CN112488371B - Pipeline intelligent early warning method and system based on big data - Google Patents
Pipeline intelligent early warning method and system based on big data Download PDFInfo
- Publication number
- CN112488371B CN112488371B CN202011313674.9A CN202011313674A CN112488371B CN 112488371 B CN112488371 B CN 112488371B CN 202011313674 A CN202011313674 A CN 202011313674A CN 112488371 B CN112488371 B CN 112488371B
- Authority
- CN
- China
- Prior art keywords
- data
- mixture model
- gaussian mixture
- pipeline
- class
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000000203 mixture Substances 0.000 claims abstract description 64
- 238000012360 testing method Methods 0.000 claims abstract description 33
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000010276 construction Methods 0.000 claims abstract description 21
- 238000012423 maintenance Methods 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 14
- 238000005520 cutting process Methods 0.000 claims abstract description 10
- 241001465754 Metazoa Species 0.000 claims abstract description 7
- 230000005611 electricity Effects 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims description 8
- 241000512668 Eunectes Species 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000009826 distribution Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 231100001261 hazardous Toxicity 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 206010002515 Animal bite Diseases 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 238000011278 co-treatment Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Primary Health Care (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A pipeline intelligent early warning method and system based on big data comprises the following steps: 1) the method comprises the steps that data are obtained and classified according to different scenes, the scene classification at least comprises large-scale electricity protection, conventional pipeline operation and maintenance construction, ground mechanical construction, cable cutting in a pipeline, and meshing of a submarine cable and an animal, and a data set of each class is divided into training data and testing data; 2) building a Gaussian mixture model, and estimating parameters of the Gaussian mixture model by using an expectation maximization algorithm; 3) simultaneously inputting the training data of each class into a Gaussian mixture model for training; 4) simultaneously inputting the test data of each class into the trained Gaussian mixture model for testing; 5) and carrying out scene recognition by adopting a Gaussian mixture model passing the test. The invention is beneficial to realizing the purpose of fine management of scene operation and maintenance of the power pipeline.
Description
Technical Field
The invention relates to the field of pipeline early warning, in particular to a pipeline intelligent early warning method and system based on big data.
Background
With the continuous revolution of social productivity and the high-speed development of industrial automation and electronic informatization, the development of productivity has been unable to leave power supply, in order to ensure the safety and reliability of power supply, the power grid operation safety needs to be highly valued, although power safety accidents may not be directly expressed as major casualties or economic losses, the power safety accidents can cause great influence on national economy, social stability and people's life, the spread range is wide, and the accident consequences have great influence.
In the process of power production or power grid operation, analysis and judgment of various unsafe factors can indirectly affect safe and stable operation of a power system or affect normal power supply, in order to control and avoid various risks, various measures need to be taken to avoid the factors, and power supply load, equipment faults and power supply users need to be comprehensively analyzed to assist power grid managers in ensuring safe and stable operation of power supply.
At present, the analysis of management and power grid safe operation is still in a manual judgment and analysis stage, the analysis comprises the load bearing user proportion of power transmission and transformation equipment and the like, the manual carding period of the work is long, the efficiency is low, the prevention and early warning of electric power safety accidents cannot be realized, and the analysis is basically in post statistical analysis. And the optical fiber sensing technology is also adopted, discrete data sets of time, place and event type are detected, and the decision basis provided for pipeline operation and maintenance personnel is insufficient in intuition.
Disclosure of Invention
The invention mainly aims to overcome the defects in the prior art, and provides a pipeline intelligent early warning method and system based on big data, which can accurately predict a scene mode according to data and a Gaussian mixture model, and is favorable for realizing the purpose of fine management of scene operation and maintenance of an electric power pipeline.
The invention adopts the following technical scheme:
a pipeline intelligent early warning method based on big data is characterized by comprising the following steps:
1) the method comprises the steps that data are obtained and classified according to different scenes, the scene classification at least comprises large-scale electricity protection, conventional pipeline operation and maintenance construction, ground mechanical construction, cable stealing in a pipeline and cable and animal biting, and a data set of each class is divided into training data and testing data;
2) building a Gaussian mixture model, and estimating parameters of the Gaussian mixture model by using an expectation maximization algorithm;
3) simultaneously inputting the training data of each class into a Gaussian mixture model for training;
4) simultaneously inputting the test data of each class into the trained Gaussian mixture model for testing;
5) and performing scene recognition by adopting a Gaussian mixture model passing the test.
