CN114091625B - Vehicle part failure prediction method and system based on fault code sequence - Google Patents
Vehicle part failure prediction method and system based on fault code sequence Download PDFInfo
- Publication number
- CN114091625B CN114091625B CN202210056757.7A CN202210056757A CN114091625B CN 114091625 B CN114091625 B CN 114091625B CN 202210056757 A CN202210056757 A CN 202210056757A CN 114091625 B CN114091625 B CN 114091625B
- Authority
- CN
- China
- Prior art keywords
- fault
- fault code
- vehicle
- sequence
- failure prediction
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
Abstract
The invention relates to a vehicle part failure prediction method and a system based on a fault code sequence, wherein the method comprises the following steps: acquiring a fault code of a target vehicle; and inputting the vehicle fault code into a trained vehicle part failure prediction model to obtain the predicted failure information of the target vehicle. According to the method, the sequence relation among fault codes is comprehensively considered, the prediction model is constructed based on the machine learning method of the feature engineering, and the model accuracy is remarkably improved compared with that of the traditional solution; on the other hand, the model generalization is good, the realization is simple, the rapid landing can be supported, the support is provided for the after-sale predictability service based on the Internet of vehicles, the model can be self-optimized along with the accumulation of data volume, and the prediction accuracy can be further improved.
Description
Technical Field
The invention belongs to the technical field of intelligent networked automobiles and fault prediction, and particularly relates to a vehicle part failure prediction method based on a fault code sequence.
Background
In recent years, with the high-speed development of information technology, intelligent networking becomes the development direction of the automobile industry, various automobiles sold in the current market are almost equipped with a vehicle networking in a standard mode, the real-time collection and return of vehicle data can be realized, and the collection of vehicle fault code data provides a basis for vehicle after-sale foreseeable service.
However, a large amount of information such as non-serious faults, instantaneous faults, associated faults and the like exists in fault code data acquired through the internet of vehicles, and how to extract fault information really influencing vehicle operation and causing failure of key parts of the vehicle is a significant challenge to the development of after-sale predictive service of the vehicle based on the internet of vehicles. At present, the mainstream means for solving the problem still relies on the experience analysis of technical staff, a key control fault code list which may cause the failure of key parts of the vehicle is defined in advance, and when the occurrence of codes in the key control fault code list is monitored by the internet of vehicles, a fault early warning is issued to remind a client of vehicle maintenance. However, due to the limitation of experience of technicians, the selection of key management and control fault codes is not accurate, and most faults do not necessarily cause the failure of parts, so that the accuracy of fault early warning is extremely low, and the requirement of vehicle after-sale anticipatory service cannot be met.
How to improve the accuracy of fault early warning based on the analysis and mining of vehicle fault code data is a problem which needs to be solved for implementing vehicle after-sale predictability service.
Disclosure of Invention
In order to solve the problems of real-time monitoring of vehicle fault codes and accurate fault early warning, the invention provides a vehicle part failure prediction method based on a fault code sequence in a first aspect, which comprises the following steps: acquiring a fault code of a target vehicle; and inputting the vehicle fault code into a trained vehicle part failure prediction model to obtain the predicted failure information of the target vehicle.
In some embodiments of the invention, the trained vehicle part failure prediction model is trained by: constructing a prediction training set according to the historical fault codes and the part failure maintenance records of the vehicle; mining statistical characteristics and sequence characteristics of the historical fault codes; and training a failure prediction model by utilizing a machine learning algorithm based on the statistical characteristics and the sequence characteristics.
Further, the statistical characteristics are mined by the following method: counting the number of vehicles with a plurality of fault codes, replacing parts of the vehicles after each fault code occurs, and calculating the probability of damage caused by each fault code; based on the probabilities of the plurality of fault codes causing damage, a fault code is determined that has a maximum probability of causing a vehicle part to fail.
Further, the sequence features are mined by the following method: establishing a fault code sequence according to the time sequence before and after each fault code appears in a vehicle replacement part; searching a fault code sequence with the highest occurrence frequency; and constructing a fault transfer map based on the transfer relation among the fault sequences according to the fault code transfer map, and determining the fault code with the largest influence according to the fault code transfer map.
