CN111934903A - Docker container fault intelligent prediction method based on time sequence evolution genes - Google Patents
Docker container fault intelligent prediction method based on time sequence evolution genes Download PDFInfo
- Publication number
- CN111934903A CN111934903A CN202010599003.7A CN202010599003A CN111934903A CN 111934903 A CN111934903 A CN 111934903A CN 202010599003 A CN202010599003 A CN 202010599003A CN 111934903 A CN111934903 A CN 111934903A
- Authority
- CN
- China
- Prior art keywords
- docker container
- time
- docker
- time sequence
- hour
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 108090000623 proteins and genes Proteins 0.000 title claims abstract description 23
- 238000012423 maintenance Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 8
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000005065 mining Methods 0.000 claims description 5
- 230000000306 recurrent effect Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- 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)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Algebra (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Debugging And Monitoring (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A Docker container fault intelligent prediction method based on time sequence evolution genes comprises the following steps: segmenting a multidimensional time sequence into a plurality of segments; clustering the segments to find a typical pattern; for different modes, adopting a conditional countermeasure network (CVAE-GAN) to capture the distribution characteristics; the changes in the distribution characteristics over time are combined to predict an impending anomaly. The maintenance level of the cloud platform Docker is effectively improved.
Description
Technical Field
The invention relates to a Docker container fault intelligent prediction method based on a time sequence evolution gene, in particular to a Docker container fault intelligent prediction method based on a time sequence evolution gene, which is provided for PaaS platform operation and maintenance and belongs to the field of communication.
Background
The traditional operation and maintenance mode of the PaaS platform is that after a network management system finds an equipment alarm, a maintenance person is informed to carry out maintenance, the manual repair after the fact is carried out, the fault response time is long, and the service requirement with high real-time performance cannot be met. The system operation and maintenance personnel have the problems of simple and repeated treatment in most of time and energy, large physical labor, low working efficiency and large investment in maintenance resources.
PaaS platforms typically have the following disadvantages:
(1) the network management system of the PaaS platform does not have an intelligent fault analysis function, and when a service is abnormal, a great amount of manpower is consumed by maintenance personnel to perform fault check and search for a fault reason, so that the system maintenance efficiency is low.
(2) The network management system of the PaaS platform has no intelligent fault early warning function, normal operation of the system can be influenced once serious faults occur, and system maintenance is passive.
Disclosure of Invention
The invention aims to provide a Docker container fault intelligent prediction method based on a time sequence evolution gene, so as to overcome the defects and shortcomings in the prior art. The method utilizes a time sequence evolution gene deep learning method to construct a Docker container fault intelligent prediction model, and accurately predicts the possible future faults of the Docker container by combining offline training and online training.
The invention aims to improve the intelligent operation and maintenance capability of the PaaS platform, realize the development of the operation and maintenance of the PaaS platform from 'after' to 'before', and really realize the 'prevention of the operation and maintenance of the PaaS platform in the bud'.
The technical problem to be solved by the invention can be realized by the following technical scheme:
as a first aspect of the present invention, a method for intelligently predicting a fault of a Docker container based on a time-series evolved gene is characterized by comprising:
segmenting a multidimensional time sequence into a plurality of segments;
clustering the segments to find a typical pattern;
for different modes, adopting a conditional countermeasure network (CVAE-GAN) to capture the distribution characteristics;
the changes in the distribution characteristics over time are combined to predict an impending anomaly.
Further, the method comprises the following steps:
step 1: collecting K8S component logs and K8S component states, wherein K8S is a Docker container management tool;
step 2: analyzing the K8S component log and the K8S component state, and extracting a Docker container characteristic index;
and step 3: constructing a time sequence evolution gene deep learning training model, and performing off-line training of historical data and on-line training of real-time data;
step four: and outputting intelligent Docker container fault early warning information and evaluating the model prediction effect.