Preferably, in step 1), the data set of each class at least comprises three elements of time, position and single event type.
Preferably, in step 2), the gaussian mixture model is a linear combination of multiple single gaussian models, the number of the single gaussian models is the same as the number of the scene classifications, and each single gaussian model is a cluster, and the gaussian mixture model can be represented by the following formula:
wherein, X is a random variable,
is the kth cluster, Π, in the Gaussian mixture model k The mixed coefficient is the weight of each single Gaussian model and satisfies pi k >0,
μ k Is an average value,
Is variance, and K is the total number of clusters.
Preferably, the estimating parameters of the gaussian mixture model by using the expectation maximization algorithm in step 2) specifically includes the following steps:
2.1) the expression of the Gaussian mixture model is substituted into the logarithm likelihood function as follows:
2.2) assumed data x n Then the probability that it belongs to the kth cluster is:
2.3) estimating the parameters of each cluster by adopting an iterative method, and assuming gamma (n, k) obtained in the last step as data x n Probability of belonging to the kth cluster, then each cluster generates γ (1, k) x 1 ,...,γ(N,k)x N From these points, we can find:
and repeating the step 2.2) -the step 2.3) until the parameter values of the Gaussian mixture model are stable.
Preferably, the training process in step 3) is implemented by using a sklern library in an Anaconda environment.
Pipeline intelligent early warning system based on big data, its characterized in that includes as follows
The data acquisition module is used for acquiring data and classifying the data according to different scenes, the scene classification at least comprises large-scale electricity conservation, conventional pipeline operation and maintenance construction, ground mechanical construction, cable cutting in the pipeline, and bite of a submarine cable and an animal, and a data group of each class is divided into training data and testing data.
The model construction module is used for constructing a Gaussian mixture model, estimating parameters of the Gaussian mixture model by using an expectation maximization algorithm and estimating parameters of the Gaussian mixture model by using the expectation maximization algorithm;
a training module for inputting the training data of each class into the Gaussian mixture model for training
The test module is used for simultaneously inputting the test data of each class into the trained Gaussian mixture model for testing
And the recognition module is used for recognizing the scene by adopting the Gaussian mixture model passing the test.
As can be seen from the above description of the present invention, compared with the prior art, the present invention has the following advantages:
1. the method and the system of the invention combine the inherent characteristics of various hazardous events of the pipeline in the basic data dimension and combine the Gaussian mixture model to study and judge the on-site complete picture of the pipeline event, thereby achieving the purpose of fine management of pipeline scene operation and maintenance.
2. According to the method and the system, the three elements of time, position and single event type of each data set are combined and judged in the dimension of the data set through scene recognition, so that the fault type can be accurately and quickly determined, passive operation and maintenance are changed into active operation and maintenance, and the intellectualization of the inspection operation is realized; the traditional inspection mode mainly based on manpower is changed, so that manpower is liberated from a large amount of repetitive field work, the sharp contradiction between the rapid increase of the length of the operation and maintenance pipeline and the shortage of operation and maintenance personnel is greatly relieved, and the monitoring requirements of wide range, long distance and all weather are met.
3. The method and the system have wide universality, and can be quickly copied and popularized in a power system and other units with massive line management requirements, such as water service, gas, radio and television and other industries. The method is flexibly applied to the power protection activities of pipeline external damage and large conferences, cable and optical cable theft prevention, dangerous house monitoring, expansion monitoring geology, road collapse and the like, and through pipeline risk information sharing, an intelligent safety city is created, and a ubiquitous Internet of things ecological circle with co-construction, co-treatment and co-win is constructed.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a graph of a single gaussian distribution and a mixed gaussian distribution model.
The invention is described in further detail below with reference to the figures and specific examples.
Detailed Description
The invention is further described below by means of specific embodiments.