Further, the constructing a fault transfer map according to the fault code transfer map based on the transfer relationship between the fault sequences and determining the fault code with the largest influence according to the fault transfer map comprises: taking each fault code as a node of a fault transfer map, and transferring probability between fault codes
Constructing a fault transfer map for the edge of the map; and calculating the influence of each fault code according to a webpage influence algorithm, and determining the fault code with the maximum influence.
Preferably said transition probabilityP ij Calculated by the following method:
wherein the content of the first and second substances,P ij indicating a faultiTo failurejThe transition probability of (2);f ij indicating a faultiTo failurejThe number of times of occurrence of the event,nis the total number of faults.
In a second aspect of the invention, there is provided a fault code sequence based vehicle part failure prediction system comprising: the acquisition module is used for acquiring a fault code of the target vehicle; and the prediction module is used for inputting the vehicle fault codes into a trained vehicle part failure prediction model to obtain the predicted failure information of the target vehicle.
Further, the prediction module comprises: the building unit is used for building a prediction training set according to the historical fault codes and the part failure maintenance records of the vehicle; the mining unit is used for mining the statistical characteristics and the sequence characteristics of the historical fault codes; and the training unit is used for training the failure prediction model by utilizing a machine learning algorithm based on the statistical characteristics and the sequence characteristics.
In a third aspect of the present invention, there is provided an electronic device comprising: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the fault code sequence based vehicle part failure prediction method provided by the invention in the first aspect.
In a fourth aspect of the present invention, a computer readable medium is provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the fault code sequence based vehicle part failure prediction method provided in the first aspect of the present invention.
The invention has the beneficial effects that:
1. according to the method, the sequence relation among fault codes is comprehensively considered, the prediction model is constructed based on the machine learning method of the feature engineering, and the model accuracy is remarkably improved compared with that of the traditional solution;
2. the prediction model constructed by the scheme of the invention integrates the statistical characteristics and the sequence characteristics in the fault, so that the generalization is good, the realization is simple, the rapid landing can be supported, and an efficient solution is provided for the after-sale predictability service based on the Internet of vehicles;
3. the scheme of the invention is based on the machine learning method to construct the model, and the model can be self-optimized along with the accumulation of data volume, so that the prediction accuracy is further improved along with the optimization of the model.
Drawings
FIG. 1 is a basic flow diagram of a fault code sequence based vehicle part failure prediction method in some embodiments of the invention;
FIG. 2 is a detailed flow diagram of a method for failure prediction of a vehicle part based on a fault code sequence in accordance with some embodiments of the present invention;
FIG. 3 is a schematic illustration of statistical feature mining steps in some embodiments of the invention;
FIG. 4 is a schematic diagram of a sequence feature mining step in some embodiments of the invention;
FIG. 5 is a second schematic diagram illustrating sequential feature mining steps in some embodiments of the invention;
FIG. 6 is a schematic block diagram of a fault code sequence based vehicle part failure prediction system in some embodiments of the invention;
fig. 7 is a schematic structural diagram of an electronic device in some embodiments of the invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1 and 2, in a first aspect of the present invention, there is provided a failure prediction method for a vehicle part based on a fault code sequence, including: s100, acquiring a fault code of a target vehicle; s200, inputting the vehicle fault code into a trained vehicle part failure prediction model to obtain the predicted failure information of the target vehicle. It can be understood that a plurality of fault codes with time precedence relationship may form a sequence, and therefore the fault code acquired in the present invention also includes a fault code sequence.
In some embodiments of the invention, the trained vehicle part failure prediction model is trained by: s201, constructing a prediction training set according to the historical fault codes and the part failure maintenance records of the vehicle; s202, mining statistical characteristics and sequence characteristics of the historical fault codes; and S203, training a failure prediction model by using a machine learning algorithm based on the statistical characteristics and the sequence characteristics.
