CN114880922A - Civil aviation-oriented flight data analysis and performance trend prediction system - Google Patents
Civil aviation-oriented flight data analysis and performance trend prediction system Download PDFInfo
- Publication number
- CN114880922A CN114880922A CN202210392693.8A CN202210392693A CN114880922A CN 114880922 A CN114880922 A CN 114880922A CN 202210392693 A CN202210392693 A CN 202210392693A CN 114880922 A CN114880922 A CN 114880922A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- analysis
- mainly used
- 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.)
- Pending
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 23
- 238000003745 diagnosis Methods 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 230000005540 biological transmission Effects 0.000 claims abstract description 10
- 238000013523 data management Methods 0.000 claims abstract description 9
- 238000007726 management method Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000008676 import Effects 0.000 claims description 10
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 17
- 238000012423 maintenance Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the field of big data analysis and intelligent prediction, and discloses a flight data analysis and performance trend prediction system for civil aviation, which is designed aiming at a client and a server respectively: the client part mainly comprises a data management and transmission module, a data analysis and diagnosis module and a performance prediction module; the central server part mainly comprises a database management module and an algorithm operation and analysis module. Aiming at the characteristics of large data quantity and large parameter quantity of the airplane, the invention realizes the storage and classification management of data and the training and operation of a prediction algorithm through a central server; the client side reads and analyzes data, performs simple fault diagnosis and visually displays the result of the prediction algorithm.
Description
Technical Field
The invention belongs to the field of big data analysis and intelligent prediction, and relates to a civil aviation-oriented flight data analysis and performance trend prediction system.
Background
The civil aviation aircraft is a very important passenger traffic, and the safety and maintenance problems are very important. At present, the maintenance of the airplane is mainly divided into regular maintenance type maintenance and fault maintenance, and data recorded in the flying process is an important means for detecting faults. The flight parameter data is called flight parameter data for short, records relatively comprehensive flight state information such as the engine speed, the engine temperature, the flight attitude and the like in the operation process of the airplane, and is an important data source for monitoring and diagnosing the operation state of the airplane. At present, the intelligent processing on flight parameter data is low, and particularly for a new type of engine, a universal monitoring system is lacked.
With the continuous development of modern science and technology, technologies such as artificial intelligence, data mining, neural networks and the like make a significant breakthrough and are beginning to be applied to various industrial scenes. Combining the flight parameter data with the intelligent algorithm becomes a breakthrough to the problem.
Most of existing software adopts a fault tree combined with experience criteria to carry out diagnosis, accuracy is low, and secondary confirmation of faults needs to be carried out manually in many times, so that data inspection efficiency is low. In addition, many slight faults are difficult to extract and judge due to unobvious parameter characteristics, and the early discovery and prevention of the faults are influenced to a certain extent. In practice, we prefer to predict as much as possible whether an engine will fail rather than merely monitor past operating conditions.
Disclosure of Invention
Aiming at the defects of the existing system, the invention provides a flight data analysis and performance trend prediction system for civil aviation. The system has the functions of data reading and storage, engine working state diagnosis, performance trend analysis and prediction and the like.
The technical scheme of the invention is as follows:
a civil aviation-oriented flight data analysis and performance trend prediction system is characterized in that a relational database is built, and the aircraft number, the engine number and the time of flight parameter data are used as unique identifiers and as main attributes of the relational database, so that the flight parameter data of different aircrafts can be conveniently stored and searched, and the problem that the conventional system is not provided with multi-aircraft batch processing is solved. The system introduces a method on-line calculation and neural network technology based on support vector data description, can also carry out fault prediction on flight parameter data on the basis of carrying out data interpretation based on a traditional fault tree, and greatly enhances the safety guarantee function of the airplane. Meanwhile, the problems of memory occupation and computational efficiency are considered, the system adopts a method of large-scale workstation centralized operation and a method of storing data by a central file server, and the requirement on the storage capacity of each client is reduced. Meanwhile, a machine learning technology which is developed rapidly at present is introduced to classify and predict flight parameter data, so that a prediction function is realized to a certain degree, and technical support is provided for implementing and maintaining according to the situation.
