CN116910478B - Lithium ion battery accident tracing method and system - Google Patents
Lithium ion battery accident tracing method and system Download PDFInfo
- Publication number
- CN116910478B CN116910478B CN202310862111.2A CN202310862111A CN116910478B CN 116910478 B CN116910478 B CN 116910478B CN 202310862111 A CN202310862111 A CN 202310862111A CN 116910478 B CN116910478 B CN 116910478B
- Authority
- CN
- China
- Prior art keywords
- accident
- tracing data
- description field
- evaluation index
- data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 229910001416 lithium ion Inorganic materials 0.000 title claims abstract description 36
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 title claims abstract description 35
- 238000011156 evaluation Methods 0.000 claims abstract description 235
- 238000012545 processing Methods 0.000 claims abstract description 165
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 85
- 238000001514 detection method Methods 0.000 claims abstract description 47
- 238000004458 analytical method Methods 0.000 claims abstract description 38
- 230000006835 compression Effects 0.000 claims description 53
- 238000007906 compression Methods 0.000 claims description 53
- 238000005457 optimization Methods 0.000 claims description 51
- 230000007704 transition Effects 0.000 claims description 31
- 238000007405 data analysis Methods 0.000 claims description 30
- 230000008569 process Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 2
- 238000011282 treatment Methods 0.000 claims description 2
- 238000005192 partition Methods 0.000 abstract description 8
- 238000012986 modification Methods 0.000 description 7
- 230000004048 modification Effects 0.000 description 7
- 230000006872 improvement Effects 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 229910052744 lithium Inorganic materials 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 206010000369 Accident Diseases 0.000 description 1
- 241000579895 Chlorostilbon Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 239000010976 emerald Substances 0.000 description 1
- 229910052876 emerald Inorganic materials 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- ZLIBICFPKPWGIZ-UHFFFAOYSA-N pyrimethanil Chemical compound CC1=CC(C)=NC(NC=2C=CC=CC=2)=N1 ZLIBICFPKPWGIZ-UHFFFAOYSA-N 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
According to the lithium ion battery accident tracing method and system, each accident tracing data in the accident tracing data example set is provided with the corresponding local mark, the local mark can correspond to the detection item in the accident tracing data, and the local mark is used for distinguishing the local information of the detection item in the accident tracing data. In the embodiment of the disclosure, each accident tracing data in the accident tracing data example set may have a real-time partition record corresponding to the detection item corresponding to the accident tracing data example set, and according to the real-time partition record, the accuracy of the clustering result of the artificial intelligence processing thread may be compared, for example, a corresponding evaluation index may be determined. By accurately determining the evaluation index, the accuracy and the confidence of the analysis result of the lithium ion battery accident can be ensured.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a lithium ion battery accident tracing method and system.
Background
A lithium ion battery is a secondary battery (rechargeable battery) that operates mainly by means of lithium ions moving between a positive electrode and a negative electrode. Li+ is inserted and extracted back and forth between the two electrodes during charge and discharge: during charging, li+ is deintercalated from the positive electrode, and is inserted into the negative electrode through the electrolyte, and the negative electrode is in a lithium-rich state; the opposite is true when discharging.
The lithium ion battery is a very common device at present, and can provide electric energy for equipment such as electric appliances, but in the actual operation process, accidents of the lithium ion battery can be caused due to collision or overhigh temperature and the like. In the traditional technology, the accident investigation department needs to analyze the accident to obtain the cause of the accident of the lithium ion battery, so that the time is long and the labor is wasted. Therefore, a technical solution is needed to improve the above-mentioned problems.
Disclosure of Invention
In order to improve the technical problems in the related art, the application provides a lithium ion battery accident tracing method and system.
In a first aspect, a lithium ion battery accident tracing method is provided, and is applied to an accident tracing system, and the method includes: obtaining an accident tracing data example set, wherein the accident tracing data example set comprises an accident tracing data binary group consisting of the accident tracing data of the same detection item and an accident tracing data binary group consisting of the accident tracing data of different detection items; obtaining a first description field and a second description field of each accident tracing data in the accident tracing data example set, and obtaining a first clustering result by using the first description field of each accident tracing data, wherein the first description field comprises a local description field, and the second description field comprises an element description field; performing description field optimization processing on each incident tracing data binary group in the incident tracing data example set to obtain a new incident tracing data binary group, wherein the description field optimization processing is to generate new first incident tracing data by using a first description field of first incident tracing data and a second description field of second incident tracing data in the incident tracing data binary group and generate new second incident tracing data by using a second description field of the first incident tracing data and a first description field of the second incident tracing data; obtaining a first evaluation index of the first clustering result, a second evaluation index of the new accident tracing data binary group and a third evaluation index of a first description field and a second description field of the new accident tracing data binary group by using a designated artificial intelligence processing thread; and debugging accident analysis coefficients of the artificial intelligent processing thread by combining at least the first evaluation index, the second evaluation index and the third evaluation index until the specified conditions are met, and analyzing accident data corresponding to the specified conditions to obtain an accident analysis result of the lithium ion battery.
In an independent embodiment, the obtaining the first description field and the second description field of each incident tracing data in the incident tracing data example set includes: loading the X accident tracing data of the accident tracing data binary group to a local compression unit and an element compression unit of the artificial intelligent processing thread, wherein X is equal to 2; and obtaining a first description field of the X-ray source tracing data in the accident source tracing data binary group by using the local compression unit, and obtaining a second description field of the X-ray source tracing data in the accident source tracing data binary group by using the element compression unit.
In an independent embodiment, the obtaining, by using a designated artificial intelligence processing thread, the first evaluation index of the first clustering result, the second evaluation index of the new incident tracing data binary group, and the third evaluation index of the first description field and the second description field of the new incident tracing data binary group includes: obtaining a first clustering result of a first description field obtained by the local compression unit; and utilizing a first appointed artificial intelligence processing thread, and combining the first clustering result and the real-time clustering result of the input accident tracing data binary group to obtain the first evaluation index.
In an independently implemented embodiment, before loading the X-incident trace data of the incident trace data doublet to the local compression unit, the method further comprises: and preprocessing the accident tracing data set of the detection item in the X accident tracing data of the accident tracing data binary group.
In an independent embodiment, the performing the description field optimization processing on each incident tracing data tuple in the incident tracing data example set to obtain a new incident tracing data tuple includes: loading a first description field and a second description field of each accident tracing data in the accident tracing data binary group of the accident tracing data example set to a generated data analysis unit of the artificial intelligent processing thread; and executing the description field optimization processing on each accident tracing data doublet in the accident tracing data example set through the generated data analysis unit to obtain the new accident tracing data doublet.
In an independent embodiment, on the premise that the input accident tracing data tuples are the accident tracing data of the same detection item, performing description field optimization processing on each accident tracing data tuple in the accident tracing data example set to obtain a new accident tracing data tuple, including: performing a description field optimization process on the accident tracing data in the accident tracing data binary group to obtain the new accident tracing data binary group, which comprises the following steps: generating new first accident tracing data by using a first description field of the first accident tracing data and a second description field of the second accident tracing data in the accident tracing data binary group, and generating new second accident tracing data by using the second description field of the first accident tracing data and the first description field of the second accident tracing data.
