CN111897630B - Method and device for constructing equipment alarm knowledge base based on deep learning - Google Patents
Method and device for constructing equipment alarm knowledge base based on deep learning Download PDFInfo
- Publication number
- CN111897630B CN111897630B CN202010526330.XA CN202010526330A CN111897630B CN 111897630 B CN111897630 B CN 111897630B CN 202010526330 A CN202010526330 A CN 202010526330A CN 111897630 B CN111897630 B CN 111897630B
- Authority
- CN
- China
- Prior art keywords
- alarm
- data
- vector representation
- equipment information
- alarm data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/466—Transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a method and a device for constructing an equipment alarm knowledge base based on deep learning, wherein the method comprises the steps of adopting synchronous processing of alarm data of the same equipment within a period of time; taking out alarm data (including alarm types and alarm levels) meeting preset frequencies and preset relativity through a correlation rule algorithm, and splicing vector representations of the alarm types and the alarm levels to obtain vector representations of the alarm data; normalizing and vectorizing equipment information data corresponding to the alarm data to obtain vector representation of the equipment information data; the method comprises the steps of training vector representation of alarm data and vector representation of equipment information data by adopting a deep learning method, obtaining important equipment information and threshold values of the important equipment information, and constructing an alarm knowledge base by selecting the alarm data, the important equipment information corresponding to the alarm data and the threshold values of the important equipment information corresponding to the alarm data, so that an alarm information base with complete and accurate data can be provided.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for constructing a device alarm knowledge base based on deep learning.
Background
The inventor finds that the prior intelligent equipment manufacturing alarm information stores have the problems of data missing, data repetition, time asynchronism and a large amount of noise in the research. And an alarm information base with complete data and accurate data has important significance for improving fault detection efficiency and guaranteeing normal production of intelligent equipment. Therefore, how to overcome the problems of missing data, repeated data, asynchronous time and large amount of noise in the alarm information base of the intelligent equipment, so as to obtain the alarm information base with more complete and accurate data is a technical problem to be solved.
Disclosure of Invention
The invention aims to provide a construction method of an equipment alarm knowledge base, which aims to solve the technical problems of data missing, data repetition and time asynchronism and large noise content of the existing intelligent equipment alarm information base.
In order to solve the above technical problems, an embodiment of the present invention provides a method for constructing a device alert knowledge base based on deep learning, including:
synchronously processing alarm data of the same equipment within a period of time in a sliding time window mode to obtain alarm transaction libraries of different windows; wherein, redundant alarm data in the same window is reserved; the alarm data comprises an alarm type and an alarm level;
extracting alarm data meeting preset frequency and preset relativity from alarm object libraries of different windows through an association rule algorithm to serve as second alarm data; the second alarm data comprises a second alarm type and a second alarm level;
carrying out vectorization processing on the second alarm type and the second alarm level respectively to obtain vector representation of the second alarm type and vector representation of the second alarm level;
splicing the vector representation of the second alarm type and the vector representation of the second alarm level to obtain the vector representation of the alarm data;
normalizing the equipment information data corresponding to the second alarm data, and vectorizing the normalized equipment information data to obtain vector representation of the equipment information data;
training the vector representation of the second alarm data and the vector representation of the equipment information data by adopting a deep learning method to acquire important equipment information corresponding to the second alarm data and a threshold value of the important equipment information corresponding to the second alarm data;
and selecting the second alarm data, the important equipment information corresponding to the second alarm data and the threshold value of the important equipment information corresponding to the second alarm data to construct an alarm knowledge base.
Further, the vectorizing processing is performed on the second alarm type and the second alarm level, so as to obtain a vector representation of the second alarm type and a vector representation of the second alarm level, which are specifically:
and respectively converting the second alarm type and the second alarm level into vectors with fixed lengths in a vector embedded mode to obtain a vector representation of the second alarm type and a vector representation of the second alarm level.
Further, the normalizing processing is performed on the device information data corresponding to the second alarm data, specifically: normalizing the equipment information data corresponding to the second alarm data to be in the range of 0-1.
