CN108509995A - Diagnosis method of automobile faults based on Chinese text analysis and OBD data processings - Google Patents
Diagnosis method of automobile faults based on Chinese text analysis and OBD data processings Download PDFInfo
- Publication number
- CN108509995A CN108509995A CN201810287208.4A CN201810287208A CN108509995A CN 108509995 A CN108509995 A CN 108509995A CN 201810287208 A CN201810287208 A CN 201810287208A CN 108509995 A CN108509995 A CN 108509995A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- text
- vehicle trouble
- trouble situation
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
Abstract
The invention discloses a kind of Diagnosis method of automobile faults based on Chinese text analysis and OBD data processings, it includes obtaining vehicle trouble situation Text Information Data and OBD data, establish vehicle trouble situation text data feature set, label preserves the abnormal data in OBD data, processing is carried out to vehicle trouble situation text data feature set using improved SimHash algorithms and forms corresponding signature collection, signature collection is subjected to similarity mode with vehicle maintenance case library model, obtains optimal fault message and troubleshooting scheme.Present invention saves the times of a large amount of artificial treatment, realize the digitization of experience, and so that diagnostic result is more accurate by the combination of the OBD data and Maintenance Cases experience of profession；In addition user can also be facilitated to grasp automobilism data and error code at any time, realize and fault detect effectively is carried out to vehicle.
Description
Technical field
The invention belongs to Automobile Failure Diagnosis Technology fields, and in particular to one kind is based on Chinese text analysis and OBD data
The Diagnosis method of automobile faults of processing.
Background technology
Automobile Failure Diagnosis Technology refers to passing through professional equipment in the case where vehicle complete vehicle is without dismantling and disintegration
And characterization vehicle, it determines the technology and working condition of automobile, investigates the Automotive Applied Technology of failure cause and trouble location.
Automobile is a complex technology system being orderly made of many assemblies, mechanism and component.Thus research automobile
The mechanism of production and changing rule of failure, the performance of regular even real-time online detection automobile, to examining promptly and accurately
Disconnected be out of order and is debugged at position, and an important content of automotive practical technology and fault diagnosis technology is just become.
Traditional automobile failure diagnosis is needed in specific place, by having experience or having relevant knowledge background
What a series of processes such as professional person's inspection, measurement, analysis, judgement were completed.Its basic skills is broadly divided into 2 kinds：Modern instrument
Device diagnostic method and artificial experience diagnosis.
(1) Modern Scientific Instruments in Chinese diagnosis is not disintegrated in automobile, using test equipment, examines equipment and inspection
Tool is tested, parameter, the wavy curve of vehicle, assembly or mechanism are detected, to analyze, judging that technical condition of vehicle provides quantitative basis
Diagnostic method：
(2) artificial experience diagnosis refers to diagnostic personnel with certain knowwhy and relevant smell of powder, in automobile
Do not disintegrate or partial teardown in the case of, using eye is seen, ear is listened, hand is touched etc. these it is intuitive feel, by simple tool instrument, into
The technology status of row Inspection and analysis automobile investigates a kind of diagnostic method of failure cause and trouble location.
In realistic situation, traditional automobile failure diagnosis often uses above two method, also referred to as comprehensive diagnos simultaneously
Method.
However, this traditional fault diagnosis is needed to meet many conditions and be had some limitations：
(1) experience and knowwhy background；
(2) expensive equipment detecting instrument；
(3) maintenance needs to carry out in specific place；
(4) vehicle trouble cannot carry out early warning in advance, all be when having occurred and that or having an impact the result of driving behavior
It could find failure；
(5) fault diagnosis can only be done in the time of time-based maintenance；
(6) maintenance behavior is not fully transparent, and car owner can not generally recognize the true original that automobile breaks down
Cause.
Invention content
The present invention goal of the invention be：In order to solve problem above existing in the prior art, the present invention proposes one kind
Automobile failure diagnosis based on Chinese text analysis and OBD (On-Board Diagnostic, onboard diagnostic system) data processing
Method easily can carry out real-time, quick diagnosis to vehicle trouble, and car owner and maintenance personal is assisted to carry out associated vehicle repair
With maintenance..
