on the power battery fault alarm data further includes:
determining the total state characteristics of the power battery based on the cloud power battery index data and the vehicle-end power battery index data;
and determining a fault alarm abnormal pattern based on the total state characteristics and the total alarm characteristics of the power battery.
Optionally, in an embodiment of the present application, the determining the cloud interaction alarm feature and the vehicle interaction alarm feature based on the cloud fault alarm data and the vehicle fault alarm data includes:
Determining cloud fault interaction alarm confidence and cloud fault alarm correlation based on cloud fault alarm data, and determining cloud interaction alarm characteristics based on the cloud fault interaction alarm confidence and the cloud fault alarm correlation;
and determining vehicle-end fault interaction alarm confidence and vehicle-end fault alarm correlation based on the vehicle-end fault alarm data, and determining vehicle-end interaction alarm characteristics based on the vehicle-end fault interaction alarm confidence and the vehicle-end fault alarm correlation.
Optionally, in one embodiment of the present application, the determining the power battery fault evolution path and the importance of the fault item based on the power battery fault profile includes:
based on the power battery fault abnormal pattern, clustering and merging to determine a power battery fault grouping sub-graph;
determining the shortest path among fault items based on the power battery fault cluster sub-graph, and determining a power battery fault evolution path;
and determining importance of fault items based on the power battery fault cluster map.
In a second aspect, the application further provides a power battery fault analysis device. The device comprises:
the data acquisition module is used for acquiring power battery fault alarm data based on the power battery fault alarm database;
The fault knowledge aggregation heterogeneous graph determining module is used for determining a power battery fault knowledge graph based on a power battery fault knowledge base, determining a fault knowledge aggregation heterogeneous graph based on the power battery fault knowledge graph, wherein the fault knowledge aggregation heterogeneous graph comprises entity nodes and topological relations among all the nodes, the entity nodes comprise fault items, and the attribute of the entity nodes comprises theoretical characteristics of the fault items;
the fault alarm abnormal pattern determining module is used for determining a fault alarm abnormal pattern based on the power battery fault alarm data, wherein the fault alarm abnormal pattern comprises entity nodes and topological relations among the nodes, the entity nodes comprise fault items, the attribute of the entity nodes comprises power battery state characteristics, and the topological relations comprise fault item interaction alarm characteristics;
the power battery fault abnormal pattern determining module is used for determining a power battery fault abnormal pattern based on the fault knowledge aggregation abnormal pattern and the fault alarm abnormal pattern, wherein the power battery fault abnormal pattern comprises entity nodes and topological relations among the nodes, the entity nodes comprise fault items, the attribute of the entity nodes comprises a fault item theoretical characteristic and a power battery state characteristic, and the topological relations comprise fault item interaction alarm characteristics;
The power battery fault analysis module is used for determining a power battery fault evolution path and a fault item importance degree based on the power battery fault heterogram;
and the fault item analysis report determining module is used for determining a fault item analysis report based on the power battery fault evolution path and the importance of the fault item.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor executing the steps of the method according to the various embodiments described above.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method described in the above embodiments.
The power battery fault analysis method, the device, the computer equipment and the storage medium firstly acquire power battery fault alarm data based on a power battery fault alarm database, then determine a power battery fault knowledge graph based on a power battery fault knowledge base, determine a fault knowledge aggregation heterogram based on the power battery fault knowledge graph, wherein the fault knowledge aggregation heterogram comprises entity nodes and topological relations among all nodes, the entity nodes are all fault items, the attributes of the entity nodes comprise theoretical characteristics of the fault items, then determine a fault alarm heterogram based on the power battery fault alarm data, the fault alarm heterogram comprises entity nodes and topological relations among all nodes, the entity nodes are all fault items, the method comprises the steps that the attributes of entity nodes comprise power battery state characteristics, the topological relation comprises fault item interaction alarm characteristics, then, a power battery fault abnormal diagram is determined based on fault knowledge aggregation abnormal diagram and fault alarm abnormal diagram, the power battery fault abnormal diagram comprises entity nodes and topological relation among all nodes, the entity nodes are all fault items, the attributes of the entity nodes comprise fault item theoretical characteristics and power battery state characteristics, the topological relation comprises fault item interaction alarm characteristics, then, a power battery fault evolution path and fault item importance degree are determined based on the power battery fault abnormal diagram, and finally, a fault item analysis report is determined based on the power battery fault evolution path and the fault item importance degree. That is, by comprehensively considering the theoretical text knowledge of the power battery faults, the possibility of interactive alarm of each fault item of the power battery, the state characteristics of the power battery during fault item alarm and other relevant information, the propagation route among the fault items and the fault items needing to be focused are determined, the association relation of the power battery faults can be accurately and effectively analyzed, and meanwhile, the reliability of power battery fault analysis is improved.
Drawings
FIG. 1 is an application environment diagram of a power cell failure analysis method in one embodiment;
FIG. 2 is a flow chart of a power cell failure analysis method in one embodiment;
FIG. 3 is a schematic diagram of a power cell failure knowledge graph in one embodiment;
FIG. 4 is a flow diagram of determining a fault knowledge aggregate iso-graph based on a power cell fault knowledge graph in one embodiment;
FIG. 5 is a flow diagram of determining shortest paths between fault terms in one embodiment;
FIG. 6 is a flow chart illustrating steps of a method for analyzing a power battery fault in one embodiment;
FIG. 7 is a schematic diagram of a fault alert profile in one embodiment;
FIG. 8 is a block diagram of a power cell failure analysis apparatus in one embodiment;
fig. 9 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The power battery fault analysis method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a power battery fault analysis method is provided, and the method is applied to the server in fig. 1 for illustration, and includes the following steps:
s201: and acquiring power battery fault alarm data based on the power battery fault alarm database.
In the embodiment of the application, firstly, power battery fault alarm data is acquired based on a power battery fault alarm database, wherein the power battery fault alarm data is alarm data obtained from a cloud power battery fault alarm database and a vehicle-end battery fault alarm database when a power battery breaks down, and comprises historical power battery fault alarm data and real-time power battery fault alarm data such as abnormal voltage, abnormal temperature rise rate and the like.