It is understood that the failure information or failure information of the vehicle part includes at least: vehicle Identification Number (VIN), fault code occurrence record, fault occurrence time, vehicle part failure maintenance record, and maintenance time. Particularly, a data set of vehicle part failure can be respectively established according to different vehicle functional components of the same part manufacturer, the whole vehicle manufacturer and the part, and then a final prediction training set is obtained through data processing means such as data cleaning and clustering. Therefore, the prediction training set is required to cover as many vehicle fault code occurrence records and maintenance records as possible in a long period of time, and the vehicle fault code occurrence records and the maintenance records can be associated through the vehicle identification numbers, so that the relationship between the vehicle fault code occurrence and the vehicle part failure maintenance is preliminarily established.
Referring to fig. 3, further, in step S202, the statistical characteristics are mined by the following method: s2021, counting the number of vehicles with a plurality of fault codes, and the condition that parts of the vehicles are replaced after each fault code appears, and calculating the probability of damage caused by each fault code; s2022, determining fault codes with the maximum probability of causing the vehicle parts to fail according to the probability of damage caused by the fault codes.
Specifically, the occurrence of a failure code per day is counted by using a statistical analysis method
Number of vehicles and corresponding vehicle future
Replacing the part X in the day, and calculating the damage probability P of the partiX(X | a failure i occurs on the day of replacement within n days). On the basis, covering each fault code in the time period for the training set
The part damage probability is arithmetically averaged to obtain an average part damage probabilityAverge(P iX )And select from themAverge(P iX )≥kThe fault code of (1) is taken as a key management and control code, namely the characteristic 1. It should be noted that, in order to eliminate the influence of the accidental fault on the result, the accidental fault whose frequency of occurrence of the fault code in the time period is lower than a certain value needs to be eliminated from the result.
It should be understood that the above statistical features do not take into account the sequence relationship between faults, and that a vehicle part failure is caused by the interaction of one or more faults, and to this end, the present invention adds sequence features to embody the relationship between fault codes, wherein one part of the sequence features mainly performs mining analysis on the time sequence between faults, and the other part of the sequence features performs mining analysis by taking into account the transfer relationship between fault codes.
Referring to fig. 4, further, the sequence features are mined by the following method: s2023, establishing a fault code sequence according to the time sequence of each fault code before and after the fault code appears in the vehicle replacement part; s2024, searching a fault code sequence with the highest occurrence frequency; s2025, based on the transfer relation among the fault sequences, constructing a fault transfer map according to the fault code transfer map, and determining the fault code with the largest influence according to the fault code transfer map.
In particular, assume that the training set hasnThe part X is replaced by each vehicle, and each vehicle is before replacing the part XAccording to the time sequence, a series of fault code sequences exist, the fault code sequences have faults which really cause part failure, and a large number of non-serious faults, transient faults and the like, and in order to find out the fault sequences which really cause part failure, the fault code sequences can be obtainednThe most frequent sequences are found in the fault sequences of the vehicles, which are most likely to be the fault sequences that actually lead to the failure of the part. In this embodiment, a prefix span algorithm is adopted to mine the frequent fault code sequences, and a fault code sequence with a frequency greater than J is selected from the found frequent fault code sequences as the feature 2. Illustratively, among the vehicles 1 to n, the fault codes b, g, d are found out by the Prefixspan algorithm, and appear in n1 vehicles, the fault codes e, f appear in n2 vehicles, and the fault codes b, g, d, e, f appear in n3 vehicles, so that the fault sequences bgd and ef serve as candidate sequence features, i.e., feature 2.
Referring to fig. 5, in the mining of the sequence features, the constructing a fault transfer map according to a fault code transfer map based on a transfer relationship between fault sequences and determining a fault code with the largest influence according to the fault transfer map includes: taking each fault code as a node of a fault transfer map, and transferring probability between fault codes
Constructing a fault transfer map for the edge of the map; and calculating the influence of each fault code according to a webpage influence algorithm, and determining the fault code with the maximum influence.
