CN111291472B - CFSFDP clustering algorithm-based water supply pipe network pressure monitoring point arrangement method - Google Patents
CFSFDP clustering algorithm-based water supply pipe network pressure monitoring point arrangement method Download PDFInfo
- Publication number
- CN111291472B CN111291472B CN202010053680.9A CN202010053680A CN111291472B CN 111291472 B CN111291472 B CN 111291472B CN 202010053680 A CN202010053680 A CN 202010053680A CN 111291472 B CN111291472 B CN 111291472B
- Authority
- CN
- China
- Prior art keywords
- pressure monitoring
- pressure
- pipe network
- data
- monitoring points
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 93
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 31
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000011425 standardization method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pipeline Systems (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention provides a water supply pipe network pressure monitoring point arrangement method based on a CFSFDP clustering algorithm, which comprises the following steps: constructing a pipe network model by using simulation software, densely distributing pressure monitoring points on the pipe network model, and recording coordinates of all the pressure monitoring points; and (B) step (B): respectively configuring a normal working condition and a leakage working condition for a pipe network model, acquiring pressure data of all pressure monitoring points under different working conditions, and calculating the pressure influence degree and difference coefficient of each pressure monitoring point; step C: constructing an original data set by utilizing coordinates of pressure monitoring points, pressure influence and difference coefficients, and inputting the original data set into a CFSFDP algorithm to obtain a clustering result; step D: and taking all the cluster centers as the arrangement positions of the pressure monitoring points. The invention has the advantages that: the virtual modeling and data acquisition are used for calculation, so that the monitoring point distribution position can be conveniently determined, and the problems of unnecessary loss and incomplete monitoring of a pipe network caused by blind arrangement of pressure monitoring points are avoided.
Description
Technical Field
The invention relates to the technical field of pipe network distribution point monitoring, in particular to a water supply pipe network pressure monitoring point arrangement method based on a CFSFDP clustering algorithm.
Background
The water supply pipe network is a pipeline system for delivering water and distributing water to users in water supply engineering, and consists of pipelines, accessories and auxiliary facilities. The auxiliary facilities include regulating structures (water tanks, water towers or water columns), water supply pump stations and the like. Because the increase of the service time of the pipeline and the untimely maintenance of the pipeline, the water supply pipeline can have hidden danger of leakage, serious safety accidents such as pipe explosion and the like can also occur, and the economic loss is even greater.
In order to ensure the safe operation of the water supply pipe network and realize the optimal scheduling of the water supply pipe network, the operation state of the water supply pipe network is comprehensively monitored; the method is characterized in that pressure monitoring points are reasonably arranged in a water supply pipe network, the number and the installation positions of the pressure monitoring points are selected, and the operating state of the pipeline can be effectively and comprehensively reflected by processing and analyzing pipeline data collected by the optimized monitoring points.
However, in the prior art, the positions of the pressure monitoring points are mainly selected according to working experience, and an effective means for determining the positions and the number of the optimal monitoring points is lacked, so that the arrangement number and the positions are unreasonable, the cost is increased, the monitoring effect is not ideal, the data processing capacity is large, and the like.
Disclosure of Invention
The invention aims to provide a method for effectively determining the positions and the number of pressure monitoring points, so as to solve the problems that the pressure monitoring point selection mode in the prior art depends on working experience, the cost is increased and the like.
The invention solves the technical problems through the following technical scheme: a water supply pipe network pressure monitoring point arrangement method based on a CFSFDP clustering algorithm comprises the following steps:
step A: constructing a pipe network model by using simulation software, densely distributing pressure monitoring points on the pipe network model, and recording coordinates of all the pressure monitoring points;
and (B) step (B): respectively configuring a normal working condition and a leakage working condition for a pipe network model, acquiring pressure data of all pressure monitoring points under different working conditions, and calculating the pressure influence degree and difference coefficient of each pressure monitoring point;
step C: constructing an original data set by utilizing coordinates of pressure monitoring points, pressure influence and difference coefficients, and inputting the original data set into a CFSFDP algorithm to obtain a clustering result;
step D: and taking all cluster centers as the arrangement positions of the pressure monitoring points, wherein the cluster-like number is the number of the pressure monitoring points.