S203: determining a power battery fault knowledge graph based on a power battery fault knowledge base, and determining a fault knowledge aggregation heterogram based on the power battery fault knowledge graph, wherein the fault knowledge aggregation heterogram comprises entity nodes and topological relations among the nodes, the entity nodes are fault items, and the attribute of the entity nodes comprises a fault item theoretical feature.
In the embodiment of the application, the power battery fault knowledge graph refers to a knowledge graph created by adopting related theoretical knowledge of power battery faults, specifically, the power battery fault knowledge graph is created by obtaining related theoretical knowledge of power battery faults through a power battery fault knowledge base, and as shown in fig. 3, the power battery fault knowledge graph uses each fault item as a central node, and is connected with characteristic nodes such as fault phenomenon, fault cause, fault mechanism, fault result, maintenance scheme and the like, and corresponding related information such as phenomenon, cause, mechanism, result, maintenance scheme and the like is used as attributes of the characteristic nodes. And then, carrying out feature aggregation on each piece of fault information based on a power battery fault knowledge graph to obtain a fault knowledge aggregation heterogram, wherein the fault knowledge aggregation heterogram comprises entity nodes and topological relations among the nodes, the entity nodes are each fault item, and the attributes of the entity nodes are the theoretical features of the fault items obtained after feature aggregation.
S205: determining a fault alarm heterogram based on the power battery fault alarm data, wherein the fault alarm heterogram comprises entity nodes and topological relations among the nodes, the entity nodes are fault items, the attribute of the entity nodes comprises power battery state characteristics, and the topological relations comprise fault item interaction alarm characteristics.
In the embodiment of the application, after power battery fault alarm data are acquired, calculation is performed based on the power battery fault alarm data, and a power battery state characteristic and a fault item interaction alarm characteristic are determined, wherein the power battery state characteristic refers to the real-time state of a power battery corresponding to each fault item in alarm, and mainly represents the change of power battery index data, the fault item interaction alarm characteristic refers to the correlation of interaction alarm among each fault item, namely the possibility of another fault item alarm and the correlation between two fault items under the condition of certain fault item alarm, after that, each fault item is taken as an entity node, the power battery state characteristic is taken as an attribute of the entity node, the fault item interaction alarm characteristic is taken as an edge, so that a fault alarm heterogeneous diagram is obtained, namely the fault alarm heterogeneous diagram comprises the entity node and the topological relation among the nodes, the entity node is each fault item, the attribute of the entity node comprises the power battery state characteristic, and the topological relation comprises the fault item interaction alarm characteristic.
S207: determining a power battery fault heterogram based on the fault knowledge aggregation heterogram and the fault alarm heterogram, wherein the power battery fault heterogram comprises entity nodes and topological relations among the nodes, the entity nodes are fault items, the attribute of the entity nodes comprises a fault item theoretical characteristic and a power battery state characteristic, and the topological relations comprise fault item interaction alarm characteristics.
In the embodiment of the application, after determining the fault knowledge aggregation iso-composition and the fault alarm iso-composition, correspondingly combining nodes and edges in the fault knowledge aggregation iso-composition to obtain a power battery fault iso-composition, wherein the power battery fault iso-composition comprises entity nodes and topological relations among the nodes, the entity nodes are corresponding fault items in the fault knowledge aggregation iso-composition and the fault alarm iso-composition, the attributes of the entity nodes comprise fault item theoretical characteristics in the fault knowledge aggregation iso-composition and power battery state characteristics in the fault alarm iso-composition, and the topological relations comprise fault item interaction alarm characteristics in the fault alarm iso-composition.
S209: and determining a power battery fault evolution path and a fault item importance degree based on the power battery fault heterogram.
In the embodiment of the application, after determining the power battery fault abnormal pattern, the association relation among the fault items is obtained by analyzing the theoretical characteristics of the fault items, the state characteristics of the power battery and the interaction alarm characteristics of the fault items, and the fault evolution path and the importance degree of the fault items of the power battery are determined, wherein the fault evolution path of the power battery refers to the propagation path among the fault items which are most likely to cause alarm when a certain fault item alarms, and the importance degree of the fault item refers to the most core fault item.
S211: and determining a fault item analysis report based on the power battery fault evolution path and the importance of the fault item.
In the embodiment of the application, after the power battery fault evolution path and the importance of the fault item are determined based on the power battery fault heterogram, a fault item analysis report is determined based on the power battery fault evolution path and the importance of the fault item, and the fault item analysis report can comprise the association relation of each fault item, the fault item needing to be detected in a key way, a fault item overhauling method and the like.
In the above power battery fault analysis method, firstly, power battery fault alarm data are acquired based on a power battery fault alarm database, then, a power battery fault knowledge graph is determined based on a power battery fault knowledge base, a fault knowledge aggregation heterogram is determined based on the power battery fault knowledge graph, the fault knowledge aggregation heterogram comprises entity nodes and topological relations among all nodes, the entity nodes comprise fault items, attributes of the entity nodes comprise fault item theoretical characteristics, then, a fault alarm heterogram is determined based on the power battery fault alarm data, the fault alarm heterogram comprises entity nodes and topological relations among all nodes, the entity nodes comprise fault items, attributes of the entity nodes comprise power battery state characteristics, the topological relations comprise fault item interactive alarm characteristics, then, the power battery fault heterogram is determined based on the fault knowledge aggregation heterogram and the fault alarm heterogram, the entity nodes comprise fault items, the attributes of the entity nodes comprise fault item theoretical characteristics and the power battery state characteristics, the topological relations comprise fault item interactive fault items, and finally, the fault state characteristics are determined based on the fault item interactive alarm characteristics and the fault release path analysis is performed based on the fault item evolution fault state characteristics. That is, by comprehensively considering the theoretical text knowledge of the power battery faults, the possibility of interactive alarm of each fault item of the power battery, the state characteristics of the power battery during fault item alarm and other relevant information, the propagation route among the fault items and the fault items needing to be focused are determined, the association relation of the power battery faults can be accurately and effectively analyzed, and meanwhile, the reliability of power battery fault analysis is improved.