Preferably said transition probabilityP ij Calculated by the following method:
wherein the content of the first and second substances,P ij indicating a faultiTo failurejThe transition probability of (2);f ij indicating a faultiTo failurejThe number of times of occurrence of the event,nis the total number of faults. Specifically, assume each fault code
The influence on the final part failure is pr (i), and the fault code with larger influence is more likely to cause the final part failure, in other words, the fault code with large influence is more likely to be transferred to the fault code with large influence through the transfer of a series of fault codes, and the part failure finally occurs through the further development of the fault codes. Therefore, we need to find such a series of fault sequences with large PR values from the map, and the PR value of each fault code cannot be obtained from the currently constructed map. In order to solve the problem, the problem is analogized with a webpage sorting problem, in a classical webpage sorting problem, the influence value of one webpage is assumed to be determined by other webpages referring to the webpage, the initial influence value of each webpage can be assumed to be 1, and the influence value of each webpage can be obtained finally through iterative convergence by a Pagerank algorithm, so that the webpages can be sorted. Similarly, we can assume that the impact of a fault code on the ultimate failure of a part is determined by the impact of other fault codes transferred to the fault code, and also using the Pagerank algorithm, the initial map can be iterated, and fault codes with PR values greater than I are selected from the converged map as features 3.
In step S203 of the above embodiment, a machine learning classification algorithm XGBoost is selected to train the model. Optionally, methods such as a decision tree, a regression tree, ensemble learning, and the like may also be used to implement fusion of the above-mentioned 3 types (feature 1 to feature 3) of features.
Example 2
Referring to fig. 6, in a second aspect of the present invention, there is provided a fault code sequence-based vehicle part failure prediction system 1, comprising: the acquisition module 11 is used for acquiring a fault code of the target vehicle; and the prediction module 12 is used for inputting the vehicle fault code into a trained vehicle part failure prediction model to obtain the predicted failure information of the target vehicle.
Further, the prediction module 12 includes: the building unit is used for building a prediction training set according to the historical fault codes and the part failure maintenance records of the vehicle; the mining unit is used for mining the statistical characteristics and the sequence characteristics of the historical fault codes; and the training unit is used for training the failure prediction model by utilizing a machine learning algorithm based on the statistical characteristics and the sequence characteristics.
Example 3
Referring to fig. 7, in a third aspect of the present invention, there is provided an electronic apparatus comprising: one or more processors; storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to carry out the method of the invention in the first aspect.
The electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following devices may be connected to the I/O interface 505 in general: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; a storage device 508 including, for example, a hard disk; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 7 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 7 may represent one device or may represent multiple devices as desired.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program, when executed by the processing device 501, performs the above-described functions defined in the methods of embodiments of the present disclosure. It should be noted that the computer readable medium described in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In embodiments of the present disclosure, however, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more computer programs which, when executed by the electronic device, cause the electronic device to:
computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, Python, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, 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 case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including 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 using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. A vehicle part failure prediction method based on a fault code sequence is characterized by comprising the following steps:
acquiring a fault code of a target vehicle;
inputting the vehicle fault code into a trained vehicle part failure prediction model to obtain the predicted failure information of the target vehicle, wherein the trained vehicle part failure prediction model is trained by the following method: constructing a prediction training set according to the historical fault codes and the part failure maintenance records of the vehicle;
mining statistical characteristics and sequence characteristics of the historical fault codes; training a failure prediction model by using a machine learning algorithm based on the statistical characteristics and the sequence characteristics;
the sequence features are mined by the following method: establishing a fault code sequence according to the time sequence before and after each fault code appears in a vehicle replacement part; searching a fault code sequence with the highest occurrence frequency; based on the transfer relationship between fault sequences, a fault transfer map is constructed according to a fault code transfer map, and fault codes with the largest influence are determined according to the fault code transfer map, wherein each fault code is used as a node of the fault transfer map, and the transfer probability among the fault codesP ij Constructing a fault transfer map for the edge of the map; and calculating the influence of each fault code according to a webpage influence algorithm, and determining the fault code with the maximum influence.