The technical scheme is that：A kind of automobile failure diagnosis side based on Chinese text analysis and OBD data processings
Method includes the following steps：
A, vehicle trouble situation Text Information Data and OBD data are obtained；
B, Chinese word segmentation, elimination stop words, synonym is carried out to the vehicle trouble situation Text Information Data in step A to return
One change is handled, and establishes corresponding vehicle trouble situation text data feature set；
C, the OBD data in step A are compared and analyzed into processing with OBD databases, guarantor is marked to abnormal data
It deposits, while being added to the vehicle trouble situation textual data in step B using the vehicle position that abnormal data occurs as special characteristic
According in feature set；
D, at using improved SimHash algorithms to the vehicle trouble situation text data feature set in step C
Reason forms corresponding signature collection；
E, the signature collection in step D is subjected to similarity mode with vehicle maintenance case library model, obtains optimal failure
Information and troubleshooting scheme.
Further, the step D uses improved SimHash algorithms to the vehicle trouble situation text in step C
Data characteristics collection is handled, and is formed corresponding signature collection and is specially：According in vehicle trouble situation text data feature set
Word frequency information and part-of-speech information calculate the weights of each Feature Words, and corresponding signature collection is built using improved SimHash algorithms.
Further, the word frequency information in the situation text data feature set according to vehicle trouble and part-of-speech information calculate
Each the calculation formula of the weights of Feature Words is specially：
Wherein, wvIndicate that the weights of Feature Words v, count (v) indicate numbers of the Feature Words v in vehicle trouble situation text d
Amount, count (d) indicate that the total quantity that vehicle trouble situation text d contains Feature Words, N indicate vehicle trouble situation text collection D
Quantity, count (v, D) indicates that vehicle trouble situation text collection D includes the amount of text of Feature Words v, wpIndicate Feature Words
The weights of part of speech.
Further, the signature collection in step D is carried out similarity mode by the step E with vehicle maintenance case library model
Specially：The Hamming distance for calculating the signature collection and vehicle maintenance case signature collection in step D, generates Candidate Set；Using BM25
Algorithm calculates similarity score to each vehicle maintenance case in vehicle trouble situation text data feature set and Candidate Set, and presses
Scoring is ranked up.
The beneficial effects of the invention are as follows：The present invention uses Chinese text analysis method, by being segmented to text data,
Feature extraction simultaneously establishes corresponding model, and similarity mode is carried out to auto repair case database in combination with SimHash algorithms,
Filter out the highest several results of similarity and be supplied to user, to save the time of a large amount of artificial treatment, realize through
The digitization tested, and so that diagnostic result is more accurate by the combination of the OBD data and Maintenance Cases experience of profession；In addition
User can also be facilitated to grasp automobilism data and error code at any time, realize and fault detect effectively is carried out to vehicle.
Description of the drawings
Fig. 1 is that the flow of the Diagnosis method of automobile faults based on Chinese text analysis and OBD data processings of this law is shown
It is intended to.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
As shown in Figure 1, being analyzed and the Diagnosis method of automobile faults of OBD data processings based on Chinese text for this law
Flow diagram.A kind of Diagnosis method of automobile faults based on Chinese text analysis and OBD data processings, includes the following steps：
A, vehicle trouble situation Text Information Data and OBD data are obtained；
B, Chinese word segmentation, elimination stop words, synonym is carried out to the vehicle trouble situation Text Information Data in step A to return
One change is handled, and establishes corresponding vehicle trouble situation text data feature set；
C, the OBD data in step A are compared and analyzed into processing with OBD databases, guarantor is marked to abnormal data
It deposits, while being added to the vehicle trouble situation textual data in step B using the vehicle position that abnormal data occurs as special characteristic
According in feature set；
D, at using improved SimHash algorithms to the vehicle trouble situation text data feature set in step C
Reason forms corresponding signature collection；
E, the signature collection in step D is subjected to similarity mode with vehicle maintenance case library model, obtains optimal failure
Information and troubleshooting scheme.