In one embodiment of the present application, the determining the failure knowledge aggregate heterogeneous graph based on the power battery failure knowledge graph includes:
s301: and determining the source node characteristics, the edge characteristics and the target node characteristics based on the power battery fault knowledge graph.
S303: determining a fault knowledge aggregation heterogram based on the source node characteristics, the edge characteristics and the target node characteristics, wherein the target node comprises a fault item, the source node comprises at least two of a fault phenomenon, a fault reason, a fault mechanism, a fault result and a maintenance scheme, and the edge characteristics comprise at least two of a phenomenon, a reason, a mechanism, a result and a scheme.
In one embodiment of the present application, as shown in fig. 4, firstly, word embedding operation is performed based on text knowledge in a power battery fault knowledge graph, corresponding feature tensors are obtained, source node features, edge features and target node features are obtained, and a power battery fault knowledge heterogram is constructed. And then, acquiring source node characteristics, edge characteristics and target node characteristics of each edge in the power battery fault knowledge heterogram through a message generating function, wherein the target node comprises fault items, the source node comprises at least two of a fault phenomenon, a fault reason, a fault mechanism, a fault result and a maintenance scheme, and the edge characteristics comprise at least two of a phenomenon, a reason, a mechanism, a result and a scheme. And then, taking each target node, namely the fault item as a center, carrying out message transmission on each source node connected with the target node, and aggregating the new characteristics to be assigned to the target node to form a fault knowledge aggregation heterogram.
In this embodiment, the source node feature, the edge feature and the target node feature are determined by the power battery fault knowledge graph, and the fault knowledge aggregation iso-graph is determined based on the source node feature, the edge feature and the target node feature, so that the information of the fault item node can be more abundant.
In one embodiment of the present application, the determining the fault knowledge aggregate heterogeneous graph based on the source node feature, the edge feature, and the target node feature includes:
s401: and aggregating the source node characteristics and the edge characteristics to obtain the theoretical characteristics of the fault item.
S403: updating target node characteristics based on the theoretical characteristics of the fault items, and determining a battery fault knowledge aggregation iso-graph based on the target node characteristics.
In one embodiment of the present application, after the source node characteristics, the edge characteristics, and the target node characteristics of each edge in the power battery fault knowledge iso-graph are obtained through the message generating function, they are named as u_feat, e_feat, and v_feat, respectively, as shown in fig. 4. And then, summing the characteristic tensor of the source node and the characteristic tensor of the edge, namely u_e_feature, taking the target node, namely the fault item as a center, and aggregating the sum u_e_feature of all source node characteristics and edge characteristics flowing into the target node through an aggregation function to obtain the theoretical characteristic of the fault item, namely the total_v_feature. And updating the target node characteristics based on the theoretical characteristics total_v_feature of the fault items through a node updating function, and determining a final battery fault knowledge aggregation iso-graph based on the target node characteristics.
In this embodiment, by aggregating the source node features and the edge features to obtain the theoretical features of the fault item, updating the target node features based on the theoretical features of the fault item, and determining the battery fault knowledge aggregation heterogram based on the target node features, the information of the fault item nodes can be unified in one target node, and the information of the fault item nodes can be combined with the fault alarm heterogram more effectively.
In one embodiment of the present application, the power battery fault alarm data includes cloud fault alarm data and vehicle-end fault alarm data, and determining the fault alarm heterogeneous map based on the power battery fault alarm data includes:
s501: and determining cloud interaction alarm characteristics and vehicle-end interaction alarm characteristics based on the cloud fault alarm data and the vehicle-end fault alarm data.
S503: and determining the total alarm characteristic based on the cloud interactive alarm characteristic and the vehicle-end interactive alarm characteristic.
In one embodiment of the application, the power battery fault alarm data comprises cloud fault alarm data and vehicle-end fault alarm data, wherein the vehicle-end fault alarm data refers to untreated fault alarm data which is stored in a vehicle-end battery fault alarm database and is directly acquired from a vehicle end, the cloud fault alarm data refers to processed fault alarm data which is stored in the cloud battery fault alarm database and is acquired from the vehicle end, and the fault alarm data comprises voltage abnormality, temperature rise rate abnormality, battery charge state display abnormality and the like. After the power battery fault Alarm data are obtained, cloud interaction Alarm characteristics and vehicle-end interaction Alarm characteristics, namely cloud interaction Alarm coefficients and vehicle-end interaction Alarm coefficients, are respectively determined based on the cloud fault Alarm data and the vehicle-end fault Alarm data and respectively recorded as Alarm_Coeff Cloud And Alarm_Coeff Vehicle with a frame Wherein, the interactive alarm features refer to the association relation, such as confidence, relevance and the like, among the fault items. Then, determining total Alarm characteristics based on cloud interaction Alarm characteristics and vehicle-end interaction Alarm characteristics, specifically, determining weights according to importance degrees of the cloud and the vehicle-end, respectively marking as alpha and 1-alpha, weighting and summing the two to obtain the total Alarm characteristics, namely total Alarm coefficients, and marking as Alarm_Coeff total The specific calculation mode is shown in the following formula.
Alarm_Coeff total ＝α×Alarm_Coeff Cloud +(1-α)×Alarm_Coeff Vehicle with a frame
In the embodiment, the cloud interactive alarm feature and the vehicle end interactive alarm feature are determined based on the cloud fault alarm data and the vehicle end fault alarm data, the total alarm feature is determined based on the cloud interactive alarm feature and the vehicle end interactive alarm feature, different weights are distributed to the cloud and the vehicle end according to the importance degree, and the fault alarm heterogeneous map is more reasonable.
In one embodiment of the present application, the power battery fault alarm data includes cloud power battery index data and vehicle-end power battery index data, and determining the fault alarm abnormal pattern based on the power battery fault alarm data further includes:
s601: and determining the total state characteristics of the power battery based on the cloud power battery index data and the vehicle-end power battery index data.