2. The fault code sequence based vehicle part failure prediction method of claim 1, wherein the statistical features are mined by:
counting the number of vehicles with a plurality of fault codes, replacing parts of the vehicles after each fault code occurs, and calculating the probability of damage caused by each fault code;
based on the probabilities of the plurality of fault codes causing damage, a fault code is determined that has a maximum probability of causing a vehicle part to fail.
3. The vehicle part failure prediction method of fault code sequence of claim 1, characterized in that said transition probabilityP ij Calculated by the following method:
wherein the content of the first and second substances,P ij indicating a faultiTo failurejThe transition probability of (2);f ij indicating a faultiTo failurejThe number of times of occurrence of the event,nis the total number of faults.
4. A vehicle part failure prediction system based on a fault code sequence, comprising:
the acquisition module is used for acquiring a fault code of the target vehicle;
the prediction module is used for inputting the vehicle fault code into a trained vehicle part failure prediction model to obtain the predicted failure information of the target vehicle, wherein the trained vehicle part failure prediction model is trained by the following method: constructing a prediction training set according to the historical fault codes and the part failure maintenance records of the vehicle;
mining statistical characteristics and sequence characteristics of the historical fault codes; training a failure prediction model by using a machine learning algorithm based on the statistical characteristics and the sequence characteristics;
the sequence features are mined by the following method: establishing a fault code sequence according to the time sequence before and after each fault code appears in a vehicle replacement part; searching a fault code sequence with the highest occurrence frequency; based on the transfer relationship between fault sequences, a fault transfer map is constructed according to a fault code transfer map, and fault codes with the largest influence are determined according to the fault code transfer map, wherein each fault code is used as a node of the fault transfer map, and the transfer probability among the fault codesP ij Constructing a fault transfer map for the edge of the map; and calculating the influence of each fault code according to a webpage influence algorithm, and determining the fault code with the maximum influence.
5. The fault code sequence based vehicle part failure prediction system of claim 4, wherein the prediction module comprises:
the building unit is used for building a prediction training set according to the historical fault codes and the part failure maintenance records of the vehicle;
the mining unit is used for mining the statistical characteristics and the sequence characteristics of the historical fault codes;
and the training unit is used for training the failure prediction model by utilizing a machine learning algorithm based on the statistical characteristics and the sequence characteristics.
6. An electronic device, comprising: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the fault code sequence based vehicle part failure prediction method of any one of claims 1 to 3.
7. A computer-readable medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the fault code sequence based vehicle part failure prediction method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210056757.7A CN114091625B (en) | 2022-01-18 | 2022-01-18 | Vehicle part failure prediction method and system based on fault code sequence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210056757.7A CN114091625B (en) | 2022-01-18 | 2022-01-18 | Vehicle part failure prediction method and system based on fault code sequence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114091625A CN114091625A (en) | 2022-02-25 |
| CN114091625B true CN114091625B (en) | 2022-04-29 |
Family
ID=80308723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210056757.7A Active CN114091625B (en) | 2022-01-18 | 2022-01-18 | Vehicle part failure prediction method and system based on fault code sequence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114091625B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522192A (en) * | 2018-10-17 | 2019-03-26 | 北京航空航天大学 | A kind of prediction technique of knowledge based map and complex network combination |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020007237A1 (en) * | 2000-06-14 | 2002-01-17 | Phung Tam A. | Method and system for the diagnosis of vehicles |
| US8676432B2 (en) * | 2010-01-13 | 2014-03-18 | GM Global Technology Operations LLC | Fault prediction framework using temporal data mining |