In an alternate embodiment of the present invention where, above-mentioned steps A inputs vehicle trouble shape using mobile terminal by user
Condition Text Information Data, vehicle trouble situation Text Information Data include the phenomenon that a variety of vehicle troubles reflect；And use vehicle
Mounted terminal hardware reads the operation information and error code of automobile by car OBD interface, while it being uploaded by 4G networks
To the OBD databases and automotive diagnostic system in high in the clouds；OBD data include error code and the operation information data flow of automobile, automobile
Operation information data flow be made of the monitoring data of multiple sensors.
In an alternate embodiment of the present invention where, above-mentioned steps B transfers vehicle maintenance case using automotive diagnostic system
Natural language processing module in database model carries out Chinese word segmentation, eliminates the processing procedures such as stop words, synonym normalization
Afterwards, corresponding vehicle trouble situation text data feature set is established.Here vehicle maintenance databases contain vehicle failure
The solution of case, profession, and above-mentioned data sorted out according to vehicle position, Vehicular system and the aspect of fault level three,
It arranges and early warning analysis judges.Vehicle maintenance case database model is by collecting previous auto repair case and processing method
Text data, the characteristics of for its short text, carried using corresponding natural language processing method, including participle, fault signature
It takes.Vehicle position includes engine, vehicle body, chassis；Vehicular system include fuel system, cooling system, lubricating system, into row
Gas system, transmission system, electric-control system, steering, braking system etc..
In an alternate embodiment of the present invention where, above-mentioned steps C judges whether to detect vehicle using automotive diagnostic system
Operation information and fault code indications data transfer OBD databases and carry out comparing analyzing processing, to exception if detected
Preservation (the vehicle concrete position that remarks abnormal data occurs in label) is marked in data, if being not detected, transfers high in the clouds guarantor
The OBD data deposited carry out data processing according to the method described above.The vehicle position that abnormal data is occurred simultaneously is as special characteristic
It is added in the vehicle trouble situation text data feature set in step B.Here include error code, Chinese in OBD databases
Definition, English definition, different automobile types Sensor monitoring parameter, background knowledge and solution.
Existing natural language processing algorithm, typically using word frequency as the weights of the word, but only using word frequency as power
Value will lose many text messages, particularly with such vehicle trouble messages, usually all be less than the short text of 500 words, word
Frequency is very sparse according to meeting, and the size of word frequency cannot represent the significance level of word completely；The present invention is considered in vehicle trouble
In information, some special proper nouns are the important embodiments in fault signature, only consider that word frequency information calculates text similarity
Precision it is not high, therefore carry out in conjunction with word frequency information and part-of-speech information the weights of COMPREHENSIVE CALCULATING keyword.
In an alternate embodiment of the present invention where, above-mentioned steps D uses improved SimHash algorithms in step C
Vehicle trouble situation text data feature set handled, forming corresponding signature collection is specially：According to vehicle trouble situation
Word frequency information and part-of-speech information in text data feature set calculate the weights of each Feature Words, are calculated using improved SimHash
The corresponding signature collection of method structure.
For vehicle trouble, the part name in vehicle is most important to entire failure-description, because it is directly
Out of order device is described, it next also should be than other to the words of description of the device i.e. adjective and verb etc.
Word is important, and weights should take second place, therefore herein when calculating weights to word, and consideration adds part-of-speech information.The present invention
Part of speech weights such as following table in embodiment.
1 part of speech weight table of table
| Part of speech | Special word | Verb | Common noun | It is other |
| Weights | 1 | 0.75 | 0.6 | 0.4 |
Under part of speech weights set by table 1, it is 1 that the weighting of the present invention setting word frequency weights and part of speech weights, which is compared,.This hair
It is bright calculate Feature Words weights when, word frequency information is combined with part-of-speech information, has considered part of speech and word frequency information pair
The significance level of Feature Words.According in vehicle trouble situation text data feature set word frequency information and part-of-speech information calculate it is each
The calculation formula of the weights of Feature Words is specially：
Wherein, wvIndicate that the weights of Feature Words v, count (v) indicate numbers of the Feature Words v in vehicle trouble situation text d
Amount, count (d) indicate that the total quantity that vehicle trouble situation text d contains Feature Words, N indicate vehicle trouble situation text collection D
Quantity, count (v, D) indicates that vehicle trouble situation text collection D includes the amount of text of Feature Words v, wpIndicate Feature Words
The weights of part of speech.