In an embodiment of independent implementation, on the premise that the input accident tracing data tuples are accident tracing data of different detection matters, performing description field optimization processing on each accident tracing data tuple in the accident tracing data example set to obtain a new accident tracing data tuple, including: performing two description field optimization treatments on the accident tracing data in the accident tracing data binary group to obtain a new accident tracing data binary group, wherein the method comprises the following steps: generating new first transition accident tracing data by using a first description field of first accident tracing data and a second description field of second accident tracing data in the accident tracing data binary group, and generating new second transition accident tracing data by using the second description field of the first accident tracing data and the first description field of the second accident tracing data; generating first accident tracing data by using the first description field of the first transition accident tracing data and the second description field of the second transition accident tracing data, and generating new second accident tracing data by using the second description field of the first transition accident tracing data and the first description field of the second transition accident tracing data.
In an independent embodiment, the obtaining, by using a designated artificial intelligence processing thread, the first evaluation index of the first clustering result, the second evaluation index of the new incident tracing data binary group, and the third evaluation index of the first description field and the second description field of the new incident tracing data binary group includes: and obtaining a second evaluation index of the new accident tracing data binary group obtained through the generated data analysis unit of the artificial intelligence processing thread relative to the initial accident tracing data binary group by utilizing a second designated artificial intelligence processing thread.
In an independent embodiment, the obtaining, by using a designated artificial intelligence processing thread, the first evaluation index of the first clustering result, the second evaluation index of the new incident tracing data binary group, and the third evaluation index of the first description field and the second description field of the new incident tracing data binary group includes: and according to a third appointed artificial intelligence processing thread, obtaining a third evaluation index of the first description field and the second description field of the new accident tracing data binary group according to the first description field and the second description field of the new accident tracing data binary group and the first description field and the second description field of the corresponding initial accident tracing data binary group.
In an independent embodiment, after performing the description field optimization processing on each incident tracing data tuple in the incident tracing data example set to obtain a new incident tracing data tuple, the method further includes: loading the generated new accident tracing data binary group to an accident data identification unit of the artificial intelligent processing thread to obtain a tag description field representing the real-time degree of the new accident tracing data binary group; and obtaining a fourth evaluation index of the new accident tracing data binary group according to the tag description field by using a fourth appointed artificial intelligence processing thread.
In an independent embodiment, the debugging the accident analysis coefficients of the artificial intelligence processing thread by combining at least the first evaluation index, the second evaluation index and the third evaluation index until the specified condition is met comprises: obtaining an evaluation index of the artificial intelligence processing thread by using the first evaluation index, the second evaluation index, the third evaluation index and the fourth evaluation index; and debugging the accident analysis coefficient of the artificial intelligent processing thread by using the evaluation index of the artificial intelligent processing thread until the specified condition is met.
In an independent embodiment, the obtaining the evaluation index of the artificial intelligence processing thread by using the first evaluation index, the second evaluation index, the third evaluation index and the fourth evaluation index includes: when the accident tracing data example set loaded to the artificial intelligent processing thread is an accident tracing data binary group of the same detection item, a fifth specified artificial intelligent processing thread is utilized to obtain a first thread evaluation index of the artificial intelligent processing thread according to the first evaluation index, the second evaluation index, the third evaluation index and the fourth evaluation index; when the accident tracing data example set loaded to the artificial intelligent processing thread is an accident tracing data binary group of different detection matters, a sixth appointed artificial intelligent processing thread is utilized to obtain a second thread evaluation index of the artificial intelligent processing thread according to the first evaluation index, the second evaluation index, the third evaluation index and the fourth evaluation index; and obtaining the evaluation index of the artificial intelligent processing thread according to the splicing result of the first thread evaluation index and the second thread evaluation index.
In a second aspect, a lithium ion battery accident traceability system is provided, including a processor and a memory in communication with each other, where the processor is configured to read a computer program from the memory and execute the computer program to implement the method described above.
According to the lithium ion battery accident tracing method and system provided by the embodiment of the application, an accident tracing data example set is obtained; obtaining a first description field and a second description field of each accident tracing data in the accident tracing data example set, and obtaining a first clustering result by using the first description field of each accident tracing data, wherein the first description field comprises a local description field, and the second description field comprises an element description field; performing description field optimization processing on each incident tracing data binary group in the incident tracing data example set to obtain a new incident tracing data binary group, wherein the description field optimization processing is to generate new first incident tracing data by using a first description field of first incident tracing data and a second description field of second incident tracing data in the incident tracing data binary group and generate new second incident tracing data by using a second description field of the first incident tracing data and a first description field of the second incident tracing data; obtaining a first evaluation index of a first clustering result, a second evaluation index of a new accident tracing data binary group and a third evaluation index of a first description field and a second description field of the new accident tracing data binary group by using a designated artificial intelligence processing thread; and debugging accident analysis coefficients of the artificial intelligent processing thread by combining at least the first evaluation index, the second evaluation index and the third evaluation index until the specified conditions are met, and analyzing accident data corresponding to the specified conditions to obtain an accident analysis result of the lithium ion battery. Each accident tracing data in the accident tracing data example set of the embodiment of the disclosure has a corresponding local mark, and the local mark can correspond to a detection item in the accident tracing data and is used for distinguishing local information of the detection item in the accident tracing data. In the embodiment of the disclosure, each accident tracing data in the accident tracing data example set may have a real-time partition record corresponding to the detection item corresponding to the accident tracing data example set, and according to the real-time partition record, the accuracy of the clustering result of the artificial intelligence processing thread may be compared, for example, a corresponding evaluation index may be determined. By accurately determining the evaluation index, the accuracy and the confidence of the analysis result of the lithium ion battery accident can be ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for tracing a lithium ion battery accident according to an embodiment of the present application.
Fig. 2 is a block diagram of a lithium ion battery accident tracing device provided in an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions described above, the following detailed description of the technical solutions of the present application is provided through the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limit the technical solutions of the present application, and the technical features of the embodiments and embodiments of the present application may be combined with each other without conflict.
Referring to fig. 1, a method for tracing an accident of a lithium ion battery is shown, which may include the following STEPs STEP100-STEP 500.
STEP100: an accident tracing data example set is obtained, wherein the accident tracing data example set comprises an accident tracing data binary group consisting of the accident tracing data of the same detection item and an accident tracing data binary group consisting of the accident tracing data of different detection items.
The accident tracing data are data obtained by tracing the accident after the lithium battery has a fault accident or a fire accident and the like. Further, the detection item may be understood as an object. An incident trace data tuple can be understood as a data pair consisting of two incident trace data.
The accident tracing data example set is obtained so that the reasons for the occurrence of the accidents can be determined in the subsequent processing steps, and thus the hidden danger of the lithium ion battery which is the occurrence of the accidents can be determined, and the hidden danger problem of the traditional lithium ion battery can be solved when the lithium ion battery is maintained or the product is updated.