A civil aviation-oriented flight data analysis and performance trend prediction system comprises: a client and a central server;
the client system includes: the system comprises a data management and transmission module, a data analysis and diagnosis module and a performance prediction module;
the data management and transmission module mainly comprises a data import submodule, a data search submodule and a data deletion submodule; the data import submodule is mainly used for supporting uploading of various types of common data and checking local import records and historical records; the data search sub-module is mainly used for inputting search keywords in a search box for searching, and a system can automatically highlight search results; the data deleting submodule is mainly used for checking and deleting the data needing to be deleted;
the data analysis and diagnosis module mainly comprises a parameter information display area and a function area; the parameter information display area is mainly used for displaying the variation trend of the selected parameters; the functional area is mainly used for curve color adjustment, detailed information display, statistic value display and curve calculation;
the performance prediction module mainly predicts the state of the engine through an algorithm;
the central server system includes: the system comprises a database management module and an algorithm operation and analysis module;
the database management module is mainly used for storing the flight parameter data read by each client in a centralized manner;
the algorithm operation and analysis module is mainly used for fault diagnosis and performance trend prediction and data analysis by using an SVDD method.
The invention has the beneficial effects that: on the basis of fault diagnosis based on the traditional fault tree, a plurality of intelligent learning algorithms are added, and the algorithms can be trained through the existing data, so that the effects of improving the fault detection rate and predicting the performance change trend of the engine in a short time in the future are achieved. In addition, the central server is adopted to run the training process of the algorithm, so that the performance loss of each client is reduced, the existing result can be transmitted to each client in real time for use, and the problem of repeated training is avoided.
Drawings
FIG. 1 is a schematic diagram of a system for analyzing flight data and predicting performance trend for civil aviation.
Detailed Description
The following further describes a specific embodiment of the present invention with reference to the drawings and technical solutions.
The invention relates to a civil aviation-oriented flight data analysis and performance trend prediction system, which comprises a client part and a central server part. The client part consists of a data management and transmission module, a data analysis and diagnosis module and a performance prediction module; the central server part consists of a database management module and an algorithm operation and analysis module.
In general, the flight parameter data name may be described by { dataname. Wherein dataname is the name of the flight parameter data, and generally includes the time information of the time data; the datatype is a flight parameter data format, which is commonly known as txt, csv and the like, and the formats of the flight parameter data recorded by airplanes of different manufacturers may be different.
The main functions of the data management and transmission module are to analyze and read data and upload the data to the central server, and provide management functions of data searching, screening, deleting and the like. The specific implementation method comprises the following steps:
1. data import:
the method supports the uploading of various types of common data, and the user can select the data file for uploading in a self-defined manner. The system judges the manufacturer of the flight parameter data according to the file format and the initial byte content of the file, and extracts information such as the airplane number, the engine number and the like. When a file or a folder to be imported is selected, the shortcut key can be used for fully selecting data in the folder, and any number of files can be imported by matching with mouse clicking. And the data import starts a new thread in the background, the user can check and operate the uploaded data while uploading the data, and the user interface is not influenced.
In the process of importing the file, a 'expansion' button on the right side of the import status bar or a 'progress' button on the upper right corner is clicked to check the local import record, the file which is currently imported and the history records of all the files which are imported can be checked, and the displayed content can be switched by clicking 'current transmission' or 'history transmission'.