Due to being all short text in the Maintenance Cases database model in vehicle breakdown diagnostic system, semantic information is very dilute
It dredges, is not suitable for using the computational methods based on semantic similarity, therefore the present invention is used in the similarity between calculating case
Method based on vector space.And text information processing has very big memory consumption, there is a large amount of cases in case library, is read
Enter calculator memory, and generate vector matrix to occupy huge memory space, and the data calculation time complexity of big dimension
Also very high.In order to solve this problem, database is stored in cloud server by the present invention, while using SimHash algorithms.Vehicle
Maintenance plan and OBD databases connect with Cloud Server and related data are transmitted to Cloud Server.Preferably, this hair
Bright setting Hamming distance threshold value is 10.
In an alternate embodiment of the present invention where, above-mentioned steps E first, in accordance with above-mentioned steps to vehicle maintenance case into
Row processing forms vehicle maintenance case signature collection, specifically includes
Obtain case characteristic word set：Vehicle maintenance case is segmented according to dictionary for word segmentation, deactivated vocabulary, part of speech filtering
After filtering stop words, synonym is normalized further according to synonymicon, obtains the feature word set of vehicle maintenance case；
Build Simhash signatures：Each Feature Words are calculated using above-mentioned calculation formula to vehicle maintenance case characteristic word set
Weights, according to SimHash generating algorithms build each case SimHash sign；
The signature collection of vehicle trouble situation is calculated with after the signature collection of vehicle maintenance case in step D in obtaining step D
Signature collection with vehicle maintenance case signature collection Hamming distance, choose Hamming distance be less than Hamming distance threshold value retrieval case
Collection is used as Candidate Set；Using BM25 algorithms to each vehicle maintenance case in vehicle trouble situation text data feature set and Candidate Set
Example calculates similarity score, and is ranked up by scoring；To filter out the highest several fault messages of similarity and failure
Processing scheme is supplied to user.
Those of ordinary skill in the art will understand that the embodiments described herein, which is to help reader, understands this hair
Bright principle, it should be understood that protection scope of the present invention is not limited to such specific embodiments and embodiments.This field
Those of ordinary skill can make according to the technical disclosures disclosed by the invention various does not depart from the other each of essence of the invention
The specific variations and combinations of kind, these variations and combinations are still within the scope of the present invention.
Claims (4)
1. a kind of Diagnosis method of automobile faults based on Chinese text analysis and OBD data processings, which is characterized in that including following
Step：
A, vehicle trouble situation Text Information Data and OBD data are obtained；
B, Chinese word segmentation carried out to the vehicle trouble situation Text Information Data in step A, eliminate stop words, synonym normalization
Processing, establishes corresponding vehicle trouble situation text data feature set；
C, the OBD data in step A are compared and analyzed into processing with OBD databases, preservation is marked to abnormal data, together
When the vehicle position that abnormal data occurs is added to as special characteristic to vehicle trouble situation text data feature in step B
It concentrates；
D, the vehicle trouble situation text data feature set in step C is handled using improved SimHash algorithms, shape
Collect at corresponding signature；
E, the signature collection in step D is subjected to similarity mode with vehicle maintenance case library model, obtains optimal fault message
And troubleshooting scheme.
2. the Diagnosis method of automobile faults as described in claim 1 based on Chinese text analysis and OBD data processings, feature
Be, the step D using improved SimHash algorithms to the vehicle trouble situation text data feature set in step C into
Row processing, forming corresponding signature collection is specially：According to the word frequency information and word in vehicle trouble situation text data feature set
Property information calculate the weights of each Feature Words, corresponding signature collection is built using improved SimHash algorithms.
3. the Diagnosis method of automobile faults as claimed in claim 2 based on Chinese text analysis and OBD data processings, feature
It is, the word frequency information and part-of-speech information in the situation text data feature set according to vehicle trouble calculate each Feature Words
The calculation formula of weights is specially：
Wherein, wvIndicate that the weights of Feature Words v, count (v) indicate quantity of the Feature Words v in vehicle trouble situation text d,
Count (d) indicates that the total quantity that vehicle trouble situation text d contains Feature Words, N indicate vehicle trouble situation text collection D's
Quantity, count (v, D) indicate the amount of text that vehicle trouble situation text collection D includes Feature Words v, wpIndicate Feature Words word
The weights of property.