The terms "first," "second," "third," and the like in this disclosure are used solely to distinguish between similar items and not necessarily to describe a particular order or sequence, nor are they to be construed as indicating or implying relative importance. In the description, the directions or positional relationships indicated by "up", "down", "left", "right", "front" and "rear" are used based on the directions or positional relationships shown in the drawings, and are only for convenience of describing the present invention, and do not indicate or imply that the device referred to must have a specific direction, be constructed and operated in a specific direction, and thus, should not be construed as limiting the scope of the present invention. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
In addition, in the description of the present application, "a plurality" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
Referring to fig. 1, a pipeline intelligent early warning method based on big data includes the following steps:
1) the obtained data are classified according to different scenes, the scene classification at least comprises large-scale electricity protection, conventional pipeline operation and maintenance construction, ground mechanical construction, cable cutting in the pipeline, submarine cable and animal biting, and the data set of each class is divided into training data and testing data.
In reality, different hazardous events have specific time rules, position rules and action rules. There are also different characteristics in the underlying data detected by fiber optic sensing technology and a certain degree of correspondence. The actual duration of each event varies from tens of minutes to hours, during which time sets of base data are generated. Each set of these base data contains three elements, time, location, and a single event type. Each group of data has different time, the position has dispersion of several meters to hundreds of meters, and the single event type is different. That is, each actual event is composed of a plurality of single events in the whole duration process, for example, a construction event in a primary pipeline may include a plurality of events such as touching an optical cable, mechanical vibration, and pulling the optical cable, and the events may occur at intervals or continuously.
2) And (5) building a Gaussian mixture model, and estimating parameters of the Gaussian mixture model by using an expectation maximization algorithm.
The Gaussian Mixture Model (GMM) is a probability statistical model, and the output is a probability value between 0 and 1, which is a statistical method of soft classification. The number of the Gaussian distributions is set to be the same as the types of the scenes to be identified, one type corresponds to one Gaussian distribution, and the recognition result with the maximum probability is selected. This corresponds to a hard classification, i.e. one input corresponds to one determined output. The number of clusters of the mixture model is arbitrarily changed, and theoretically, the distribution of any continuous probability density function can be approximated. Compared with hard classification, the fusion of the method to other models is better.
Assuming that data obey the distribution of the Gaussian mixture model, linearly combining a plurality of single Gaussian models, taking each single Gaussian model as a cluster, and obtaining a model called the Gaussian mixture model.
Referring to fig. 2, the solid curves represent three single gaussian distributions and the dashed curves represent their linear sum, i.e., a mixed gaussian distribution. Almost all probability density functions can be well fitted as long as the mean, variance and mixed coefficients of the three single-Gaussian distributions can be adjusted.
The Gaussian mixture model can be represented by the following equation:
wherein, X is a random variable,
is the kth cluster, Π, in the Gaussian mixture model k The mixed coefficient is the weight of each single Gaussian model and satisfies pi k >0,
μ k Is an average value,
Is the variance.
If there are three clusters for the three single gaussian distributions of fig. 2, then the number of components K is 3, Π k Is a mixture coefficient (coefficient), satisfies Π k >0,
Then II k Is the weight of each sub-gaussian model.
The use of GMMs is typically used for cluster distribution, where a point is randomly chosen in the GMM, i.e. one of K gaussian distributions is randomly selected, where each probability is a mixture coefficient pi k . Next one is selected in this single gaussian distribution,this becomes a problem of the ordinary gaussian distribution.
From the mixed Gaussian distribution formula, it can be seen that the total number of the unknown parameters is three, and the three are respectively the mixing coefficients pi k Mean value of μ k Variance, variance
The method uses an Expectation Maximization (EM) algorithm to estimate the parameters of the GMM through the EM algorithm.
In GMM, assuming there are N data points, the probability that a given data point will be generated by its determined Gaussian mixture distribution is maximized by finding a set of parameters that can be used
This product is then a likelihood function. Since the probability values are all small, they are usually logarithmized during calculation
If the maximum value of this function is found, the parameter at this time is considered to be the most suitable parameter, and the process of parameter estimation is completed, specifically including the following steps:
2.1) the expression of the Gaussian mixture model is substituted into the logarithm likelihood function as follows:
2.2) estimating the probability that the data is clustered by a certain cluster, i.e. assuming data X n Then the probability that it belongs to the kth cluster is:
2.3) estimating the parameters of each cluster by adopting an iterative method, and assuming gamma (n, k) obtained in the last step as data x n The probability of belonging to the kth cluster, can also be considered as thisThe contribution of each cluster in generating this data is considered by aggregating all the data points, which can be seen as γ (1, k) x is generated for each cluster 1 ,...,γ(N,k)x N From these points, we can find:
repeating the steps 2.2) to 2.3) until the parameter value pi of the Gaussian mixture model k 、μ k And
until stable.