STEP200: obtaining a first description field and a second description field of each accident tracing data in the accident tracing data example set, and obtaining a first clustering result by using the first description field of each accident tracing data, wherein the first description field comprises a local description field, and the second description field comprises an element description field.
By way of example, the description field may be understood as a feature, which is core data obtained from the trace data, wherein the first description field may be understood as core data of an accident due to a fault, and the second description field may be understood as core data of an accident due to a fire.
The local description field may be understood as a part of contents of the description field, and the part of contents may be a key factor of an accident of the lithium ion battery.
STEP300: and performing description field optimization processing on each accident tracing data in the accident tracing data example set to obtain a new accident tracing data binary group, wherein the description field optimization processing is to generate new first accident tracing data by using a first description field of first accident tracing data and a second description field of second accident tracing data in the accident tracing data binary group and generate new second accident tracing data by using a second description field of the first accident tracing data and the first description field of the second accident tracing data.
STEP400: and obtaining a first evaluation index of the first clustering result, a second evaluation index of the new accident tracing data binary group and a third evaluation index of a first description field and a second description field of the new accident tracing data binary group by using a specified artificial intelligence processing thread.
Illustratively, the evaluation index may be understood as a loss value. In particular, the condition of data loss of the data processed by the specified artificial intelligence processing thread can be understood.
STEP500: and debugging accident analysis coefficients of the artificial intelligent processing thread at least by combining the first evaluation index, the second evaluation index and the third evaluation index until the specified conditions are met, and analyzing accident data corresponding to the specified conditions to obtain an accident analysis result of the lithium ion battery.
Illustratively, the specified condition may be understood as an error-permitting condition. The accident analysis result of the lithium ion battery can be understood as being obtained by analyzing the accident.
In the embodiment of the disclosure, when the artificial intelligence processing thread is configured by the embodiment of the disclosure, an accident tracing data example set may be input to the artificial intelligence processing thread first, where the accident tracing data example set is used as example accident tracing data for configuring the artificial intelligence processing thread. In this embodiment of the present disclosure, the set of accident tracing data examples may include two accident tracing data examples, where the first example is an accident tracing data binary group composed of different accident tracing data of the same detection item, and the second example is an accident tracing data binary group composed of different accident tracing data of different detection items, that is, in the first example, the accident tracing data in each of the accident tracing data binary groups is different accident tracing data of the same detection item, and in the second example, the accident tracing data in each of the accident tracing data binary groups is different accident tracing data of different detection items. Wherein each incident trace data doublet may include X incident trace data, such as first incident trace data and second incident trace data as described below. In addition, the embodiment of the disclosure can respectively configure the artificial intelligence processing thread by using the two types of accident tracing data examples.
Further, each incident trace data in the incident trace data example set of the embodiment of the disclosure has a corresponding local mark, where the local mark may correspond to a detection item in the incident trace data and is used to distinguish local information of the detection item in the incident trace data. In the embodiment of the disclosure, each accident tracing data in the accident tracing data example set may have a real-time partition record corresponding to the detection item corresponding to the accident tracing data example set, and according to the real-time partition record, the accuracy of the clustering result of the artificial intelligence processing thread may be compared, for example, a corresponding evaluation index may be determined; by accurately determining the evaluation index, the accuracy and the confidence of the analysis result of the lithium ion battery accident can be ensured.
After obtaining the accident traceability data example set, a specific updating step of the artificial intelligence processing thread can be executed. In STEP200, first description fields and second description fields of first incident trace data and second incident trace data of respective incident trace data tuples may first be identified. The second description field may be a description field other than the first description field, such as an element description field. The following illustrates the acquisition of a first description field and a second description field artificial intelligence processing thread.
According to STEP200 in the thread optimization method in the embodiment of the present disclosure, the obtaining the first description field and the second description field of each incident tracing data in the incident tracing data example set, and obtaining the first clustering result by using the first description field of each incident tracing data may include the following.
STEP201: and loading the X accident tracing data of the accident tracing data binary group to a local compression unit and an element compression unit of the artificial intelligent processing thread.
STEP202: and obtaining a first description field of the X-ray source tracing data in the accident source tracing data binary group by using the local compression unit, and obtaining a second description field of the X-ray source tracing data in the accident source tracing data binary group by using the element compression unit.
STEP203: and obtaining a first clustering result corresponding to the first description field by using the classification unit of the artificial intelligence processing thread.
The artificial intelligence processing thread of the embodiment of the disclosure may include a local compression unit and an element compression unit, where the local compression unit may be used to identify a local description field of a detection item in the incident tracing data, and the element compression unit may be used to identify an element description field of the detection item in the incident tracing data. Therefore, each accident tracing data binary unit in the obtained accident tracing data example set can be respectively loaded into the local compression unit and the element compression unit. The first description field of the X-ray source tracing data in the received accident source tracing data binary group can be obtained through the local compression unit, and the second description field of the X-ray source tracing data in the received accident source tracing data binary group can be obtained through the element compression unit. For example, if the X-ray source data in the input source-tracing data doublet are represented by M and N, the first description field of M obtained by the local compression unit is M1, the first description field of N obtained by the local compression unit is N1, the second description field of M obtained by the element compression unit is M2, and the second description field of N obtained by the element compression unit is N2.
After the first description field and the second description field of the X-incident tracing data in the tracing data doublet are extracted, the embodiment of the disclosure may perform the operation of classification and identification by using the first description field, and may also perform the subsequent description field optimization processing.
In addition, after the first description field and the second description field of each incident tracing data are obtained, description field optimization processing between each X incident tracing data of each incident tracing data binary group can be performed. The description field optimization processing may optimize a second description field of the first incident tracing data and a second description field of the second incident tracing data in the incident tracing data binary group, and obtain new incident tracing data based on the first description field and the optimized second description field.
Through description field optimization processing, a first description field of one accident tracing data and a second description field of another accident tracing data can be spliced to form new accident tracing data, classification is performed by using the new accident tracing data, and identification of local information based on the local description field can be effectively realized, so that interference is reduced.
STEP300 in the accident tracing data processing method in the embodiment of the present disclosure, where performing the description field optimization processing on each accident tracing data tuple in the accident tracing data example set to obtain a new accident tracing data tuple may include the following STEPs.
STEP301: and loading the accident tracing data binary groups of the accident tracing data example set to a generated data analysis unit of the artificial intelligent processing thread.
STEP302: and executing the description field optimization processing on each accident tracing data doublet in the accident tracing data example set through the generated data analysis unit to obtain the new accident tracing data doublet.
The artificial intelligence processing thread in the embodiment of the disclosure may further include a generated data analysis unit, where the generated data analysis unit may perform description field optimization processing on the first description field and the second description field obtained by the local compression unit and the element compression unit, and obtain new incident tracing data according to the optimized description field.
Illustratively, as described in the above embodiments, the incident trace data example set input by the embodiments of the present disclosure may include two types of incident trace data example sets. The accident tracing data doublet in the first example is accident tracing data of the same detection item. For the first example of the incident tracing data doublet, the embodiments of the present disclosure may perform a description field optimization process on the incident tracing data within each of the incident tracing data doublets.