4. the Diagnosis method of automobile faults as claimed in claim 3 based on Chinese text analysis and OBD data processings, feature
It is, the signature collection in step D is carried out similarity mode with vehicle maintenance case library model and is specially by the step E：It calculates
The Hamming distance of signature collection and vehicle maintenance case signature collection in step D, generates Candidate Set；Using BM25 algorithms to vehicle event
Barrier situation text data feature set calculates similarity score with each vehicle maintenance case in Candidate Set, and is arranged by scoring
Sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810287208.4A CN108509995A (en) | 2018-04-03 | 2018-04-03 | Diagnosis method of automobile faults based on Chinese text analysis and OBD data processings |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810287208.4A CN108509995A (en) | 2018-04-03 | 2018-04-03 | Diagnosis method of automobile faults based on Chinese text analysis and OBD data processings |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108509995A true CN108509995A (en) | 2018-09-07 |
Family
ID=63379800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810287208.4A Pending CN108509995A (en) | 2018-04-03 | 2018-04-03 | Diagnosis method of automobile faults based on Chinese text analysis and OBD data processings |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108509995A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109189050A (en) * | 2018-10-22 | 2019-01-11 | 爱驰汽车（上海）有限公司 | Troubleshooting methodology, calculates equipment and computer storage medium at device |
| CN109543855A (en) * | 2018-11-23 | 2019-03-29 | 深圳市元征科技股份有限公司 | A kind of auto repair method, apparatus, equipment and computer readable storage medium |
| CN110377009A (en) * | 2019-07-30 | 2019-10-25 | 南京爱福路汽车科技有限公司 | A kind of method and system for automobile failure diagnosis |
| CN110430277A (en) * | 2019-08-13 | 2019-11-08 | 山东浪潮人工智能研究院有限公司 | It is a kind of based on cloud computing, big data, the car networking application system of technology of Internet of things |
| CN112232056A (en) * | 2020-10-09 | 2021-01-15 | 北京酷车易美网络科技有限公司 | Intelligent algorithm system for vehicle condition analysis |
| CN113624533A (en) * | 2021-10-12 | 2021-11-09 | 南京佰思智能科技有限公司 | Power plant equipment fault diagnosis system and method based on artificial intelligence |
| CN113655770A (en) * | 2021-07-02 | 2021-11-16 | 上海乐意修科技有限公司 | Automobile fault diagnosis teaching system and method |
| CN113807547A (en) * | 2021-08-12 | 2021-12-17 | 江铃汽车股份有限公司 | Vehicle fault early warning method and system, readable storage medium and computer equipment |
| CN114715139A (en) * | 2020-12-18 | 2022-07-08 | 北京百度网讯科技有限公司 | Automatic parking abnormal data acquisition method and device, storage medium and product |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8527441B2 (en) * | 2011-03-10 | 2013-09-03 | GM Global Technology Operations LLC | Developing fault model from service procedures |
| CN107168285A (en) * | 2017-05-26 | 2017-09-15 | 大连理工大学 | A kind of automobile intelligent fault diagnosis of combination subjective and objective information and cloud model and maintenance householder method and system |
-
2018
- 2018-04-03 CN CN201810287208.4A patent/CN108509995A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8527441B2 (en) * | 2011-03-10 | 2013-09-03 | GM Global Technology Operations LLC | Developing fault model from service procedures |
| CN107168285A (en) * | 2017-05-26 | 2017-09-15 | 大连理工大学 | A kind of automobile intelligent fault diagnosis of combination subjective and objective information and cloud model and maintenance householder method and system |
Non-Patent Citations (3)
| Title |
|---|
| WEIZHI LIAO等: "《Research on Dependable Architecture of Saas based Platform Supporting the Industry Chain Coordination》", 《ADVANCED MATERIALS RESEARCH》 * |
| 张晓阳: "《基于案例相似度的车辆故障智能诊断系统研究》", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 王韵: "《基于案例信息检索的车辆故障诊断系统》", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109189050A (en) * | 2018-10-22 | 2019-01-11 | 爱驰汽车（上海）有限公司 | Troubleshooting methodology, calculates equipment and computer storage medium at device |