According to the method, the calculation is carried out through the virtual modeling collected data, the construction cost of early hardware is reduced, different leakage working conditions are conveniently constructed, the monitoring point distribution position can be conveniently determined, and the problems that unnecessary loss is caused by blindly arranging pressure monitoring points, the monitoring of a pipe network is incomplete and the like are avoided; the clustering processing is carried out through the CFSFDP algorithm, the number of clusters is not required to be preset, the non-spherical clusters can be processed, repeated iterative operation is not required, and the operation speed of the algorithm is high.
Preferably, under the normal working condition described in the step B, recording pressure data of the N pressure monitoring points at M times to obtain a pressure data matrix q= { P under the normal working condition ij |i∈[1,M],j∈[1,N]};
Respectively configuring the same-level leakage loss for each pressure monitoring point to obtain N leakage loss working conditions, and acquiring pressure data of all the pressure monitoring points at M moments for each leakage loss working condition, wherein the kth pressure monitoring point is configured as a pressure data matrix under the leakage loss working condition and is recorded as
Preferably, the pressure influence EF in step B k The calculation method of (1) is as follows:
R k =Q-Q k
coefficient of difference CV k The calculation method of (1) is as follows:
wherein sigma k Is the standard deviation of pressure data of the pressure monitoring point k at M moments under normal working conditions,the average number of the pressure data of the pressure monitoring point k at M moments under the normal working condition.
Preferably, the coordinates of the pressure monitoring point k are expressed as (X k ,Y k ) The original dataset described in step C is then in the form of:
D={D k |k∈[1,N]}
D k =(X k ,Y k ,EF k ,CV k ),k∈[1,N]
the original data set D is input into a CFSFDP algorithm after being standardized, and the standardized processing adopts a z-score standardized method, wherein the formula is as follows:
wherein D is k ' is the input data after the normalization,for the average number of attribute data in D σ And calculating the data of each pressure monitoring point in the D to obtain standardized input data D' for the standard deviation of the attribute data in the D.
Preferably, the clustering method of the CFSFDP algorithm in the step C is: the Euclidean distance between two data objects in the data set D' is sequentially calculated, the local density of each data object is determined based on the Euclidean distance, the cluster center distance of each data object is determined based on the local density, and the cluster center point is determined based on the local density and the cluster center distance.
Preferably, the local density ρ j The calculation method of (1) is as follows:
where dc denotes the cut-off distance, dis (t, j) denotes the data object D t ,D j Euclidean distance between them.
Preferably, the cluster center distance delta j The calculation method of (1) is as follows:
wherein ψ is j Is local density greater than ρ j Is provided for the pressure monitoring points.
Preferably, the method for determining a cluster center includes: at ρ j In the horizontal direction of the axis of abscissa,δ j and constructing a decision graph for the ordinate, wherein the pressure monitoring point at the upper right part of the decision graph is the clustering center.
Preferably, the method for determining a cluster center includes:
computing gamma for each pressure monitoring point j Values of gamma, wherein gamma j =ρ j ·δ j The method comprises the steps of carrying out a first treatment on the surface of the By gamma j Construction of gamma for ordinate j Scatter plot, at gamma j The point before the jump of the numerical change occurs is the cluster center.
The water supply pipe network pressure monitoring point arrangement method based on the CFSFDP clustering algorithm has the advantages that: the data are acquired through virtual modeling for calculation, so that the construction cost of early hardware is reduced, different leakage working conditions are conveniently constructed, the monitoring point distribution position can be conveniently determined, and the problems of unnecessary loss, incomplete monitoring of a pipe network and the like caused by blind arrangement of pressure monitoring points are avoided; the clustering processing is carried out through the CFSFDP algorithm, the number of clusters is not required to be preset, the non-spherical clusters can be processed, repeated iterative operation is not required, and the operation speed of the algorithm is high.