For the first example, performing the description field optimization processing on each incident tracing data in the incident tracing data example set to obtain a new incident tracing data tuple may include: and performing one-time description field optimization processing on the accident tracing data in the accident tracing data binary group to obtain the new accident tracing data binary group. The process may include: generating new first accident tracing data by using the first description field of the first accident tracing data and the second description field of the second accident tracing data in each accident tracing data binary group, and generating new second accident tracing data by using the second description field of the first accident tracing data and the first description field of the second accident tracing data.
Because the X-ray incident trace data in the incident trace data doublet in the first example are different incident trace data of the same detection item, the new incident trace data obtained after the description field optimization processing is still the detection item of the same detection item. After the description field optimization processing is performed, the evaluation index of the artificial intelligence processing thread can be determined by utilizing the obtained difference between the new accident tracing data and the corresponding initial accident tracing data and the difference between the first description field and the second description field of the new accident tracing data and the first description field and the second description field of the corresponding initial accident tracing data, and the identification classification can be directly performed according to the generated new accident tracing data, at the moment, the new accident tracing data binary group which can be generated is loaded to the classification unit, and the second classification result is obtained by performing classification.
For example, the incident tracing data doublet in the first example includes the incident tracing data M and the incident tracing data N, the first description field of M may be obtained as M1 by the local compression unit, the first description field of N may be obtained as N1 by the local compression unit, the second description field of M may be obtained as M2 by the element compression unit, and the second description field of N may be obtained as N2 by the element compression unit. M and N are respectively first accident tracing data and second accident tracing data of the same detection item, and the first accident tracing data and the second accident tracing data are different. When the description field optimization process is performed, new first incident tracing data Ma may be obtained by using the first description field M1 of M and the second description field N2 of N, and new second incident tracing data Na may be obtained by using the second description field M2 of the first description field N1 of N and the second description field N1 of M.
Further, the artificial intelligence processing thread of an embodiment of the present disclosure may include a generated data analysis unit that may be configured to generate new incident trace source data from the received first description field and second description field. For example, the generated data analysis unit may include at least one convolution unit, or may also include other processing units, and the generated data analysis unit may obtain the accident tracing data corresponding to the first description field and the second description field. The optimization of the second description field and the generation of the accident tracing data based on the optimized description field can be completed through the generation thread.
Through the description field optimization processing, new data can be formed by optimizing the second description fields of the two accident tracing data, so that the description fields related to the local information and the description fields not related to the local information can be extracted successfully, and the artificial intelligence processing thread is configured through the artificial intelligence processing thread, so that the identification accuracy of the artificial intelligence processing thread to the local description fields can be improved.
In addition, the accident tracing data example set of the embodiment of the disclosure may further include a second example group, where the accident tracing data doublet is accident tracing data of different detection matters. For the incident trace data doublet in the second example, embodiments of the present disclosure may perform twice description field optimization processing on the incident trace data in each incident trace data doublet.
For the second example set, according to the thread optimization method STEP303 in the embodiment of the present disclosure, on the premise that the input incident tracing data doublet is incident tracing data of different detection items, performing description field optimization processing on each incident tracing data in the incident tracing data example set to obtain a new incident tracing data doublet may include: and performing twice description field optimization processing on the accident tracing data in the accident tracing data binary group to obtain a new accident tracing data binary group, wherein the process can comprise the following steps.
STEP3031: generating new first transition accident tracing data by using the first description field of the first accident tracing data and the second description field of the second accident tracing data in each accident tracing data binary group in the second example, and generating new second transition accident tracing data by using the second description field of the first accident tracing data and the first description field of the second accident tracing data.
STEP3032: generating first accident tracing data by using the first description field of the first transition accident tracing data and the second description field of the second transition accident tracing data, and generating new second accident tracing data by using the second description field of the first transition accident tracing data and the first description field of the second transition accident tracing data.
For example, the first description field of M is obtained by the partial compression unit as M1, the first description field of N is obtained by the partial compression unit as N1, the second description field of M is obtained by the element compression unit as M2, and the second description field of N is obtained by the element compression unit as N2.M and N are respectively first accident tracing data and second accident tracing data of different detection matters. When the first description field optimization processing is executed, new first transition accident tracing data Ma can be obtained by using the first description field M1 of M and the second description field N2 of N, and new second transition accident tracing data Na can be obtained by using the first description field N1 of N and the second description field M2 of M. Correspondingly, when the second description field optimization processing is executed, the local compression unit and the element compression unit can be used for respectively obtaining the first description field Ma1 and the second description field Ma2 of the first transition accident tracing data Ma, the first description field Na1 and the second description field Na2 of the second transition accident tracing data Na, further executing the optimization processing of the second description field Ma2 of the first transition accident tracing data Ma and the second description field Na2 of the second transition accident tracing data Na by using the generating thread, generating new first accident tracing data m″ by using the first description field Ma1 of the first transition accident tracing data Ma and the second description field Na2 of the second transition accident tracing data Na, and generating new second accident tracing data N "by using the second description field Ma2 of the first transition accident tracing data Ma and the first description field Na1 of the second transition accident tracing data Na.
After the description field optimization processing is performed, the obtained difference between the new incident tracing data and the corresponding initial incident tracing data and the difference between the first description field and the second description field of the new incident tracing data and the first description field and the second description field of the corresponding initial incident tracing data can be utilized, and meanwhile, the first description field of the new incident tracing data can be loaded to the classification unit to perform classification processing to obtain a second classification result. In the case of the first example, the second aggregate result of the first description field of the final new incident tracing data may be directly obtained, and in the case of the second example, the second aggregate result of the first description field of the final new incident tracing data may be obtained, in addition to the second aggregate result of the first description field of the final new incident tracing data, the second aggregate result of the first description field of the transition incident tracing data may also be obtained. The embodiment of the disclosure can optimize the artificial intelligence processing thread according to the second aggregation result, the difference between the new accident tracing data and the initial accident tracing data and the difference between description fields.
That is, the embodiment of the disclosure may perform feedback debugging on the artificial intelligence processing thread according to the evaluation indexes of the output results obtained by the units of the artificial intelligence processing thread, until the evaluation indexes of the artificial intelligence processing thread meet the specified conditions, for example, when the evaluation indexes are lower than the specified values of the evaluation indexes, the evaluation indexes may be determined to meet the specified conditions. The evaluation index network of the artificial intelligence processing thread according to the embodiment of the disclosure may be related to the evaluation index network of each data analysis unit, for example, may be a weighted sum of the evaluation index networks of each data analysis unit, based on which the evaluation index of each data analysis unit may be used to obtain the evaluation index of the artificial intelligence processing thread, so as to adjust the accident analysis coefficient of each unit of the artificial intelligence processing thread until the specified condition that the evaluation index is lower than the specified value of the evaluation index is met, where the specified value of the evaluation index can be set by a person skilled in the art according to the needs, and the disclosure does not specifically limit the present disclosure.
The feedback debugging process of the embodiment of the present disclosure is described in detail below.
After the first description field of each accident tracing data is obtained through the local compression unit, the classification unit may obtain a first clustering result according to the first description field. The accident tracing data processing method according to the embodiment of the present disclosure includes STEP400, where the process of obtaining the first evaluation index includes the following STEPs.
STEP401: and obtaining a first clustering result of the first description field obtained by the local compression unit.
STEP402: and utilizing a first appointed artificial intelligence processing thread, and combining the first clustering result and the real-time clustering result of the input accident tracing data binary group to obtain the first evaluation index.
As described in the foregoing embodiments, in STEP200, when obtaining the first description field of the incident tracing data in the example, the classification unit may perform classification recognition of the first description field to obtain a first clustering result corresponding to the first description field, where the first clustering result may be represented by a queue, where each element is represented by a likelihood corresponding to each local information tag, and by comparing the first clustering result with the real-time clustering result, a first comparison value may be obtained, and the embodiment of the present disclosure may determine the first comparison value as the first evaluation index. Or in other embodiments, the first clustering result and the real-time clustering result may also be loaded into the first evaluation index network of the classification unit to obtain the first evaluation index, which is not specifically limited in this disclosure.
In the embodiment of the disclosure, when the artificial intelligence processing thread is configured by the first example and the second example, the evaluation index networks adopted may be the same or may be different. In addition, according to the embodiment of the disclosure, the evaluation index of the artificial intelligence processing thread obtained through the first example configuration and the evaluation index of the artificial intelligence processing thread obtained through the second example configuration can be spliced to obtain the final evaluation index of the artificial intelligence processing thread, and the evaluation index is used for carrying out feedback debugging on the thread, wherein the accident analysis coefficients of each data analysis unit of the artificial intelligence processing thread can be debugged in the feedback debugging process, and the accident analysis coefficients of a part of units can be debugged, so that the method is not disclosed and is not particularly limited.
First, the embodiment of the disclosure may obtain, by using a first specified artificial intelligence processing thread, a first evaluation index of a first clustering result obtained by the first description field obtained by the local compression unit.
And obtaining a first evaluation index of the first clustering result through the classification unit in the artificial intelligence processing thread. The embodiment of the disclosure may perform feedback debugging on accident analysis coefficients of the local compression unit, the element compression unit and the classification unit according to the first evaluation index, or determine an overall evaluation index of the artificial intelligent processing thread according to the first evaluation index and evaluation indexes of other data analysis units, and perform unified feedback debugging on each unit of the artificial intelligent processing thread unit, which is not limited in the disclosure.
Secondly, the embodiment of the disclosure can further process the new accident tracing data binary group generated by the generated data analysis unit to obtain a second evaluation index of the new accident tracing data binary group and a third evaluation index corresponding to the description field. Wherein the artificial intelligence processing thread that determines the second evaluation index may include: and obtaining a second evaluation index of the new accident tracing data binary group obtained by the generated data analysis unit relative to the initial accident tracing data binary group by using a second designated artificial intelligence processing thread.
In the embodiment of the disclosure, a new accident tracing data binary group can be obtained through the generation thread, and the embodiment of the disclosure can determine the second evaluation index according to the difference between the new accident tracing data binary group and the initial accident tracing data binary group.
The artificial intelligence processing thread can obtain a second evaluation index corresponding to the new accident tracing data binary group generated by the generated data analysis unit for the first example.
In addition, the embodiment of the disclosure may further obtain a third evaluation index corresponding to the description field of the new second incident tracing data binary group, where the third evaluation index may be obtained by using a third specified artificial intelligence processing thread.
And obtaining a third evaluation index corresponding to the description field of the new accident tracing data binary group generated by the generated data analysis unit through the classification unit in the artificial intelligence processing thread.
Similarly, in the embodiment of the disclosure, the accident analysis coefficient of the generated data analysis unit may be feedback-debugged according to the second evaluation index and the third evaluation index, or the units of the artificial intelligence processing thread may be feedback-debugged simultaneously in combination with the first evaluation index. For example, in some possible implementations of the present disclosure, the weighted sum of the first evaluation index, the second evaluation index, and the third evaluation index may be used to obtain the evaluation index of the artificial intelligence processing thread, that is, the evaluation index network of the artificial intelligence processing thread is the weighted sum of the first evaluation index network, the second evaluation index network, and the third evaluation index network, where the weight of each evaluation index network is not specifically limited, and may be set by a person skilled in the art according to the needs. When the obtained evaluation index is larger than the evaluation index specified value, the accident analysis coefficients of the data analysis units are fed back and debugged until the evaluation index is smaller than the evaluation index specified value, the configuration can be terminated, and the artificial intelligence processing thread is optimized.
In addition, in the embodiment of the present disclosure, when the first evaluation index network, the second evaluation index network, and the third evaluation index network are configured based on the accident-tracing-data binary group of the first example, the first evaluation index network, the second evaluation index network, and the third evaluation index network may be different from each other when the accident-tracing-data binary group based on the second example is performed, but are not particularly limited to the present disclosure.
The embodiment of the disclosure can load the generated new accident tracing data binary group to the accident data identification unit of the artificial intelligence processing thread, and obtain a fourth evaluation index of the new accident tracing data binary group by using a fourth appointed artificial intelligence processing thread.
In the embodiment of the disclosure, the configuration process of the accident data identification unit may be separately executed, that is, the generated new accident tracing data and the corresponding real-time accident tracing data may be input to the accident data identification unit, and the accident data identification unit may be configured based on the fourth evaluation index network until the evaluation index corresponding to the fourth evaluation index network is lower than the evaluation index specified value required by the configuration.
In other possible embodiments, the accident data identifying unit may be configured simultaneously with the foregoing local compressing unit, element compressing unit, and generated data analyzing unit, and correspondingly, STEP400 in the embodiment of the disclosure may also obtain the evaluation index of the artificial intelligence processing thread by using the foregoing first evaluation index, second evaluation index, third evaluation index, and fourth evaluation index. That is, the evaluation index network of the artificial intelligence processing thread is a weighted sum of the first evaluation index network, the second evaluation index network, the third evaluation index network and the fourth evaluation index network, and the weight value of each evaluation index network is not specifically limited, and can be set by a person skilled in the art according to the requirements. When the obtained evaluation index is larger than the evaluation index specified value, the accident analysis coefficients of the data analysis units of the artificial intelligence processing thread are fed back and debugged until the evaluation index is smaller than the evaluation index specified value, configuration can be terminated, and the artificial intelligence processing thread is optimized.
In addition, in the embodiment of the present disclosure, when the first evaluation index network, the second evaluation index network, and the third evaluation index network are configured based on the accident-tracing-data binary group of the first example, the first evaluation index network, the second evaluation index network, and the third evaluation index network may be different from each other when the accident-tracing-data binary group based on the second pseudo-group is performed, but are not particularly limited to the present disclosure.
In the configuration process, when the obtained evaluation index is larger than the evaluation index specified value, the accident analysis coefficients of the artificial intelligent processing thread are fed back and debugged, for example, the accident analysis coefficients of each data analysis unit (a local compression unit, an element compression unit, a generated data analysis unit, an accident data identification unit and the like) can be fed back and debugged until the evaluation index of the artificial intelligent processing thread is smaller than the evaluation index specified value, the configuration can be terminated, and the optimization of the artificial intelligent processing thread is completed at the moment. Alternatively, in other embodiments, the accident analysis coefficients of the local compression unit, the element compression unit and the classification unit may be debugged according to the first evaluation index, the accident analysis coefficients of the data analysis unit may be generated by feedback debugging according to the second evaluation index and the third evaluation index, and the accident analysis coefficients of the accident data recognition unit may be debugged according to the fourth evaluation index until the evaluation index is smaller than the evaluation index specified value of the corresponding evaluation index network, that is, the configuration is terminated. That is, in the embodiment of the disclosure, feedback debugging and configuration can be performed on each unit separately, and unified debugging can be performed on each unit of the artificial intelligence processing thread through the evaluation index of the artificial intelligence processing thread, so that a person skilled in the art can select an appropriate artificial intelligence processing thread to execute the debugging process according to requirements.
In addition, in the embodiment of the present disclosure, in order to improve the recognition accuracy of the local description field of the artificial intelligence processing thread, noise may be further added to each incident tracing data before loading each incident tracing data example set into the local compression unit, for example, preprocessing an incident tracing data set of the detection item in the X incident tracing data of the incident tracing data binary group. In the embodiment of the disclosure, the artificial intelligence processing thread with the cover layer added in the part of the accident tracing data set of the detection item is used for preprocessing, and the size of the cover layer can be set by a person skilled in the art according to the requirement, so that the disclosure is not limited. It should be noted that, in the embodiment of the present disclosure, the preprocessing is performed only on the accident tracing data loaded to the local compression unit, and no noise is introduced to other data analysis units. The accuracy of local information identification of the artificial intelligence processing thread can be effectively improved through the artificial intelligence processing thread.
In order to more clearly illustrate the embodiments of the present disclosure, the configuration process of the first example and the second example is described below by way of example.
Optimizing a second description field in the binary group of the accident tracing data, obtaining optimized X-transition accident tracing data by using a generator, further obtaining a first description field and a second description field of the X-transition accident tracing data by using a local compression unit and an element compression unit, and then optimizing the second description field of the transition accident tracing data to obtain new accident tracing data. At this time, a second evaluation index corresponding to the X new accident tracing data binary set and a third evaluation index corresponding to the first description field and the second description field corresponding to the X new accident tracing data binary set may be obtained, and the transition accident tracing data or the new accident tracing data is loaded to the accident data identification unit D to obtain a fourth evaluation index. And at the moment, the first evaluation index, the second evaluation index, the third evaluation index and the fourth evaluation index can be used for obtaining the evaluation index of the artificial intelligent processing thread, and the configuration is stopped when the evaluation index is smaller than the designated value of the evaluation index, otherwise, the accident analysis coefficients of the data analysis units of the artificial intelligent processing thread are fed back and debugged.
According to the embodiment of the disclosure, the first description field (local description field) and the second description field except the first description field in the input accident tracing data can be effectively extracted, and a new picture is formed by optimizing the second description fields of the two pieces of accident tracing data, so that the description fields related to the local information and the description fields unrelated to the local information can be successfully separated, wherein the description fields related to the local information can be effectively used for pedestrian re-identification. The embodiment of the disclosure provides that no auxiliary information except the accident tracing data set is needed in the configuration and application stages, and sufficient generation supervision can be provided, and the recognition precision is effectively improved.
On the basis of the foregoing, referring to fig. 2, a lithium ion battery accident tracing apparatus 200 is provided, and the apparatus includes:
the data obtaining module 210 is configured to obtain an accident tracing data example set, where the accident tracing data example set includes an accident tracing data binary group composed of accident tracing data of the same detection item, and an accident tracing data binary group composed of accident tracing data of different detection items;
the result obtaining module 220 is configured to obtain a first description field and a second description field of each incident tracing data in the incident tracing data example set, and obtain a first clustering result by using the first description field of each incident tracing data, where the first description field includes a local description field, and the second description field includes an element description field;
the data tracing module 230 is configured to perform a description field optimization process on each incident tracing data tuple in the incident tracing data example set to obtain a new incident tracing data tuple, where the description field optimization process is to generate new first incident tracing data by using a first description field of first incident tracing data and a second description field of second incident tracing data in the incident tracing data tuple, and generate new second incident tracing data by using a second description field of the first incident tracing data and the first description field of the second incident tracing data;
The index evaluation module 240 is configured to obtain a first evaluation index of the first clustering result, a second evaluation index of the new incident tracing data binary group, and a third evaluation index of the first description field and the second description field of the new incident tracing data binary group by using a specified artificial intelligence processing thread;
the result analysis module 250 is configured to debug the accident analysis coefficient of the artificial intelligence processing thread by combining at least the first evaluation index, the second evaluation index and the third evaluation index until the accident analysis coefficient meets the specified condition, and analyze the accident data corresponding to the specified condition to obtain the accident analysis result of the lithium ion battery.
On the basis of the above, a lithium ion battery accident traceability system is shown, which comprises a processor and a memory, wherein the processor and the memory are communicated with each other, and the processor is used for reading a computer program from the memory and executing the computer program so as to realize the method.
On the basis of the above, there is also provided a computer readable storage medium on which a computer program stored which, when run, implements the above method.
In summary, based on the scheme, an accident tracing data example set is obtained; obtaining a first description field and a second description field of each accident tracing data in the accident tracing data example set, and obtaining a first clustering result by using the first description field of each accident tracing data, wherein the first description field comprises a local description field, and the second description field comprises an element description field; performing description field optimization processing on each incident tracing data binary group in the incident tracing data example set to obtain a new incident tracing data binary group, wherein the description field optimization processing is to generate new first incident tracing data by using a first description field of first incident tracing data and a second description field of second incident tracing data in the incident tracing data binary group and generate new second incident tracing data by using a second description field of the first incident tracing data and a first description field of the second incident tracing data; obtaining a first evaluation index of a first clustering result, a second evaluation index of a new accident tracing data binary group and a third evaluation index of a first description field and a second description field of the new accident tracing data binary group by using a designated artificial intelligence processing thread; and debugging accident analysis coefficients of the artificial intelligent processing thread by combining at least the first evaluation index, the second evaluation index and the third evaluation index until the specified conditions are met, and analyzing accident data corresponding to the specified conditions to obtain an accident analysis result of the lithium ion battery. Each accident tracing data in the accident tracing data example set of the embodiment of the disclosure has a corresponding local mark, and the local mark can correspond to a detection item in the accident tracing data and is used for distinguishing local information of the detection item in the accident tracing data. In the embodiment of the disclosure, each accident tracing data in the accident tracing data example set may have a real-time partition record corresponding to the detection item corresponding to the accident tracing data example set, and according to the real-time partition record, the accuracy of the clustering result of the artificial intelligence processing thread may be compared, for example, a corresponding evaluation index may be determined. By accurately determining the evaluation index, the accuracy and the confidence of the analysis result of the lithium ion battery accident can be ensured.
It should be appreciated that the systems and modules thereof shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may then be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only with hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also with software, such as executed by various types of processors, and with a combination of the above hardware circuitry and software (e.g., firmware).
It should be noted that, the advantages that may be generated by different embodiments may be different, and in different embodiments, the advantages that may be generated may be any one or a combination of several of the above, or any other possible advantages that may be obtained.
While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations of the present application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this application, and are therefore within the spirit and scope of the exemplary embodiments of this application.
Meanwhile, the present application uses specific words to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present application may be combined as suitable.
Furthermore, those skilled in the art will appreciate that the various aspects of the invention are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.
The computer storage medium may contain a propagated data signal with the computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer storage medium may be any computer readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or a combination of any of the foregoing.
The computer program code necessary for operation of portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C ++, c#, vb net, python, etc., a conventional programming language such as C language, visual Basic, fortran 2003, perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, ruby and Groovy, or other programming languages, etc. The program code may execute entirely on the user's computer or as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or the use of services such as software as a service (SaaS) in a cloud computing environment.
Furthermore, the order in which the elements and sequences are presented, the use of numerical letters, or other designations are used in the application and are not intended to limit the order in which the processes and methods of the application are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present application. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.
Likewise, it should be noted that in order to simplify the presentation disclosed herein and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the subject application. Indeed, less than all of the features of a single embodiment disclosed above.
In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the numbers allow for adaptive variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.
Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this application is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the present application, documents that are currently or later attached to this application for which the broadest scope of the claims to the present application is limited. It is noted that the descriptions, definitions, and/or terms used in the subject matter of this application are subject to such descriptions, definitions, and/or terms if they are inconsistent or conflicting with such descriptions, definitions, and/or terms.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of this application. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present application may be considered in keeping with the teachings of the present application. Accordingly, embodiments of the present application are not limited to only the embodiments explicitly described and depicted herein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (8)
1. The lithium ion battery accident tracing method is characterized by being applied to an accident tracing system, and comprises the following steps:
obtaining an accident tracing data example set, wherein the accident tracing data example set comprises an accident tracing data binary group consisting of the accident tracing data of the same detection item and an accident tracing data binary group consisting of the accident tracing data of different detection items;
obtaining a first description field and a second description field of each accident tracing data in the accident tracing data example set, and obtaining a first clustering result by using the first description field of each accident tracing data, wherein the first description field comprises a local description field, and the second description field comprises an element description field;
performing description field optimization processing on each incident tracing data binary group in the incident tracing data example set to obtain a new incident tracing data binary group, wherein the description field optimization processing is to generate new first incident tracing data by using a first description field of first incident tracing data and a second description field of second incident tracing data in the incident tracing data binary group and generate new second incident tracing data by using a second description field of the first incident tracing data and a first description field of the second incident tracing data;
Obtaining a first evaluation index of the first clustering result, a second evaluation index of the new accident tracing data binary group and a third evaluation index of a first description field and a second description field of the new accident tracing data binary group by using a designated artificial intelligence processing thread;
debugging accident analysis coefficients of the artificial intelligent processing thread by combining at least the first evaluation index, the second evaluation index and the third evaluation index until the specified conditions are met, and analyzing accident data corresponding to the specified conditions to obtain a lithium ion battery accident analysis result;
the obtaining the first description field and the second description field of each accident tracing data in the accident tracing data example set includes:
loading the X accident tracing data of the accident tracing data binary group to a local compression unit and an element compression unit of the artificial intelligent processing thread, wherein X is equal to 2;
obtaining a first description field of the X-ray source tracing data in the accident source tracing data binary group by using the local compression unit, and obtaining a second description field of the X-ray source tracing data in the accident source tracing data binary group by using the element compression unit;
The step of obtaining a first evaluation index of the first clustering result, a second evaluation index of the new accident tracing data binary group and a third evaluation index of a first description field and a second description field of the new accident tracing data binary group by using a specified artificial intelligence processing thread comprises the following steps:
obtaining a first clustering result of a first description field obtained by the local compression unit;
and utilizing a first appointed artificial intelligence processing thread, and combining the first clustering result and the real-time clustering result of the input accident tracing data binary group to obtain the first evaluation index.
2. The method of claim 1, wherein prior to loading the X incident trace data of the incident trace data doublet to the local compression unit, the method further comprises: and preprocessing the accident tracing data set of the detection item in the X accident tracing data of the accident tracing data binary group.
3. The method of claim 1, wherein performing a description field optimization process on each incident trace data tuple in the incident trace data example set to obtain a new incident trace data tuple comprises:
Loading a first description field and a second description field of each accident tracing data in the accident tracing data binary group of the accident tracing data example set to a generated data analysis unit of the artificial intelligent processing thread;
and executing the description field optimization processing on each accident tracing data doublet in the accident tracing data example set through the generated data analysis unit to obtain the new accident tracing data doublet.
4. The method of claim 1, wherein on the premise that the input incident trace data tuples are incident trace data of the same detection item, performing description field optimization processing on each incident trace data tuple in the incident trace data example set to obtain a new incident trace data tuple, including: performing a description field optimization process on the accident tracing data in the accident tracing data binary group to obtain the new accident tracing data binary group, which comprises the following steps: generating new first accident tracing data by using a first description field of the first accident tracing data and a second description field of the second accident tracing data in the accident tracing data binary group, and generating new second accident tracing data by using the second description field of the first accident tracing data and the first description field of the second accident tracing data.
5. The method of claim 1, wherein on the premise that the input accident-tracing-data tuples are accident-tracing data of different detection matters, performing description field optimization processing on each accident-tracing-data tuple in the accident-tracing-data example set to obtain a new accident tracing-data tuple, including: performing two description field optimization treatments on the accident tracing data in the accident tracing data binary group to obtain a new accident tracing data binary group, wherein the method comprises the following steps: generating new first transition accident tracing data by using a first description field of first accident tracing data and a second description field of second accident tracing data in the accident tracing data binary group, and generating new second transition accident tracing data by using the second description field of the first accident tracing data and the first description field of the second accident tracing data; generating first accident tracing data by using the first description field of the first transition accident tracing data and the second description field of the second transition accident tracing data, and generating new second accident tracing data by using the second description field of the first transition accident tracing data and the first description field of the second transition accident tracing data;
The step of obtaining a first evaluation index of the first clustering result, a second evaluation index of the new accident tracing data binary group and a third evaluation index of a first description field and a second description field of the new accident tracing data binary group by using a specified artificial intelligence processing thread comprises the following steps: and obtaining a second evaluation index of the new accident tracing data binary group obtained through the generated data analysis unit of the artificial intelligence processing thread relative to the initial accident tracing data binary group by utilizing a second designated artificial intelligence processing thread.
6. The method of claim 1, wherein obtaining, with the designated artificial intelligence processing thread, the first evaluation index of the first clustering result, the second evaluation index of the new incident tracing data tuple, and the third evaluation index of the first description field and the second description field of the new incident tracing data tuple comprises: and according to a third appointed artificial intelligence processing thread, obtaining a third evaluation index of the first description field and the second description field of the new accident tracing data binary group according to the first description field and the second description field of the new accident tracing data binary group and the first description field and the second description field of the corresponding initial accident tracing data binary group.