| CN109543855A (en) * | 2018-11-23 | 2019-03-29 | 深圳市元征科技股份有限公司 | A kind of auto repair method, apparatus, equipment and computer readable storage medium |
| CN110377009A (en) * | 2019-07-30 | 2019-10-25 | 南京爱福路汽车科技有限公司 | A kind of method and system for automobile failure diagnosis |
| CN110430277A (en) * | 2019-08-13 | 2019-11-08 | 山东浪潮人工智能研究院有限公司 | It is a kind of based on cloud computing, big data, the car networking application system of technology of Internet of things |
| CN112232056A (en) * | 2020-10-09 | 2021-01-15 | 北京酷车易美网络科技有限公司 | Intelligent algorithm system for vehicle condition analysis |
| CN114715139A (en) * | 2020-12-18 | 2022-07-08 | 北京百度网讯科技有限公司 | Automatic parking abnormal data acquisition method and device, storage medium and product |
| CN114715139B (en) * | 2020-12-18 | 2024-04-16 | 北京百度网讯科技有限公司 | Automatic parking abnormal data acquisition method, device, storage medium and product |
| CN113655770A (en) * | 2021-07-02 | 2021-11-16 | 上海乐意修科技有限公司 | Automobile fault diagnosis teaching system and method |
| CN113807547A (en) * | 2021-08-12 | 2021-12-17 | 江铃汽车股份有限公司 | Vehicle fault early warning method and system, readable storage medium and computer equipment |
| CN113624533A (en) * | 2021-10-12 | 2021-11-09 | 南京佰思智能科技有限公司 | Power plant equipment fault diagnosis system and method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108509995A (en) | Diagnosis method of automobile faults based on Chinese text analysis and OBD data processings | |
| CN104712542B (en) | A kind of reciprocating compressor sensitive features based on Internet of Things are extracted and method for diagnosing faults | |
| CN107153914B (en) | System and method for evaluating automobile operation risk | |
| US20170091289A1 (en) | Apparatus and method for executing an automated analysis of data, in particular social media data, for product failure detection | |
| US20110035094A1 (en) | System and method for automatic fault detection of a machine | |
| CN103761173A (en) | Log based computer system fault diagnosis method and device | |
| CN107168285A (en) | A kind of automobile intelligent fault diagnosis of combination subjective and objective information and cloud model and maintenance householder method and system | |
| CN107316057A (en) | Based on the nuclear power unit method for diagnosing faults being locally linear embedding into K nearest neighbor classifiers | |
| CN103514183A (en) | Information search method and system based on interactive document clustering | |
| CN104677997B (en) | A kind of transformer oil chromatographic on-line monitoring differentiation method for early warning | |
| Vong et al. | Simultaneous-fault detection based on qualitative symptom descriptions for automotive engine diagnosis | |
| US20170213222A1 (en) | Natural language processing and statistical techniques based methods for combining and comparing system data | |
| CN109240258A (en) | Vehicle failure intelligent auxiliary diagnosis method and system based on term vector | |
| CN112818008A (en) | Intelligent diagnosis method, system, medium and electronic equipment for nuclear power debugging faults | |
| CN114239734B (en) | Distributed vehicle-mounted health management system | |
| CN111506048A (en) | Vehicle fault early warning method and related equipment | |
| US11807253B2 (en) | Method and system for detecting driving anomalies | |
| CN111678699A (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| TWI677830B (en) | Method and device for detecting key variables in a model | |
| Kim et al. | An empirical study on real-time data analytics for connected cars: Sensor-based applications for smart cars | |
| CN113240133B (en) | Relay protection equipment familial defect identification method based on artificial intelligence | |
| CN118035757A (en) | Electric drive assembly fault diagnosis method and device based on large language model | |
| CN109871304B (en) | Satellite power state evaluation method | |
| CN112182193A (en) | Log obtaining method, device and medium in traffic industry | |
| CN116737882A (en) | Vehicle-mounted fault analysis method and device, computer equipment and storage medium |
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: 20180907 |