In a second aspect, an embodiment of the present invention provides a device alert knowledge base construction apparatus based on deep learning, including:
the processing module is used for synchronously processing the alarm data of the same equipment within a period of time in a sliding time window mode to obtain alarm transaction libraries of different windows; wherein, redundant alarm data in the same window is reserved; the alarm data comprises an alarm type and an alarm level;
the extraction module is used for extracting alarm data meeting preset frequency and preset relativity from alarm object libraries of different windows through an association rule algorithm to serve as second alarm data; the second alarm data comprises a second alarm type and a second alarm level;
the alarm data vectorization module is used for respectively carrying out vectorization processing on the second alarm type and the second alarm level to obtain vector representation of the second alarm type and vector representation of the second alarm level;
the vector splicing module is used for splicing the vector representation of the second alarm type and the vector representation of the second alarm level to obtain the vector representation of the alarm data;
the normalization processing module is used for performing normalization processing on the equipment information data corresponding to the second alarm data;
the device information data vectorization module is used for carrying out vectorization processing on the normalized device information data and obtaining vector representation of the device information data;
the training module is used for training the vector representation of the second alarm data and the vector representation of the equipment information data by adopting a deep learning method, and acquiring important equipment information corresponding to the second alarm data and a threshold value of the important equipment information corresponding to the second alarm data;
and the alarm knowledge base construction module is used for selecting the second alarm data, the important equipment information corresponding to the second alarm data and the threshold value of the important equipment information corresponding to the second alarm data to construct an alarm knowledge base.
Further, the vectorizing processing is performed on the second alarm type and the second alarm level, so as to obtain a vector representation of the second alarm type and a vector representation of the second alarm level, which are specifically:
and respectively converting the second alarm type and the second alarm level into vectors with fixed lengths in a vector embedded mode to obtain a vector representation of the second alarm type and a vector representation of the second alarm level.
Further, the normalizing processing is performed on the device information data corresponding to the second alarm data, specifically: normalizing the equipment information data corresponding to the second alarm data to be in the range of 0-1.
In a third aspect, an embodiment of the present invention further provides a computer readable storage medium, where the computer readable storage medium includes a stored computer program, where when the computer program runs, the device where the computer readable storage medium is located is controlled to execute the method for building the device alert knowledge base based on deep learning as described above.
In summary, the beneficial effects of the embodiment of the invention are as follows:
according to the embodiment of the invention, the alarm data of the same equipment in a period of time are synchronously processed in a sliding time window mode, and redundant alarm data in the same window is reserved; taking out alarm data (the alarm data comprises alarm types and alarm levels) meeting preset frequencies and preset relativity through a correlation rule algorithm, respectively carrying out vectorization processing on the alarm types and the alarm levels, and splicing vector representations of the alarm types and the alarm levels to obtain vector representations of the alarm data; normalizing the equipment information data corresponding to the alarm data, and vectorizing the normalized equipment information data to obtain vector representation of the equipment information data; the method comprises the steps of training vector representation of alarm data and vector representation of equipment information data by adopting a deep learning method, obtaining important equipment information and threshold values of the important equipment information, and constructing an alarm knowledge base by selecting the alarm data, the important equipment information corresponding to the alarm data and the threshold values of the important equipment information corresponding to the alarm data, so that the problems that the intelligent equipment alarm information base is in data deficiency, data repetition, time dyssynchrony and contains a large amount of noise are solved, and a more complete and accurate alarm information base can be provided, thereby enabling equipment maintenance personnel to rapidly predict the cause of equipment failure and rapidly position fault points according to real-time equipment information data.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for constructing a deep learning-based device alert knowledge base according to one embodiment of the present invention.
FIG. 2 is a table of alarm data provided in one embodiment of the present invention.
FIG. 3 is an alarm knowledge base constructed in accordance with an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the step numbers used herein are for convenience of description only and are not limiting as to the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Referring to fig. 1, an embodiment of the present invention provides a method for constructing an equipment alarm knowledge base, including:
s1, synchronously processing alarm data of the same equipment within a period of time in a sliding time window mode to obtain alarm transaction libraries of different windows; wherein, redundant alarm data in the same window is reserved; the alert data includes an alert type and an alert level.