2. Data search:
for large amounts of data, a retrieval function is often required. And inputting search keywords in the search box for searching, and automatically highlighting search results by the system. Because the flight parameter data volume is large, the efficiency is low by adopting a conventional search algorithm, and therefore the system is optimized aiming at the problem. The field structure is simplified when the data storage table is established, so that unnecessary redundant data is minimized, and the quantity of connection queries is reduced. Since string of a fixed length is relatively more efficient, char is used instead of varchar type when storing character information such as airplane number, engine number, and the like. After a data table is used for a long time, the data may generate a lot of disk fragments due to a large number of update and delete operations, and the time taken to perform a physical search in the table may also increase. In the MySQL underlying design, the database would be mapped to a directory with some file structure, while the tables would be mapped to files. Therefore, the system can automatically generate and regularly update the index so as to achieve the purpose of improving the query speed.
3. And (3) deleting data:
the user can select a data deletion option in a data management option card in a menu above the main interface, and the data to be deleted can be deleted by checking the data to be deleted in a popup data selection window.
The data analysis and diagnosis module has the main functions of displaying and performing basic analysis on the flight parameter data. The module window interface comprises a data parameter information display area and a function area. The parameter information display area is used for displaying the variation trend of the selected parameter, and the function area comprises four sub-functions, namely 'parameter', 'display', 'judgment' and 'calculation'.
The parameter to be displayed can be selected in the parameter function, the color of the curve and the corresponding parameter name can be displayed below the parameter, and the color palette can be popped up by clicking the color square, so that the color of the curve can be modified. The intermediate search box provides a parameter search function in which an entered character automatically highlights all parameters whose name contains the entered character.
The "display" function is used to display detailed information of the playback curve. When the mouse cursor is moved to the curve display area, the reference line is automatically displayed at the cursor and moves along with the mouse, and the name of the curve is displayed near the intersection point of the reference line and the curve. And displaying the time of the position of the reference line where the cursor is located and the parameter value of the currently selected curve in real time in the right area of the page.
The judging function can display the maximum and minimum values, the average value and Delta value information of the curve in the current drawing area, and the statistical range can be modified by dragging the mouse to adjust the drawing area. The horizontal scroll bar may adjust information displayed in the tab page.
The 'calculation' function can perform basic arithmetic operations such as addition and subtraction on the selected data curves, and facilitates the comparative analysis between different data.
The primary function of the performance prediction module is to predict engine states via an algorithm. And the client reads the algorithm module data from the server and displays the prediction result in a graph form.
The main function of the database management module in the central server is to store the flight parameter data read by each client in a centralized manner. The system is improved aiming at the data management and analysis system based on the independent single machine, a large workstation centralized computing method and a large central file server data storage method are adopted, a large amount of aeroengine state monitoring data are placed in the central file server, and the storage requirement and the performance requirement on a small terminal are reduced. The server stores data by adopting a relational database in a row and column mode to form a two-dimensional table, each field of the data is defined in the table in advance, and the data is stored according to the label classification during storage, so that the data can be read and modified quickly. The large-scale workstation can utilize high computing power to compute the data sent by the terminal and then return the data to the terminal, so that the time for data analysis is saved.
The file server uses SQL language to inquire and control the database. The flight number and time serve as unique identifiers, as the main attributes of the relational database, the long integer variable type is adopted, and each record serves as a tuple. Besides the main attributes, the aeroengine state data are stored in data fields by adopting a data type of a double array, analysis results, judgment contents, expert opinions and the like are stored in each field in a text form respectively, and the data type of a char array is adopted.
The algorithm operation and analysis module is mainly used for training the intelligent learning algorithm through a large amount of stored data, the server is used for carrying out the part of work, the problem that the training time is long due to insufficient configuration of a client computer can be solved, and the trained algorithm can be directly transmitted to each client for use. In the system, a mode of workstation calculation can be adopted when the neural network algorithm is adopted in the aspect of fault diagnosis for predicting and diagnosing fault points, and a mode of workstation calculation is also required when the multi-section curve is subjected to hybrid calculation in data analysis. The data are stored in the server, so that the time consumption of data transmission and summarization is saved. And the simple task needs less data volume and can be directly calculated by a small terminal. For the selection of the two calculation methods, a preset method can be adopted, and an algorithm for judging time complexity can also be added to automatically switch the two calculation methods.