3) And simultaneously inputting the training data of each class into a Gaussian mixture model for training.
The Gaussian mixture model training process of the invention can adopt a sklern library in an Anaconda environment, which is a machine learning library for python language and has various classification, regression and aggregation algorithms including random forest, gradient enhancement, k-means and the like. And simultaneously inputting training data of each class according to the classification of the scene into the Gaussian mixture model for training, respectively corresponding to large-scale power conservation, conventional pipeline operation and maintenance construction, ground mechanical construction, cable cutting in the pipeline, submarine cables, animal bite and the like to obtain a single Gaussian model corresponding to the scene, and then carrying out the next test.
4) And simultaneously inputting the test data of each class into the trained mixed Gaussian model for testing, and directly using the single Gaussian model which meets the accuracy requirement after testing in actual work.
5) And carrying out scene recognition by adopting a Gaussian mixture model passing the test.
The invention also provides a pipeline intelligent early warning system based on big data, which adopts the pipeline intelligent early warning method based on big data, and comprises the following modules:
the data acquisition module is used for acquiring data and classifying the data according to different scenes, the scene classification at least comprises large-scale electricity conservation, conventional pipeline operation and maintenance construction, ground mechanical construction, cable cutting in the pipeline, and bite of a submarine cable and an animal, and a data group of each class is divided into training data and testing data.
The model construction module is used for constructing a Gaussian mixture model, estimating parameters of the Gaussian mixture model by using an expectation maximization algorithm and estimating parameters of the Gaussian mixture model by using the expectation maximization algorithm;
the training module is used for inputting the training data of each class into the Gaussian mixture model for training;
the test module is used for inputting the test data of each class into the trained Gaussian mixture model for testing;
and the recognition module is used for recognizing scenes by adopting the Gaussian mixture model passing the test and outputting the recognized specific scene type, such as 'steal and cut cables'.
For example: theft-cutting device for cable in pipeline
The practical process has the following characteristics: a. the method is characterized in that the method is mainly used for controlling the opening and closing of manhole and well covers of pipelines, stepping or touching facilities in the pipelines, cutting by saws, pulling cables and the like. Each feature, if considered individually, is similar or even identical to an individual feature of the other events, and the combination of features becomes an inherent feature that is different from the other events.
Data given by the optical fiber sensing technology is a data set with time stamps, discrete positions and discrete disturbance types, and the discrete data are aggregated according to the prior classification in the GMM training process. By adopting the Gaussian mixture model, a macroscopic scene type result can be given to the cable stealing and cutting event according to the obtained scene mode through prediction.
The above description is only an embodiment of the present invention, but the design concept of the present invention is not limited thereto, and any insubstantial modifications made by using the design concept should fall within the scope of infringing the present invention.
Claims (4)
1. A pipeline intelligent early warning method based on big data is characterized by comprising the following steps:
1) the method comprises the steps that data are obtained and classified according to different scenes, wherein the scene classification comprises large-scale electricity conservation, conventional pipeline operation and maintenance construction, ground mechanical construction, cable cutting in a pipeline, and meshing of a submarine cable and an animal, and a data set of each class is divided into training data and testing data;
2) building a Gaussian mixture model, wherein the Gaussian mixture model is a linear combination of a plurality of single Gaussian models, the number of the single Gaussian models is the same as the scene classification number, each single Gaussian model is a cluster, and the Gaussian mixture model is represented by the following formula:
wherein, X is a random variable,
is the kth cluster, Π, in the Gaussian mixture model k Is a mixed coefficient, is the weight of each single Gaussian model and satisfies pi k >0,
μ k Is the mean value,
And estimating parameters of the Gaussian mixture model by using an expectation maximization algorithm, wherein the variance is K and the total number of clusters is K, and the method specifically comprises the following steps:
2.1) the expression of the Gaussian mixture model is substituted into the logarithm likelihood function as follows:
2.2) assumed data x n Then the probability that it belongs to the kth cluster is:
2.3) estimating the parameters of each cluster by adopting an iterative method, and assuming gamma (n, k) obtained in the last step as data x n Probability of belonging to the kth cluster, then each cluster generates γ (1, k) x 1 ,...,γ(N,k)x N From these points, we can find:
repeating the step 2.2) -the step 2.3) until the parameter value of the Gaussian mixture model is stable;
3) simultaneously inputting the training data of each class into a Gaussian mixture model for training;
4) simultaneously inputting the test data of each class into the trained Gaussian mixture model for testing;
5) and carrying out scene recognition by adopting a Gaussian mixture model passing the test.