In the embodiment of the invention, the alarm transaction data in a period of time of the same equipment is synchronously processed in a sliding time window mode, specifically, according to an alarm data table (shown in fig. 2), the alarm data in a period of time of the same equipment is synchronously processed in a sliding time window mode, wherein the alarm data table comprises alarm data, labeling of alarm level & alarm type, equipment number and time (alarm time); the alarm data specifically comprises an alarm type and an alarm level.
S2, extracting alarm data meeting preset frequency and preset relativity from alarm object libraries of different windows to serve as second alarm data; the second alarm data comprises a second alarm type and a second alarm level.
One algorithm commonly used in association rules is the Apriori algorithm. The algorithm mainly comprises two steps: firstly, finding out all frequent item sets in a data set, wherein the occurrence frequency of the item sets is greater than or equal to the minimum support degree; strong association rules are then generated from the frequent item sets, which must meet a minimum support and minimum confidence. Taking the alarm data table of fig. 2 as an example, the association rule algorithm can learn that {1,4}, {1,3,4} has a larger association. Therefore, it is necessary to extract alarm data having a relatively high frequency of occurrence and a relatively high correlation.
S3, carrying out vectorization processing on the second alarm type and the second alarm level respectively to obtain vector representation of the second alarm type and vector representation of the second alarm level.
In the embodiment of the present invention, specifically, the second alarm type and the second alarm level are respectively converted into vector representations with fixed lengths by means of embedding.
S4, splicing the vector representation of the second alarm type and the vector representation of the second alarm level to obtain the vector representation of the alarm data.
For example, the vectorized representation of type A alarms is 000111; vectorization of the primary alarms is expressed as: 111001, the vector resulting in the first alert data of fig. 2 is denoted as "000111111001" by vector stitching.
S5, carrying out normalization processing on the equipment information data corresponding to the second alarm data, and carrying out vectorization processing on the normalized equipment information data to obtain vector representation of the equipment information data.
Specifically, the device information data is normalized to be in the range of 0-1.
It should be noted that, since there are a plurality of pieces of equipment information triggering equipment alarms (such as fan rotation, machine pressure, temperature, etc.), and each piece of equipment information has different contributions to various alarm transactions (the alarm transactions include alarm types and alarm levels, which are commonly called as alarm data in the embodiment of the present invention), if the original equipment information data is directly adopted for data processing, noise problems may be caused due to inconsistent orders of magnitude of each piece of equipment information data, and thus calculation result errors are large. According to the embodiment of the invention, the normalization processing is carried out on the equipment information parameters, namely the orders of magnitude of the equipment information data are unified, the problem of noise introduction is solved, and the calculation result is more accurate. By performing normalization processing and vectorization processing on the device information data, the computational complexity of the algorithm can be reduced.
In one embodiment, the device information data is converted into a fixed length vector representation by means of embedding.
And S6, training the vector representation of the second alarm data and the vector representation of the equipment information data by adopting a deep learning method, and acquiring important equipment information corresponding to the second alarm data and a threshold value of the important equipment information corresponding to the second alarm data.
The training the vector representation of the second alarm data and the vector representation of the device information data by adopting a deep learning method, and obtaining the important device information corresponding to the second alarm data and the threshold value of the important device information corresponding to the second alarm data includes:
training the vector representation of the second alarm data and the vector representation of the equipment information data by adopting a deep learning method to obtain important equipment information vectors corresponding to the second alarm data;
and deconvoluting the important equipment information vector corresponding to the second alarm data to obtain a threshold value of the important equipment information corresponding to the second alarm data.
Because the types of equipment faults are various and the faults have correlation, and the traditional neural network can only process one output, the embodiment of the invention solves the problem that the traditional neural network can not process by vectorizing equipment information (fault attributes such as the transfer of a fan, the pressure and the temperature of a machine) and marking the diversification of the fault attributes by adopting a method of splicing the alarm types and the alarm levels.
S7, selecting the second alarm data, the important equipment information corresponding to the second alarm data and the threshold value of the important equipment information corresponding to the second alarm data to construct an alarm knowledge base.
In one embodiment, the alert knowledge base is shown in FIG. 3.