S603: and determining a fault alarm abnormal pattern based on the total state characteristics and the total alarm characteristics of the power battery.
In one embodiment of the application, the power battery fault alarm data comprise cloud power battery index data and vehicle-end power battery index data, which are corresponding power battery index data obtained when each fault item of the power battery alarms, wherein the power battery index data refer to each index data of a battery when a certain fault is alarmed by a vehicle, such as power battery state of charge (SOC), power battery state of health (SOH), power battery residual energy (SOE), battery pack depth of discharge (DOD), battery pressure difference consistency, battery temperature and the like. Then, based on the cloud power battery index data and the vehicle-end power battery index data, respectively, calculating modes in the cloud power battery index data and the vehicle-end power battery index data to obtain cloud power battery state characteristics and vehicle-end power battery state characteristics, and respectively recording the cloud power battery state characteristics and the vehicle-end power battery state characteristics as features Cloud And Feature Vehicle with a frame Determining weights according to importance degrees of a cloud end and a vehicle end, respectively marking the weights as alpha and 1-alpha, and obtaining the total state characteristic Feature of the power battery after weighting and summing the weights total The specific calculation mode is shown in the following formula.
Feature total ＝α×Feature Cloud +(1-α)×Feature Vehicle with a frame
And then, taking the entity node as each fault item, taking the total state characteristic of the power battery corresponding to each fault item as the entity node characteristic of the fault alarm abnormal pattern, and taking the total alarm characteristic as the edge characteristic to obtain the fault alarm abnormal pattern.
In the embodiment, the total state characteristics of the power battery are determined through the power battery index data during power battery fault alarming, and the fault alarming abnormal pattern is determined based on the total state characteristics and the total alarming characteristics of the power battery, so that the power battery fault analysis is more reliable.
In one embodiment of the present application, the determining the cloud interaction alarm feature and the vehicle interaction alarm feature based on the cloud fault alarm data and the vehicle end fault alarm data includes:
s701: determining cloud fault interaction alarm confidence and cloud fault alarm correlation based on cloud fault alarm data, and determining cloud interaction alarm characteristics based on the cloud fault interaction alarm confidence and the cloud fault alarm correlation.
S703: and determining vehicle-end fault interaction alarm confidence and vehicle-end fault alarm correlation based on the vehicle-end fault alarm data, and determining vehicle-end interaction alarm characteristics based on the vehicle-end fault interaction alarm confidence and the vehicle-end fault alarm correlation.
In one embodiment of the application, a cloud fault interaction alarm Confidence and a cloud fault alarm correlation are determined based on cloud fault alarm data, wherein the cloud fault interaction alarm Confidence refers to the frequency of another fault item alarm under the condition of a certain fault item alarm, for example, the frequency of a fault item A alarm under the condition of a fault item B alarm is calculated and recorded as a Confidence (B-A), and the calculation mode is shown as follows.
Wherein P (B) is the frequency of the fault B alarm, and P (A n B) is the frequency of the fault A and the fault B interactive alarm.
The cloud fault alarm correlation refers to the correlation among various fault items, such as the correlation of the calculated faults A and B, and is recorded asThe calculation mode is shown in the following formula.
Wherein cov (A, B) is the covariance of fault A and fault B, σ A Is the standard deviation of fault a.
And then determining vehicle-end interaction alarm characteristics, namely vehicle-end interaction alarm coefficients, based on the vehicle-end fault interaction alarm confidence and the vehicle-end fault alarm correlation. For example, the interactive Alarm coefficient of the fault A Alarm after the fault B Alarm is calculated and is marked as Alarm_Coeff (B.fwdarw.A), and the calculation mode is shown as the following formula.
And determining the vehicle-end fault interactive alarm confidence coefficient and the vehicle-end fault alarm correlation based on the vehicle-end fault alarm data and determining the vehicle-end interactive alarm characteristics based on the vehicle-end fault interactive alarm confidence coefficient and the vehicle-end fault alarm correlation by adopting the same calculation mode.
In the embodiment, the cloud fault interaction alarm confidence and the cloud fault alarm correlation are determined based on the cloud fault alarm data, the cloud interaction alarm characteristics are determined based on the cloud fault interaction alarm confidence and the cloud fault alarm correlation, the vehicle end fault interaction alarm confidence and the vehicle end fault alarm correlation are determined based on the vehicle end fault alarm data, the vehicle end interaction alarm characteristics are determined based on the vehicle end fault interaction alarm confidence and the vehicle end fault alarm correlation, the correlation among fault items and the fault interaction alarm probability are comprehensively considered, and the possibility of fault interaction alarm can be more comprehensively considered.
In one embodiment of the present application, the determining the power battery fault evolution path and the importance of the fault term based on the power battery fault profile includes:
s801: and based on the power battery fault abnormal pattern, clustering and merging to determine a power battery fault grouping sub-graph.
S803: and determining the shortest path among fault items based on the power battery fault cluster map, and determining a power battery fault evolution path.
S805: and determining importance of fault items based on the power battery fault cluster map.