2. The big-data-based intelligent pipeline early warning method as claimed in claim 1, wherein in step 1), the data set of each class at least comprises three elements of time, position and single event type.
3. The big-data-based intelligent pipeline early warning method as claimed in claim 1, wherein the training process in step 3) is implemented by using a sklern library in an Anaconda environment.
4. A pipeline intelligent early warning system based on big data is characterized in that the pipeline intelligent early warning method based on big data, which is disclosed by any one of claims 1 to 3, is adopted, and comprises the following steps
The data acquisition module is used for acquiring data and classifying the data according to different scenes, wherein the scene classification comprises large-scale electricity conservation, conventional pipeline operation and maintenance construction, ground mechanical construction, cable cutting in a pipeline, and bite of a submarine cable and an animal, and a data group of each class is divided into training data and test data;
the model construction module is used for constructing a Gaussian mixture model, estimating parameters of the Gaussian mixture model by using an expected value maximum algorithm and estimating the parameters of the Gaussian mixture model by using the expected value maximum algorithm;
the training module is used for inputting the training data of each class into the Gaussian mixture model for training;
the test module is used for inputting the test data of each class into the trained Gaussian mixture model for testing;
and the recognition module is used for recognizing the scene by adopting the Gaussian mixture model passing the test.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011313674.9A CN112488371B (en) | 2020-11-20 | 2020-11-20 | Pipeline intelligent early warning method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011313674.9A CN112488371B (en) | 2020-11-20 | 2020-11-20 | Pipeline intelligent early warning method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112488371A CN112488371A (en) | 2021-03-12 |
| CN112488371B true CN112488371B (en) | 2022-09-13 |
Family
ID=74932598
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011313674.9A Active CN112488371B (en) | 2020-11-20 | 2020-11-20 | Pipeline intelligent early warning method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112488371B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108171271B (en) * | 2018-01-11 | 2022-04-29 | 湖南大唐先一科技有限公司 | Early warning method and system for equipment degradation |
| CN113506025A (en) * | 2021-07-27 | 2021-10-15 | 中国科学院计算机网络信息中心 | Method and system for pipeline digital management |
| CN113808370A (en) * | 2021-09-17 | 2021-12-17 | 国家石油天然气管网集团有限公司 | Landslide-oriented multi-index coupling monitoring and early warning method |
| CN115841742A (en) * | 2022-11-16 | 2023-03-24 | 国网福建省电力有限公司厦门供电公司 | Diversified application scene pipeline monitoring risk early warning key method and system |
| CN117662974B (en) * | 2023-12-01 | 2024-07-30 | 中国特种设备检测研究院 | Vapor cold screen system for large-scale ship-borne liquid hydrogen spherical tank and working method thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2467828A1 (en) * | 2009-08-23 | 2012-06-27 | iAd Gesellschaft für Informatik, Automatisierung und Datenverarbeitung mbH | Method and system for automatic object detection and subsequent object tracking in accordance with the object shape |
| CN103605822B (en) * | 2013-10-08 | 2016-05-04 | 交通运输部天津水运工程科学研究所 | The dangerous dynamic classification method of Petrochemical Wharf liquid chemicals pipe leakage |
| CN103196038B (en) * | 2013-03-14 | 2016-08-10 | 清华大学 | Gas ductwork source of leaks real-time positioning analyzes method and system |
| EP3486837A1 (en) * | 2017-11-21 | 2019-05-22 | Nuctech Company Limited | Method of identifying vehicle, apparatus, inspection system and electronic device using the same, and storage of the same |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU713886B2 (en) * | 1996-07-22 | 1999-12-16 | Gary Wayne Jarmyn | Underground warning system for underground conduits or pipes |
| US8874413B2 (en) * | 2011-06-29 | 2014-10-28 | Rael Automatic Sprinkler Company, Inc. | Computer-implemented system and method for designing a fire protection system |
| CN102968620B (en) * | 2012-11-16 | 2015-05-20 | 华中科技大学 | Scene recognition method based on layered Gaussian hybrid model |
| CN106372299B (en) * | 2016-08-29 | 2019-05-07 | 西安建筑科技大学 | A kind of pipeline method for predicting residual useful life based on inverse Gaussian process and EM-PF |