| US8301333B2 (en) * | 2010-03-24 | 2012-10-30 | GM Global Technology Operations LLC | Event-driven fault diagnosis framework for automotive systems |
| CN103996077B (en) * | 2014-05-22 | 2018-01-05 | 中国南方电网有限责任公司电网技术研究中心 | A kind of electrical equipment malfunction Forecasting Methodology based on multidimensional time-series |
| CN106066642B (en) * | 2016-05-27 | 2019-04-19 | 大连楼兰科技股份有限公司 | Error code diagnosis vehicle work item and spare part search method based on FP-Tree sequential mode mining |
| CN106056221B (en) * | 2016-05-27 | 2019-10-29 | 大连楼兰科技股份有限公司 | The method of the vehicle remote diagnosis and spare part retrieval classified based on FP-Tree sequential mode mining and error code |
| CN106056222B (en) * | 2016-05-27 | 2020-03-24 | 大连楼兰科技股份有限公司 | Fault diagnosis and evaluation method based on FP-Tree sequence pattern mining |
| CN108073575A (en) * | 2016-06-14 | 2018-05-25 | 电子科技大学 | A kind of radar data Frequent Pattern Mining method based on improvement Prefixspan algorithms |
| US11605252B2 (en) * | 2016-10-12 | 2023-03-14 | Harman International Industries, Incorporated | Systems and methods for in-vehicle predictive failure detection |
| CN106406229B (en) * | 2016-12-20 | 2018-04-03 | 吉林大学 | A kind of diagnosing faults of numerical control machine method |
| CN108953071A (en) * | 2017-05-25 | 2018-12-07 | 中国电力科学研究院 | A kind of fault early warning method and system of paddle change system of wind turbines |
| EP3451101B1 (en) * | 2017-09-05 | 2022-04-20 | Lisa Dräxlmaier GmbH | Method for determining a cause of a malfunction in a vehicle component |
| CN107844540A (en) * | 2017-10-25 | 2018-03-27 | 电子科技大学 | A kind of time series method for digging for electric power data |
| CN108537259A (en) * | 2018-03-27 | 2018-09-14 | 北京交通大学 | Train control on board equipment failure modes and recognition methods based on Rough Sets Neural Networks model |
| CN113064976A (en) * | 2021-04-19 | 2021-07-02 | 深圳市明睿数据科技有限公司 | Accident vehicle judgment method based on deep learning algorithm |
-
2022
- 2022-01-18 CN CN202210056757.7A patent/CN114091625B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522192A (en) * | 2018-10-17 | 2019-03-26 | 北京航空航天大学 | A kind of prediction technique of knowledge based map and complex network combination |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114091625A (en) | 2022-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10366095B2 (en) | Processing time series | |
| CN110555640B (en) | Route planning method and device | |
| CN110807515A (en) | Model generation method and device | |
| JP6802916B2 (en) | Demand forecaster | |
| CN109636047B (en) | User activity prediction model training method, system, device and storage medium | |
| CN109978619B (en) | Method, system, equipment and medium for screening air ticket pricing strategy | |
| US20190147390A1 (en) | Predicting timely completion of a work order | |
| CN104035779A (en) | Method for handling missing values during data stream decision tree classification | |
| CN112256886B (en) | Probability calculation method and device in atlas, computer equipment and storage medium | |
| WO2023207411A1 (en) | Traffic determination method and apparatus based on spatio-temporal data, and device and medium | |
| CN114417192B (en) | Method, device, equipment, medium and product for updating POI (Point of interest) state | |
| CN111507541B (en) | Goods quantity prediction model construction method, goods quantity measurement device and electronic equipment | |
| CN109240916A (en) | Information output controlling method, device and computer readable storage medium | |
| CN114091625B (en) | Vehicle part failure prediction method and system based on fault code sequence | |
| CN114385808A (en) | Text classification model construction method and text classification method | |
| CN111861000A (en) | Daily income prediction method, system, equipment and storage medium based on historical data | |
| CN116865254A (en) | Power load index prediction method, system, equipment and medium | |
| CN113868368A (en) | Method, electronic device and computer program product for information processing | |
| CN111967806B (en) | User risk updating method and device based on periodic retrace and electronic equipment | |
| CN115905293A (en) | Switching method and device of job execution engine | |
| CN115206102A (en) | Method, apparatus, electronic device, and medium for determining traffic path | |
| CN114997414A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN114357180A (en) | Knowledge graph updating method and electronic equipment | |
| CN111949867A (en) | Cross-APP user behavior analysis model training method, analysis method and related equipment | |
| US20230064674A1 (en) | Iterative training of computer model for machine learning |
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 |