Wherein, step 3 still includes:
step 3.1: at the time of one completionIn sequence, for each time segment
Training a classifier C to distinguish the type i of the Docker collected data in each time window,
step 3.2: then, for each one, a variation self-encoder (VAE) (including encoder network E, decoder network G)
Performing feature extraction;
specifically, the encoder E will
Coding a characteristic hidden layer including the combination of mean value and variance of multidimensional mixed Gaussian distribution
The decoder G then restores the samples by sampling this multi-dimensional mixed distribution;
step 3.3: reducing errors between encoding and sampling by KL divergence;
step 3.4: the generator network G being resampled
Performing inverse coding on the data to restore a real sample, and then enabling the discriminator not to identify errors as far as possible, wherein the target function is as follows:
step 3.5: the discriminator network D object distinguishes the real sample from the generated sample, and the objective function is as follows:
step 3.6: after the training is completed, the model is combinedHidden variable of each time interval
With real samples
By recurrent neural networks
Mining and analyzing the whole evolution process, and outputting the probability P and the characteristic estimated value of the abnormity of the Docker in the next period
Further, the Docker vessel characterization indices are as follows:
number of logs in the first 24 hours;
number of logs per hour;
minimum value of mean variance of component Name in each hour;
the maximum value and the minimum value of the host mean variance in each hour;
the proportions and amounts of info, error, and warning in each hour of maintenance.
As a second aspect of the invention, a Docker container fault intelligent prediction model map based on time sequence evolution genes.
Wherein the model combines hidden variables for each time interval
With real samples
By recurrent neural networks
Mining and analyzing the whole evolution process, and outputting the probability P and the characteristic estimated value of the abnormity of the Docker in the next period
The characteristic indexes of the Docker container are as follows:
number of logs in the first 24 hours;
number of logs per hour;
minimum value of mean variance of component Name in each hour;
the maximum value and the minimum value of the host mean variance in each hour;
the proportions and amounts of info, error, and warning in each hour of maintenance.
The invention has the beneficial effects that:
1. according to the method, the fault prediction model of the Docker container is obtained through historical time series data training of the Docker container, the operation fault of the Docker container can be accurately predicted through the gene evolution model, and the maintenance level of the Docker of the cloud platform is effectively improved.
2. Meanwhile, through the input of online time sequence data, the method can continuously update the algorithm of the Docker container, and provides more latest characteristic sequences for the running gene evolution model of the Docker container, thereby ensuring the timeliness and the accuracy of the Docker container fault algorithm.
Drawings
Fig. 1 is a flowchart of deep learning data processing.
Fig. 2 is a schematic diagram of the principle of the present invention.
Fig. 3 is a line graph of the failure feature 1.
Fig. 4 is a line graph of the failure feature 2.
Fig. 5 is a line graph of the failure feature 3.
Fig. 6 is a line graph of the failure feature 4.
Detailed Description
The present invention will be further described with reference to the following examples. It should be understood that the following examples are illustrative only and are not intended to limit the scope of the present invention.
Example 1
Fig. 1 is a flow chart of deep learning data processing, and fig. 2 is a schematic diagram of the principle of the present invention, as shown in fig. 1-2. A Docker container fault intelligent prediction method based on time sequence evolution genes comprises the following steps:
the deep learning data processing flow of the invention is as follows:
the invention discloses a Docker container fault intelligent prediction method based on a time sequence evolution gene, which comprises the following steps:
(1) segmenting the multidimensional time sequence into a plurality of segments;
(2) clustering the segments to find a typical mode;
(3) for different modes, adopting a conditional countermeasure network (CVAE-GAN) to capture the distribution characteristics of the modes;
(4) and combining the changes of the distribution characteristics with time to predict the impending abnormality.
Further, the method comprises the following steps:
step 1: collecting K8S component logs and K8S component states, wherein K8S is a Docker container management tool;
step 2: analyzing the K8S component log and the K8S component state, and extracting a Docker container characteristic index;
and step 3: constructing a time sequence evolution gene deep learning training model, and performing off-line training of historical data and on-line training of real-time data;
step four: and outputting intelligent Docker container fault early warning information and evaluating the model prediction effect.
Wherein, step 3 still includes:
step 3.1: on a complete time sequence, for each time segment
Training a classifier C to distinguish the type i of the Docker collected data in each time window,
step 3.2: then, for each one, a variation self-encoder (VAE) (including encoder network E, decoder network G)
Performing feature extraction;
specifically, the encoder E will
Coding a characteristic hidden layer including the combination of mean value and variance of multidimensional mixed Gaussian distribution
The decoder G then restores the samples by sampling this multi-dimensional mixed distribution;
step 3.3: reducing errors between encoding and sampling by KL divergence;
step 3.4: the generator network G being resampled
Performing inverse coding on the data to restore a real sample, and then enabling the discriminator not to identify errors as far as possible, wherein the target function is as follows:
step 3.5: the discriminator network D object distinguishes the real sample from the generated sample, and the objective function is as follows:
step 3.6: after the training is completed, the model combines the hidden variables of each time interval
With real samples
By recurrent neural networks
Mining and analyzing the whole evolution process, and outputting the probability P and the characteristic estimated value of the abnormity of the Docker in the next period
The experimental results are as follows:
1. failure feature 1: some host accesses with low previous accesses suddenly become more.