Drawings
FIG. 1 is a flow chart of a method for arranging pressure monitoring points of a water supply pipe network based on a CFSFDP clustering algorithm provided by an embodiment of the invention;
FIG. 2 is a pipe network model diagram of a water supply pipe network pressure monitoring point arrangement method based on a CFSFDP clustering algorithm provided by an embodiment of the invention;
FIG. 3 is a decision diagram of a water supply network pressure monitoring point arrangement method based on a CFSFDP clustering algorithm provided by an embodiment of the invention;
FIG. 4 shows a gamma of a method for arranging pressure monitoring points of a water supply pipe network based on a CFSFDP clustering algorithm according to an embodiment of the present invention j A scatter plot.
Detailed Description
The present invention will be further described in detail below with reference to specific embodiments and with reference to the accompanying drawings, in order to make the objects, technical solutions and advantages of the present invention more apparent.
As shown in fig. 1, the embodiment provides a water supply pipe network pressure monitoring point arrangement method based on a CFSFDP clustering algorithm, which comprises the following steps:
step A: constructing a pipe network model by using simulation software, densely distributing pressure monitoring points on the pipe network model, and recording coordinates of all the pressure monitoring points;
referring to fig. 2, in this embodiment, a central divertor cooling loop test stand of a plasma physics research institute technology in a scientific island of the combined fertilizer city of Anhui province is taken as a research object, a pipe network hydraulics model is constructed by means of the EPANET software, and positions of 34 pressure monitoring points in total are densely distributed on the constructed pipe network model; the coordinates (X j ,Y j )。
And (B) step (B): respectively configuring a normal working condition and a leakage working condition for the pipe network model; under normal working conditions, recording the pressure data of N pressure monitoring points at M moments to obtain a pressure data matrix Q= { P under the normal working conditions ij |i∈[1,M],j∈[1,N]};
Respectively configuring the same-level leakage loss for each pressure monitoring point so as to obtain N leakage loss working conditions, wherein each leakage loss working condition has only one leakage loss point, and acquiring the pressure data of all the pressure monitoring points at M moments for each leakage loss working condition, wherein the kth pressure monitoring point is configured as a pressure data matrix under the leakage loss working condition, and the matrix is recorded as
According to the pressure data under different working conditions, calculating the pressure influence degree EF of each pressure monitoring point k ,
R k =Q-Q k
Then calculating a difference coefficient CV according to the data under the normal working condition k ,
Wherein sigma k Is the standard deviation of pressure data of the pressure monitoring point k at M moments under normal working conditions,the average number of the pressure data of the pressure monitoring point k at M moments under the normal working condition.
Step C: constructing an original data set by utilizing coordinates of pressure monitoring points, pressure influence and difference coefficients, and inputting the original data set into a CFSFDP algorithm to obtain a clustering result;
the original dataset is in the form of:
D={D k |k∈[1,N]}
D k =(X k ,Y k ,EF k ,CV k ),k∈[1,N]
the data of the original data set obtained in this embodiment are as follows:
the obtained partial data are shown in table 1,
table 1: raw data set
In order to simplify the operation complexity, the original data set D needs to be standardized and then input into an algorithm, and in this embodiment, a z-score standardization method is selected, where the formula is as follows:
wherein D is k ' is the input data after the normalization,for the average number of attribute data in D σ Calculating the data of each pressure monitoring point in the D to obtain standardized input data D' for the standard deviation of the attribute data in the D, wherein the standardized data are shown in the table 2:
table 2: normalized dataset
The normalized data set D' is input into the CFSFDP algorithm, and the clustering method is as follows:
step I: sequentially computing two data objects D in a data set D t ,D j Euclidean distance Dis (t, j) between;
step II: computing local density ρ for each data object based on Euclidean distance j ,
Wherein dc represents the cut-off distance, which is an empirical value, and the user can set the cut-off distance as required, and according to the above formula, it can be determined that the partial density statistics is the number of data objects whose Euclidean distance with the current data object j is smaller than the cut-off distance dc.
Step III: calculating cluster center distance delta for each data object based on local density j ,
Wherein ψ is j Is local density greater than ρ j Of data objects of (i.e. local density ρ) j Cluster center distance delta of maximum data object j j For the maximum value of Euclidean distance between the data object j and all other data objects, the cluster center distance delta of the other data objects j j Is the local density ρ j The minimum value of the euclidean distance of all data objects larger than it from that data object j.