In summary, the method for constructing the equipment alarm knowledge base provided by the embodiment of the invention can provide an alarm information base with more complete and accurate data, so that equipment maintenance personnel can rapidly predict the cause of equipment failure and rapidly locate failure points according to real-time equipment information data.
In one preferred embodiment, the vectorizing processing is performed on the second alarm type and the second alarm level, so as to obtain a vector representation of the second alarm type and a vector representation of the second alarm level, which are specifically:
and respectively converting the second alarm type and the second alarm level into vectors with fixed lengths in a vector embedded mode to obtain a vector representation of the second alarm type and a vector representation of the second alarm level.
In one preferred embodiment, the normalizing processing is performed on the device information data corresponding to the second alarm data, specifically: normalizing the equipment information data corresponding to the second alarm data to be in the range of 0-1.
Example 2:
the embodiment of the invention provides a device alarm knowledge base construction device based on deep learning, which comprises the following components:
the processing module is used for synchronously processing the alarm data of the same equipment within a period of time in a sliding time window mode to obtain alarm transaction libraries of different windows; wherein, redundant alarm data in the same window is reserved; the alarm data comprises an alarm type and an alarm level;
the extraction module is used for extracting alarm data meeting preset frequency and preset relativity from alarm object libraries of different windows through an association rule algorithm to serve as second alarm data; the second alarm data comprises a second alarm type and a second alarm level;
the alarm data vectorization module is used for respectively carrying out vectorization processing on the second alarm type and the second alarm level to obtain vector representation of the second alarm type and vector representation of the second alarm level;
the vector splicing module is used for splicing the vector representation of the second alarm type and the vector representation of the second alarm level to obtain the vector representation of the alarm data;
the normalization processing module is used for performing normalization processing on the equipment information data corresponding to the second alarm data;
the device information data vectorization module is used for carrying out vectorization processing on the normalized device information data and obtaining vector representation of the device information data;
the training module is used for training the vector representation of the second alarm data and the vector representation of the equipment information data by adopting a deep learning method, and acquiring important equipment information corresponding to the second alarm data and a threshold value of the important equipment information corresponding to the second alarm data;
and the alarm knowledge base construction module is used for selecting the second alarm data, the important equipment information corresponding to the second alarm data and the threshold value of the important equipment information corresponding to the second alarm data to construct an alarm knowledge base.
In one preferred embodiment, the vectorizing processing is performed on the second alarm type and the second alarm level, so as to obtain a vector representation of the second alarm type and a vector representation of the second alarm level, which are specifically:
and respectively converting the second alarm type and the second alarm level into vectors with fixed lengths in a vector embedded mode to obtain a vector representation of the second alarm type and a vector representation of the second alarm level.
In one preferred embodiment, the normalizing processing is performed on the device information data corresponding to the second alarm data, specifically: normalizing the equipment information data corresponding to the second alarm data to be in the range of 0-1.
It should be noted that, all technical contents and technical effects of the method for constructing a deep learning-based device alert knowledge base provided in the first embodiment of the present invention and all explanations and descriptions of the method for constructing a deep learning-based device alert knowledge base provided in the first embodiment of the present invention are applicable to the device for constructing a deep learning-based device alert knowledge base provided in the second embodiment of the present invention, so that the second embodiment of the present invention is not repeated herein.
Example 3:
the embodiment of the invention also provides a computer readable storage medium, which comprises a stored computer program, wherein when the computer program runs, equipment in which the storage medium is controlled to execute the construction method of the equipment alarm knowledge base based on the deep learning, and the technical effect consistent with the construction method of the equipment alarm knowledge base based on the deep learning is achieved.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer-readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
Claims (7)
1. The method for constructing the equipment warning knowledge base based on deep learning is characterized by comprising the following steps of:
synchronously processing alarm data of the same equipment within a period of time in a sliding time window mode to obtain alarm transaction libraries of different windows; wherein, redundant alarm data in the same window is reserved; the alarm data comprises an alarm type and an alarm level;
extracting alarm data meeting preset frequency and preset relativity from alarm object libraries of different windows through an association rule algorithm to serve as second alarm data; the second alarm data comprises a second alarm type and a second alarm level;
carrying out vectorization processing on the second alarm type and the second alarm level respectively to obtain vector representation of the second alarm type and vector representation of the second alarm level;
splicing the vector representation of the second alarm type and the vector representation of the second alarm level to obtain the vector representation of the alarm data;
normalizing the equipment information data corresponding to the second alarm data, and vectorizing the normalized equipment information data to obtain vector representation of the equipment information data;
training the vector representation of the second alarm data and the vector representation of the equipment information data by adopting a deep learning method to acquire important equipment information corresponding to the second alarm data and a threshold value of the important equipment information corresponding to the second alarm data; wherein the threshold is used to characterize a critical value of the important device information;
and selecting the second alarm data, the important equipment information corresponding to the second alarm data and the threshold value of the important equipment information corresponding to the second alarm data to construct an alarm knowledge base.