Fig. 3 is a line graph of the fault signature 1, the upper graph being a line graph of the number of log occurrences per minute for 8 months, and the lower graph being a line graph of the number of log occurrences for a certain value of the fault signature 1 per minute for 8 months, as shown in fig. 3. The black line represents the time at which the abnormality occurred.
2. Failure feature 2: as many host accesses are made, a rising edge occurs.
Fig. 4 is a line graph of the fault signature 2, as shown in fig. 4, the upper graph being a line graph of the number of log occurrences per minute for 8 months, and the lower graph being a line graph of the number of log occurrences for a certain value of the fault signature 2 per minute for 8 months. The black line represents the time at which the abnormality occurred.
3. Failure feature 3: the log number becomes large, and the number of Warning and Error becomes large.
Fig. 5 is a line graph of the fault signature 3, the upper graph being a line graph of the number of log occurrences per minute for 8 months, and the lower graph being a line graph of the number of log occurrences for a certain value of the fault signature 3 per minute for 8 months, as shown in fig. 5. The black line represents the time at which the abnormality occurred.
4. Failure feature 4: the call volume for a certain service is suddenly increased.
Fig. 6 is a line graph of the fault signature 4, as shown in fig. 6, the upper graph being a line graph of the number of log occurrences per minute for 8 months, and the lower graph being a line graph of the number of log occurrences for a certain value of the fault signature 4 per minute for 8 months. The black line represents the time at which the abnormality occurred.
While the present invention has been described with reference to the specific embodiments, the present invention is not limited thereto, and various changes may be made without departing from the spirit of the present invention.
Claims (7)
1. A Docker container fault intelligent prediction method based on time sequence evolution genes is characterized by comprising the following steps:
segmenting a multidimensional time sequence into a plurality of segments;
clustering the segments to find a typical pattern;
for different modes, adopting a conditional countermeasure network (CVAE-GAN) to capture the distribution characteristics;
the changes in the distribution characteristics over time are combined to predict an impending anomaly.
2. The Docker container fault intelligent prediction method based on the time sequence evolution genes as claimed in claim 1, is characterized by comprising the following steps:
step 1: collecting K8S component logs and K8S component states, wherein K8S is a Docker container management tool;
step 2: analyzing the K8S component log and the K8S component state, and extracting a Docker container characteristic index;
and step 3: constructing a time sequence evolution gene deep learning training model, and performing off-line training of historical data and on-line training of real-time data;
step four: and outputting intelligent Docker container fault early warning information and evaluating the model prediction effect.
3. The Docker container fault intelligent prediction method based on the time-series evolution gene as claimed in claim 2, wherein step 3 further comprises:
step 3.1: on a complete time sequence, for each time segment
Training a classifier C to distinguish the type i of the Docker collected data in each time window,
step 3.2: then, for each one, a variation self-encoder (VAE) (including encoder network E, decoder network G)
Performing feature extraction;
specifically, the encoder E will
Coding a characteristic hidden layer including the combination of mean value and variance of multidimensional mixed Gaussian distribution
The decoder G then restores the samples by sampling this multi-dimensional mixed distribution;
step 3.3: reducing errors between encoding and sampling by KL divergence;
step 3.4: the generator network G being resampled
Performing inverse coding on the data to restore a real sample, and then enabling the discriminator not to identify errors as far as possible, wherein the target function is as follows:
step 3.5: the discriminator network D object distinguishes the real sample from the generated sample, and the objective function is as follows:
step 3.6: after the training is completed, the model combines the hidden variables of each time interval
With real samples
By recurrent neural networks
Mining and analyzing the whole evolution process, and outputting the probability P and the characteristic estimated value of the abnormity of the Docker in the next period
4. The Docker container fault intelligent prediction method based on the time-series evolution genes as claimed in claim 3 is characterized in that Docker container characteristic indexes are as follows:
number of logs in the first 24 hours;
number of logs per hour;
minimum value of mean variance of component Name in each hour;
the maximum value and the minimum value of the host mean variance in each hour;
the proportions and amounts of info, error, and warning in each hour of maintenance.