In one embodiment of the application, after the power failure abnormal pattern is determined, based on the power battery failure abnormal pattern, each node in the power battery failure abnormal pattern is clustered and combined, and the power battery failure abnormal pattern is divided into a plurality of power battery failure grouping subgraphs, wherein the clustering and combining can adopt a graph convolution algorithm, a Louvain community detection algorithm and the like. And then, determining the shortest path among fault items based on the power battery fault cluster map, and determining a power battery fault evolution path, namely a power battery fault potential evolution path. Wherein, the shortest path between fault items can be determined by adopting the methods of Floyd algorithm, breadth first search algorithm, depth first search algorithm and the like. Specifically, taking the Floyd algorithm as an example, as shown in fig. 5, first, an adjacent matrix in each power battery fault cluster sub-graph is extracted, and the adjacent matrix is used as an initialization path matrix P 0 Representing the shortest distance between all nodes under the condition that any transit node does not pass through in the current subgraph, wherein the numerical value of A row and B column represents the distance from node A to node B under the current condition, counting the number of fault item nodes to be L, assigning 1 to i, traversing all fault item nodes by taking the i fault item node as the transit node, and calculating the distance between any two nodes, if the distance is smaller than P i-1 The distance in the matrix is updated in the path matrix, and the updated path matrix is used as a new path matrix P i And sequentially traversing L nodes, sequentially taking different nodes as transit nodes, updating a path matrix, and finally updating the path matrix after traversing the L nodes to be the shortest path matrix of the cluster map, namely the potential evolution path of the fault. Then, determining importance of fault items based on a power battery fault block sub-graph, namely determining importance of fault items by adopting feature vector centrality or intermediate centrality based on theoretical characteristics of fault items of entity node attributes, state characteristics of power batteries and interactive alarm characteristics of topology relation fault items, specifically taking feature vector centrality as an example, firstly, the feature vector centrality of nodes and surrounding nodes thereof The feature vector centrality of a point is an average value of feature vector centralities of other nodes adjacent to the point, and can be expressed as follows in a matrix manner:
λc＝Ac
wherein c is a vectorWherein element->For the feature vector centrality of the node i, the feature vector centrality of each node is obtained by solving the feature vector of the adjacency matrix A;
then, solving the eigenvalue lambda of the adjacent matrix A and taking the largest eigenvalue lambda max Then, solve the maximum eigenvalue lambda max Corresponding feature vector c max The element in the vector is the centrality of the feature vector of each node in the graph, and then the feature vector c is calculated max The element ordering of the corresponding label is the order of importance of the fault item.
In this embodiment, by determining the power battery fault cluster sub-graph based on the power battery fault heterogram, clustering and merging, determining the power battery fault evolution path and the importance of the fault item based on the power battery fault cluster sub-graph, and performing path evolution analysis and fault item importance analysis in the cluster sub-graph with association relation, the power battery fault evolution analysis can be more reasonable and efficient, the fault item needing to be monitored in a key way is determined, and the power battery fault analysis is more reliable.
The following describes the steps of the power cell failure analysis method according to the present application in a specific embodiment. As shown in fig. 6, first, S901 acquires power battery failure warning data based on a power battery failure warning database. And then, S903, determining a power battery fault knowledge graph based on a power battery fault knowledge base, determining a fault knowledge aggregation iso-graph based on the power battery fault knowledge graph, wherein the fault knowledge aggregation iso-graph comprises entity nodes and topological relations among all nodes, the entity nodes are all fault items, the attribute of the entity nodes comprises a fault item theoretical feature, specifically, S905-S909, determining a source node feature, an edge feature and a target node feature based on the power battery fault knowledge graph, aggregating the source node feature and the edge feature to obtain a fault item theoretical feature, updating the target node feature based on the fault item theoretical feature, and determining a battery fault knowledge aggregation iso-graph based on the target node feature.
And then, S911, determining a fault alarm heterogram based on the power battery fault alarm data, wherein the fault alarm heterogram comprises entity nodes and topological relations among the nodes, the entity nodes are fault items, the attribute of the entity nodes comprises power battery state characteristics, and the topological relations comprise fault item interaction alarm characteristics. Specifically, S913-S921 determine a cloud fault interaction alarm confidence and a cloud fault alarm correlation based on cloud fault alarm data, determine a cloud interaction alarm feature based on the cloud fault interaction alarm confidence and the cloud fault alarm correlation, determine a vehicle end fault interaction alarm confidence and a vehicle end fault alarm correlation based on vehicle end fault alarm data, determine a vehicle end interaction alarm feature based on the vehicle end fault interaction alarm confidence and the vehicle end fault alarm correlation, determine a total alarm feature based on the cloud interaction alarm feature and the vehicle end interaction alarm feature, determine a total state feature of the power battery based on the cloud power battery index data and the vehicle end power battery index data, and determine a fault alarm abnormal pattern based on the total state feature and the total alarm feature of the power battery. As shown in fig. 7, a schematic diagram of a fault Alarm abnormal pattern is shown, wherein the entity nodes of the fault Alarm abnormal pattern are each fault item, the relation edge of the fault Alarm abnormal pattern is the total Alarm feature, for example, the relation edge from the node B of the fault item to the node a of the fault item is alarm_coeff total (B.fwdarw.A) the relation edge from the node of the fault item A to the node of the fault item B is Alarm_Coeff total (A.fwdarw.B) the node attribute of the fault alert profile is the power cell total state Feature, e.g., the attribute of the fault term node A is Feature total (A)。
And S923, determining a power battery fault heterogram based on the fault knowledge aggregation heterogram and the fault alarm heterogram, wherein the power battery fault heterogram comprises entity nodes and topological relations among the nodes, the entity nodes are fault items, the attribute of the entity nodes comprises a fault item theoretical characteristic and a power battery state characteristic, and the topological relations comprise a fault item interaction alarm characteristic. And then, S925-S929, determining a power battery fault grouping sub-graph based on the power battery fault heterograms, clustering and merging, determining the shortest path among fault items based on the power battery fault grouping sub-graph, determining a power battery fault evolution path, and determining the importance of the fault items based on the power battery fault grouping sub-graph.
Finally, S933 determines a fault term analysis report based on the power cell fault evolution path and the fault term importance.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a power battery fault analysis device for realizing the power battery fault analysis method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the power battery fault analysis device or devices provided below may be referred to the limitation of the power battery fault analysis method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 8, there is provided a power battery failure analysis apparatus 800 including: a data acquisition module 801, a fault knowledge aggregation iso-composition determination module 803, a fault alert iso-composition determination module 805, a power cell fault iso-composition determination module 807, a power cell fault analysis module 809, and a fault item analysis report determination module 811, wherein:
the data acquisition module 801 is configured to acquire power battery fault alarm data based on the power battery fault alarm database.
The fault knowledge aggregation heterogeneous map determining module 803 is configured to determine a power battery fault knowledge map based on a power battery fault knowledge base, determine a fault knowledge aggregation heterogeneous map based on the power battery fault knowledge map, where the fault knowledge aggregation heterogeneous map includes entity nodes and topological relations among the nodes, the entity nodes include fault terms, and attributes of the entity nodes include theoretical features of the fault terms.