Step IV: according to local density ρ j And cluster center distance delta j Determining a clustering center point;
specifically, decision graphs can be selected for determination, and referring to FIG. 3, at ρ j In abscissa, delta j Drawing a decision graph for an ordinate, wherein the local density and the cluster center distance of corresponding pressure monitoring points at the upper right part are high, and the points are the cluster centers; the local density value of the upper left part of the decision graph is lower, the point with the higher distance value of the cluster center is a noise point, the local density value of the lower part of the decision graph is relatively higher, and the point with the lower distance value is a point in the cluster, so that the number and the center position of the cluster can be determined.
Based on the decision diagram, it can be known that the clustering center is a point with higher local density and clustering value of the clustering center, so that gamma can be also used j Determining a clustering center and gamma by using a scatter diagram j The calculation formula of the value is gamma j =ρ j ·δ j All monitoring points are gamma j The values are ordered from big to small, with the sequence number very abscissa, gamma j Construction of gamma with values on the ordinate j With reference to fig. 4, there is a significant jump from the values of the clustered central points to the non-clustered central points, the trend of the non-clustered central points is gentle, the variation amplitude of the clustered central points is large, and the non-clustered central points are in gamma j Scattered pointsIn the figure, the points above the jump position are the cluster centers.
The person skilled in the art can choose any method to determine the clustering center, and can also adopt the two methods to mutually verify.
After the clustering center is obtained, other non-clustering center points are divided into clusters, wherein the dividing method is that each data object and the data object which is higher than the local density of the data object and has the nearest Euclidean distance belong to the same cluster until all the data objects are divided into clusters.
Step D: and taking all the clustering centers as the arrangement positions of the pressure monitoring points, wherein the number of the actual pressure monitoring points is equal to the number of the clusters.
The same cluster can be covered by arranging a pressure monitoring point in the cluster center, and the final result is shown in Table 3
Table 3: clustering results
After the number and the positions of the pressure monitoring points are determined through modeling analysis, a pressure detection device can be arranged on an actual pipe network according to a simulation result to perform operation monitoring.
Claims (6)
1. A water supply pipe network pressure monitoring point arrangement method based on a CFSFDP clustering algorithm is characterized by comprising the following steps of: the method comprises the following steps:
step A: constructing a pipe network model by using simulation software, densely distributing pressure monitoring points on the pipe network model, and recording coordinates of all the pressure monitoring points;
and (B) step (B): respectively configuring a normal working condition and a leakage working condition for a pipe network model, acquiring pressure data of all pressure monitoring points under different working conditions, and calculating the pressure influence degree and difference coefficient of each pressure monitoring point; the normal work described in the step BUnder the condition, recording the pressure data of N pressure monitoring points at M moments to obtain a pressure data matrix Q= { P under normal working conditions ij ,i∈[1,M],j∈[1,N]};
Respectively configuring the same-level leakage loss for each pressure monitoring point to obtain N leakage loss working conditions, and acquiring pressure data of all the pressure monitoring points at M moments for each leakage loss working condition, wherein the kth pressure monitoring point is configured as a pressure data matrix under the leakage loss working condition and is recorded asThe degree of influence EF of the pressure in step B k The calculation method of (1) is as follows:
R k =Q-Q k
coefficient of difference CV k The calculation method of (1) is as follows:
wherein sigma k Is the standard deviation of pressure data of the pressure monitoring point k at M moments under normal working conditions,the average number of the pressure data of the pressure monitoring point k at M moments under the normal working condition is calculated;
step C: by means of the coordinates and pressure shadow of pressure monitoring pointsConstructing an original data set by loudness and difference coefficient, and inputting the original data set into a CFSFDP algorithm to obtain a clustering result; the coordinates of the pressure monitoring point k are expressed as (X k ,Y k ) The original dataset described in step C is then in the form of:
D={D k |k∈[1,N]}
D k =(X k ,Y k ,EF k ,CV k ),k∈[1,N]
the original data set D is input into a CFSFDP algorithm after being standardized, and the standardized processing adopts a z-score standardized method, wherein the formula is as follows:
wherein D' k For the input data to be normalized,for the average number of attribute data in D σ Calculating the data of each pressure monitoring point in the D to obtain standardized input data D' for the standard deviation of each attribute data in the D;
step D: and taking all cluster centers as the arrangement positions of the pressure monitoring points, wherein the cluster-like number is the number of the pressure monitoring points.