5. A Docker vessel fault intelligent prediction model map based on time-series evolution genes, established by the method of any one of claims 1 to 4.
6. The Docker container fault intelligent prediction model map based on time-series evolution genes as claimed in claim 5, wherein the model combines hidden variables of each time interval
With real samples
By recurrent neural networks
Mining and analyzing the whole evolution process, and outputting the probability P and the characteristic estimated value of the abnormity of the Docker in the next period
7. The Docker container fault intelligent prediction model map based on the time-series evolution genes as claimed in claim 6, wherein the Docker container characteristic indexes are as follows:
number of logs in the first 24 hours;
number of logs per hour;
minimum value of mean variance of component Name in each hour;
the maximum value and the minimum value of the host mean variance in each hour;
the proportions and amounts of info, error, and warning in each hour of maintenance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010599003.7A CN111934903B (en) | 2020-06-28 | 2020-06-28 | Docker container fault intelligent prediction method based on time sequence evolution gene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010599003.7A CN111934903B (en) | 2020-06-28 | 2020-06-28 | Docker container fault intelligent prediction method based on time sequence evolution gene |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111934903A true CN111934903A (en) | 2020-11-13 |
| CN111934903B CN111934903B (en) | 2023-12-12 |
Family
ID=73317242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010599003.7A Active CN111934903B (en) | 2020-06-28 | 2020-06-28 | Docker container fault intelligent prediction method based on time sequence evolution gene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111934903B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205856A (en) * | 2021-06-22 | 2021-08-03 | 南开大学 | Microorganism metagenome binning method and system |
| CN113887749A (en) * | 2021-08-23 | 2022-01-04 | 国网江苏省电力有限公司信息通信分公司 | Cloud edge cooperation-based multi-dimensional monitoring and disposal method, device and platform for power internet of things |
| CN114328116A (en) * | 2021-12-29 | 2022-04-12 | 香港中文大学（深圳） | Android application program running information visualization method and related components |
| CN117034020A (en) * | 2023-10-09 | 2023-11-10 | 贵州大学 | A zero-sample fault detection method for UAV sensors based on CVAE-GAN model |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080154808A1 (en) * | 2006-10-20 | 2008-06-26 | Genalytics, Inc. | Use and construction of time series interactions in a predictive model |
| CN101425066A (en) * | 2007-11-02 | 2009-05-06 | 日电（中国）有限公司 | Entity assorting device and method based on time sequence diagram |
| JP2016007169A (en) * | 2014-06-25 | 2016-01-18 | 大日本印刷株式会社 | Abnormality determination apparatus and program |
| CN110059845A (en) * | 2019-02-01 | 2019-07-26 | 国网浙江省电力有限公司温州供电公司 | Metering device clocking error trend forecasting method based on timing evolved genes model |
| CN110572288A (en) * | 2019-11-04 | 2019-12-13 | 河南戎磐网络科技有限公司 | Data exchange method based on trusted container |
| CN110825589A (en) * | 2019-11-07 | 2020-02-21 | 字节跳动有限公司 | Anomaly detection method and device for micro-service system and electronic equipment |
| CN111198808A (en) * | 2019-12-25 | 2020-05-26 | 东软集团股份有限公司 | Method, device, storage medium and electronic equipment for predicting performance index |
-
2020
- 2020-06-28 CN CN202010599003.7A patent/CN111934903B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080154808A1 (en) * | 2006-10-20 | 2008-06-26 | Genalytics, Inc. | Use and construction of time series interactions in a predictive model |
| CN101425066A (en) * | 2007-11-02 | 2009-05-06 | 日电（中国）有限公司 | Entity assorting device and method based on time sequence diagram |
| JP2016007169A (en) * | 2014-06-25 | 2016-01-18 | 大日本印刷株式会社 | Abnormality determination apparatus and program |
| CN110059845A (en) * | 2019-02-01 | 2019-07-26 | 国网浙江省电力有限公司温州供电公司 | Metering device clocking error trend forecasting method based on timing evolved genes model |
| CN110572288A (en) * | 2019-11-04 | 2019-12-13 | 河南戎磐网络科技有限公司 | Data exchange method based on trusted container |
| CN110825589A (en) * | 2019-11-07 | 2020-02-21 | 字节跳动有限公司 | Anomaly detection method and device for micro-service system and electronic equipment |