The fault diagnosis and performance trend prediction in the system can be calculated by combining a large amount of data by using empirical criteria, wherein the empirical criteria are that a threshold curve is made by using empirical fault data, the threshold curve is directly used for judgment, and the online calculation can also be carried out by adopting a mode based on an intelligent learning algorithm. In addition, different from built-in experience criteria, the system supports the user to customize an online judgment method for adding fault diagnosis, and the user can freely select different methods for operation.
The system adopts a method for calculation based on support vector data description, is different from a single diagnosis method based on single machine experience criterion, can analyze the fault which occurs in the past by utilizing the existing data, can predict the fault which is not found in the past diagnosis by extracting data characteristics, and can obtain a conclusion with higher security by combining the experience criterion after error report.
SVDD is a description of support vector data, and a hypersphere which surrounds all normal sample data as much as possible is obtained through optimization. And for different engines and different routes, the abnormal data are different frequently, the value of initial time in a section of route is selected as sample data of SVDD training, input data is preprocessed to obtain a characteristic vector, then the characteristic vector is input into a training model, and classification models f (z) and R for detecting the abnormality are obtained after classification training. After new data is imported, preprocessing is similarly performed to obtain a feature vector, the feature vector is put into a classifier f (z), if f (z) < ═ R, the imported data is normal, and if f (z) > < R, the imported data is abnormal.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made to the present invention by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (1)
1. A civil aviation-oriented flight data analysis and performance trend prediction system is characterized by comprising the following components: a client and a central server;
the client system includes: the device comprises a data management and transmission module, a data analysis and diagnosis module and a performance prediction module;
the data management and transmission module mainly comprises a data import submodule, a data search submodule and a data deletion submodule; the data import submodule is mainly used for supporting uploading of various types of common data and checking local import records and historical records; the data search sub-module is mainly used for inputting search keywords in a search box for searching, and a system can automatically highlight search results; the data deleting submodule is mainly used for checking and deleting the data needing to be deleted;
the data analysis and diagnosis module mainly comprises a parameter information display area and a function area; the parameter information display area is mainly used for displaying the variation trend of the selected parameters; the functional area is mainly used for curve color adjustment, detailed information display, statistic value display and curve calculation;
the performance prediction module mainly predicts the state of the engine through an algorithm;
the central server system includes: the system comprises a database management module and an algorithm operation and analysis module;
the database management module is mainly used for storing the flight parameter data read by each client in a centralized manner;
the algorithm operation and analysis module is mainly used for fault diagnosis and performance trend prediction and data analysis by using an SVDD method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210392693.8A CN114880922A (en) | 2022-04-15 | 2022-04-15 | Civil aviation-oriented flight data analysis and performance trend prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210392693.8A CN114880922A (en) | 2022-04-15 | 2022-04-15 | Civil aviation-oriented flight data analysis and performance trend prediction system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114880922A true CN114880922A (en) | 2022-08-09 |
Family
ID=82669780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210392693.8A Pending CN114880922A (en) | 2022-04-15 | 2022-04-15 | Civil aviation-oriented flight data analysis and performance trend prediction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114880922A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101907681A (en) * | 2010-07-15 | 2010-12-08 | 南京航空航天大学 | Analog circuit dynamic online failure diagnosing method based on GSD-SVDD |