The failure alarm abnormal pattern determining module 805 is configured to determine a failure alarm abnormal pattern based on the power battery failure alarm data, where the failure alarm abnormal pattern includes entity nodes and a topological relation between the nodes, the entity nodes include failure terms, an attribute of the entity nodes includes a power battery state feature, and the topological relation includes a failure term interaction alarm feature.
The power battery fault heterogram determining module 807 is configured to determine a power battery fault heterogram based on the fault knowledge aggregation heterogram and the fault alarm heterogram, where the power battery fault heterogram includes entity nodes and a topological relation between the nodes, the entity nodes include fault terms, attributes of the entity nodes include fault term theoretical features and power battery state features, and the topological relation includes fault term interactive alarm features.
The power battery fault analysis module 809 is configured to determine a power battery fault evolution path and a fault term importance based on the power battery fault heterogram.
The fault term analysis report determining module 811 is configured to determine a fault term analysis report based on the power battery fault evolution path and the importance of the fault term.
In one embodiment of the present application, the fault knowledge aggregate heterogeneous graph determining module is further configured to:
determining source node characteristics, edge characteristics and target node characteristics based on a power battery fault knowledge graph;
determining a fault knowledge aggregation heterogram based on the source node characteristics, the edge characteristics and the target node characteristics, wherein the target node comprises a fault item, the source node comprises at least two of a fault phenomenon, a fault reason, a fault mechanism, a fault result and a maintenance scheme, and the edge characteristics comprise at least two of a phenomenon, a reason, a mechanism, a result and a scheme.
In one embodiment of the present application, the fault knowledge aggregate heterogeneous graph determining module is further configured to:
aggregating the source node characteristics and the edge characteristics to obtain theoretical characteristics of fault items;
updating target node characteristics based on the theoretical characteristics of the fault items, and determining a battery fault knowledge aggregation iso-graph based on the target node characteristics.
In one embodiment of the present application, the power battery fault alarm data includes cloud fault alarm data and vehicle-end fault alarm data, and the fault alarm heterogeneous map determining module is further configured to:
determining cloud interaction alarm characteristics and vehicle-end interaction alarm characteristics based on cloud fault alarm data and vehicle-end fault alarm data;
And determining the total alarm characteristic based on the cloud interactive alarm characteristic and the vehicle-end interactive alarm characteristic.
In an embodiment of the present application, the power battery failure alarm data includes cloud power battery index data and vehicle-end power battery index data, and the failure alarm heterogeneous map determining module is further configured to:
determining the total state characteristics of the power battery based on the cloud power battery index data and the vehicle-end power battery index data;
and determining a fault alarm abnormal pattern based on the total state characteristics and the total alarm characteristics of the power battery.
In one embodiment of the present application, the failure alarm heterogeneous map determining module is further configured to:
determining cloud fault interaction alarm confidence and cloud fault alarm correlation based on cloud fault alarm data, and determining cloud interaction alarm characteristics based on the cloud fault interaction alarm confidence and the cloud fault alarm correlation;
and determining vehicle-end fault interaction alarm confidence and vehicle-end fault alarm correlation based on the vehicle-end fault alarm data, and determining vehicle-end interaction alarm characteristics based on the vehicle-end fault interaction alarm confidence and the vehicle-end fault alarm correlation.
In one embodiment of the application, the power battery fault analysis module is further configured to:
Based on the power battery fault abnormal pattern, clustering and merging to determine a power battery fault grouping sub-graph;
determining the shortest path among fault items based on the power battery fault cluster sub-graph, and determining a power battery fault evolution path;
and determining importance of fault items based on the power battery fault cluster map.
The above-described respective modules in the power battery failure analysis apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 9. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured 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 and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program when executed by a processor implements a power battery fault analysis method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by persons skilled in the art that the architecture shown in fig. 9 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. A method of power cell failure analysis, the method comprising:
acquiring power battery fault alarm data based on a power battery fault alarm database;
determining a power battery fault knowledge graph based on a power battery fault knowledge base, and determining a fault knowledge aggregation heterogram based on the power battery fault knowledge graph, wherein the fault knowledge aggregation heterogram comprises entity nodes and topological relations among the nodes, the entity nodes are fault items, and the attribute of the entity nodes comprises a fault item theoretical feature;
Determining a fault alarm heterogram based on the power battery fault alarm data, wherein the fault alarm heterogram comprises entity nodes and topological relations among the nodes, the entity nodes are fault items, the attribute of the entity nodes comprises power battery state characteristics, and the topological relations comprise fault item interaction alarm characteristics;
determining a power battery fault heterogram based on the fault knowledge aggregation heterogram and the fault alarm heterogram, wherein the power battery fault heterogram comprises entity nodes and topological relations among the nodes, the entity nodes are fault items, the attribute of the entity nodes comprises a fault item theoretical characteristic and a power battery state characteristic, and the topological relations comprise fault item interaction alarm characteristics;
determining a power battery fault evolution path and a fault item importance based on the power battery fault heterogram;
and determining a fault item analysis report based on the power battery fault evolution path and the importance of the fault item.
2. The method of claim 1, wherein determining a fault knowledge aggregate heterogeneous map based on a power cell fault knowledge map comprises:
determining source node characteristics, edge characteristics and target node characteristics based on a power battery fault knowledge graph;
Determining a fault knowledge aggregation heterogram based on the source node characteristics, the edge characteristics and the target node characteristics, wherein the target node comprises a fault item, the source node comprises at least two of a fault phenomenon, a fault reason, a fault mechanism, a fault result and a maintenance scheme, and the edge characteristics comprise at least two of a phenomenon, a reason, a mechanism, a result and a scheme.
3. The method of claim 2, wherein the determining a fault knowledge aggregate heterogeneous graph based on the source node feature, edge feature, and target node feature comprises:
aggregating the source node characteristics and the edge characteristics to obtain theoretical characteristics of fault items;
updating target node characteristics based on the theoretical characteristics of the fault items, and determining a battery fault knowledge aggregation iso-graph based on the target node characteristics.