2. The water supply pipe network pressure measuring point arrangement method based on the CFSFDP clustering algorithm as set forth in claim 1, wherein the method is characterized in that: the clustering method of the CFSFDP algorithm in the step C is as follows: the Euclidean distance between two data objects in the data set D' is sequentially calculated, the local density of each data object is determined based on the Euclidean distance, the cluster center distance of each data object is determined based on the local density, and the cluster center point is determined based on the local density and the cluster center distance.
3. The water supply pipe network pressure measuring point arrangement method based on CFSFDP clustering algorithm as set forth in claim 2, wherein the method is characterized in thatIn the following steps: the local density ρ j The calculation method of (1) is as follows:
where dc denotes the cut-off distance, dis (t, j) denotes the data object D t ,D j Euclidean distance between them.
4. The water supply pipe network pressure measuring point arrangement method based on the CFSFDP clustering algorithm as set forth in claim 3, wherein the method is characterized in that: the cluster center distance delta j The calculation method of (1) is as follows:
wherein ψ is j Is local density greater than ρ j Is provided for the pressure monitoring points.
5. The method for arranging the pressure monitoring points of the water supply pipe network based on the CFSFDP clustering algorithm, which is characterized by comprising the following steps of: the method for determining the cluster center comprises the following steps: at ρ j In abscissa, delta j And constructing a decision graph for the ordinate, wherein the pressure monitoring point at the upper right part of the decision graph is the clustering center.
6. The method for arranging the pressure monitoring points of the water supply pipe network based on the CFSFDP clustering algorithm according to claim 4 or 5 is characterized by comprising the following steps: the method for determining the cluster center comprises the following steps:
computing gamma for each pressure monitoring point j Values of gamma, wherein gamma j =ρ j ·δ j The method comprises the steps of carrying out a first treatment on the surface of the By gamma j Construction of gamma for ordinate j A scatter plot of the images,at gamma j The point before the jump of the numerical change occurs is the cluster center.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010053680.9A CN111291472B (en) | 2020-01-17 | 2020-01-17 | CFSFDP clustering algorithm-based water supply pipe network pressure monitoring point arrangement method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010053680.9A CN111291472B (en) | 2020-01-17 | 2020-01-17 | CFSFDP clustering algorithm-based water supply pipe network pressure monitoring point arrangement method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111291472A CN111291472A (en) | 2020-06-16 |
CN111291472B true CN111291472B (en) | 2024-01-05 |
Family
ID=71022311
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010053680.9A Active CN111291472B (en) | 2020-01-17 | 2020-01-17 | CFSFDP clustering algorithm-based water supply pipe network pressure monitoring point arrangement method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111291472B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113177283B (en) * | 2021-04-28 | 2023-05-23 | 中国能源建设集团广东省电力设计研究院有限公司 | Intelligent design method, system, equipment and storage medium for instrument measuring point installation |
CN113420965B (en) * | 2021-06-08 | 2023-07-07 | 上海城投水务(集团)有限公司 | Method for auxiliary manual scheduling based on virtual measuring points |
CN113762132A (en) * | 2021-09-01 | 2021-12-07 | 国网浙江省电力有限公司金华供电公司 | Automatic classification and automatic naming system for unmanned aerial vehicle inspection image |
CN113719760B (en) * | 2021-09-16 | 2022-10-14 | 武汉博水信息科技有限公司 | Pipe network operation intelligent early warning analysis method and system based on geographic information |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107368648A (en) * | 2017-07-19 | 2017-11-21 | 安徽建筑大学 | Municipal water supply network oriented pressure monitoring point optimal arrangement method |