| CN111198808A (en) * | 2019-12-25 | 2020-05-26 | 东软集团股份有限公司 | Method, device, storage medium and electronic equipment for predicting performance index |
Non-Patent Citations (3)
| Title |
|---|
| SHAIFU GUPTA.ETC: ""A Supervised Deep Learning Framework for Proactive Anomaly Detection in Cloud Workloads"", 《2017 14TH IEEE INDIA COUNCIL INTERNATIONAL CONFERENCE (INDICON)》 * |
| 张硕: ""面向Docker容错的性能监控和自适应预复制检查点技术研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 王帅: ""基于日志的微服务化系统监测与故障预测的研究与实现"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205856A (en) * | 2021-06-22 | 2021-08-03 | 南开大学 | Microorganism metagenome binning method and system |
| CN113205856B (en) * | 2021-06-22 | 2022-07-12 | 南开大学 | Microorganism metagenome binning method and system |
| CN113887749A (en) * | 2021-08-23 | 2022-01-04 | 国网江苏省电力有限公司信息通信分公司 | Cloud edge cooperation-based multi-dimensional monitoring and disposal method, device and platform for power internet of things |
| CN114328116A (en) * | 2021-12-29 | 2022-04-12 | 香港中文大学（深圳） | Android application program running information visualization method and related components |
| CN117034020A (en) * | 2023-10-09 | 2023-11-10 | 贵州大学 | A zero-sample fault detection method for UAV sensors based on CVAE-GAN model |
| CN117034020B (en) * | 2023-10-09 | 2024-01-09 | 贵州大学 | A zero-sample fault detection method for UAV sensors based on CVAE-GAN model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111934903B (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111914873B (en) | A two-stage unsupervised anomaly prediction method for cloud servers | |
| CN114201374B (en) | Operation and maintenance time sequence data anomaly detection method and system based on hybrid machine learning | |
| CN111934903B (en) | Docker container fault intelligent prediction method based on time sequence evolution gene | |
| CN111506478A (en) | Method for realizing alarm management control based on artificial intelligence | |
| CN111582542B (en) | A power load prediction method and system based on abnormality repair | |
| CN114723285B (en) | Power grid equipment safety evaluation prediction method | |
| CN117749409A (en) | Large-scale network security event analysis system | |
| CN112816898B (en) | Battery failure prediction method and device, electronic equipment and storage medium | |
| CN118941071A (en) | Industrial safety risk assessment and management system and method based on cognitive computing | |
| CN117633779A (en) | Rapid deployment method and system for element learning detection model of network threat in power network | |
| CN116467592A (en) | Production equipment fault intelligent monitoring method and system based on deep learning | |
| CN119716362A (en) | Station power consumption system safety energy-efficiency monitoring system based on multisource information fusion | |
| CN118939505A (en) | Monitoring and early warning method, device, system, electronic device and storage medium | |
| CN117993562A (en) | Wind turbine generator system fault prediction method and system based on artificial intelligent big data analysis | |
| CN111209955A (en) | Airplane power supply system fault identification method based on deep neural network and random forest | |
| CN119475231B (en) | Substation equipment fault early warning system and method integrating defect detection | |
| CN115169650B (en) | Equipment health prediction method for big data analysis | |
| CN118228089A (en) | An improved method for fault diagnosis of dissolved gas in transformer oil | |
| CN112884170A (en) | Predictive intelligent operation and maintenance system and method for comprehensive pipe gallery | |
| CN118972235B (en) | Power communication network fault diagnosis method, system and device based on deep learning | |
| CN118656611B (en) | A surge event identification method and identification system based on multi-parameter learning | |
| CN120321034B (en) | Virtual power plant network security pollution identification method, device, electronic equipment and storage medium | |
| CN114371686B (en) | Multi-working condition process fault detection method and system based on local neighborhood standardization | |
| CN119987832A (en) | Software automated operation and maintenance method and system based on AI technology | |
| CN119740003A (en) | A method for predicting fault trends in complex power systems |
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 |