4. The method of claim 1, wherein the power battery fault alert data comprises cloud fault alert data and vehicle end fault alert data, and wherein determining a fault alert heterogeneous map based on the power battery fault alert data comprises:
determining cloud interaction alarm characteristics and vehicle-end interaction alarm characteristics based on cloud fault alarm data and vehicle-end fault alarm data;
And determining the total alarm characteristic based on the cloud interactive alarm characteristic and the vehicle-end interactive alarm characteristic.
5. The method of claim 4, wherein the power battery fault alert data comprises cloud power battery index data and vehicle-side power battery index data, and wherein determining a fault alert profile based on the power battery fault alert data further comprises:
determining the total state characteristics of the power battery based on the cloud power battery index data and the vehicle-end power battery index data;
and determining a fault alarm abnormal pattern based on the total state characteristics and the total alarm characteristics of the power battery.
6. The method of claim 4, wherein determining cloud and peer interaction alert features based on cloud and peer fault alert data comprises:
determining cloud fault interaction alarm confidence and cloud fault alarm correlation based on cloud fault alarm data, and determining cloud interaction alarm characteristics based on the cloud fault interaction alarm confidence and the cloud fault alarm correlation;
and determining vehicle-end fault interaction alarm confidence and vehicle-end fault alarm correlation based on the vehicle-end fault alarm data, and determining vehicle-end interaction alarm characteristics based on the vehicle-end fault interaction alarm confidence and the vehicle-end fault alarm correlation.
7. The method of claim 1, wherein the determining a power battery fault evolution path and a fault term importance based on the power battery fault profile comprises:
based on the power battery fault abnormal pattern, clustering and merging to determine a power battery fault grouping sub-graph;
determining the shortest path among fault items based on the power battery fault cluster sub-graph, and determining a power battery fault evolution path;
and determining importance of fault items based on the power battery fault cluster map.
8. A power battery fault analysis apparatus, the apparatus comprising:
the data acquisition module is used for acquiring power battery fault alarm data based on the power battery fault alarm database;
the fault knowledge aggregation heterogeneous graph determining module is used for determining a power battery fault knowledge graph based on a power battery fault knowledge base, determining a fault knowledge aggregation heterogeneous graph based on the power battery fault knowledge graph, wherein the fault knowledge aggregation heterogeneous graph comprises entity nodes and topological relations among all the nodes, the entity nodes comprise fault items, and the attribute of the entity nodes comprises theoretical characteristics of the fault items;
The fault alarm abnormal pattern determining module is used for determining a fault alarm abnormal pattern based on the power battery fault alarm data, wherein the fault alarm abnormal pattern comprises entity nodes and topological relations among the nodes, the entity nodes comprise fault items, the attribute of the entity nodes comprises power battery state characteristics, and the topological relations comprise fault item interaction alarm characteristics;
the power battery fault abnormal pattern determining module is used for determining a power battery fault abnormal pattern based on the fault knowledge aggregation abnormal pattern and the fault alarm abnormal pattern, wherein the power battery fault abnormal pattern comprises entity nodes and topological relations among the nodes, the entity nodes comprise fault items, the attribute of the entity nodes comprises a fault item theoretical characteristic and a power battery state characteristic, and the topological relations comprise fault item interaction alarm characteristics;
the power battery fault analysis module is used for determining a power battery fault evolution path and a fault item importance degree based on the power battery fault heterogram;
and the fault item analysis report determining module is used for determining a fault item analysis report based on the power battery fault evolution path and the importance of the fault item.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310994993.8A CN117192373B (en) | 2023-08-08 | 2023-08-08 | Power battery fault analysis method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310994993.8A CN117192373B (en) | 2023-08-08 | 2023-08-08 | Power battery fault analysis method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117192373A true CN117192373A (en) | 2023-12-08 |
| CN117192373B CN117192373B (en) | 2024-05-07 |
Family
ID=89002477
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310994993.8A Active CN117192373B (en) | 2023-08-08 | 2023-08-08 | Power battery fault analysis method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117192373B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103941158A (en) * | 2014-04-17 | 2014-07-23 | 国家电网公司 | Power distribution network fault diagnosis system and method based on multi-source information |
| WO2017177077A2 (en) * | 2016-04-08 | 2017-10-12 | Cloud Knox, Inc. | Method and system to detect discrepancy in infrastructure security configurations from translated security best practice configurations in heterogeneous environments |
| US20180103052A1 (en) * | 2016-10-11 | 2018-04-12 | Battelle Memorial Institute | System and methods for automated detection, reasoning and recommendations for resilient cyber systems |
| CN109492777A (en) * | 2018-09-14 | 2019-03-19 | 国电电力宁夏新能源开发有限公司 | A kind of Wind turbines health control method based on machine learning algorithm platform |
| WO2020227429A1 (en) * | 2019-05-06 | 2020-11-12 | Strong Force Iot Portfolio 2016, Llc | Platform for facilitating development of intelligence in an industrial internet of things system |
| CN112231493A (en) * | 2020-11-10 | 2021-01-15 | 泽恩科技有限公司 | Method, device, equipment and medium for diagnosing machine room faults based on knowledge graph |
| CN112990551A (en) * | 2021-02-20 | 2021-06-18 | 国电南瑞科技股份有限公司 | Cascading failure evolution path tracing and predicting method and device based on knowledge graph |