| KR101991581B1 (en) * | 2017-11-15 | 2019-06-20 | 인하대학교 산학협력단 | Apparatus for predicting congestion of concrete conveying pipe using sensor mounting bracket and method thereof |
| CN108494594A (en) * | 2018-03-21 | 2018-09-04 | 中国人民解放军陆军炮兵防空兵学院郑州校区 | A kind of analysis method and system of EIGRP route networks failure |
| CN108804740B (en) * | 2018-04-02 | 2023-09-29 | 西安建筑科技大学 | Long-distance pipeline pressure monitoring method based on integrated improved ICA-KRR algorithm |
| AU2018100903A4 (en) * | 2018-06-29 | 2018-10-04 | LinkTap Pty Ltd | A tap timer system, method and apparatus capable of detecting device's burst-off accident and notifying user immediately |
| CN109344195B (en) * | 2018-10-25 | 2021-09-21 | 电子科技大学 | HMM model-based pipeline security event recognition and knowledge mining method |
-
2020
- 2020-11-20 CN CN202011313674.9A patent/CN112488371B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2467828A1 (en) * | 2009-08-23 | 2012-06-27 | iAd Gesellschaft für Informatik, Automatisierung und Datenverarbeitung mbH | Method and system for automatic object detection and subsequent object tracking in accordance with the object shape |
| CN103196038B (en) * | 2013-03-14 | 2016-08-10 | 清华大学 | Gas ductwork source of leaks real-time positioning analyzes method and system |
| CN103605822B (en) * | 2013-10-08 | 2016-05-04 | 交通运输部天津水运工程科学研究所 | The dangerous dynamic classification method of Petrochemical Wharf liquid chemicals pipe leakage |
| EP3486837A1 (en) * | 2017-11-21 | 2019-05-22 | Nuctech Company Limited | Method of identifying vehicle, apparatus, inspection system and electronic device using the same, and storage of the same |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112488371A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112488371B (en) | Pipeline intelligent early warning method and system based on big data | |
| CN107169628B (en) | Power distribution network reliability assessment method based on big data mutual information attribute reduction | |
| CN110097297A (en) | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium | |
| CN105740975B (en) | A kind of equipment deficiency assessment and prediction technique based on data correlation relation | |
| CN107918830B (en) | Power distribution network running state evaluation method based on big data technology | |
| CN110807550B (en) | Distribution transformer overload recognition and early warning method based on neural network and terminal equipment | |
| CN104392391A (en) | Power grid running safety risk quantification method | |
| CN106327062A (en) | State evaluation method of power distribution network equipment | |
| CN105488740A (en) | Risk level evaluation method and system for urban power distribution network operation mode | |
| CN107784393A (en) | A kind of the defects of transmission line of electricity Forecasting Methodology and device | |
| CN112199805B (en) | Power transmission line hidden danger identification model evaluation method and device | |
| Sun et al. | An ensemble system to predict the spatiotemporal distribution of energy security weaknesses in transmission networks | |
| CN117674119A (en) | Power grid operation risk assessment method, device, computer equipment and storage medium | |
| CN116976318A (en) | Intelligent auditing system for switching operation ticket of power grid based on deep learning and model reasoning | |
| CN117312293B (en) | Electric power multisource heterogeneous data management and intelligent analysis method and system | |
| Sachan et al. | Multiple correspondence analysis to study failures in a diverse population of a cable | |
| CN106655181A (en) | Priority setting method and system for power grid nodes | |
| Pisica et al. | Feature selection filter for classification of power system operating states | |
| CN116415724A (en) | Photovoltaic power station operation maintenance time prediction method and device | |
| CN116151799A (en) | BP neural network-based distribution line multi-working-condition fault rate rapid assessment method | |
| CN113723478B (en) | Track circuit fault diagnosis method based on priori knowledge | |
| CN116719665B (en) | Intelligent judging and identifying method for abnormal state of meteorological numerical mode | |
| CN113568779B (en) | Community data backup system based on routing equipment | |
| CN112736878B (en) | Power grid cascading failure warning method and system | |
| CN117633456B (en) | Marine wind power weather event identification method and device based on self-adaptive focus loss |
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 |