| CN104760892A (en) * | 2014-01-06 | 2015-07-08 | 中国特种设备检测研究院 | Harbor crane health monitoring and forecasting visualization system |
| CN107545613A (en) * | 2016-06-29 | 2018-01-05 | 河南蓝信软件有限公司 | EMUs ATP runs monitoring record data analysis system |
| CN109657953A (en) * | 2018-12-10 | 2019-04-19 | 杭州意能电力技术有限公司 | Grounding net of transformer substation digital management system |
| CN110097144A (en) * | 2019-06-15 | 2019-08-06 | 青岛大学 | A kind of tire detects big data and cloud computing system and its application study automatically |
| CN111953783A (en) * | 2020-08-14 | 2020-11-17 | 赫谱信息技术有限公司 | Data acquisition and analysis system and method for warehousing and transportation equipment |
| CN112084575A (en) * | 2020-08-14 | 2020-12-15 | 陕西千山航空电子有限责任公司 | Helicopter vibration data processing and analyzing software platform architecture |
| CN213123069U (en) * | 2020-09-27 | 2021-05-04 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Aircraft health management system |
-
2022
- 2022-04-15 CN CN202210392693.8A patent/CN114880922A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101907681A (en) * | 2010-07-15 | 2010-12-08 | 南京航空航天大学 | Analog circuit dynamic online failure diagnosing method based on GSD-SVDD |
| CN104760892A (en) * | 2014-01-06 | 2015-07-08 | 中国特种设备检测研究院 | Harbor crane health monitoring and forecasting visualization system |
| CN107545613A (en) * | 2016-06-29 | 2018-01-05 | 河南蓝信软件有限公司 | EMUs ATP runs monitoring record data analysis system |
| CN109657953A (en) * | 2018-12-10 | 2019-04-19 | 杭州意能电力技术有限公司 | Grounding net of transformer substation digital management system |
| CN110097144A (en) * | 2019-06-15 | 2019-08-06 | 青岛大学 | A kind of tire detects big data and cloud computing system and its application study automatically |
| CN111953783A (en) * | 2020-08-14 | 2020-11-17 | 赫谱信息技术有限公司 | Data acquisition and analysis system and method for warehousing and transportation equipment |
| CN112084575A (en) * | 2020-08-14 | 2020-12-15 | 陕西千山航空电子有限责任公司 | Helicopter vibration data processing and analyzing software platform architecture |
| CN213123069U (en) * | 2020-09-27 | 2021-05-04 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Aircraft health management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cheng et al. | Data and knowledge mining with big data towards smart production | |
| CN106716416A (en) | Data retrieval apparatus, program and recording medium | |
| US11886471B2 (en) | Synthetic intelligent extraction of relevant solutions for lifecycle management of complex systems | |
| WO2017183065A1 (en) | Device and method for tuning relational database | |
| CN104598367A (en) | System and method for automatically managing fault events of data center | |
| CN106383916B (en) | Data processing method based on predictive maintenance of industrial equipment | |
| CN112000773B (en) | Search engine technology-based data association relation mining method and application | |
| US20060129609A1 (en) | Database synchronization using change log | |
| CN108073681A (en) | Retrieve device, search method and search program | |
| CN116485576A (en) | Intelligent manufacturing management platform for brain data with known source in aviation manufacturing industry | |
| US11789931B2 (en) | User-interactive defect analysis for root cause | |
| CN112579728A (en) | Behavior abnormity identification method and device based on mass data full-text retrieval | |
| CN116882978B (en) | Deep sea submersible operation and maintenance support system based on product information frame | |
| CN114398442A (en) | Data-driven information processing system | |
| CN117194919A (en) | Production data analysis system | |
| KR100877156B1 (en) | System and method of access path analysis for dynamic sql before executed | |
| JP2007011604A (en) | Fault diagnostic system and program | |
| US11875230B1 (en) | Artificial intelligence system with intuitive interactive interfaces for guided labeling of training data for machine learning models | |
| CN114118222A (en) | Coal mill state early warning system and fault identification and diagnosis method | |
| CN114880922A (en) | Civil aviation-oriented flight data analysis and performance trend prediction system | |
| Li et al. | Improving performance of log anomaly detection with semantic and time features based on bilstm-attention | |
| CN116302984A (en) | Root cause analysis method and device for test task and related equipment | |
| JP7022472B1 (en) | Data management system, data management method and data management program | |
| CN113296994A (en) | Fault diagnosis system and method based on domestic computing platform | |
| US11868436B1 (en) | Artificial intelligence system for efficient interactive training of machine learning models |
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 |