| CN113626616A (en) * | 2021-08-25 | 2021-11-09 | 中国电子科技集团公司第三十六研究所 | Aircraft safety early warning method, device and system |
| CN114580263A (en) * | 2021-12-02 | 2022-06-03 | 国家电网有限公司信息通信分公司 | Knowledge graph-based information system fault prediction method and related equipment |
| CN115658930A (en) * | 2022-12-26 | 2023-01-31 | 中建科技集团有限公司 | Production line fault analysis method and device based on knowledge graph and storage medium |
| CN115809183A (en) * | 2022-11-21 | 2023-03-17 | 浪潮软件集团有限公司 | Method for discovering and disposing information-creating terminal fault based on knowledge graph |
| WO2023045417A1 (en) * | 2021-09-24 | 2023-03-30 | 中兴通讯股份有限公司 | Fault knowledge graph construction method and apparatus |
| CN116184209A (en) * | 2022-12-06 | 2023-05-30 | 浙江凌骁能源科技有限公司 | Early warning method and device suitable for thermal runaway of power battery |
| CN116307672A (en) * | 2022-09-08 | 2023-06-23 | 中国农业银行股份有限公司 | Fault diagnosis method, device, electronic equipment and medium |
-
2023
- 2023-08-08 CN CN202310994993.8A patent/CN117192373B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103941158A (en) * | 2014-04-17 | 2014-07-23 | 国家电网公司 | Power distribution network fault diagnosis system and method based on multi-source information |
| WO2017177077A2 (en) * | 2016-04-08 | 2017-10-12 | Cloud Knox, Inc. | Method and system to detect discrepancy in infrastructure security configurations from translated security best practice configurations in heterogeneous environments |
| US20180103052A1 (en) * | 2016-10-11 | 2018-04-12 | Battelle Memorial Institute | System and methods for automated detection, reasoning and recommendations for resilient cyber systems |
| CN109492777A (en) * | 2018-09-14 | 2019-03-19 | 国电电力宁夏新能源开发有限公司 | A kind of Wind turbines health control method based on machine learning algorithm platform |
| WO2020227429A1 (en) * | 2019-05-06 | 2020-11-12 | Strong Force Iot Portfolio 2016, Llc | Platform for facilitating development of intelligence in an industrial internet of things system |
| CN112231493A (en) * | 2020-11-10 | 2021-01-15 | 泽恩科技有限公司 | Method, device, equipment and medium for diagnosing machine room faults based on knowledge graph |
| CN112990551A (en) * | 2021-02-20 | 2021-06-18 | 国电南瑞科技股份有限公司 | Cascading failure evolution path tracing and predicting method and device based on knowledge graph |
| CN113626616A (en) * | 2021-08-25 | 2021-11-09 | 中国电子科技集团公司第三十六研究所 | Aircraft safety early warning method, device and system |
| WO2023045417A1 (en) * | 2021-09-24 | 2023-03-30 | 中兴通讯股份有限公司 | Fault knowledge graph construction method and apparatus |
| CN114580263A (en) * | 2021-12-02 | 2022-06-03 | 国家电网有限公司信息通信分公司 | Knowledge graph-based information system fault prediction method and related equipment |
| CN116307672A (en) * | 2022-09-08 | 2023-06-23 | 中国农业银行股份有限公司 | Fault diagnosis method, device, electronic equipment and medium |
| CN115809183A (en) * | 2022-11-21 | 2023-03-17 | 浪潮软件集团有限公司 | Method for discovering and disposing information-creating terminal fault based on knowledge graph |
| CN116184209A (en) * | 2022-12-06 | 2023-05-30 | 浙江凌骁能源科技有限公司 | Early warning method and device suitable for thermal runaway of power battery |
| CN115658930A (en) * | 2022-12-26 | 2023-01-31 | 中建科技集团有限公司 | Production line fault analysis method and device based on knowledge graph and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| WEI WANG 等: "KGBIAC: Knowledge Graph Based Intelligent Alert Correlation Framework", 《CYBERSPACE SAFETY AND SECURITY》, 21 October 2017 (2017-10-21), pages 523, XP047451572, DOI: 10.1007/978-3-319-69471-9_41 * |
| 张锐 等: "基于迁移学习的电网故障处置知识图谱构建及实时辅助决策研究", 《电力信息与通信技术, vol. 20, no. 6, 3 December 2022 (2022-12-03), pages 24 - 34 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117192373B (en) | 2024-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10025813B1 (en) | Distributed data transformation system | |
| US10102220B2 (en) | Activity based analytics | |
| CN111612041B (en) | Abnormal user identification method and device, storage medium and electronic equipment | |
| CN111612039B (en) | Abnormal user identification method and device, storage medium and electronic equipment | |
| TW202326537A (en) | Anti-fraud risk assessment method and device, training method and device and readable storage medium | |
| Qiao et al. | Fast outlier detection for high-dimensional data of wireless sensor networks | |
| CN114579584A (en) | Data table processing method and device, computer equipment and storage medium | |
| CN117389780A (en) | Converter station fault analysis method, device, computer equipment and storage medium | |
| CN116150507B (en) | Water army group identification method, device, equipment and medium | |
| CN117192373B (en) | Power battery fault analysis method, device, computer equipment and storage medium | |
| CN117435130A (en) | Financial data storage method, apparatus, computer device and storage medium | |
| CN116346638A (en) | Data tampering inference method based on power grid power and alarm information interaction verification | |
| JP2019105870A (en) | Discrimination program, discrimination method and discrimination device | |
| Susanto et al. | Dimensional Reduction With Fast ICA for IoT Botnet Detection | |
| CN116613754B (en) | Power distribution system reliability assessment method, model training method, device and equipment | |
| CN116881092A (en) | Method, device, equipment and storage medium for predicting alarm data | |
| CN117829287A (en) | Method, device, equipment and storage medium for evaluating performance of knowledge graph embedded model | |
| CN118152464A (en) | Regional resource index data processing method and device and computer equipment | |
| CN117764529A (en) | Target item determining method, device, computer equipment, storage medium and product | |
| CN118521040A (en) | Reliability prediction method, apparatus, device, storage medium, and program product | |
| CN118820950A (en) | Automatic determination method and device for operation result, computer equipment and storage medium | |
| CN117495128A (en) | Power consumption data prediction method, device, computer equipment and storage medium | |
| CN117437083A (en) | Power grid edge cluster monitoring method based on cloud edge fusion intelligent scheduling operation platform | |
| CN117034083A (en) | Method, device and equipment for selecting interpretation method of partial discharge classification model | |
| CN116319405A (en) | Flow data anomaly detection method and device and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |