CN111832974A - Vehicle fault early warning method and storage medium - Google Patents
Vehicle fault early warning method and storage medium Download PDFInfo
- Publication number
- CN111832974A CN111832974A CN202010738711.4A CN202010738711A CN111832974A CN 111832974 A CN111832974 A CN 111832974A CN 202010738711 A CN202010738711 A CN 202010738711A CN 111832974 A CN111832974 A CN 111832974A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- fault
- early warning
- risk
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
Abstract
The invention discloses a vehicle fault early warning method and a storage medium, comprising the following steps: s1, determining to obtain a to-be-detected fault type and a detection time range of a vehicle; s2, constructing a vehicle fault knowledge map, and defining logical relations between the system and the subsystems and between signal items; s3, generating a sample data set by a characteristic project; s4, constructing a vehicle fault early warning model; s5, verifying the accuracy of the model by performing fault early warning test on the vehicle; and S6, predicting the risk of possible failure of the vehicle according to the data change condition of the vehicle in the detection time range. The invention can quickly and accurately analyze and position the vehicle fault, pre-warn the vehicle fault, trace the source and find the reason of the fault pre-warning.
Description
Technical Field
The invention belongs to the technical field of vehicle fault early warning, and particularly relates to a vehicle fault early warning method and a storage medium.
Background
With the development of the technology level, automobiles become important transportation means for people to live. People also have higher requirements on the safety of the vehicle, and many accidents are caused by the problem of the self-failure of the vehicle. Therefore, how to analyze potential hidden trouble and early warning according to the vehicle state and fault data and to be able to check and prevent as early as possible is a main problem of safety vehicles. Effective fault diagnosis and early warning, and also provides effective support for an after-sale service system of the vehicle. Due to the complexity of the automobile structure and the electric control, the causes of the vehicle faults are diversified, complicated and randomized, and have certain uncertainty, so that the early warning of the faults is difficult.
However, in the existing vehicle fault early warning based on data analysis and algorithm models, the algorithm is automatically learned only by directly transmitting data to the algorithm model, and then early warning is performed. The method is difficult to find the reason of fault early warning and poor in interpretability. Therefore, the vehicle fault early warning method can trace back to the source and find the reason of the fault early warning while aiming at the vehicle fault early warning, and the problem which needs to be solved urgently is solved.
Disclosure of Invention
The invention aims to provide a vehicle fault early warning method and a storage medium, which can quickly and accurately analyze and position vehicle faults, early warn the vehicle faults, trace back to the source and find out the reasons of fault early warning.
The invention relates to a vehicle fault early warning method, which comprises the following steps:
s1, determining to obtain a to-be-detected fault type and a detection time range of a vehicle;
s2, constructing a vehicle fault knowledge map, and defining logical relations between the system and the subsystems and between signal items;
s3, generating a sample data set by a characteristic project;
s4, constructing a vehicle fault early warning model;
s5, verifying the accuracy of the model by performing fault early warning test on the vehicle;
and S6, predicting the risk of possible failure of the vehicle according to the data change condition of the vehicle in the detection time range.
Further, in step S2, a vehicle failure knowledge map is constructed, specifically:
the signals of the vehicle are collected and,
data mining is carried out on vehicle signals when a vehicle fault occurs, and the vehicle signals related to the vehicle fault are determined to be related signals corresponding to the vehicle fault;
and constructing the vehicle fault knowledge graph according to the corresponding relation between the vehicle fault and the associated signal.
Further, in step S3, specifically, the method includes:
combing a fault tree based on the vehicle fault knowledge map;
analyzing the existing fault data, and screening data field factors;
and cleaning the data after screening, calculating corresponding characteristic values and generating a sample data set.
Further, in step S4, specifically, the method includes:
and constructing a vehicle fault early warning model by using a Bayesian network method, and training according to the existing data.
Further, in step S5, specifically, the method includes:
and extracting a part of fault vehicle data sets as a model verification set, performing characteristic processing on original data of the model verification set, using the processed data as a model input variable, and performing percentage statistics on fault early warning after a model result is obtained to obtain the model accuracy.
Further, in step S6, specifically, the method includes:
according to the data change condition of the vehicle in the detection time range;
determining a risk category for the risk based on the predicted risk;
determining whether the vehicle needs to be pre-warned or not according to the risk category of the risk;
and finding out the fault early warning reason according to the fault early warning result and by combining the fault knowledge map.
Further, the risk categories include primary risk, secondary risk, and tertiary risk;
accumulating the number of the first-level risk, the second-level risk and the third-level risk in a preset time, wherein the higher the risk level is, the higher the risk is;
if the three-level risk occurs within the preset time, early warning is carried out on the vehicle;
and when the number of the first-level risks and/or the number of the second-level risks in the preset time reach a preset threshold value, early warning is carried out on the vehicle.
Further, in the step S1, the fault types include failure to raise high voltage, skip gun charging, automatic lowering high voltage, power limitation, and failure of starting the vehicle.
Further, in step S1, the detection time range includes any past time range of each fault data and each normal data of the vehicle.
In the present invention, a storage medium stores a computer readable program, and when the computer readable program is called by a processor, the steps of the vehicle fault early warning method according to the present invention can be implemented.
The invention has the following advantages: before data is input into a machine learning algorithm, the relation between signal data and faults is fully analyzed and mined, a fault knowledge graph which can be relied on is generated, a Bayesian network model trained based on the fault knowledge graph is more reliable, accuracy and generalization capability are stronger, and the vehicle faults can be analyzed and positioned quickly and accurately, early warning is carried out on the vehicle faults, and the reason of fault early warning can be found by tracing back.
Drawings
Fig. 1 is a flowchart in the present embodiment.
Detailed Description
The invention will be further explained with reference to the drawings.
As shown in fig. 1, in this embodiment, a vehicle fault early warning method includes the following steps:
s1, determining and obtaining the type and the detection time range of the fault to be detected of the vehicle.
And determining and acquiring vehicle data and fault flag bits of normal vehicle conditions and fault vehicle conditions of the vehicle to be detected. In this embodiment, the fault types include that high voltage cannot be applied, gun skip during charging, automatic high voltage application, power limitation, and the vehicle cannot be started. The detection period is a period of time in the past and may include any period of time data.
In this step, vehicle history data including various fault data and normal data of the vehicle is extracted from the source data.
And S2, constructing a vehicle fault knowledge map, and determining the logical relationship between the system and the subsystem as well as the signal items.
In this embodiment, a vehicle fault knowledge map is constructed, specifically as follows:
collecting vehicle signals;
data mining is carried out on vehicle signals when a vehicle fault occurs, and the vehicle signals related to the vehicle fault are determined to be related signals corresponding to the vehicle fault;
and constructing the vehicle fault knowledge graph according to the corresponding relation between the vehicle fault and the associated signal.
The basis for vehicle fault knowledge-map construction may be data acquisition of an approximately full amount of vehicle signals. And according to the definition of the vehicle fault code, combing the logical relation between the fault and the data field factors, and making a basis for constructing a bottom-layer signal knowledge map.
And combing the logical relationship between the faults according to the electrical principle and the battery property (chemical principle) through the fault grade and the electrical system architecture. Decomposing the top layer fault downwards, and establishing a correlation relationship among all factors;
in order to construct a knowledge graph system, a corresponding knowledge system needs to be constructed, namely the relationship between entities is extracted. In this embodiment, the method for constructing the knowledge system includes a manual construction method and an automatic construction method, and the vehicle fault knowledge system is perfected by combining the two methods.
Taking the pure electric vehicle incapable of being charged with high voltage and jumping a gun as an example, a manual construction method determines fault expression and associated signal abnormal expression thereof through certain experience input of a service expert.
In the whole process, specific fault concepts, attributes and relationships are listed, so that the knowledge architecture is determined, the attributes and the relationships are defined, and the process of constraint is defined:
in this embodiment, the automated construction method includes structured and unstructured knowledge data as input.
Extracting historical data of the vehicle in the source data, wherein the data comprises fault data and normal data of the vehicle;
analyzing field factors in the data, and extracting field factors which are valuable for fault early warning;
extracting fault data and associated signal item data of the charging gun jump which cannot be applied with high voltage;
using Apriori algorithm to analyze the association rule of the association signals of the same fault;
association rule analysis is the task of finding correlations in large-scale data sets, including a frequent set of items (a collection of items that often appear in a block), association rules (suggesting that there may be a strong relationship between two items).
Taking the case of the failure to have the high voltage fault as an example, the event which comprises K associated signal items and meets the minimum support degree of the failure to have the high voltage fault is a frequent K item set;
k-dimensional data item set LKThe necessary condition of the frequent item set is that all K-1 dimensional sub-item sets are also frequent item sets and are marked as LK-1；
If the K-dimensional data item set LKAny one of the K-1 dimensional subsets Lk-1If it is not a frequent item set, then the K-dimensional data item set LKNor is it the largest set of data items itself;
Lkis K-dimensional frequent item set, if all K-1-dimensional frequent item sets Lk-1In which contains LKIs less than K, then LkNot likely to be a K-dimensional set of most frequent data items;
a rule that satisfies both the minimum support threshold and the minimum confidence threshold is called a strong rule;
through iteration, retrieving all frequent item sets in the transaction database, namely item sets with the support degree not lower than a threshold value set by a user, constructing a rule meeting the minimum trust degree of the user by using the frequent item sets, and outputting the correlation degree of each signal item;
sorting the correlation degrees, and adding the field factors with high final correlation degrees into the fault knowledge graph;
thus, a relatively complete fault knowledge graph system is formed, which is programmed to analyze the relationships between the field contents, primary keys, and foreign keys in the data sheet.
And S3, generating a sample data set by using a characteristic project.
Combing a fault tree based on the vehicle fault knowledge map;
analyzing the existing fault data, and screening data field factors;
and cleaning the data after screening, calculating corresponding characteristic values and generating a sample data set.
In this embodiment, the screening includes continuous variable screening and discrete variable screening; wherein:
continuous variable screening-multiple collinearity (VIF): the method for processing the collinearity is VIF test, and the feature with the coefficient of variance expansion factor (VIF) test more than 5 is judged as the collinearity feature and is deleted.
Discrete variable screening-IV value: IV measures the predictive power of variables: the prediction capability is strong: IV is more than or equal to 0.3; IV is more than or equal to 0.1 and less than 0.3 in the prediction capability.
And after screening, performing data cleaning and corresponding characteristic value calculation to generate a sample data set.
And S4, constructing a vehicle fault early warning model.
And constructing a vehicle fault early warning model by using a Bayesian network method, and training according to the existing data.
And S5, verifying the accuracy of the model by carrying out fault early warning test on the vehicle.
And extracting a part of fault vehicle data sets as a model verification set, performing characteristic processing on original data of the model verification set, using the processed data as a model input variable, and performing percentage statistics on fault early warning after a model result is obtained to obtain the model accuracy.
And S6, predicting the possible failure risk of the vehicle.
According to the data change condition of the vehicle in the detection time range;
determining a risk category for the risk based on the predicted risk;
determining whether the vehicle needs to be pre-warned or not according to the risk category of the risk;
and finding out the fault early warning reason according to the fault early warning result and by combining the fault knowledge map.
In this embodiment, the risk categories include a first-level risk, a second-level risk, and a third-level risk. The amounts of the primary risk, the secondary risk and the tertiary risk occurring within a preset time (generally, within seven days) are respectively accumulated. The higher the risk, the higher the risk level. If the three-level risk occurs, the vehicle needs to be warned even if the number of the three-level risk is small. And if the number of the first-level risks and/or the number of the second-level risks reach a preset threshold value, early warning is carried out on the vehicle. And if the third-level risk does not occur and the first-level and second-level risk quantity does not reach the preset threshold value, the vehicle is not warned.
In this embodiment, a storage medium stores a computer readable program, and when the computer readable program is called by a processor, the steps of the vehicle fault early warning method as described in this embodiment can be implemented.
Claims (10)
1. A vehicle fault early warning method is characterized by comprising the following steps:
s1, determining to obtain a to-be-detected fault type and a detection time range of a vehicle;
s2, constructing a vehicle fault knowledge map, and defining logical relations between the system and the subsystems and between signal items;
s3, generating a sample data set by a characteristic project;
s4, constructing a vehicle fault early warning model;
s5, verifying the accuracy of the model by performing fault early warning test on the vehicle;
and S6, predicting the risk of possible failure of the vehicle according to the data change condition of the vehicle in the detection time range.
2. The vehicle fault early warning method according to claim 1, characterized in that: in step S2, a vehicle failure knowledge map is constructed, specifically:
collecting vehicle signals;
data mining is carried out on vehicle signals when a vehicle fault occurs, and the vehicle signals related to the vehicle fault are determined to be related signals corresponding to the vehicle fault;
and constructing the vehicle fault knowledge graph according to the corresponding relation between the vehicle fault and the associated signal.
3. The vehicle fault early warning method according to claim 2, characterized in that: the step S3 specifically includes:
combing a fault tree based on the vehicle fault knowledge map;
analyzing the existing fault data, and screening data field factors;
and cleaning the data after screening, calculating corresponding characteristic values and generating a sample data set.
4. The vehicle fault early warning method according to claim 3, characterized in that: the step S4 specifically includes:
and constructing a vehicle fault early warning model by using a Bayesian network method, and training according to the existing data.
5. The vehicle fault early warning method according to claim 4, wherein: the step S5 specifically includes:
and extracting a part of fault vehicle data sets as a model verification set, performing characteristic processing on original data of the model verification set, using the processed data as a model input variable, and performing percentage statistics on fault early warning after a model result is obtained to obtain the model accuracy.
6. The vehicle fault early warning method according to claim 5, characterized in that: the step S6 specifically includes:
according to the data change condition of the vehicle in the detection time range;
determining a risk category for the risk based on the predicted risk;
determining whether the vehicle needs to be pre-warned or not according to the risk category of the risk;
and finding out the fault early warning reason according to the fault early warning result and by combining the fault knowledge map.
7. The vehicle fault early warning method according to claim 6, characterized in that: the risk categories include primary risk, secondary risk, and tertiary risk;
accumulating the number of the first-level risk, the second-level risk and the third-level risk in a preset time, wherein the higher the risk level is, the higher the risk is;
if the three-level risk occurs within the preset time, early warning is carried out on the vehicle;
and when the number of the first-level risks and/or the number of the second-level risks in the preset time reach a preset threshold value, early warning is carried out on the vehicle.
8. The vehicle malfunction early warning method according to any one of claims 1 to 7, characterized in that: in the step S1, the fault types include failure to raise high voltage, gun skip during charging, automatic lowering of high voltage, power limitation, and failure to start the vehicle.
9. The vehicle fault early warning method according to claim 8, wherein: in step S1, the detection time range includes any past time range of each fault data and each normal data of the vehicle.
10. A storage medium having a computer readable program stored therein, the computer readable program when being called by a processor is capable of implementing the steps of the vehicle malfunction early warning method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010738711.4A CN111832974A (en) | 2020-07-28 | 2020-07-28 | Vehicle fault early warning method and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010738711.4A CN111832974A (en) | 2020-07-28 | 2020-07-28 | Vehicle fault early warning method and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111832974A true CN111832974A (en) | 2020-10-27 |
Family
ID=72919164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010738711.4A Pending CN111832974A (en) | 2020-07-28 | 2020-07-28 | Vehicle fault early warning method and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111832974A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112519703A (en) * | 2020-11-24 | 2021-03-19 | 深圳市元征科技股份有限公司 | Vehicle detection reminding method, system and device and readable storage medium |
| CN112699171A (en) * | 2020-12-31 | 2021-04-23 | 东软睿驰汽车技术（沈阳）有限公司 | Vehicle alarm data knowledge graph construction method and related device |
| CN113112036A (en) * | 2021-04-07 | 2021-07-13 | 东软睿驰汽车技术（沈阳）有限公司 | Data processing method and device for vehicle and computer equipment |
| CN113379053A (en) * | 2020-12-17 | 2021-09-10 | 中国人民公安大学 | Emergency response decision-making method and device and electronic equipment |
| CN116910478A (en) * | 2023-07-14 | 2023-10-20 | 西安科技大学 | Lithium ion battery accident tracing method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109460010A (en) * | 2018-12-18 | 2019-03-12 | 彩虹无线（北京）新技术有限公司 | The vehicle fault detection method, apparatus and storage medium of knowledge based map |
| CN109724812A (en) * | 2018-12-29 | 2019-05-07 | 彩虹无线（北京）新技术有限公司 | Method, apparatus, storage medium and the terminal device of vehicle trouble early warning |
| CN110033101A (en) * | 2019-03-07 | 2019-07-19 | 华中科技大学 | The Fault Diagnosis Method of Hydro-generating Unit and system of knowledge mapping based on fusion feature |
| CN110059325A (en) * | 2018-01-19 | 2019-07-26 | 罗伯特·博世有限公司 | Vehicle trouble early warning system and corresponding vehicle trouble method for early warning |
| CN110456774A (en) * | 2019-08-15 | 2019-11-15 | 中车大连机车研究所有限公司 | A kind of fault diagnosis of rapid freight transportation locomotive and prior-warning device and method |
-
2020
- 2020-07-28 CN CN202010738711.4A patent/CN111832974A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059325A (en) * | 2018-01-19 | 2019-07-26 | 罗伯特·博世有限公司 | Vehicle trouble early warning system and corresponding vehicle trouble method for early warning |
| CN109460010A (en) * | 2018-12-18 | 2019-03-12 | 彩虹无线（北京）新技术有限公司 | The vehicle fault detection method, apparatus and storage medium of knowledge based map |
| CN109724812A (en) * | 2018-12-29 | 2019-05-07 | 彩虹无线（北京）新技术有限公司 | Method, apparatus, storage medium and the terminal device of vehicle trouble early warning |
| CN110033101A (en) * | 2019-03-07 | 2019-07-19 | 华中科技大学 | The Fault Diagnosis Method of Hydro-generating Unit and system of knowledge mapping based on fusion feature |
| CN110456774A (en) * | 2019-08-15 | 2019-11-15 | 中车大连机车研究所有限公司 | A kind of fault diagnosis of rapid freight transportation locomotive and prior-warning device and method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112519703A (en) * | 2020-11-24 | 2021-03-19 | 深圳市元征科技股份有限公司 | Vehicle detection reminding method, system and device and readable storage medium |
| CN113379053A (en) * | 2020-12-17 | 2021-09-10 | 中国人民公安大学 | Emergency response decision-making method and device and electronic equipment |
| CN112699171A (en) * | 2020-12-31 | 2021-04-23 | 东软睿驰汽车技术（沈阳）有限公司 | Vehicle alarm data knowledge graph construction method and related device |
| CN113112036A (en) * | 2021-04-07 | 2021-07-13 | 东软睿驰汽车技术（沈阳）有限公司 | Data processing method and device for vehicle and computer equipment |
| CN116910478A (en) * | 2023-07-14 | 2023-10-20 | 西安科技大学 | Lithium ion battery accident tracing method and system |
| CN116910478B (en) * | 2023-07-14 | 2024-01-30 | 西安科技大学 | Lithium ion battery accident tracing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111832974A (en) | Vehicle fault early warning method and storage medium | |
| CN111241154B (en) | Storage battery fault early warning method and system based on big data | |
| KR101984730B1 (en) | Automatic predicting system for server failure and automatic predicting method for server failure | |
| CN111414477A (en) | Vehicle fault automatic diagnosis method, device and equipment | |
| KR102215107B1 (en) | Vehicle state predicting system and method based on driving data | |
| CN117196066A (en) | Intelligent operation and maintenance information analysis model | |
| CN110991668A (en) | Electric vehicle power battery monitoring data analysis method based on association rule | |
| CN114267178A (en) | Intelligent operation maintenance method and device for station | |
| CN111179591A (en) | Road network traffic time sequence characteristic data quality diagnosis and restoration method | |
| CN111191855B (en) | Water quality abnormal event identification and early warning method based on pipe network multi-element water quality time sequence data | |
| CN112836967B (en) | New energy automobile battery safety risk assessment system | |
| CN117540826A (en) | Optimization method and device of machine learning model, electronic equipment and storage medium | |
| CN117310500A (en) | Battery state classification model construction method and battery state classification method | |
| Smirnov | Intelligent decision support system for the control of complex technical systems | |
| Zhang et al. | Predicting consistent clone change | |
| CN106371030A (en) | New energy automobile battery fault diagnosis method based on uncertainty reasoning | |
| CN116061690A (en) | Safety early warning method and device in electric automobile charging process | |
| CN114879632A (en) | Multi-mode fusion vehicle fault diagnosis method and system based on big data | |
| CN112925806A (en) | Association rule-based performance degradation characteristic parameter extraction method, system, medium, and device | |
| CN111915184A (en) | Early warning method for quality of parts in automobile industry and storage medium | |
| Fransson et al. | Finding patterns in vehicle diagnostic trouble codes: A data mining study applying associative classification | |
| CN110865939A (en) | Application program quality monitoring method and device, computer equipment and storage medium | |
| CN116502156B (en) | Intelligent identification method and system for light CT abnormal state of converter station | |
| CN115599077B (en) | Vehicle fault delimiting method and device, electronic equipment and storage medium | |
| Azzalini et al. | Data Quality and Data Ethics: Towards a Trade-off Evaluation |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201027 |