CN108334994A (en) * | 2018-03-20 | 2018-07-27 | 哈尔滨工业大学 | A kind of heating network flow and pressure monitoring point optimization placement method |
CN108647470A (en) * | 2018-05-29 | 2018-10-12 | 杭州电子科技大学 | A kind of localization method at the beginning of based on the leakage loss with depth belief network is clustered |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10969775B2 (en) * | 2017-06-23 | 2021-04-06 | Johnson Controls Technology Company | Predictive diagnostics system with fault detector for preventative maintenance of connected equipment |
-
2020
- 2020-01-17 CN CN202010053680.9A patent/CN111291472B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107368648A (en) * | 2017-07-19 | 2017-11-21 | 安徽建筑大学 | Municipal water supply network oriented pressure monitoring point optimal arrangement method |
CN108334994A (en) * | 2018-03-20 | 2018-07-27 | 哈尔滨工业大学 | A kind of heating network flow and pressure monitoring point optimization placement method |
CN108647470A (en) * | 2018-05-29 | 2018-10-12 | 杭州电子科技大学 | A kind of localization method at the beginning of based on the leakage loss with depth belief network is clustered |
Non-Patent Citations (2)
Title |
---|
刘永鑫 ; 金虹 ; 邹平华 ; 马月璇 ; .供热管网阻抗辨识观测点优化布置策略.暖通空调.2017,(05),全文. * |
蔡亮 ; 王荣合 ; 赵仁鑫 ; 平俊晖 ; 荆延龙 ; 孙继龙 ; .基于无线传感网络与水量反演方法的供水管网监测模式研究.给水排水.2016,(S1),全文. * |
Also Published As
Publication number | Publication date |
---|---|
CN111291472A (en) | 2020-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111291472B (en) | CFSFDP clustering algorithm-based water supply pipe network pressure monitoring point arrangement method | |
CN110703057B (en) | Power equipment partial discharge diagnosis method based on data enhancement and neural network | |
CN105894130A (en) | Optimized arrangement method for monitoring points of urban water supply pipe network | |
CN107330056A (en) | Wind power plant SCADA system and its operation method based on big data cloud computing platform | |
CN112700326A (en) | Credit default prediction method for optimizing BP neural network based on Grey wolf algorithm | |
CN104835174B (en) | Robust Model approximating method based on Hypergraph model search | |
CN106354803B (en) | Method for detecting bad data of electric power transmission and transformation equipment load based on characteristic indexes | |
CN114662712A (en) | Rotating machine state monitoring method based on Wasserstein depth digital twin model | |
CN104182511B (en) | A kind of fuzzy distribution clustering method that compacts of cluster characteristic weighing | |
CN116956189A (en) | Current abnormality detection system, method, electronic equipment and medium | |
CN105590167A (en) | Method and device for analyzing electric field multivariate operating data | |
CN117149395A (en) | IDC machine room resource management method and system | |
CN111582362A (en) | Farmland water pump fault diagnosis method and device based on random forest algorithm | |
CN117037841A (en) | Acoustic signal hierarchical cavitation intensity identification method based on hierarchical transition network | |
CN114912372B (en) | High-precision filling pipeline fault early warning method based on artificial intelligence algorithm | |
CN116150692A (en) | Power grid fault diagnosis method and system based on cloud platform and improved isolated forest | |
Li | Integrated Evaluation Technology of landing signal officer for carrier-based aircraft | |
CN114493234A (en) | Method for identifying key pressure control points of water supply pipe network | |
Qiao et al. | Study on K-means method based on Data-Mining | |
CN114840591A (en) | Method and device for determining sectional switch power data | |
CN109101998B (en) | Clustering method and system based on spatial information of residential ground context | |
Wang et al. | Fault diagnosis of ship ballast water system based on support vector machine optimized by improved sparrow search algorithm | |
CN112131605A (en) | Differential privacy dynamic data publishing method based on mutual information correlation technology | |
CN107562534B (en) | Load balancing method for weighted minimum data volume | |
CN112116213A (en) | FAHP-based reliability distribution method for linear feeding system of numerical control machine tool |
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 |