7. The method of claim 1, wherein after performing description field optimization processing on each incident trace data tuple in the incident trace data example set to obtain a new incident trace data tuple, the method further comprises:
loading the generated new accident tracing data binary group to an accident data identification unit of the artificial intelligent processing thread to obtain a tag description field representing the real-time degree of the new accident tracing data binary group;
obtaining a fourth evaluation index of the new accident tracing data binary group according to the tag description field by using a fourth appointed artificial intelligence processing thread;
wherein, at least, the accident analysis coefficient of the artificial intelligence processing thread is debugged by combining the first evaluation index, the second evaluation index and the third evaluation index until the accident analysis coefficient meets the specified condition, and the method comprises the following steps: obtaining an evaluation index of the artificial intelligence processing thread by using the first evaluation index, the second evaluation index, the third evaluation index and the fourth evaluation index; debugging accident analysis coefficients of the artificial intelligent processing thread by using the evaluation indexes of the artificial intelligent processing thread until the accident analysis coefficients meet specified conditions;
Wherein, the obtaining the evaluation index of the artificial intelligence processing thread by using the first evaluation index, the second evaluation index, the third evaluation index and the fourth evaluation index includes:
when the accident tracing data example set loaded to the artificial intelligent processing thread is an accident tracing data binary group of the same detection item, a fifth specified artificial intelligent processing thread is utilized to obtain a first thread evaluation index of the artificial intelligent processing thread according to the first evaluation index, the second evaluation index, the third evaluation index and the fourth evaluation index;
when the accident tracing data example set loaded to the artificial intelligent processing thread is an accident tracing data binary group of different detection matters, a sixth appointed artificial intelligent processing thread is utilized to obtain a second thread evaluation index of the artificial intelligent processing thread according to the first evaluation index, the second evaluation index, the third evaluation index and the fourth evaluation index;
and obtaining the evaluation index of the artificial intelligent processing thread according to the splicing result of the first thread evaluation index and the second thread evaluation index.
8. A lithium ion battery incident tracing system comprising a processor and a memory in communication with each other, the processor being configured to read a computer program from the memory and execute the computer program to implement the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310862111.2A CN116910478B (en) | 2023-07-14 | 2023-07-14 | Lithium ion battery accident tracing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310862111.2A CN116910478B (en) | 2023-07-14 | 2023-07-14 | Lithium ion battery accident tracing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116910478A CN116910478A (en) | 2023-10-20 |
| CN116910478B true CN116910478B (en) | 2024-01-30 |
Family
ID=88364139
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310862111.2A Active CN116910478B (en) | 2023-07-14 | 2023-07-14 | Lithium ion battery accident tracing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116910478B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118296565B (en) * | 2024-04-01 | 2024-09-13 | 娄底职业技术学院 | Power battery accident tracing management and control system based on data mining |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423414A (en) * | 2017-07-28 | 2017-12-01 | 西安交通大学 | A kind of process industry complex electromechanical systems fault source tracing method based on information transmission model |
| CN111832974A (en) * | 2020-07-28 | 2020-10-27 | 重庆长安新能源汽车科技有限公司 | Vehicle fault early warning method and storage medium |
| CN113515402A (en) * | 2021-06-08 | 2021-10-19 | 中联重科股份有限公司 | Fault information classification method and device for engineering equipment and engineering equipment |
| EP3926891A1 (en) * | 2020-06-19 | 2021-12-22 | Accenture Global Solutions Limited | Intelligent network operation platform for network fault mitigation |
| CN114461864A (en) * | 2021-12-30 | 2022-05-10 | 奇安信科技集团股份有限公司 | Alarm tracing method and device |
| CN115508672A (en) * | 2022-11-22 | 2022-12-23 | 中国电力科学研究院有限公司 | Power grid main equipment fault tracing reasoning method, system, equipment and medium |
| CN115902675A (en) * | 2022-11-25 | 2023-04-04 | 中国汽车工程研究院股份有限公司 | Power battery risk tracing method based on equivalent internal resistance consistency |
-
2023
- 2023-07-14 CN CN202310862111.2A patent/CN116910478B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423414A (en) * | 2017-07-28 | 2017-12-01 | 西安交通大学 | A kind of process industry complex electromechanical systems fault source tracing method based on information transmission model |
| EP3926891A1 (en) * | 2020-06-19 | 2021-12-22 | Accenture Global Solutions Limited | Intelligent network operation platform for network fault mitigation |
| CN111832974A (en) * | 2020-07-28 | 2020-10-27 | 重庆长安新能源汽车科技有限公司 | Vehicle fault early warning method and storage medium |
| CN113515402A (en) * | 2021-06-08 | 2021-10-19 | 中联重科股份有限公司 | Fault information classification method and device for engineering equipment and engineering equipment |
| CN114461864A (en) * | 2021-12-30 | 2022-05-10 | 奇安信科技集团股份有限公司 | Alarm tracing method and device |
| CN115508672A (en) * | 2022-11-22 | 2022-12-23 | 中国电力科学研究院有限公司 | Power grid main equipment fault tracing reasoning method, system, equipment and medium |
| CN115902675A (en) * | 2022-11-25 | 2023-04-04 | 中国汽车工程研究院股份有限公司 | Power battery risk tracing method based on equivalent internal resistance consistency |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116910478A (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116910478B (en) | Lithium ion battery accident tracing method and system | |
| CN112184508A (en) | Student model training method and device for image processing | |
| CN109633448B (en) | Method and device for identifying battery health state and terminal equipment | |
| CN112684396B (en) | Data preprocessing method and system for electric energy meter operation error monitoring model | |
| CN113378554B (en) | Intelligent interaction method and system for medical information | |
| CN112419268A (en) | Method, device, equipment and medium for detecting image defects of power transmission line | |
| CN116112746B (en) | Online education live video compression method and system | |
| CN113344079B (en) | Image tag semi-automatic labeling method, system, terminal and medium | |
| CN116737975A (en) | Public health data query method and system applied to image analysis | |
| CN116739184B (en) | Landslide prediction method and system | |
| CN112446601B (en) | Method and system for diagnosing data of uncomputable area | |
| CN115514570B (en) | Network diagnosis processing method, system and cloud platform | |
| CN115373688B (en) | Optimization method and system of software development thread and cloud platform | |
| CN115481197B (en) | Distributed data processing method, system and cloud platform | |
| CN115473822B (en) | 5G intelligent gateway data transmission method, system and cloud platform | |
| CN113626538B (en) | Medical information intelligent classification method and system based on big data | |
| CN113589700B (en) | Method and system for checking intelligent household zigbee request | |
| CN115756576B (en) | Translation method of software development kit and software development system | |
| CN113610117B (en) | Underwater sensing data processing method and system based on depth data | |
| CN115409510B (en) | Online transaction security system and method | |
| CN112418930B (en) | Test method, system and computer equipment | |
| CN114217240B (en) | Uninterruptible power supply detection method and system | |
| CN115509811B (en) | Distributed storage data recovery method, system and cloud platform | |
| US20230042838A1 (en) | Method for data processing, device, and storage medium | |
| CN115079882B (en) | Human-computer interaction processing method and system based on virtual reality |
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 |