2. The method for constructing a deep learning-based device alert knowledge base according to claim 1, wherein the vectorizing processing is performed on the second alert type and the second alert level, respectively, to obtain a vector representation of the second alert type and a vector representation of the second alert level, specifically:
and respectively converting the second alarm type and the second alarm level into vectors with fixed lengths in a vector embedded mode to obtain a vector representation of the second alarm type and a vector representation of the second alarm level.
3. The method for constructing a deep learning-based device alert knowledge base according to claim 1, wherein the normalizing the device information data corresponding to the second alert data specifically includes: normalizing the equipment information data corresponding to the second alarm data to be in the range of 0-1.
4. The device for constructing the equipment warning knowledge base based on deep learning is characterized by comprising the following components:
the processing module is used for synchronously processing the alarm data of the same equipment within a period of time in a sliding time window mode to obtain alarm transaction libraries of different windows; wherein, redundant alarm data in the same window is reserved; the alarm data comprises an alarm type and an alarm level;
the extraction module is used for extracting alarm data meeting preset frequency and preset relativity from alarm object libraries of different windows through an association rule algorithm to serve as second alarm data; the second alarm data comprises a second alarm type and a second alarm level;
the alarm data vectorization module is used for respectively carrying out vectorization processing on the second alarm type and the second alarm level to obtain vector representation of the second alarm type and vector representation of the second alarm level;
the vector splicing module is used for splicing the vector representation of the second alarm type and the vector representation of the second alarm level to obtain the vector representation of the alarm data;
the normalization processing module is used for performing normalization processing on the equipment information data corresponding to the second alarm data;
the device information data vectorization module is used for carrying out vectorization processing on the normalized device information data and obtaining vector representation of the device information data;
the training module is used for training the vector representation of the second alarm data and the vector representation of the equipment information data by adopting a deep learning method, and acquiring important equipment information corresponding to the second alarm data and a threshold value of the important equipment information corresponding to the second alarm data; wherein the threshold is used to characterize a critical value of the important device information;
and the alarm knowledge base construction module is used for selecting the second alarm data, the important equipment information corresponding to the second alarm data and the threshold value of the important equipment information corresponding to the second alarm data to construct an alarm knowledge base.
5. The device for building a deep learning-based equipment alert knowledge base according to claim 4, wherein the vectorizing processing is performed on the second alert type and the second alert level to obtain a vector representation of the second alert type and a vector representation of the second alert level, specifically:
and respectively converting the second alarm type and the second alarm level into vectors with fixed lengths in a vector embedded mode to obtain a vector representation of the second alarm type and a vector representation of the second alarm level.
6. The device for constructing a deep learning-based device alert knowledge base according to claim 4, wherein the normalizing process is performed on the device information data corresponding to the second alert data, specifically: normalizing the equipment information data corresponding to the second alarm data to be in the range of 0-1.
7. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program when run controls a device in which the computer readable storage medium is located to execute the method for building the deep learning based device alert knowledge base according to any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010526330.XA CN111897630B (en) | 2020-06-10 | 2020-06-10 | Method and device for constructing equipment alarm knowledge base based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010526330.XA CN111897630B (en) | 2020-06-10 | 2020-06-10 | Method and device for constructing equipment alarm knowledge base based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111897630A CN111897630A (en) | 2020-11-06 |
| CN111897630B true CN111897630B (en) | 2023-07-18 |
Family
ID=73206257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010526330.XA Active CN111897630B (en) | 2020-06-10 | 2020-06-10 | Method and device for constructing equipment alarm knowledge base based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111897630B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102130783A (en) * | 2011-01-24 | 2011-07-20 | 浪潮通信信息系统有限公司 | Intelligent alarm monitoring method of neural network |
| CN110447215A (en) * | 2017-11-10 | 2019-11-12 | 华为技术有限公司 | The dynamic alarm method and terminal of application software malicious act |
| CN110781333A (en) * | 2019-06-26 | 2020-02-11 | 杭州鲁尔物联科技有限公司 | Method for processing unstructured monitoring data of cable-stayed bridge based on machine learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2831981B1 (en) * | 2001-11-08 | 2005-07-08 | Cit Alcatel | METHOD AND DEVICE FOR ANALYZING ALARMS FROM A COMMUNICATION NETWORK |
-
2020
- 2020-06-10 CN CN202010526330.XA patent/CN111897630B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102130783A (en) * | 2011-01-24 | 2011-07-20 | 浪潮通信信息系统有限公司 | Intelligent alarm monitoring method of neural network |
| CN110447215A (en) * | 2017-11-10 | 2019-11-12 | 华为技术有限公司 | The dynamic alarm method and terminal of application software malicious act |
| CN110781333A (en) * | 2019-06-26 | 2020-02-11 | 杭州鲁尔物联科技有限公司 | Method for processing unstructured monitoring data of cable-stayed bridge based on machine learning |
Non-Patent Citations (2)
| Title |
|---|
| Clustering analysis of process alarms using word embedding;embeddingShuang Cai et.al;《Journal of Process Control》;20191231;第260-269页 * |
| 基于Apriori 算法的时序关联关系数据挖掘装置的实现;国悦婷 等;《计算机与数字工程》;20181231;第46卷(第2期);第12-19页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111897630A (en) | 2020-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111897970B (en) | Text comparison method, device, equipment and storage medium based on knowledge graph | |
| CN110197099B (en) | Method and device for cross-age face recognition and model training thereof | |
| CN114218403B (en) | Fault root cause positioning method, device, equipment and medium based on knowledge graph | |
| Bui et al. | Learning Bayesian network structure using Markov blanket decomposition | |
| CN111125405A (en) | Power monitoring image anomaly detection method and device, electronic equipment and storage medium | |
| CN113008583A (en) | Method and device for monitoring state and automatically alarming abnormality of rotating machine | |
| CN115329876A (en) | Equipment fault processing method and device, computer equipment and storage medium | |
| CN112419268A (en) | Method, device, equipment and medium for detecting image defects of power transmission line | |
| CN117158923A (en) | Remote home-care monitoring method based on meta universe | |
| CN116910592B (en) | Log detection method and device, electronic equipment and storage medium | |
| CN114582325A (en) | Audio detection method and device, computer equipment and storage medium | |
| CN111897630B (en) | Method and device for constructing equipment alarm knowledge base based on deep learning | |
| Jianli et al. | Identification of fabric defects based on discrete wavelet transform and back-propagation neural network | |
| CN112528040B (en) | Detection method for guiding drive corpus based on knowledge graph and related equipment thereof | |
| Inacio et al. | Fault diagnosis with evolving fuzzy classifier based on clustering algorithm and drift detection | |
| CN112419243B (en) | Power distribution room equipment fault identification method based on infrared image analysis | |
| CN117409890A (en) | Transformer fault self-identification method and system based on two-way long and short-time memory | |
| CN116597635A (en) | Wireless communication intelligent gas meter controller and control method thereof | |
| CN114627462A (en) | Chemical formula identification method and device, computer equipment and storage medium | |
| CN114783423A (en) | Speech segmentation method and device based on speech rate adjustment, computer equipment and medium | |
| CN112541557B (en) | Training method and device for generating countermeasure network and electronic equipment | |
| CN111797194B (en) | Text risk detection method and device, electronic equipment and storage medium | |
| Li et al. | Changepoint detection in autocorrelated ordinal categorical time series | |
| CN112612260A (en) | Deep self-coding network process monitoring method based on dynamic estimation | |
| CN115471893B (en) | Face recognition model training, face recognition method and device |
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 |